Implementing size-optimal discrete neural networks require analog circuitry
Energy Technology Data Exchange (ETDEWEB)
Beiu, V.
1998-12-01
This paper starts by overviewing results dealing with the approximation capabilities of neural networks, as well as bounds on the size of threshold gate circuits. Based on a constructive solution for Kolmogorov`s superpositions the authors show that implementing Boolean functions can be done using neurons having an identity transfer function. Because in this case the size of the network is minimized, it follows that size-optimal solutions for implementing Boolean functions can be obtained using analog circuitry. Conclusions and several comments on the required precision are ending the paper.
Implementing size-optimal discrete neural networks requires analog circuitry
Energy Technology Data Exchange (ETDEWEB)
Beiu, V.
1998-03-01
Neural networks (NNs) have been experimentally shown to be quite effective in many applications. This success has led researchers to undertake a rigorous analysis of the mathematical properties that enable them to perform so well. It has generated two directions of research: (i) to find existence/constructive proofs for what is now known as the universal approximation problem; (ii) to find tight bounds on the size needed by the approximation problem (or some particular cases). The paper will focus on both aspects, for the particular case when the functions to be implemented are Boolean.
Directory of Open Access Journals (Sweden)
Yue Wu
2017-01-01
Full Text Available Firefly Algorithm (FA, for short is inspired by the social behavior of fireflies and their phenomenon of bioluminescent communication. Based on the fundamentals of FA, two improved strategies are proposed to conduct size and topology optimization for trusses with discrete design variables. Firstly, development of structural topology optimization method and the basic principle of standard FA are introduced in detail. Then, in order to apply the algorithm to optimization problems with discrete variables, the initial positions of fireflies and the position updating formula are discretized. By embedding the random-weight and enhancing the attractiveness, the performance of this algorithm is improved, and thus an Improved Firefly Algorithm (IFA, for short is proposed. Furthermore, using size variables which are capable of including topology variables and size and topology optimization for trusses with discrete variables is formulated based on the Ground Structure Approach. The essential techniques of variable elastic modulus technology and geometric construction analysis are applied in the structural analysis process. Subsequently, an optimization method for the size and topological design of trusses based on the IFA is introduced. Finally, two numerical examples are shown to verify the feasibility and efficiency of the proposed method by comparing with different deterministic methods.
Optimization strategies for discrete multi-material stiffness optimization
DEFF Research Database (Denmark)
Hvejsel, Christian Frier; Lund, Erik; Stolpe, Mathias
2011-01-01
Design of composite laminated lay-ups are formulated as discrete multi-material selection problems. The design problem can be modeled as a non-convex mixed-integer optimization problem. Such problems are in general only solvable to global optimality for small to moderate sized problems. To attack...... which numerically confirm the sought properties of the new scheme in terms of convergence to a discrete solution....
Discrete size optimization of steel trusses using a refined big bang-big crunch algorithm
Hasançebi, O.; Kazemzadeh Azad, S.
2014-01-01
This article presents a methodology that provides a method for design optimization of steel truss structures based on a refined big bang-big crunch (BB-BC) algorithm. It is shown that a standard formulation of the BB-BC algorithm occasionally falls short of producing acceptable solutions to problems from discrete size optimum design of steel trusses. A reformulation of the algorithm is proposed and implemented for design optimization of various discrete truss structures according to American Institute of Steel Construction Allowable Stress Design (AISC-ASD) specifications. Furthermore, the performance of the proposed BB-BC algorithm is compared to its standard version as well as other well-known metaheuristic techniques. The numerical results confirm the efficiency of the proposed algorithm in practical design optimization of truss structures.
Wu, Yue; Li, Q.; Hu, Qingjie; Borgart, A.
2017-01-01
Firefly Algorithm (FA, for short) is inspired by the social behavior of fireflies and their phenomenon of bioluminescent communication. Based on the fundamentals of FA, two improved strategies are proposed to conduct size and topology optimization for trusses with discrete design variables. Firstly,
Discrete hierarchical organization of social group sizes.
Zhou, W-X; Sornette, D; Hill, R A; Dunbar, R I M
2005-02-22
The 'social brain hypothesis' for the evolution of large brains in primates has led to evidence for the coevolution of neocortical size and social group sizes, suggesting that there is a cognitive constraint on group size that depends, in some way, on the volume of neural material available for processing and synthesizing information on social relationships. More recently, work on both human and non-human primates has suggested that social groups are often hierarchically structured. We combine data on human grouping patterns in a comprehensive and systematic study. Using fractal analysis, we identify, with high statistical confidence, a discrete hierarchy of group sizes with a preferred scaling ratio close to three: rather than a single or a continuous spectrum of group sizes, humans spontaneously form groups of preferred sizes organized in a geometrical series approximating 3-5, 9-15, 30-45, etc. Such discrete scale invariance could be related to that identified in signatures of herding behaviour in financial markets and might reflect a hierarchical processing of social nearness by human brains.
Particle Swarm Based Approach of a Real-Time Discrete Neural Identifier for Linear Induction Motors
Directory of Open Access Journals (Sweden)
Alma Y. Alanis
2013-01-01
Full Text Available This paper focusses on a discrete-time neural identifier applied to a linear induction motor (LIM model, whose model is assumed to be unknown. This neural identifier is robust in presence of external and internal uncertainties. The proposed scheme is based on a discrete-time recurrent high-order neural network (RHONN trained with a novel algorithm based on extended Kalman filter (EKF and particle swarm optimization (PSO, using an online series-parallel con figuration. Real-time results are included in order to illustrate the applicability of the proposed scheme.
Chaotic Hopfield Neural Network Swarm Optimization and Its Application
Directory of Open Access Journals (Sweden)
Yanxia Sun
2013-01-01
Full Text Available A new neural network based optimization algorithm is proposed. The presented model is a discrete-time, continuous-state Hopfield neural network and the states of the model are updated synchronously. The proposed algorithm combines the advantages of traditional PSO, chaos and Hopfield neural networks: particles learn from their own experience and the experiences of surrounding particles, their search behavior is ergodic, and convergence of the swarm is guaranteed. The effectiveness of the proposed approach is demonstrated using simulations and typical optimization problems.
Exponential stability result for discrete-time stochastic fuzzy uncertain neural networks
International Nuclear Information System (INIS)
Mathiyalagan, K.; Sakthivel, R.; Marshal Anthoni, S.
2012-01-01
This Letter addresses the stability analysis problem for a class of uncertain discrete-time stochastic fuzzy neural networks (DSFNNs) with time-varying delays. By constructing a new Lyapunov–Krasovskii functional combined with the free weighting matrix technique, a new set of delay-dependent sufficient conditions for the robust exponential stability of the considered DSFNNs is established in terms of Linear Matrix Inequalities (LMIs). Finally, numerical examples with simulation results are provided to illustrate the applicability and usefulness of the obtained theory. -- Highlights: ► Applications of neural networks require the knowledge of dynamic behaviors. ► Exponential stability of discrete-time stochastic fuzzy neural networks is studied. ► Linear matrix inequality optimization approach is used to obtain the result. ► Delay-dependent stability criterion is established in terms of LMIs. ► Examples with simulation are provided to show the effectiveness of the result.
Hybrid discrete-time neural networks.
Cao, Hongjun; Ibarz, Borja
2010-11-13
Hybrid dynamical systems combine evolution equations with state transitions. When the evolution equations are discrete-time (also called map-based), the result is a hybrid discrete-time system. A class of biological neural network models that has recently received some attention falls within this category: map-based neuron models connected by means of fast threshold modulation (FTM). FTM is a connection scheme that aims to mimic the switching dynamics of a neuron subject to synaptic inputs. The dynamic equations of the neuron adopt different forms according to the state (either firing or not firing) and type (excitatory or inhibitory) of their presynaptic neighbours. Therefore, the mathematical model of one such network is a combination of discrete-time evolution equations with transitions between states, constituting a hybrid discrete-time (map-based) neural network. In this paper, we review previous work within the context of these models, exemplifying useful techniques to analyse them. Typical map-based neuron models are low-dimensional and amenable to phase-plane analysis. In bursting models, fast-slow decomposition can be used to reduce dimensionality further, so that the dynamics of a pair of connected neurons can be easily understood. We also discuss a model that includes electrical synapses in addition to chemical synapses with FTM. Furthermore, we describe how master stability functions can predict the stability of synchronized states in these networks. The main results are extended to larger map-based neural networks.
On global stability criterion for neural networks with discrete and distributed delays
International Nuclear Information System (INIS)
Park, Ju H.
2006-01-01
Based on the Lyapunov functional stability analysis for differential equations and the linear matrix inequality (LMI) optimization approach, a new delay-dependent criterion for neural networks with discrete and distributed delays is derived to guarantee global asymptotic stability. The criterion is expressed in terms of LMIs, which can be solved easily by various convex optimization algorithms. Some numerical examples are given to show the effectiveness of proposed method
In-plane material continuity for the discrete material optimization method
DEFF Research Database (Denmark)
Sørensen, Rene; Lund, Erik
2015-01-01
When performing discrete material optimization of laminated composite structures, the variation of the in-plane material continuity is typically governed by the size of the finite element discretization. For a fine mesh, this can lead to designs that cannot be manufactured due to the complexity...
Qi, Donglian; Liu, Meiqin; Qiu, Meikang; Zhang, Senlin
2010-08-01
This brief studies exponential H(infinity) synchronization of a class of general discrete-time chaotic neural networks with external disturbance. On the basis of the drive-response concept and H(infinity) control theory, and using Lyapunov-Krasovskii (or Lyapunov) functional, state feedback controllers are established to not only guarantee exponential stable synchronization between two general chaotic neural networks with or without time delays, but also reduce the effect of external disturbance on the synchronization error to a minimal H(infinity) norm constraint. The proposed controllers can be obtained by solving the convex optimization problems represented by linear matrix inequalities. Most discrete-time chaotic systems with or without time delays, such as Hopfield neural networks, cellular neural networks, bidirectional associative memory networks, recurrent multilayer perceptrons, Cohen-Grossberg neural networks, Chua's circuits, etc., can be transformed into this general chaotic neural network to be H(infinity) synchronization controller designed in a unified way. Finally, some illustrated examples with their simulations have been utilized to demonstrate the effectiveness of the proposed methods.
Handbook on modelling for discrete optimization
Pitsoulis, Leonidas; Williams, H
2006-01-01
The primary objective underlying the Handbook on Modelling for Discrete Optimization is to demonstrate and detail the pervasive nature of Discrete Optimization. While its applications cut across an incredibly wide range of activities, many of the applications are only known to specialists. It is the aim of this handbook to correct this. It has long been recognized that "modelling" is a critically important mathematical activity in designing algorithms for solving these discrete optimization problems. Nevertheless solving the resultant models is also often far from straightforward. In recent years it has become possible to solve many large-scale discrete optimization problems. However, some problems remain a challenge, even though advances in mathematical methods, hardware, and software technology have pushed the frontiers forward. This handbook couples the difficult, critical-thinking aspects of mathematical modeling with the hot area of discrete optimization. It will be done in an academic handbook treatment...
Liu, Lei; Wang, Zhanshan; Zhang, Huaguang
2018-04-01
This paper is concerned with the robust optimal tracking control strategy for a class of nonlinear multi-input multi-output discrete-time systems with unknown uncertainty via adaptive critic design (ACD) scheme. The main purpose is to establish an adaptive actor-critic control method, so that the cost function in the procedure of dealing with uncertainty is minimum and the closed-loop system is stable. Based on the neural network approximator, an action network is applied to generate the optimal control signal and a critic network is used to approximate the cost function, respectively. In contrast to the previous methods, the main features of this paper are: 1) the ACD scheme is integrated into the controllers to cope with the uncertainty and 2) a novel cost function, which is not in quadric form, is proposed so that the total cost in the design procedure is reduced. It is proved that the optimal control signals and the tracking errors are uniformly ultimately bounded even when the uncertainty exists. Finally, a numerical simulation is developed to show the effectiveness of the present approach.
Impulsive stabilization and impulsive synchronization of discrete-time delayed neural networks.
Chen, Wu-Hua; Lu, Xiaomei; Zheng, Wei Xing
2015-04-01
This paper investigates the problems of impulsive stabilization and impulsive synchronization of discrete-time delayed neural networks (DDNNs). Two types of DDNNs with stabilizing impulses are studied. By introducing the time-varying Lyapunov functional to capture the dynamical characteristics of discrete-time impulsive delayed neural networks (DIDNNs) and by using a convex combination technique, new exponential stability criteria are derived in terms of linear matrix inequalities. The stability criteria for DIDNNs are independent of the size of time delay but rely on the lengths of impulsive intervals. With the newly obtained stability results, sufficient conditions on the existence of linear-state feedback impulsive controllers are derived. Moreover, a novel impulsive synchronization scheme for two identical DDNNs is proposed. The novel impulsive synchronization scheme allows synchronizing two identical DDNNs with unknown delays. Simulation results are given to validate the effectiveness of the proposed criteria of impulsive stabilization and impulsive synchronization of DDNNs. Finally, an application of the obtained impulsive synchronization result for two identical chaotic DDNNs to a secure communication scheme is presented.
Directory of Open Access Journals (Sweden)
Carlos López-Franco
2015-01-01
Full Text Available We present an inverse optimal neural controller for a nonholonomic mobile robot with parameter uncertainties and unknown external disturbances. The neural controller is based on a discrete-time recurrent high order neural network (RHONN trained with an extended Kalman filter. The reference velocities for the neural controller are obtained with a visual sensor. The effectiveness of the proposed approach is tested by simulations and real-time experiments.
ABOUT HYBRID BIDIRECTIONAL ASSOCIATIVE MEMORY NEURAL NETWORKS WITH DISCRETE DELAYS
Institute of Scientific and Technical Information of China (English)
无
2010-01-01
In this paper, hybrid bidirectional associative memory neural networks with discrete delays is considered. By ingeniously importing real parameters di > 0(i = 1,2,···,n) which can be adjusted, we establish some new sufficient conditions for the dynamical characteristics of hybrid bidirectional associative memory neural networks with discrete delays by the method of variation of parameters and some analysis techniques. Our results generalize and improve the related results in [10,11]. Our work is significant...
Neural Network for Sparse Reconstruction
Directory of Open Access Journals (Sweden)
Qingfa Li
2014-01-01
Full Text Available We construct a neural network based on smoothing approximation techniques and projected gradient method to solve a kind of sparse reconstruction problems. Neural network can be implemented by circuits and can be seen as an important method for solving optimization problems, especially large scale problems. Smoothing approximation is an efficient technique for solving nonsmooth optimization problems. We combine these two techniques to overcome the difficulties of the choices of the step size in discrete algorithms and the item in the set-valued map of differential inclusion. In theory, the proposed network can converge to the optimal solution set of the given problem. Furthermore, some numerical experiments show the effectiveness of the proposed network in this paper.
Heuristic Optimization for the Discrete Virtual Power Plant Dispatch Problem
DEFF Research Database (Denmark)
Petersen, Mette Kirschmeyer; Hansen, Lars Henrik; Bendtsen, Jan Dimon
2014-01-01
We consider a Virtual Power Plant, which is given the task of dispatching a fluctuating power supply to a portfolio of flexible consumers. The flexible consumers are modeled as discrete batch processes, and the associated optimization problem is denoted the Discrete Virtual Power Plant Dispatch...... Problem. First NP-completeness of the Discrete Virtual Power Plant Dispatch Problem is proved formally. We then proceed to develop tailored versions of the meta-heuristic algorithms Hill Climber and Greedy Randomized Adaptive Search Procedure (GRASP). The algorithms are tuned and tested on portfolios...... of varying sizes. We find that all the tailored algorithms perform satisfactorily in the sense that they are able to find sub-optimal, but usable, solutions to very large problems (on the order of 10 5 units) at computation times on the scale of just 10 seconds, which is far beyond the capabilities...
Discrete-time BAM neural networks with variable delays
Liu, Xin-Ge; Tang, Mei-Lan; Martin, Ralph; Liu, Xin-Bi
2007-07-01
This Letter deals with the global exponential stability of discrete-time bidirectional associative memory (BAM) neural networks with variable delays. Using a Lyapunov functional, and linear matrix inequality techniques (LMI), we derive a new delay-dependent exponential stability criterion for BAM neural networks with variable delays. As this criterion has no extra constraints on the variable delay functions, it can be applied to quite general BAM neural networks with a broad range of time delay functions. It is also easy to use in practice. An example is provided to illustrate the theoretical development.
Discrete-time BAM neural networks with variable delays
International Nuclear Information System (INIS)
Liu Xinge; Tang Meilan; Martin, Ralph; Liu Xinbi
2007-01-01
This Letter deals with the global exponential stability of discrete-time bidirectional associative memory (BAM) neural networks with variable delays. Using a Lyapunov functional, and linear matrix inequality techniques (LMI), we derive a new delay-dependent exponential stability criterion for BAM neural networks with variable delays. As this criterion has no extra constraints on the variable delay functions, it can be applied to quite general BAM neural networks with a broad range of time delay functions. It is also easy to use in practice. An example is provided to illustrate the theoretical development
Discrete-time bidirectional associative memory neural networks with variable delays
International Nuclear Information System (INIS)
Liang Jinling; Cao Jinde; Ho, Daniel W.C.
2005-01-01
Based on the linear matrix inequality (LMI), some sufficient conditions are presented in this Letter for the existence, uniqueness and global exponential stability of the equilibrium point of discrete-time bidirectional associative memory (BAM) neural networks with variable delays. Some of the stability criteria obtained in this Letter are delay-dependent, and some of them are delay-independent, they are less conservative than the ones reported so far in the literature. Furthermore, the results provide one more set of easily verified criteria for determining the exponential stability of discrete-time BAM neural networks
Discrete-time bidirectional associative memory neural networks with variable delays
Liang, variable delays [rapid communication] J.; Cao, J.; Ho, D. W. C.
2005-02-01
Based on the linear matrix inequality (LMI), some sufficient conditions are presented in this Letter for the existence, uniqueness and global exponential stability of the equilibrium point of discrete-time bidirectional associative memory (BAM) neural networks with variable delays. Some of the stability criteria obtained in this Letter are delay-dependent, and some of them are delay-independent, they are less conservative than the ones reported so far in the literature. Furthermore, the results provide one more set of easily verified criteria for determining the exponential stability of discrete-time BAM neural networks.
Directory of Open Access Journals (Sweden)
Huaiqin Wu
2012-01-01
Full Text Available By combing the theories of the switched systems and the interval neural networks, the mathematics model of the switched interval neural networks with discrete and distributed time-varying delays of neural type is presented. A set of the interval parameter uncertainty neural networks with discrete and distributed time-varying delays of neural type are used as the individual subsystem, and an arbitrary switching rule is assumed to coordinate the switching between these networks. By applying the augmented Lyapunov-Krasovskii functional approach and linear matrix inequality (LMI techniques, a delay-dependent criterion is achieved to ensure to such switched interval neural networks to be globally asymptotically robustly stable in terms of LMIs. The unknown gain matrix is determined by solving this delay-dependent LMIs. Finally, an illustrative example is given to demonstrate the validity of the theoretical results.
The continuous 1.5D terrain guarding problem: Discretization, optimal solutions, and PTAS
Directory of Open Access Journals (Sweden)
Stephan Friedrichs
2016-05-01
Full Text Available In the NP-hard continuous 1.5D Terrain Guarding Problem (TGP we are given an $x$-monotone chain of line segments in $R^2$ (the terrain $T$, and ask for the minimum number of guards (located anywhere on $T$ required to guard all of $T$. We construct guard candidate and witness sets $G, W \\subset T$ of polynomial size such that any feasible (optimal guard cover $G^* \\subseteq G$ for $W$ is also feasible (optimal for the continuous TGP. This discretization allows us to: (1 settle NP-completeness for the continuous TGP; (2 provide a Polynomial Time Approximation Scheme (PTAS for the continuous TGP using the PTAS for the discrete TGP by Gibson et al.; (3 formulate the continuous TGP as an Integer Linear Program (IP. Furthermore, we propose several filtering techniques reducing the size of our discretization, allowing us to devise an efficient IP-based algorithm that reliably provides optimal guard placements for terrains with up to $10^6$ vertices within minutes on a standard desktop computer.
Discrete Orthogonal Transforms and Neural Networks for Image Interpolation
Directory of Open Access Journals (Sweden)
J. Polec
1999-09-01
Full Text Available In this contribution we present transform and neural network approaches to the interpolation of images. From transform point of view, the principles from [1] are modified for 1st and 2nd order interpolation. We present several new interpolation discrete orthogonal transforms. From neural network point of view, we present interpolation possibilities of multilayer perceptrons. We use various configurations of neural networks for 1st and 2nd order interpolation. The results are compared by means of tables.
International Nuclear Information System (INIS)
Park, Ju H.
2007-01-01
This paper considers the robust stability analysis of cellular neural networks with discrete and distributed delays. Based on the Lyapunov stability theory and linear matrix inequality (LMI) technique, a novel stability criterion guaranteeing the global robust convergence of the equilibrium point is derived. The criterion can be solved easily by various convex optimization algorithms. An example is given to illustrate the usefulness of our results
International Nuclear Information System (INIS)
Huang Zhenkun; Wang Xinghua; Gao Feng
2006-01-01
In this Letter, we discuss discrete-time analogue of a continuous-time cellular neural network. Sufficient conditions are obtained for the existence of a unique almost periodic sequence solution which is globally attractive. Our results demonstrate dynamics of the formulated discrete-time analogue as mathematical models for the continuous-time cellular neural network in almost periodic case. Finally, a computer simulation illustrates the suitability of our discrete-time analogue as numerical algorithms in simulating the continuous-time cellular neural network conveniently
Khulood A. Dagher; Ahmed S. Al-Araji
2013-01-01
A particle swarm optimization algorithm and neural network like self-tuning PID controller for CSTR system is presented. The scheme of the discrete-time PID control structure is based on neural network and tuned the parameters of the PID controller by using a particle swarm optimization PSO technique as a simple and fast training algorithm. The proposed method has advantage that it is not necessary to use a combined structure of identification and decision because it used PSO. Simulation resu...
Global exponential stability of mixed discrete and distributively delayed cellular neural network
International Nuclear Information System (INIS)
Yao Hong-Xing; Zhou Jia-Yan
2011-01-01
This paper concernes analysis for the global exponential stability of a class of recurrent neural networks with mixed discrete and distributed delays. It first proves the existence and uniqueness of the balance point, then by employing the Lyapunov—Krasovskii functional and Young inequality, it gives the sufficient condition of global exponential stability of cellular neural network with mixed discrete and distributed delays, in addition, the example is provided to illustrate the applicability of the result. (general)
Single- and Multiple-Objective Optimization with Differential Evolution and Neural Networks
Rai, Man Mohan
2006-01-01
Genetic and evolutionary algorithms have been applied to solve numerous problems in engineering design where they have been used primarily as optimization procedures. These methods have an advantage over conventional gradient-based search procedures became they are capable of finding global optima of multi-modal functions and searching design spaces with disjoint feasible regions. They are also robust in the presence of noisy data. Another desirable feature of these methods is that they can efficiently use distributed and parallel computing resources since multiple function evaluations (flow simulations in aerodynamics design) can be performed simultaneously and independently on ultiple processors. For these reasons genetic and evolutionary algorithms are being used more frequently in design optimization. Examples include airfoil and wing design and compressor and turbine airfoil design. They are also finding increasing use in multiple-objective and multidisciplinary optimization. This lecture will focus on an evolutionary method that is a relatively new member to the general class of evolutionary methods called differential evolution (DE). This method is easy to use and program and it requires relatively few user-specified constants. These constants are easily determined for a wide class of problems. Fine-tuning the constants will off course yield the solution to the optimization problem at hand more rapidly. DE can be efficiently implemented on parallel computers and can be used for continuous, discrete and mixed discrete/continuous optimization problems. It does not require the objective function to be continuous and is noise tolerant. DE and applications to single and multiple-objective optimization will be included in the presentation and lecture notes. A method for aerodynamic design optimization that is based on neural networks will also be included as a part of this lecture. The method offers advantages over traditional optimization methods. It is more
In-plane Material Filters for the Discrete Material Optimization Method
DEFF Research Database (Denmark)
Sørensen, Rene; Lund, Erik
2015-01-01
, because the projection filter is a non-linear function of the design variables, the projected variables have to be re-scaled in a final so-called normalization filter. This is done to prevent the optimizer in creating superior, but non-physical pseudo-materials. The method is demonstrated on a series......This paper presents in-plane material filters for the Discrete Material Optimization method used for optimizing laminated composite structures. The filters make it possible for engineers to specify a minimum length scale which governs the minimum size of areas with constant material continuity....... Consequently, engineers can target the available production methods, and thereby increase its manufacturability while the optimizer is free to determine which material to apply together with an optimum location, shape, and size of these areas with constant material continuity. By doing so, engineers no longer...
Systematization of Accurate Discrete Optimization Methods
Directory of Open Access Journals (Sweden)
V. A. Ovchinnikov
2015-01-01
Full Text Available The object of study of this paper is to define accurate methods for solving combinatorial optimization problems of structural synthesis. The aim of the work is to systemize the exact methods of discrete optimization and define their applicability to solve practical problems.The article presents the analysis, generalization and systematization of classical methods and algorithms described in the educational and scientific literature.As a result of research a systematic presentation of combinatorial methods for discrete optimization described in various sources is given, their capabilities are described and properties of the tasks to be solved using the appropriate methods are specified.
Discrete-time optimal control and games on large intervals
Zaslavski, Alexander J
2017-01-01
Devoted to the structure of approximate solutions of discrete-time optimal control problems and approximate solutions of dynamic discrete-time two-player zero-sum games, this book presents results on properties of approximate solutions in an interval that is independent lengthwise, for all sufficiently large intervals. Results concerning the so-called turnpike property of optimal control problems and zero-sum games in the regions close to the endpoints of the time intervals are the main focus of this book. The description of the structure of approximate solutions on sufficiently large intervals and its stability will interest graduate students and mathematicians in optimal control and game theory, engineering, and economics. This book begins with a brief overview and moves on to analyze the structure of approximate solutions of autonomous nonconcave discrete-time optimal control Lagrange problems.Next the structures of approximate solutions of autonomous discrete-time optimal control problems that are discret...
Discrete-continuous analysis of optimal equipment replacement
YATSENKO, Yuri; HRITONENKO, Natali
2008-01-01
In Operations Research, the equipment replacement process is usually modeled in discrete time. The optimal replacement strategies are found from discrete (or integer) programming problems, well known for their analytic and computational complexity. An alternative approach is represented by continuous-time vintage capital models that explicitly involve the equipment lifetime and are described by nonlinear integral equations. Then the optimal replacement is determined via the opt...
Parker, R Gary
1988-01-01
This book treats the fundamental issues and algorithmic strategies emerging as the core of the discipline of discrete optimization in a comprehensive and rigorous fashion. Following an introductory chapter on computational complexity, the basic algorithmic results for the two major models of polynomial algorithms are introduced--models using matroids and linear programming. Further chapters treat the major non-polynomial algorithms: branch-and-bound and cutting planes. The text concludes with a chapter on heuristic algorithms.Several appendixes are included which review the fundamental ideas o
Coupling Strength and System Size Induce Firing Activity of Globally Coupled Neural Network
International Nuclear Information System (INIS)
Wei Duqu; Luo Xiaoshu; Zou Yanli
2008-01-01
We investigate how firing activity of globally coupled neural network depends on the coupling strength C and system size N. Network elements are described by space-clamped FitzHugh-Nagumo (SCFHN) neurons with the values of parameters at which no firing activity occurs. It is found that for a given appropriate coupling strength, there is an intermediate range of system size where the firing activity of globally coupled SCFHN neural network is induced and enhanced. On the other hand, for a given intermediate system size level, there exists an optimal value of coupling strength such that the intensity of firing activity reaches its maximum. These phenomena imply that the coupling strength and system size play a vital role in firing activity of neural network
Optimization of recurrent neural networks for time series modeling
DEFF Research Database (Denmark)
Pedersen, Morten With
1997-01-01
The present thesis is about optimization of recurrent neural networks applied to time series modeling. In particular is considered fully recurrent networks working from only a single external input, one layer of nonlinear hidden units and a li near output unit applied to prediction of discrete time...... series. The overall objective s are to improve training by application of second-order methods and to improve generalization ability by architecture optimization accomplished by pruning. The major topics covered in the thesis are: 1. The problem of training recurrent networks is analyzed from a numerical...... of solution obtained as well as computation time required. 3. A theoretical definition of the generalization error for recurrent networks is provided. This definition justifies a commonly adopted approach for estimating generalization ability. 4. The viability of pruning recurrent networks by the Optimal...
Engineering applications of discrete-time optimal control
DEFF Research Database (Denmark)
Vidal, Rene Victor Valqui; Ravn, Hans V.
1990-01-01
Many problems of design and operation of engineering systems can be formulated as optimal control problems where time has been discretisized. This is also true even if 'time' is not involved in the formulation of the problem, but rather another one-dimensional parameter. This paper gives a review...... of some well-known and new results in discrete time optimal control methods applicable to practical problem solving within engineering. Emphasis is placed on dynamic programming, the classical maximum principle and generalized versions of the maximum principle for optimal control of discrete time systems...
Galerkin v. discrete-optimal projection in nonlinear model reduction
Energy Technology Data Exchange (ETDEWEB)
Carlberg, Kevin Thomas [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Barone, Matthew Franklin [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Antil, Harbir [George Mason Univ., Fairfax, VA (United States)
2015-04-01
Discrete-optimal model-reduction techniques such as the Gauss{Newton with Approximated Tensors (GNAT) method have shown promise, as they have generated stable, accurate solutions for large-scale turbulent, compressible ow problems where standard Galerkin techniques have failed. However, there has been limited comparative analysis of the two approaches. This is due in part to difficulties arising from the fact that Galerkin techniques perform projection at the time-continuous level, while discrete-optimal techniques do so at the time-discrete level. This work provides a detailed theoretical and experimental comparison of the two techniques for two common classes of time integrators: linear multistep schemes and Runge{Kutta schemes. We present a number of new ndings, including conditions under which the discrete-optimal ROM has a time-continuous representation, conditions under which the two techniques are equivalent, and time-discrete error bounds for the two approaches. Perhaps most surprisingly, we demonstrate both theoretically and experimentally that decreasing the time step does not necessarily decrease the error for the discrete-optimal ROM; instead, the time step should be `matched' to the spectral content of the reduced basis. In numerical experiments carried out on a turbulent compressible- ow problem with over one million unknowns, we show that increasing the time step to an intermediate value decreases both the error and the simulation time of the discrete-optimal reduced-order model by an order of magnitude.
Discrete-time inverse optimal control for nonlinear systems
Sanchez, Edgar N
2013-01-01
Discrete-Time Inverse Optimal Control for Nonlinear Systems proposes a novel inverse optimal control scheme for stabilization and trajectory tracking of discrete-time nonlinear systems. This avoids the need to solve the associated Hamilton-Jacobi-Bellman equation and minimizes a cost functional, resulting in a more efficient controller. Design More Efficient Controllers for Stabilization and Trajectory Tracking of Discrete-Time Nonlinear Systems The book presents two approaches for controller synthesis: the first based on passivity theory and the second on a control Lyapunov function (CLF). Th
Intelligent discrete particle swarm optimization for multiprocessor task scheduling problem
Directory of Open Access Journals (Sweden)
S Sarathambekai
2017-03-01
Full Text Available Discrete particle swarm optimization is one of the most recently developed population-based meta-heuristic optimization algorithm in swarm intelligence that can be used in any discrete optimization problems. This article presents a discrete particle swarm optimization algorithm to efficiently schedule the tasks in the heterogeneous multiprocessor systems. All the optimization algorithms share a common algorithmic step, namely population initialization. It plays a significant role because it can affect the convergence speed and also the quality of the final solution. The random initialization is the most commonly used method in majority of the evolutionary algorithms to generate solutions in the initial population. The initial good quality solutions can facilitate the algorithm to locate the optimal solution or else it may prevent the algorithm from finding the optimal solution. Intelligence should be incorporated to generate the initial population in order to avoid the premature convergence. This article presents a discrete particle swarm optimization algorithm, which incorporates opposition-based technique to generate initial population and greedy algorithm to balance the load of the processors. Make span, flow time, and reliability cost are three different measures used to evaluate the efficiency of the proposed discrete particle swarm optimization algorithm for scheduling independent tasks in distributed systems. Computational simulations are done based on a set of benchmark instances to assess the performance of the proposed algorithm.
Quasicanonical structure of optimal control in constrained discrete systems
Sieniutycz, S.
2003-06-01
This paper considers discrete processes governed by difference rather than differential equations for the state transformation. The basic question asked is if and when Hamiltonian canonical structures are possible in optimal discrete systems. Considering constrained discrete control, general optimization algorithms are derived that constitute suitable theoretical and computational tools when evaluating extremum properties of constrained physical models. The mathematical basis of the general theory is the Bellman method of dynamic programming (DP) and its extension in the form of the so-called Carathéodory-Boltyanski (CB) stage criterion which allows a variation of the terminal state that is otherwise fixed in the Bellman's method. Two relatively unknown, powerful optimization algorithms are obtained: an unconventional discrete formalism of optimization based on a Hamiltonian for multistage systems with unconstrained intervals of holdup time, and the time interval constrained extension of the formalism. These results are general; namely, one arrives at: the discrete canonical Hamilton equations, maximum principles, and (at the continuous limit of processes with free intervals of time) the classical Hamilton-Jacobi theory along with all basic results of variational calculus. Vast spectrum of applications of the theory is briefly discussed.
Integrals of Motion for Discrete-Time Optimal Control Problems
Torres, Delfim F. M.
2003-01-01
We obtain a discrete time analog of E. Noether's theorem in Optimal Control, asserting that integrals of motion associated to the discrete time Pontryagin Maximum Principle can be computed from the quasi-invariance properties of the discrete time Lagrangian and discrete time control system. As corollaries, results for first-order and higher-order discrete problems of the calculus of variations are obtained.
Optimal system size for complex dynamics in random neural networks near criticality
Energy Technology Data Exchange (ETDEWEB)
Wainrib, Gilles, E-mail: wainrib@math.univ-paris13.fr [Laboratoire Analyse Géométrie et Applications, Université Paris XIII, Villetaneuse (France); García del Molino, Luis Carlos, E-mail: garciadelmolino@ijm.univ-paris-diderot.fr [Institute Jacques Monod, Université Paris VII, Paris (France)
2013-12-15
In this article, we consider a model of dynamical agents coupled through a random connectivity matrix, as introduced by Sompolinsky et al. [Phys. Rev. Lett. 61(3), 259–262 (1988)] in the context of random neural networks. When system size is infinite, it is known that increasing the disorder parameter induces a phase transition leading to chaotic dynamics. We observe and investigate here a novel phenomenon in the sub-critical regime for finite size systems: the probability of observing complex dynamics is maximal for an intermediate system size when the disorder is close enough to criticality. We give a more general explanation of this type of system size resonance in the framework of extreme values theory for eigenvalues of random matrices.
Optimal system size for complex dynamics in random neural networks near criticality
International Nuclear Information System (INIS)
Wainrib, Gilles; García del Molino, Luis Carlos
2013-01-01
In this article, we consider a model of dynamical agents coupled through a random connectivity matrix, as introduced by Sompolinsky et al. [Phys. Rev. Lett. 61(3), 259–262 (1988)] in the context of random neural networks. When system size is infinite, it is known that increasing the disorder parameter induces a phase transition leading to chaotic dynamics. We observe and investigate here a novel phenomenon in the sub-critical regime for finite size systems: the probability of observing complex dynamics is maximal for an intermediate system size when the disorder is close enough to criticality. We give a more general explanation of this type of system size resonance in the framework of extreme values theory for eigenvalues of random matrices
Search Parameter Optimization for Discrete, Bayesian, and Continuous Search Algorithms
2017-09-01
NAVAL POSTGRADUATE SCHOOL MONTEREY, CALIFORNIA THESIS SEARCH PARAMETER OPTIMIZATION FOR DISCRETE , BAYESIAN, AND CONTINUOUS SEARCH ALGORITHMS by...to 09-22-2017 4. TITLE AND SUBTITLE SEARCH PARAMETER OPTIMIZATION FOR DISCRETE , BAYESIAN, AND CON- TINUOUS SEARCH ALGORITHMS 5. FUNDING NUMBERS 6...simple search and rescue acts to prosecuting aerial/surface/submersible targets on mission. This research looks at varying the known discrete and
Meshes optimized for discrete exterior calculus (DEC).
Energy Technology Data Exchange (ETDEWEB)
Mousley, Sarah C. [Univ. of Illinois, Urbana-Champaign, IL (United States); Deakin, Michael [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Knupp, Patrick [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States); Mitchell, Scott A. [Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
2017-12-01
We study the optimization of an energy function used by the meshing community to measure and improve mesh quality. This energy is non-traditional because it is dependent on both the primal triangulation and its dual Voronoi (power) diagram. The energy is a measure of the mesh's quality for usage in Discrete Exterior Calculus (DEC), a method for numerically solving PDEs. In DEC, the PDE domain is triangulated and this mesh is used to obtain discrete approximations of the continuous operators in the PDE. The energy of a mesh gives an upper bound on the error of the discrete diagonal approximation of the Hodge star operator. In practice, one begins with an initial mesh and then makes adjustments to produce a mesh of lower energy. However, we have discovered several shortcomings in directly optimizing this energy, e.g. its non-convexity, and we show that the search for an optimized mesh may lead to mesh inversion (malformed triangles). We propose a new energy function to address some of these issues.
Cycles of a discrete time bipolar artificial neural network
International Nuclear Information System (INIS)
Cheng Suisun; Chen, J.-S.; Yueh, W.-C.
2009-01-01
A discrete time bipolar neural network depending on two parameters is studied. It is observed that its dynamical behaviors can be classified into six cases. For each case, the long time behaviors can be summarized in terms of fixed points, periodic points, basin of attractions, and related initial distributions. Mathematical reasons are supplied for these observations and applications in cellular automata are illustrated.
Global exponential stability of BAM neural networks with time-varying delays: The discrete-time case
Raja, R.; Marshal Anthoni, S.
2011-02-01
This paper deals with the problem of stability analysis for a class of discrete-time bidirectional associative memory (BAM) neural networks with time-varying delays. By employing the Lyapunov functional and linear matrix inequality (LMI) approach, a new sufficient conditions is proposed for the global exponential stability of discrete-time BAM neural networks. The proposed LMI based results can be easily checked by LMI control toolbox. Moreover, an example is also provided to demonstrate the effectiveness of the proposed method.
Global exponential stability for discrete-time neural networks with variable delays
International Nuclear Information System (INIS)
Chen Wuhua; Lu Xiaomei; Liang Dongying
2006-01-01
This Letter provides new exponential stability criteria for discrete-time neural networks with variable delays. The main technique is to reduce exponential convergence estimation of the neural network solution to that of one component of the corresponding solution by constructing Lyapunov function based on M-matrix. By introducing the tuning parameter diagonal matrix, the delay-independent and delay-dependent exponential stability conditions have been unified in the same mathematical formula. The effectiveness of the new results are illustrated by three examples
International Nuclear Information System (INIS)
Zhou Tiejun; Liu Yuehua; Li Xiaoping; Liu Yirong
2009-01-01
The discrete-time bidirectional associative memory neural network with periodic coefficients and infinite delays is studied. And not by employing the continuation theorem of coincidence degree theory as other literatures, but by constructing suitable Liapunov function, using fixed point theorem and some analysis techniques, a sufficient criterion is obtained which ensures the existence and global exponential stability of periodic solution for the type of discrete-time BAM neural network. The obtained result is less restrictive to the BAM neural networks than previously known criteria. Furthermore, it can be applied to the BAM neural network which signal transfer functions are neither bounded nor differentiable. In addition, an example and its numerical simulation are given to illustrate the effectiveness of the obtained result
Artificial neural network based particle size prediction of polymeric nanoparticles.
Youshia, John; Ali, Mohamed Ehab; Lamprecht, Alf
2017-10-01
Particle size of nanoparticles and the respective polydispersity are key factors influencing their biopharmaceutical behavior in a large variety of therapeutic applications. Predicting these attributes would skip many preliminary studies usually required to optimize formulations. The aim was to build a mathematical model capable of predicting the particle size of polymeric nanoparticles produced by a pharmaceutical polymer of choice. Polymer properties controlling the particle size were identified as molecular weight, hydrophobicity and surface activity, and were quantified by measuring polymer viscosity, contact angle and interfacial tension, respectively. A model was built using artificial neural network including these properties as input with particle size and polydispersity index as output. The established model successfully predicted particle size of nanoparticles covering a range of 70-400nm prepared from other polymers. The percentage bias for particle prediction was 2%, 4% and 6%, for the training, validation and testing data, respectively. Polymer surface activity was found to have the highest impact on the particle size followed by viscosity and finally hydrophobicity. Results of this study successfully highlighted polymer properties affecting particle size and confirmed the usefulness of artificial neural networks in predicting the particle size and polydispersity of polymeric nanoparticles. Copyright © 2017 Elsevier B.V. All rights reserved.
A Software Tool for Optimal Sizing of PV Systems in Malaysia
Directory of Open Access Journals (Sweden)
Tamer Khatib
2012-01-01
Full Text Available This paper presents a MATLAB based user friendly software tool called as PV.MY for optimal sizing of photovoltaic (PV systems. The software has the capabilities of predicting the metrological variables such as solar energy, ambient temperature and wind speed using artificial neural network (ANN, optimizes the PV module/ array tilt angle, optimizes the inverter size and calculate optimal capacities of PV array, battery, wind turbine and diesel generator in hybrid PV systems. The ANN based model for metrological prediction uses four meteorological variables, namely, sun shine ratio, day number and location coordinates. As for PV system sizing, iterative methods are used for determining the optimal sizing of three types of PV systems, which are standalone PV system, hybrid PV/wind system and hybrid PV/diesel generator system. The loss of load probability (LLP technique is used for optimization in which the energy sources capacities are the variables to be optimized considering very low LLP. As for determining the optimal PV panels tilt angle and inverter size, the Liu and Jordan model for solar energy incident on a tilt surface is used in optimizing the monthly tilt angle, while a model for inverter efficiency curve is used in the optimization of inverter size.
Discrete Biogeography Based Optimization for Feature Selection in Molecular Signatures.
Liu, Bo; Tian, Meihong; Zhang, Chunhua; Li, Xiangtao
2015-04-01
Biomarker discovery from high-dimensional data is a complex task in the development of efficient cancer diagnoses and classification. However, these data are usually redundant and noisy, and only a subset of them present distinct profiles for different classes of samples. Thus, selecting high discriminative genes from gene expression data has become increasingly interesting in the field of bioinformatics. In this paper, a discrete biogeography based optimization is proposed to select the good subset of informative gene relevant to the classification. In the proposed algorithm, firstly, the fisher-markov selector is used to choose fixed number of gene data. Secondly, to make biogeography based optimization suitable for the feature selection problem; discrete migration model and discrete mutation model are proposed to balance the exploration and exploitation ability. Then, discrete biogeography based optimization, as we called DBBO, is proposed by integrating discrete migration model and discrete mutation model. Finally, the DBBO method is used for feature selection, and three classifiers are used as the classifier with the 10 fold cross-validation method. In order to show the effective and efficiency of the algorithm, the proposed algorithm is tested on four breast cancer dataset benchmarks. Comparison with genetic algorithm, particle swarm optimization, differential evolution algorithm and hybrid biogeography based optimization, experimental results demonstrate that the proposed method is better or at least comparable with previous method from literature when considering the quality of the solutions obtained. © 2015 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.
Optimization of Operations Resources via Discrete Event Simulation Modeling
Joshi, B.; Morris, D.; White, N.; Unal, R.
1996-01-01
The resource levels required for operation and support of reusable launch vehicles are typically defined through discrete event simulation modeling. Minimizing these resources constitutes an optimization problem involving discrete variables and simulation. Conventional approaches to solve such optimization problems involving integer valued decision variables are the pattern search and statistical methods. However, in a simulation environment that is characterized by search spaces of unknown topology and stochastic measures, these optimization approaches often prove inadequate. In this paper, we have explored the applicability of genetic algorithms to the simulation domain. Genetic algorithms provide a robust search strategy that does not require continuity and differentiability of the problem domain. The genetic algorithm successfully minimized the operation and support activities for a space vehicle, through a discrete event simulation model. The practical issues associated with simulation optimization, such as stochastic variables and constraints, were also taken into consideration.
Mehraeen, Shahab; Dierks, Travis; Jagannathan, S; Crow, Mariesa L
2013-12-01
In this paper, the nearly optimal solution for discrete-time (DT) affine nonlinear control systems in the presence of partially unknown internal system dynamics and disturbances is considered. The approach is based on successive approximate solution of the Hamilton-Jacobi-Isaacs (HJI) equation, which appears in optimal control. Successive approximation approach for updating control and disturbance inputs for DT nonlinear affine systems are proposed. Moreover, sufficient conditions for the convergence of the approximate HJI solution to the saddle point are derived, and an iterative approach to approximate the HJI equation using a neural network (NN) is presented. Then, the requirement of full knowledge of the internal dynamics of the nonlinear DT system is relaxed by using a second NN online approximator. The result is a closed-loop optimal NN controller via offline learning. A numerical example is provided illustrating the effectiveness of the approach.
On the application of Discrete Time Optimal Control Concepts to ...
African Journals Online (AJOL)
On the application of Discrete Time Optimal Control Concepts to Economic Problems. ... Journal of the Nigerian Association of Mathematical Physics ... Abstract. An extension of the use of the maximum principle to solve Discrete-time Optimal Control Problems (DTOCP), in which the state equations are in the form of general ...
International Nuclear Information System (INIS)
Liu Yurong; Wang Zidong; Liu Xiaohui
2008-01-01
In this Letter, we investigate the state estimation problem for a new class of discrete-time neural networks with Markovian jumping parameters as well as mode-dependent mixed time-delays. The parameters of the discrete-time neural networks are subject to the switching from one mode to another at different times according to a Markov chain, and the mixed time-delays consist of both discrete and distributed delays that are dependent on the Markovian jumping mode. New techniques are developed to deal with the mixed time-delays in the discrete-time setting, and a novel Lyapunov-Krasovskii functional is put forward to reflect the mode-dependent time-delays. Sufficient conditions are established in terms of linear matrix inequalities (LMIs) that guarantee the existence of the state estimators. We show that both the existence conditions and the explicit expression of the desired estimator can be characterized in terms of the solution to an LMI. A numerical example is exploited to show the usefulness of the derived LMI-based conditions
Actor-critic-based optimal tracking for partially unknown nonlinear discrete-time systems.
Kiumarsi, Bahare; Lewis, Frank L
2015-01-01
This paper presents a partially model-free adaptive optimal control solution to the deterministic nonlinear discrete-time (DT) tracking control problem in the presence of input constraints. The tracking error dynamics and reference trajectory dynamics are first combined to form an augmented system. Then, a new discounted performance function based on the augmented system is presented for the optimal nonlinear tracking problem. In contrast to the standard solution, which finds the feedforward and feedback terms of the control input separately, the minimization of the proposed discounted performance function gives both feedback and feedforward parts of the control input simultaneously. This enables us to encode the input constraints into the optimization problem using a nonquadratic performance function. The DT tracking Bellman equation and tracking Hamilton-Jacobi-Bellman (HJB) are derived. An actor-critic-based reinforcement learning algorithm is used to learn the solution to the tracking HJB equation online without requiring knowledge of the system drift dynamics. That is, two neural networks (NNs), namely, actor NN and critic NN, are tuned online and simultaneously to generate the optimal bounded control policy. A simulation example is given to show the effectiveness of the proposed method.
Adaptive optimization and control using neural networks
Energy Technology Data Exchange (ETDEWEB)
Mead, W.C.; Brown, S.K.; Jones, R.D.; Bowling, P.S.; Barnes, C.W.
1993-10-22
Recent work has demonstrated the ability of neural-network-based controllers to optimize and control machines with complex, non-linear, relatively unknown control spaces. We present a brief overview of neural networks via a taxonomy illustrating some capabilities of different kinds of neural networks. We present some successful control examples, particularly the optimization and control of a small-angle negative ion source.
International Nuclear Information System (INIS)
Avci, E.
2007-01-01
In this paper, an automatic system is presented for word recognition using real Turkish word signals. This paper especially deals with combination of the feature extraction and classification from real Turkish word signals. A Discrete Wavelet Neural Network (DWNN) model is used, which consists of two layers: discrete wavelet layer and multi-layer perceptron. The discrete wavelet layer is used for adaptive feature extraction in the time-frequency domain and is composed of Discrete Wavelet Transform (DWT) and wavelet entropy. The multi-layer perceptron used for classification is a feed-forward neural network. The performance of the used system is evaluated by using noisy Turkish word signals. Test results showing the effectiveness of the proposed automatic system are presented in this paper. The rate of correct recognition is about 92.5% for the sample speech signals. (author)
International Nuclear Information System (INIS)
Huo Haifeng; Li Wantong
2009-01-01
This paper is concerned with the global stability characteristics of a system of equations modelling the dynamics of continuous-time bidirectional associative memory neural networks with impulses. Sufficient conditions which guarantee the existence of a unique equilibrium and its exponential stability of the networks are obtained. For the goal of computation, discrete-time analogues of the corresponding continuous-time bidirectional associative memory neural networks with impulses are also formulated and studied. Our results show that the above continuous-time and discrete-time systems with impulses preserve the dynamics of the networks without impulses when we make some modifications and impose some additional conditions on the systems, the convergence characteristics dynamics of the networks are preserved by both continuous-time and discrete-time systems with some restriction imposed on the impulse effect.
Comments on `A discrete optimal control problem for descriptor systems'
DEFF Research Database (Denmark)
Ravn, Hans
1990-01-01
In the above-mentioned work (see ibid., vol.34, p.177-81 (1989)), necessary and sufficient optimality conditions are derived for a discrete-time optimal problem, as well as other specific cases of implicit and explicit dynamic systems. The commenter corrects a mistake and demonstrates that there ......In the above-mentioned work (see ibid., vol.34, p.177-81 (1989)), necessary and sufficient optimality conditions are derived for a discrete-time optimal problem, as well as other specific cases of implicit and explicit dynamic systems. The commenter corrects a mistake and demonstrates...
Kumfor, Fiona; Irish, Muireann; Hodges, John R.; Piguet, Olivier
2013-01-01
Patients with frontotemporal dementia have pervasive changes in emotion recognition and social cognition, yet the neural changes underlying these emotion processing deficits remain unclear. The multimodal system model of emotion proposes that basic emotions are dependent on distinct brain regions, which undergo significant pathological changes in frontotemporal dementia. As such, this syndrome may provide important insight into the impact of neural network degeneration upon the innate ability to recognise emotions. This study used voxel-based morphometry to identify discrete neural correlates involved in the recognition of basic emotions (anger, disgust, fear, sadness, surprise and happiness) in frontotemporal dementia. Forty frontotemporal dementia patients (18 behavioural-variant, 11 semantic dementia, 11 progressive nonfluent aphasia) and 27 healthy controls were tested on two facial emotion recognition tasks: The Ekman 60 and Ekman Caricatures. Although each frontotemporal dementia group showed impaired recognition of negative emotions, distinct associations between emotion-specific task performance and changes in grey matter intensity emerged. Fear recognition was associated with the right amygdala; disgust recognition with the left insula; anger recognition with the left middle and superior temporal gyrus; and sadness recognition with the left subcallosal cingulate, indicating that discrete neural substrates are necessary for emotion recognition in frontotemporal dementia. The erosion of emotion-specific neural networks in neurodegenerative disorders may produce distinct profiles of performance that are relevant to understanding the neurobiological basis of emotion processing. PMID:23805313
State transformations and Hamiltonian structures for optimal control in discrete systems
Sieniutycz, S.
2006-04-01
Preserving usual definition of Hamiltonian H as the scalar product of rates and generalized momenta we investigate two basic classes of discrete optimal control processes governed by the difference rather than differential equations for the state transformation. The first class, linear in the time interval θ, secures the constancy of optimal H and satisfies a discrete Hamilton-Jacobi equation. The second class, nonlinear in θ, does not assure the constancy of optimal H and satisfies only a relationship that may be regarded as an equation of Hamilton-Jacobi type. The basic question asked is if and when Hamilton's canonical structures emerge in optimal discrete systems. For a constrained discrete control, general optimization algorithms are derived that constitute powerful theoretical and computational tools when evaluating extremum properties of constrained physical systems. The mathematical basis is Bellman's method of dynamic programming (DP) and its extension in the form of the so-called Carathéodory-Boltyanski (CB) stage optimality criterion which allows a variation of the terminal state that is otherwise fixed in Bellman's method. For systems with unconstrained intervals of the holdup time θ two powerful optimization algorithms are obtained: an unconventional discrete algorithm with a constant H and its counterpart for models nonlinear in θ. We also present the time-interval-constrained extension of the second algorithm. The results are general; namely, one arrives at: discrete canonical equations of Hamilton, maximum principles, and (at the continuous limit of processes with free intervals of time) the classical Hamilton-Jacobi theory, along with basic results of variational calculus. A vast spectrum of applications and an example are briefly discussed with particular attention paid to models nonlinear in the time interval θ.
Energy Technology Data Exchange (ETDEWEB)
Stavrakakis, G.M.; Karadimou, D.P.; Zervas, P.L.; Markatos, N.C. [Computational Fluid Dynamics Unit, School of Chemical Engineering, National Technical University of Athens, Heroon Polytechniou 9, GR-15780 Athens (Greece); Sarimveis, H. [Unit of Process Control and Informatics, School of Chemical Engineering, National Technical University of Athens, Heroon Polytechniou 9, GR-15780 Athens (Greece)
2011-02-15
The present paper presents a novel computational method to optimize window sizes for thermal comfort and indoor air quality in naturally ventilated buildings. The methodology is demonstrated by means of a prototype case, which corresponds to a single-sided naturally ventilated apartment. Initially, the airflow in and around the building is simulated using a Computational Fluid Dynamics model. Local prevailing weather conditions are imposed in the CFD model as inlet boundary conditions. The produced airflow patterns are utilized to predict thermal comfort indices, i.e. the PMV and its modifications for non-air-conditioned buildings, as well as indoor air quality indices, such as ventilation effectiveness based on carbon dioxide and volatile organic compounds removal. Mean values of these indices (output/objective variables) within the occupied zone are calculated for different window sizes (input/design variables), to generate a database of input-output data pairs. The database is then used to train and validate Radial Basis Function Artificial Neural Network input-output ''meta-models''. The produced meta-models are used to formulate an optimization problem, which takes into account special constraints recommended by design guidelines. It is concluded that the proposed methodology determines appropriate windows architectural designs for pleasant and healthy indoor environments. (author)
Modified Discrete Grey Wolf Optimizer Algorithm for Multilevel Image Thresholding
Directory of Open Access Journals (Sweden)
Linguo Li
2017-01-01
Full Text Available The computation of image segmentation has become more complicated with the increasing number of thresholds, and the option and application of the thresholds in image thresholding fields have become an NP problem at the same time. The paper puts forward the modified discrete grey wolf optimizer algorithm (MDGWO, which improves on the optimal solution updating mechanism of the search agent by the weights. Taking Kapur’s entropy as the optimized function and based on the discreteness of threshold in image segmentation, the paper firstly discretizes the grey wolf optimizer (GWO and then proposes a new attack strategy by using the weight coefficient to replace the search formula for optimal solution used in the original algorithm. The experimental results show that MDGWO can search out the optimal thresholds efficiently and precisely, which are very close to the result examined by exhaustive searches. In comparison with the electromagnetism optimization (EMO, the differential evolution (DE, the Artifical Bee Colony (ABC, and the classical GWO, it is concluded that MDGWO has advantages over the latter four in terms of image segmentation quality and objective function values and their stability.
Estimation of break location and size for loss of coolant accidents using neural networks
International Nuclear Information System (INIS)
Na, Man Gyun; Shin, Sun Ho; Jung, Dong Won; Kim, Soong Pyung; Jeong, Ji Hwan; Lee, Byung Chul
2004-01-01
In this work, a probabilistic neural network (PNN) that has been applied well to the classification problems is used in order to identify the break locations of loss of coolant accidents (LOCA) such as hot-leg, cold-leg and steam generator tubes. Also, a fuzzy neural network (FNN) is designed to estimate the break size. The inputs to PNN and FNN are time-integrated values obtained by integrating measurement signals during a short time interval after reactor scram. An automatic structure constructor for the fuzzy neural network automatically selects the input variables from the time-integrated values of many measured signals, and optimizes the number of rules and its related parameters. It is verified that the proposed algorithm identifies very well the break locations of LOCAs and also, estimate their break size accurately
Discrete ternary particle swarm optimization for area optimization of MPRM circuits
International Nuclear Information System (INIS)
Yu Haizhen; Wang Pengjun; Wang Disheng; Zhang Huihong
2013-01-01
Having the advantage of simplicity, robustness and low computational costs, the particle swarm optimization (PSO) algorithm is a powerful evolutionary computation tool for synthesis and optimization of Reed-Muller logic based circuits. Exploring discrete PSO and probabilistic transition rules, the discrete ternary particle swarm optimization (DTPSO) is proposed for mixed polarity Reed-Muller (MPRM) circuits. According to the characteristics of mixed polarity OR/XNOR expression, a tabular technique is improved, and it is applied in the polarity conversion of MPRM functions. DTPSO is introduced to search the best polarity for an area of MPRM circuits by building parameter mapping relationships between particles and polarities. The computational results show that the proposed DTPSO outperforms the reported method using maxterm conversion starting from POS Boolean functions. The average saving in the number of terms is about 11.5%; the algorithm is quite efficient in terms of CPU time and achieves 12.2% improvement on average. (semiconductor integrated circuits)
Uher, Vojtěch; Gajdoš, Petr; Radecký, Michal; Snášel, Václav
2016-01-01
The Differential Evolution (DE) is a widely used bioinspired optimization algorithm developed by Storn and Price. It is popular for its simplicity and robustness. This algorithm was primarily designed for real-valued problems and continuous functions, but several modified versions optimizing both integer and discrete-valued problems have been developed. The discrete-coded DE has been mostly used for combinatorial problems in a set of enumerative variants. However, the DE has a great potential in the spatial data analysis and pattern recognition. This paper formulates the problem as a search of a combination of distinct vertices which meet the specified conditions. It proposes a novel approach called the Multidimensional Discrete Differential Evolution (MDDE) applying the principle of the discrete-coded DE in discrete point clouds (PCs). The paper examines the local searching abilities of the MDDE and its convergence to the global optimum in the PCs. The multidimensional discrete vertices cannot be simply ordered to get a convenient course of the discrete data, which is crucial for good convergence of a population. A novel mutation operator utilizing linear ordering of spatial data based on the space filling curves is introduced. The algorithm is tested on several spatial datasets and optimization problems. The experiments show that the MDDE is an efficient and fast method for discrete optimizations in the multidimensional point clouds.
Optimal Brain Surgeon on Artificial Neural Networks in
DEFF Research Database (Denmark)
Christiansen, Niels Hørbye; Job, Jonas Hultmann; Klyver, Katrine
2012-01-01
It is shown how the procedure know as optimal brain surgeon can be used to trim and optimize artificial neural networks in nonlinear structural dynamics. Beside optimizing the neural network, and thereby minimizing computational cost in simulation, the surgery procedure can also serve as a quick...
Application of the minimum fuel neural network to music signals
DEFF Research Database (Denmark)
Harbo, Anders La-Cour
2004-01-01
) for finding sparse representations of music signals. This method is a set of two ordinary differential equations. We argue that the most important parameter for optimal use of this method is the discretization step size, and we demonstrate that this can be a priori determined. This significantly speeds up......Finding an optimal representation of a signal in an over-complete dictionary is often quite difficult. Since general results in this field are not very application friendly it truly helps to specify the framework as much as possible. We investigate the method Minimum Fuel Neural Network (MFNN...
Global stability of discrete-time recurrent neural networks with impulse effects
International Nuclear Information System (INIS)
Zhou, L; Li, C; Wan, J
2008-01-01
This paper formulates and studies a class of discrete-time recurrent neural networks with impulse effects. A stability criterion, which characterizes the effects of impulse and stability property of the corresponding impulse-free networks on the stability of the impulsive networks in an aggregate form, is established. Two simplified and numerically tractable criteria are also provided
Adaptive Neural Tracking Control for Discrete-Time Switched Nonlinear Systems with Dead Zone Inputs
Directory of Open Access Journals (Sweden)
Jidong Wang
2017-01-01
Full Text Available In this paper, the adaptive neural controllers of subsystems are proposed for a class of discrete-time switched nonlinear systems with dead zone inputs under arbitrary switching signals. Due to the complicated framework of the discrete-time switched nonlinear systems and the existence of the dead zone, it brings about difficulties for controlling such a class of systems. In addition, the radial basis function neural networks are employed to approximate the unknown terms of each subsystem. Switched update laws are designed while the parameter estimation is invariable until its corresponding subsystem is active. Then, the closed-loop system is stable and all the signals are bounded. Finally, to illustrate the effectiveness of the proposed method, an example is employed.
Discrete Bat Algorithm for Optimal Problem of Permutation Flow Shop Scheduling
Luo, Qifang; Zhou, Yongquan; Xie, Jian; Ma, Mingzhi; Li, Liangliang
2014-01-01
A discrete bat algorithm (DBA) is proposed for optimal permutation flow shop scheduling problem (PFSP). Firstly, the discrete bat algorithm is constructed based on the idea of basic bat algorithm, which divide whole scheduling problem into many subscheduling problems and then NEH heuristic be introduced to solve subscheduling problem. Secondly, some subsequences are operated with certain probability in the pulse emission and loudness phases. An intensive virtual population neighborhood search is integrated into the discrete bat algorithm to further improve the performance. Finally, the experimental results show the suitability and efficiency of the present discrete bat algorithm for optimal permutation flow shop scheduling problem. PMID:25243220
Discrete bat algorithm for optimal problem of permutation flow shop scheduling.
Luo, Qifang; Zhou, Yongquan; Xie, Jian; Ma, Mingzhi; Li, Liangliang
2014-01-01
A discrete bat algorithm (DBA) is proposed for optimal permutation flow shop scheduling problem (PFSP). Firstly, the discrete bat algorithm is constructed based on the idea of basic bat algorithm, which divide whole scheduling problem into many subscheduling problems and then NEH heuristic be introduced to solve subscheduling problem. Secondly, some subsequences are operated with certain probability in the pulse emission and loudness phases. An intensive virtual population neighborhood search is integrated into the discrete bat algorithm to further improve the performance. Finally, the experimental results show the suitability and efficiency of the present discrete bat algorithm for optimal permutation flow shop scheduling problem.
Directory of Open Access Journals (Sweden)
Shen-yan Chen
2015-01-01
Full Text Available This paper presents an Improved Genetic Algorithm with Two-Level Approximation (IGATA to minimize truss weight by simultaneously optimizing size, shape, and topology variables. On the basis of a previously presented truss sizing/topology optimization method based on two-level approximation and genetic algorithm (GA, a new method for adding shape variables is presented, in which the nodal positions are corresponding to a set of coordinate lists. A uniform optimization model including size/shape/topology variables is established. First, a first-level approximate problem is constructed to transform the original implicit problem to an explicit problem. To solve this explicit problem which involves size/shape/topology variables, GA is used to optimize individuals which include discrete topology variables and shape variables. When calculating the fitness value of each member in the current generation, a second-level approximation method is used to optimize the continuous size variables. With the introduction of shape variables, the original optimization algorithm was improved in individual coding strategy as well as GA execution techniques. Meanwhile, the update strategy of the first-level approximation problem was also improved. The results of numerical examples show that the proposed method is effective in dealing with the three kinds of design variables simultaneously, and the required computational cost for structural analysis is quite small.
Directory of Open Access Journals (Sweden)
S. Wang
2017-08-01
Full Text Available Electromagnetic acoustic transducers (EMATs are noncontact transducers generating ultrasonic waves directly in the conductive sample. Despite the advantages, their transduction efficiencies are relatively low, so it is imperative to build accurate multiphysics models of EMATs and optimize the structural parameters accordingly, using a suitable optimization algorithm. The optimizing process often involves a large number of runs of the computationally expensive numerical models, so metamodels as substitutes for the real numerical models are helpful for the optimizations. In this work the focus is on the artificial neural networks as the metamodels of an omnidirectional EMAT, including the multilayer feedforward networks trained with the basic and improved back propagation algorithms and the radial basis function networks with exact and nonexact interpolations. The developed neural-network programs are tested on an example problem. Then the model of an omnidirectional EMAT generating Lamb waves in a linearized steel plate is introduced, and various approaches to calculate the amplitudes of the displacement component waveforms are discussed. The neural-network metamodels are then built for the EMAT model and compared to the displacement component amplitude (or ratio of amplitudes surface data on a discrete grid of the design variables as the reference, applying a multifrequency model with FFT (fast Fourier transform/IFFT (inverse FFT processing. Finally the two-objective optimization problem is formulated with one objective function minimizing the ratio of the amplitude of the S0-mode Lamb wave to that of the A0 mode, and the other objective function minimizing as the negative amplitude of the A0 mode. Pareto fronts in the criterion space are solved with the neural-network models and the total time consumption is greatly decreased. From the study it could be observed that the radial basis function network with exact interpolation has the best
Optimization of operation cycles in BWRs using neural networks
International Nuclear Information System (INIS)
Ortiz S, J. J.; Castillo, A.; Alejandro P, D.
2011-11-01
The first results of a system for the optimization of operation cycles in boiling water reactors by means of a multi state recurrent neural network are present in this work. The neural network finds the best combination of fuel cells; fuel reloads and control bars patterns previously designed, according to an energy function that qualifies the performance of the three partial solutions for the solution of the whole problem. The partial solutions are designed by means of optimization systems non couple among them and that can use any optimization technique. The phase of the fuel axial design is not made and the size of the axial areas is fixed during the optimization process. The methodology was applied to design a balance cycle of 18 months for the reactors of the nuclear power station of Laguna Verde. The results show that is possible to find combinations of partial solutions that in set represent good solutions to the complete design problem of an operation cycle of a nuclear reactor. The results are compared with others obtained previously by other techniques. This system was developed in platform Li nux and programmed in Fortran 95 taking advantage of the 8 nuclei of a work station Dell Precision T7400. (Author)
Directory of Open Access Journals (Sweden)
Reza Sirjani
2017-09-01
Full Text Available Currently, many wind farms exist throughout the world and, in some cases, supply a significant portion of energy to networks. However, numerous uncertainties remain with respect to the amount of energy generated by wind turbines and other sophisticated operational aspects, such as voltage and reactive power management, which requires further development and consideration. To fix the problem of poor reactive power compensation in wind farms, optimal capacitor placement has been proposed in existing wind farms as a simple and relatively inexpensive method. However, the use of induction generators, transformers, and additional capacitors represent potential problems for the harmonics of a system and therefore must be taken into account at wind farms. The optimal location and size of capacitors at buses of an 80-MW wind farm were determined according to modelled wind speed, system equivalent circuits, and harmonics in order to minimize energy losses, optimize reactive power and reduce the management costs. The discrete version of the lightning search algorithm (DLSA is a powerful and flexible nature-inspired optimization technique that was developed and implemented herein for optimal capacitor placement in wind farms. The obtained results are compared with the results of the genetic algorithm (GA and the discrete harmony search algorithm (DHSA.
Optimization of stochastic discrete systems and control on complex networks computational networks
Lozovanu, Dmitrii
2014-01-01
This book presents the latest findings on stochastic dynamic programming models and on solving optimal control problems in networks. It includes the authors' new findings on determining the optimal solution of discrete optimal control problems in networks and on solving game variants of Markov decision problems in the context of computational networks. First, the book studies the finite state space of Markov processes and reviews the existing methods and algorithms for determining the main characteristics in Markov chains, before proposing new approaches based on dynamic programming and combinatorial methods. Chapter two is dedicated to infinite horizon stochastic discrete optimal control models and Markov decision problems with average and expected total discounted optimization criteria, while Chapter three develops a special game-theoretical approach to Markov decision processes and stochastic discrete optimal control problems. In closing, the book's final chapter is devoted to finite horizon stochastic con...
Petrović, Jelena; Ibrić, Svetlana; Betz, Gabriele; Đurić, Zorica
2012-05-30
The main objective of the study was to develop artificial intelligence methods for optimization of drug release from matrix tablets regardless of the matrix type. Static and dynamic artificial neural networks of the same topology were developed to model dissolution profiles of different matrix tablets types (hydrophilic/lipid) using formulation composition, compression force used for tableting and tablets porosity and tensile strength as input data. Potential application of decision trees in discovering knowledge from experimental data was also investigated. Polyethylene oxide polymer and glyceryl palmitostearate were used as matrix forming materials for hydrophilic and lipid matrix tablets, respectively whereas selected model drugs were diclofenac sodium and caffeine. Matrix tablets were prepared by direct compression method and tested for in vitro dissolution profiles. Optimization of static and dynamic neural networks used for modeling of drug release was performed using Monte Carlo simulations or genetic algorithms optimizer. Decision trees were constructed following discretization of data. Calculated difference (f(1)) and similarity (f(2)) factors for predicted and experimentally obtained dissolution profiles of test matrix tablets formulations indicate that Elman dynamic neural networks as well as decision trees are capable of accurate predictions of both hydrophilic and lipid matrix tablets dissolution profiles. Elman neural networks were compared to most frequently used static network, Multi-layered perceptron, and superiority of Elman networks have been demonstrated. Developed methods allow simple, yet very precise way of drug release predictions for both hydrophilic and lipid matrix tablets having controlled drug release. Copyright © 2012 Elsevier B.V. All rights reserved.
A Fourier analysis on the maximum acceptable grid size for discrete proton beam dose calculation
International Nuclear Information System (INIS)
Li, Haisen S.; Romeijn, H. Edwin; Dempsey, James F.
2006-01-01
We developed an analytical method for determining the maximum acceptable grid size for discrete dose calculation in proton therapy treatment plan optimization, so that the accuracy of the optimized dose distribution is guaranteed in the phase of dose sampling and the superfluous computational work is avoided. The accuracy of dose sampling was judged by the criterion that the continuous dose distribution could be reconstructed from the discrete dose within a 2% error limit. To keep the error caused by the discrete dose sampling under a 2% limit, the dose grid size cannot exceed a maximum acceptable value. The method was based on Fourier analysis and the Shannon-Nyquist sampling theorem as an extension of our previous analysis for photon beam intensity modulated radiation therapy [J. F. Dempsey, H. E. Romeijn, J. G. Li, D. A. Low, and J. R. Palta, Med. Phys. 32, 380-388 (2005)]. The proton beam model used for the analysis was a near mono-energetic (of width about 1% the incident energy) and monodirectional infinitesimal (nonintegrated) pencil beam in water medium. By monodirection, we mean that the proton particles are in the same direction before entering the water medium and the various scattering prior to entrance to water is not taken into account. In intensity modulated proton therapy, the elementary intensity modulation entity for proton therapy is either an infinitesimal or finite sized beamlet. Since a finite sized beamlet is the superposition of infinitesimal pencil beams, the result of the maximum acceptable grid size obtained with infinitesimal pencil beam also applies to finite sized beamlet. The analytic Bragg curve function proposed by Bortfeld [T. Bortfeld, Med. Phys. 24, 2024-2033 (1997)] was employed. The lateral profile was approximated by a depth dependent Gaussian distribution. The model included the spreads of the Bragg peak and the lateral profiles due to multiple Coulomb scattering. The dependence of the maximum acceptable dose grid size on the
Fast and Epsilon-Optimal Discretized Pursuit Learning Automata.
Zhang, JunQi; Wang, Cheng; Zhou, MengChu
2015-10-01
Learning automata (LA) are powerful tools for reinforcement learning. A discretized pursuit LA is the most popular one among them. During an iteration its operation consists of three basic phases: 1) selecting the next action; 2) finding the optimal estimated action; and 3) updating the state probability. However, when the number of actions is large, the learning becomes extremely slow because there are too many updates to be made at each iteration. The increased updates are mostly from phases 1 and 3. A new fast discretized pursuit LA with assured ε -optimality is proposed to perform both phases 1 and 3 with the computational complexity independent of the number of actions. Apart from its low computational complexity, it achieves faster convergence speed than the classical one when operating in stationary environments. This paper can promote the applications of LA toward the large-scale-action oriented area that requires efficient reinforcement learning tools with assured ε -optimality, fast convergence speed, and low computational complexity for each iteration.
Neural Network for Optimization of Existing Control Systems
DEFF Research Database (Denmark)
Madsen, Per Printz
1995-01-01
The purpose of this paper is to develop methods to use Neural Network based Controllers (NNC) as an optimization tool for existing control systems.......The purpose of this paper is to develop methods to use Neural Network based Controllers (NNC) as an optimization tool for existing control systems....
Spatial Treatment of the Slab-geometry Discrete Ordinates Equations Using Artificial Neural Networks
International Nuclear Information System (INIS)
Brantley, P S
2001-01-01
An artificial neural network (ANN) method is developed for treating the spatial variable of the one-group slab-geometry discrete ordinates (S N ) equations in a homogeneous medium with linearly anisotropic scattering. This ANN method takes advantage of the function approximation capability of multilayer ANNs. The discrete ordinates angular flux is approximated by a multilayer ANN with a single input representing the spatial variable x and N outputs representing the angular flux in each of the discrete ordinates angular directions. A global objective function is formulated which measures how accurately the output of the ANN approximates the solution of the discrete ordinates equations and boundary conditions at specified spatial points. Minimization of this objective function determines the appropriate values for the parameters of the ANN. Numerical results are presented demonstrating the accuracy of the method for both fixed source and incident angular flux problems
Chen, Guiling; Li, Dingshi; Shi, Lin; van Gaans, Onno; Verduyn Lunel, Sjoerd
2018-03-01
We present new conditions for asymptotic stability and exponential stability of a class of stochastic recurrent neural networks with discrete and distributed time varying delays. Our approach is based on the method using fixed point theory, which do not resort to any Liapunov function or Liapunov functional. Our results neither require the boundedness, monotonicity and differentiability of the activation functions nor differentiability of the time varying delays. In particular, a class of neural networks without stochastic perturbations is also considered. Examples are given to illustrate our main results.
Global stability of stochastic high-order neural networks with discrete and distributed delays
International Nuclear Information System (INIS)
Wang Zidong; Fang Jianan; Liu Xiaohui
2008-01-01
High-order neural networks can be considered as an expansion of Hopfield neural networks, and have stronger approximation property, faster convergence rate, greater storage capacity, and higher fault tolerance than lower-order neural networks. In this paper, the global asymptotic stability analysis problem is considered for a class of stochastic high-order neural networks with discrete and distributed time-delays. Based on an Lyapunov-Krasovskii functional and the stochastic stability analysis theory, several sufficient conditions are derived, which guarantee the global asymptotic convergence of the equilibrium point in the mean square. It is shown that the stochastic high-order delayed neural networks under consideration are globally asymptotically stable in the mean square if two linear matrix inequalities (LMIs) are feasible, where the feasibility of LMIs can be readily checked by the Matlab LMI toolbox. It is also shown that the main results in this paper cover some recently published works. A numerical example is given to demonstrate the usefulness of the proposed global stability criteria
A one-layer recurrent neural network for constrained nonsmooth optimization.
Liu, Qingshan; Wang, Jun
2011-10-01
This paper presents a novel one-layer recurrent neural network modeled by means of a differential inclusion for solving nonsmooth optimization problems, in which the number of neurons in the proposed neural network is the same as the number of decision variables of optimization problems. Compared with existing neural networks for nonsmooth optimization problems, the global convexity condition on the objective functions and constraints is relaxed, which allows the objective functions and constraints to be nonconvex. It is proven that the state variables of the proposed neural network are convergent to optimal solutions if a single design parameter in the model is larger than a derived lower bound. Numerical examples with simulation results substantiate the effectiveness and illustrate the characteristics of the proposed neural network.
Liu, Qingshan; Guo, Zhishan; Wang, Jun
2012-02-01
In this paper, a one-layer recurrent neural network is proposed for solving pseudoconvex optimization problems subject to linear equality and bound constraints. Compared with the existing neural networks for optimization (e.g., the projection neural networks), the proposed neural network is capable of solving more general pseudoconvex optimization problems with equality and bound constraints. Moreover, it is capable of solving constrained fractional programming problems as a special case. The convergence of the state variables of the proposed neural network to achieve solution optimality is guaranteed as long as the designed parameters in the model are larger than the derived lower bounds. Numerical examples with simulation results illustrate the effectiveness and characteristics of the proposed neural network. In addition, an application for dynamic portfolio optimization is discussed. Copyright © 2011 Elsevier Ltd. All rights reserved.
Value Iteration Adaptive Dynamic Programming for Optimal Control of Discrete-Time Nonlinear Systems.
Wei, Qinglai; Liu, Derong; Lin, Hanquan
2016-03-01
In this paper, a value iteration adaptive dynamic programming (ADP) algorithm is developed to solve infinite horizon undiscounted optimal control problems for discrete-time nonlinear systems. The present value iteration ADP algorithm permits an arbitrary positive semi-definite function to initialize the algorithm. A novel convergence analysis is developed to guarantee that the iterative value function converges to the optimal performance index function. Initialized by different initial functions, it is proven that the iterative value function will be monotonically nonincreasing, monotonically nondecreasing, or nonmonotonic and will converge to the optimum. In this paper, for the first time, the admissibility properties of the iterative control laws are developed for value iteration algorithms. It is emphasized that new termination criteria are established to guarantee the effectiveness of the iterative control laws. Neural networks are used to approximate the iterative value function and compute the iterative control law, respectively, for facilitating the implementation of the iterative ADP algorithm. Finally, two simulation examples are given to illustrate the performance of the present method.
Neural networks for tracking of unknown SISO discrete-time nonlinear dynamic systems.
Aftab, Muhammad Saleheen; Shafiq, Muhammad
2015-11-01
This article presents a Lyapunov function based neural network tracking (LNT) strategy for single-input, single-output (SISO) discrete-time nonlinear dynamic systems. The proposed LNT architecture is composed of two feedforward neural networks operating as controller and estimator. A Lyapunov function based back propagation learning algorithm is used for online adjustment of the controller and estimator parameters. The controller and estimator error convergence and closed-loop system stability analysis is performed by Lyapunov stability theory. Moreover, two simulation examples and one real-time experiment are investigated as case studies. The achieved results successfully validate the controller performance. Copyright © 2015 ISA. Published by Elsevier Ltd. All rights reserved.
Neural Meta-Memes Framework for Combinatorial Optimization
Song, Li Qin; Lim, Meng Hiot; Ong, Yew Soon
In this paper, we present a Neural Meta-Memes Framework (NMMF) for combinatorial optimization. NMMF is a framework which models basic optimization algorithms as memes and manages them dynamically when solving combinatorial problems. NMMF encompasses neural networks which serve as the overall planner/coordinator to balance the workload between memes. We show the efficacy of the proposed NMMF through empirical study on a class of combinatorial problem, the quadratic assignment problem (QAP).
Choi, Hyun Duck; Ahn, Choon Ki; Karimi, Hamid Reza; Lim, Myo Taeg
2017-10-01
This paper studies delay-dependent exponential dissipative and l 2 - l ∞ filtering problems for discrete-time switched neural networks (DSNNs) including time-delayed states. By introducing a novel discrete-time inequality, which is a discrete-time version of the continuous-time Wirtinger-type inequality, we establish new sets of linear matrix inequality (LMI) criteria such that discrete-time filtering error systems are exponentially stable with guaranteed performances in the exponential dissipative and l 2 - l ∞ senses. The design of the desired exponential dissipative and l 2 - l ∞ filters for DSNNs can be achieved by solving the proposed sets of LMI conditions. Via numerical simulation results, we show the validity of the desired discrete-time filter design approach.
A stochastic-field description of finite-size spiking neural networks.
Dumont, Grégory; Payeur, Alexandre; Longtin, André
2017-08-01
Neural network dynamics are governed by the interaction of spiking neurons. Stochastic aspects of single-neuron dynamics propagate up to the network level and shape the dynamical and informational properties of the population. Mean-field models of population activity disregard the finite-size stochastic fluctuations of network dynamics and thus offer a deterministic description of the system. Here, we derive a stochastic partial differential equation (SPDE) describing the temporal evolution of the finite-size refractory density, which represents the proportion of neurons in a given refractory state at any given time. The population activity-the density of active neurons per unit time-is easily extracted from this refractory density. The SPDE includes finite-size effects through a two-dimensional Gaussian white noise that acts both in time and along the refractory dimension. For an infinite number of neurons the standard mean-field theory is recovered. A discretization of the SPDE along its characteristic curves allows direct simulations of the activity of large but finite spiking networks; this constitutes the main advantage of our approach. Linearizing the SPDE with respect to the deterministic asynchronous state allows the theoretical investigation of finite-size activity fluctuations. In particular, analytical expressions for the power spectrum and autocorrelation of activity fluctuations are obtained. Moreover, our approach can be adapted to incorporate multiple interacting populations and quasi-renewal single-neuron dynamics.
Thermodynamic framework for discrete optimal control in multiphase flow systems
Sieniutycz, Stanislaw
1999-08-01
Bellman's method of dynamic programming is used to synthesize diverse optimization approaches to active (work producing) and inactive (entropy generating) multiphase flow systems. Thermal machines, optimally controlled unit operations, nonlinear heat conduction, spontaneous relaxation processes, and self-propagating wave fronts are all shown to satisfy a discrete Hamilton-Jacobi-Bellman equation and a corresponding discrete optimization algorithm of Pontryagin's type, with the maximum principle for a Hamiltonian. The extremal structures are always canonical. A common unifying criterion is set for all considered systems, which is the criterion of a minimum generated entropy. It is shown that constraints can modify the entropy functionals in a different way for each group of the processes considered; thus the resulting structures of these functionals may differ significantly. Practical conclusions are formulated regarding the energy savings and energy policy in optimally controlled systems.
Jin, Long; Liao, Bolin; Liu, Mei; Xiao, Lin; Guo, Dongsheng; Yan, Xiaogang
2017-01-01
By incorporating the physical constraints in joint space, a different-level simultaneous minimization scheme, which takes both the robot kinematics and robot dynamics into account, is presented and investigated for fault-tolerant motion planning of redundant manipulator in this paper. The scheme is reformulated as a quadratic program (QP) with equality and bound constraints, which is then solved by a discrete-time recurrent neural network. Simulative verifications based on a six-link planar redundant robot manipulator substantiate the efficacy and accuracy of the presented acceleration fault-tolerant scheme, the resultant QP and the corresponding discrete-time recurrent neural network.
International Nuclear Information System (INIS)
Ali, M. Syed
2014-01-01
In this paper, the global asymptotic stability problem of Markovian jumping stochastic Cohen—Grossberg neural networks with discrete and distributed time-varying delays (MJSCGNNs) is considered. A novel LMI-based stability criterion is obtained by constructing a new Lyapunov functional to guarantee the asymptotic stability of MJSCGNNs. Our results can be easily verified and they are also less restrictive than previously known criteria and can be applied to Cohen—Grossberg neural networks, recurrent neural networks, and cellular neural networks. Finally, the proposed stability conditions are demonstrated with numerical examples
A one-layer recurrent neural network for constrained nonconvex optimization.
Li, Guocheng; Yan, Zheng; Wang, Jun
2015-01-01
In this paper, a one-layer recurrent neural network is proposed for solving nonconvex optimization problems subject to general inequality constraints, designed based on an exact penalty function method. It is proved herein that any neuron state of the proposed neural network is convergent to the feasible region in finite time and stays there thereafter, provided that the penalty parameter is sufficiently large. The lower bounds of the penalty parameter and convergence time are also estimated. In addition, any neural state of the proposed neural network is convergent to its equilibrium point set which satisfies the Karush-Kuhn-Tucker conditions of the optimization problem. Moreover, the equilibrium point set is equivalent to the optimal solution to the nonconvex optimization problem if the objective function and constraints satisfy given conditions. Four numerical examples are provided to illustrate the performances of the proposed neural network.
Sampled-data and discrete-time H2 optimal control
Trentelman, Harry L.; Stoorvogel, Anton A.
1993-01-01
This paper deals with the sampled-data H2 optimal control problem. Given a linear time-invariant continuous-time system, the problem of minimizing the H2 performance over all sampled-data controllers with a fixed sampling period can be reduced to a pure discrete-time H2 optimal control problem. This
Real-time parameter optimization based on neural network for smart injection molding
Lee, H.; Liau, Y.; Ryu, K.
2018-03-01
The manufacturing industry has been facing several challenges, including sustainability, performance and quality of production. Manufacturers attempt to enhance the competitiveness of companies by implementing CPS (Cyber-Physical Systems) through the convergence of IoT(Internet of Things) and ICT(Information & Communication Technology) in the manufacturing process level. Injection molding process has a short cycle time and high productivity. This features have been making it suitable for mass production. In addition, this process is used to produce precise parts in various industry fields such as automobiles, optics and medical devices. Injection molding process has a mixture of discrete and continuous variables. In order to optimized the quality, variables that is generated in the injection molding process must be considered. Furthermore, Optimal parameter setting is time-consuming work to predict the optimum quality of the product. Since the process parameter cannot be easily corrected during the process execution. In this research, we propose a neural network based real-time process parameter optimization methodology that sets optimal process parameters by using mold data, molding machine data, and response data. This paper is expected to have academic contribution as a novel study of parameter optimization during production compare with pre - production parameter optimization in typical studies.
Discrete particle swarm optimization for identifying community structures in signed social networks.
Cai, Qing; Gong, Maoguo; Shen, Bo; Ma, Lijia; Jiao, Licheng
2014-10-01
Modern science of networks has facilitated us with enormous convenience to the understanding of complex systems. Community structure is believed to be one of the notable features of complex networks representing real complicated systems. Very often, uncovering community structures in networks can be regarded as an optimization problem, thus, many evolutionary algorithms based approaches have been put forward. Particle swarm optimization (PSO) is an artificial intelligent algorithm originated from social behavior such as birds flocking and fish schooling. PSO has been proved to be an effective optimization technique. However, PSO was originally designed for continuous optimization which confounds its applications to discrete contexts. In this paper, a novel discrete PSO algorithm is suggested for identifying community structures in signed networks. In the suggested method, particles' status has been redesigned in discrete form so as to make PSO proper for discrete scenarios, and particles' updating rules have been reformulated by making use of the topology of the signed network. Extensive experiments compared with three state-of-the-art approaches on both synthetic and real-world signed networks demonstrate that the proposed method is effective and promising. Copyright © 2014 Elsevier Ltd. All rights reserved.
Dynamic Optimization of a Polymer Flooding Process Based on Implicit Discrete Maximum Principle
Directory of Open Access Journals (Sweden)
Yang Lei
2012-01-01
Full Text Available Polymer flooding is one of the most important technologies for enhanced oil recovery (EOR. In this paper, an optimal control model of distributed parameter systems (DPSs for polymer injection strategies is established, which involves the performance index as maximum of the profit, the governing equations as the fluid flow equations of polymer flooding, and some inequality constraints as polymer concentration and injection amount limitation. The optimal control model is discretized by full implicit finite-difference method. To cope with the discrete optimal control problem (OCP, the necessary conditions for optimality are obtained through application of the calculus of variations and Pontryagin’s discrete maximum principle. A modified gradient method with new adjoint construction is proposed for the computation of optimal injection strategies. The numerical results of an example illustrate the effectiveness of the proposed method.
PARTICLE SWARM OPTIMIZATION (PSO FOR TRAINING OPTIMIZATION ON CONVOLUTIONAL NEURAL NETWORK (CNN
Directory of Open Access Journals (Sweden)
Arie Rachmad Syulistyo
2016-02-01
Full Text Available Neural network attracts plenty of researchers lately. Substantial number of renowned universities have developed neural network for various both academically and industrially applications. Neural network shows considerable performance on various purposes. Nevertheless, for complex applications, neural network’s accuracy significantly deteriorates. To tackle the aforementioned drawback, lot of researches had been undertaken on the improvement of the standard neural network. One of the most promising modifications on standard neural network for complex applications is deep learning method. In this paper, we proposed the utilization of Particle Swarm Optimization (PSO in Convolutional Neural Networks (CNNs, which is one of the basic methods in deep learning. The use of PSO on the training process aims to optimize the results of the solution vectors on CNN in order to improve the recognition accuracy. The data used in this research is handwritten digit from MNIST. The experiments exhibited that the accuracy can be attained in 4 epoch is 95.08%. This result was better than the conventional CNN and DBN. The execution time was also almost similar to the conventional CNN. Therefore, the proposed method was a promising method.
Hybrid discrete PSO and OPF approach for optimization of biomass fueled micro-scale energy system
International Nuclear Information System (INIS)
Gómez-González, M.; López, A.; Jurado, F.
2013-01-01
Highlights: ► Method to determine the optimal location and size of biomass power plants. ► The proposed approach is a hybrid of PSO algorithm and optimal power flow. ► Comparison among the proposed algorithm and other methods. ► Computational costs are enough lower than that required for exhaustive search. - Abstract: This paper addresses generation of electricity in the specific aspect of finding the best location and sizing of biomass fueled gas micro-turbine power plants, taking into account the variables involved in the problem, such as the local distribution of biomass resources, biomass transportation and extraction costs, operation and maintenance costs, power losses costs, network operation costs, and technical constraints. In this paper a hybrid method is introduced employing discrete particle swarm optimization and optimal power flow. The approach can be applied to search the best sites and capacities to connect biomass fueled gas micro-turbine power systems in a distribution network among a large number of potential combinations and considering the technical constraints of the network. A fair comparison among the proposed algorithm and other methods is performed.
Empirical Investigation of Optimization Algorithms in Neural Machine Translation
Directory of Open Access Journals (Sweden)
Bahar Parnia
2017-06-01
Full Text Available Training neural networks is a non-convex and a high-dimensional optimization problem. In this paper, we provide a comparative study of the most popular stochastic optimization techniques used to train neural networks. We evaluate the methods in terms of convergence speed, translation quality, and training stability. In addition, we investigate combinations that seek to improve optimization in terms of these aspects. We train state-of-the-art attention-based models and apply them to perform neural machine translation. We demonstrate our results on two tasks: WMT 2016 En→Ro and WMT 2015 De→En.
DEFF Research Database (Denmark)
Munoz, Eduardo; Stolpe, Mathias; Bendsøe, Martin P.
2009-01-01
in any discrete angle optimization design, or material selection problems. The mathematical modeling of this problem is more general than the one of standard topology optimization. When considering only two material candidates with a considerable difference in stiffness, it corresponds exactly...... to a topology optimization problem. The problem is modeled as a discrete design problem coming from a finite element discretization of the continuum problem. This discretization is made of shell or plate elements. For each element (selection domain), only one of the material candidates must be selected...... of the relaxed master problem and the current best compliance (weight) found get close enough with respect to certain tolerance. The method is investigated by computational means, using the finite element method to solve the analysis problems, and a commercial branch and cut method for solving the relaxed master...
Cao, Jianfang; Cui, Hongyan; Shi, Hao; Jiao, Lijuan
2016-01-01
A back-propagation (BP) neural network can solve complicated random nonlinear mapping problems; therefore, it can be applied to a wide range of problems. However, as the sample size increases, the time required to train BP neural networks becomes lengthy. Moreover, the classification accuracy decreases as well. To improve the classification accuracy and runtime efficiency of the BP neural network algorithm, we proposed a parallel design and realization method for a particle swarm optimization (PSO)-optimized BP neural network based on MapReduce on the Hadoop platform using both the PSO algorithm and a parallel design. The PSO algorithm was used to optimize the BP neural network's initial weights and thresholds and improve the accuracy of the classification algorithm. The MapReduce parallel programming model was utilized to achieve parallel processing of the BP algorithm, thereby solving the problems of hardware and communication overhead when the BP neural network addresses big data. Datasets on 5 different scales were constructed using the scene image library from the SUN Database. The classification accuracy of the parallel PSO-BP neural network algorithm is approximately 92%, and the system efficiency is approximately 0.85, which presents obvious advantages when processing big data. The algorithm proposed in this study demonstrated both higher classification accuracy and improved time efficiency, which represents a significant improvement obtained from applying parallel processing to an intelligent algorithm on big data.
A one-layer recurrent neural network for constrained nonsmooth invex optimization.
Li, Guocheng; Yan, Zheng; Wang, Jun
2014-02-01
Invexity is an important notion in nonconvex optimization. In this paper, a one-layer recurrent neural network is proposed for solving constrained nonsmooth invex optimization problems, designed based on an exact penalty function method. It is proved herein that any state of the proposed neural network is globally convergent to the optimal solution set of constrained invex optimization problems, with a sufficiently large penalty parameter. In addition, any neural state is globally convergent to the unique optimal solution, provided that the objective function and constraint functions are pseudoconvex. Moreover, any neural state is globally convergent to the feasible region in finite time and stays there thereafter. The lower bounds of the penalty parameter and convergence time are also estimated. Two numerical examples are provided to illustrate the performances of the proposed neural network. Copyright © 2013 Elsevier Ltd. All rights reserved.
Cellular Neural Networks for NP-Hard Optimization
Directory of Open Access Journals (Sweden)
Mária Ercsey-Ravasz
2009-02-01
Full Text Available A cellular neural/nonlinear network (CNN is used for NP-hard optimization. We prove that a CNN in which the parameters of all cells can be separately controlled is the analog correspondent of a two-dimensional Ising-type (Edwards-Anderson spin-glass system. Using the properties of CNN, we show that one single operation (template always yields a local minimum of the spin-glass energy function. This way, a very fast optimization method, similar to simulated annealing, can be built. Estimating the simulation time needed on CNN-based computers, and comparing it with the time needed on normal digital computers using the simulated annealing algorithm, the results are astonishing. CNN computers could be faster than digital computers already at 10×10 lattice sizes. The local control of the template parameters was already partially realized on some of the hardwares, we think this study could further motivate their development in this direction.
DEFF Research Database (Denmark)
Achtziger, Wolfgang; Stolpe, Mathias
2007-01-01
this problem is well-studied for continuous bar areas, we consider in this study the case of discrete areas. This problem is of major practical relevance if the truss must be built from pre-produced bars with given areas. As a special case, we consider the design problem for a single available bar area, i.......e., a 0/1 problem. In contrast to the heuristic methods considered in many other approaches, our goal is to compute guaranteed globally optimal structures. This is done by a branch-and-bound method for which convergence can be proven. In this branch-and-bound framework, lower bounds of the optimal......-integer problems. The main intention of this paper is to provide optimal solutions for single and multiple load benchmark examples, which can be used for testing and validating other methods or heuristics for the treatment of this discrete topology design problem....
A One-Layer Recurrent Neural Network for Constrained Complex-Variable Convex Optimization.
Qin, Sitian; Feng, Jiqiang; Song, Jiahui; Wen, Xingnan; Xu, Chen
2018-03-01
In this paper, based on calculus and penalty method, a one-layer recurrent neural network is proposed for solving constrained complex-variable convex optimization. It is proved that for any initial point from a given domain, the state of the proposed neural network reaches the feasible region in finite time and converges to an optimal solution of the constrained complex-variable convex optimization finally. In contrast to existing neural networks for complex-variable convex optimization, the proposed neural network has a lower model complexity and better convergence. Some numerical examples and application are presented to substantiate the effectiveness of the proposed neural network.
Directory of Open Access Journals (Sweden)
Carlos Villaseñor
2017-12-01
Full Text Available Nowadays, there are several meta-heuristics algorithms which offer solutions for multi-variate optimization problems. These algorithms use a population of candidate solutions which explore the search space, where the leadership plays a big role in the exploration-exploitation equilibrium. In this work, we propose to use a Germinal Center Optimization algorithm (GCO which implements temporal leadership through modeling a non-uniform competitive-based distribution for particle selection. GCO is used to find an optimal set of parameters for a neural inverse optimal control applied to all-terrain tracked robot. In the Neural Inverse Optimal Control (NIOC scheme, a neural identifier, based on Recurrent High Orden Neural Network (RHONN trained with an extended kalman filter algorithm, is used to obtain a model of the system, then, a control law is design using such model with the inverse optimal control approach. The RHONN identifier is developed without knowledge of the plant model or its parameters, on the other hand, the inverse optimal control is designed for tracking velocity references. Applicability of the proposed scheme is illustrated using simulations results as well as real-time experimental results with an all-terrain tracked robot.
Stability and bifurcation of a discrete BAM neural network model with delays
International Nuclear Information System (INIS)
Zheng Baodong; Zhang Yang; Zhang Chunrui
2008-01-01
A map modelling a discrete bidirectional associative memory neural network with delays is investigated. Its dynamics is studied in terms of local analysis and Hopf bifurcation analysis. By analyzing the associated characteristic equation, its linear stability is investigated and Hopf bifurcations are demonstrated. It is found that there exist Hopf bifurcations when the delay passes a sequence of critical values. Numerical simulation is performed to verify the analytical results
Optimal Robust Fault Detection for Linear Discrete Time Systems
Directory of Open Access Journals (Sweden)
Nike Liu
2008-01-01
Full Text Available This paper considers robust fault-detection problems for linear discrete time systems. It is shown that the optimal robust detection filters for several well-recognized robust fault-detection problems, such as ℋ−/ℋ∞, ℋ2/ℋ∞, and ℋ∞/ℋ∞ problems, are the same and can be obtained by solving a standard algebraic Riccati equation. Optimal filters are also derived for many other optimization criteria and it is shown that some well-studied and seeming-sensible optimization criteria for fault-detection filter design could lead to (optimal but useless fault-detection filters.
Zhou, Caigen; Zeng, Xiaoqin; Luo, Chaomin; Zhang, Huaguang
In this paper, local bipolar auto-associative memories are presented based on discrete recurrent neural networks with a class of gain type activation function. The weight parameters of neural networks are acquired by a set of inequalities without the learning procedure. The global exponential stability criteria are established to ensure the accuracy of the restored patterns by considering time delays and external inputs. The proposed methodology is capable of effectively overcoming spurious memory patterns and achieving memory capacity. The effectiveness, robustness, and fault-tolerant capability are validated by simulated experiments.In this paper, local bipolar auto-associative memories are presented based on discrete recurrent neural networks with a class of gain type activation function. The weight parameters of neural networks are acquired by a set of inequalities without the learning procedure. The global exponential stability criteria are established to ensure the accuracy of the restored patterns by considering time delays and external inputs. The proposed methodology is capable of effectively overcoming spurious memory patterns and achieving memory capacity. The effectiveness, robustness, and fault-tolerant capability are validated by simulated experiments.
DEFF Research Database (Denmark)
Sørensen, Søren Nørgaard; Lund, Erik
2012-01-01
This work concerns a novel large-scale multi-material topology optimization method for simultaneous determination of the optimum variable integer thickness and fiber orientation throughout laminate structures with fixed outer geometries while adhering to certain manufacturing constraints....... The conceptual combinatorial/integer problem is relaxed to a continuous problem and solved on basis of the so-called Discrete Material Optimization method, explicitly including the manufacturing constraints as linear constraints....
Optimized Neural Network for Fault Diagnosis and Classification
International Nuclear Information System (INIS)
Elaraby, S.M.
2005-01-01
This paper presents a developed and implemented toolbox for optimizing neural network structure of fault diagnosis and classification. Evolutionary algorithm based on hierarchical genetic algorithm structure is used for optimization. The simplest feed-forward neural network architecture is selected. Developed toolbox has friendly user interface. Multiple solutions are generated. The performance and applicability of the proposed toolbox is verified with benchmark data patterns and accident diagnosis of Egyptian Second research reactor (ETRR-2)
GÖKCE, Kürşad; UYAROĞLU, Yılmaz
2013-01-01
This paper proposes a feedforward neural network-based control scheme to control the chaotic trajectories of a discrete-Hénon map in order to stay within an acceptable distance from the stable fixed point. An adaptive learning back propagation algorithm with online training is employed to improve the effectiveness of the proposed method. The simulation study carried in the discrete-Hénon system verifies the validity of the proposed control system.
Recent developments of discrete material optimization of laminated composite structures
DEFF Research Database (Denmark)
Lund, Erik; Sørensen, Rene
2015-01-01
This work will give a quick summary of recent developments of the Discrete Material Optimization approach for structural optimization of laminated composite structures. This approach can be seen as a multi-material topology optimization approach for selecting the best ply material and number...... of plies in a laminated composite structure. The conceptual combinatorial design problem is relaxed to a continuous problem such that well-established gradient based optimization techniques can be applied, and the optimization problem is solved on basis of interpolation schemes with penalization...
Chen, Xiaofeng; Song, Qiankun; Li, Zhongshan; Zhao, Zhenjiang; Liu, Yurong
2018-07-01
This paper addresses the problem of stability for continuous-time and discrete-time quaternion-valued neural networks (QVNNs) with linear threshold neurons. Applying the semidiscretization technique to the continuous-time QVNNs, the discrete-time analogs are obtained, which preserve the dynamical characteristics of their continuous-time counterparts. Via the plural decomposition method of quaternion, homeomorphic mapping theorem, as well as Lyapunov theorem, some sufficient conditions on the existence, uniqueness, and global asymptotical stability of the equilibrium point are derived for the continuous-time QVNNs and their discrete-time analogs, respectively. Furthermore, a uniform sufficient condition on the existence, uniqueness, and global asymptotical stability of the equilibrium point is obtained for both continuous-time QVNNs and their discrete-time version. Finally, two numerical examples are provided to substantiate the effectiveness of the proposed results.
Continuous and Discrete-Time Optimal Controls for an Isolated Signalized Intersection
Directory of Open Access Journals (Sweden)
Jiyuan Tan
2017-01-01
Full Text Available A classical control problem for an isolated oversaturated intersection is revisited with a focus on the optimal control policy to minimize total delay. The difference and connection between existing continuous-time planning models and recently proposed discrete-time planning models are studied. A gradient descent algorithm is proposed to convert the optimal control plan of the continuous-time model to the plan of the discrete-time model in many cases. Analytic proof and numerical tests for the algorithm are also presented. The findings shed light on the links between two kinds of models.
Finite Volumes Discretization of Topology Optimization Problems
DEFF Research Database (Denmark)
Evgrafov, Anton; Gregersen, Misha Marie; Sørensen, Mads Peter
, FVMs represent a standard method of discretization within engineering communities dealing with computational uid dy- namics, transport, and convection-reaction problems. Among various avours of FVMs, cell based approaches, where all variables are associated only with cell centers, are particularly...... computations is done using nite element methods (FEMs). Despite some limited recent eorts [1, 2], we have only started to develop our understanding of the interplay between the control in the coecients and FVMs. Recent advances in discrete functional analysis allow us to analyze convergence of FVM...... of the induced parametrization of the design space that allows optimization algorithms to eciently explore it, and the ease of integration with existing computational codes in a variety of application areas, the simplicity and eciency of sensitivity analyses|all stemming from the use of the same grid throughout...
International Nuclear Information System (INIS)
Zhu Xunlin; Wang Youyi
2009-01-01
This Letter studies the exponential stability for a class of neural networks (NNs) with both discrete and distributed time-varying delays. Under weaker assumptions on the activation functions, by defining a more general type of Lyapunov functionals and developing a new convex combination technique, new less conservative and less complex stability criteria are established to guarantee the global exponential stability of the discussed NNs. The obtained conditions are dependent on both discrete and distributed delays, are expressed in terms of linear matrix inequalities (LMIs), and contain fewer decision variables. Numerical examples are given to illustrate the effectiveness and the less conservatism of the proposed conditions.
A two-layer recurrent neural network for nonsmooth convex optimization problems.
Qin, Sitian; Xue, Xiaoping
2015-06-01
In this paper, a two-layer recurrent neural network is proposed to solve the nonsmooth convex optimization problem subject to convex inequality and linear equality constraints. Compared with existing neural network models, the proposed neural network has a low model complexity and avoids penalty parameters. It is proved that from any initial point, the state of the proposed neural network reaches the equality feasible region in finite time and stays there thereafter. Moreover, the state is unique if the initial point lies in the equality feasible region. The equilibrium point set of the proposed neural network is proved to be equivalent to the Karush-Kuhn-Tucker optimality set of the original optimization problem. It is further proved that the equilibrium point of the proposed neural network is stable in the sense of Lyapunov. Moreover, from any initial point, the state is proved to be convergent to an equilibrium point of the proposed neural network. Finally, as applications, the proposed neural network is used to solve nonlinear convex programming with linear constraints and L1 -norm minimization problems.
Improved result on stability analysis of discrete stochastic neural networks with time delay
International Nuclear Information System (INIS)
Wu Zhengguang; Su Hongye; Chu Jian; Zhou Wuneng
2009-01-01
This Letter investigates the problem of exponential stability for discrete stochastic time-delay neural networks. By defining a novel Lyapunov functional, an improved delay-dependent exponential stability criterion is established in terms of linear matrix inequality (LMI) approach. Meanwhile, the computational complexity of the newly established stability condition is reduced because less variables are involved. Numerical example is given to illustrate the effectiveness and the benefits of the proposed method.
Luo, Biao; Liu, Derong; Wu, Huai-Ning
2018-06-01
Reinforcement learning has proved to be a powerful tool to solve optimal control problems over the past few years. However, the data-based constrained optimal control problem of nonaffine nonlinear discrete-time systems has rarely been studied yet. To solve this problem, an adaptive optimal control approach is developed by using the value iteration-based Q-learning (VIQL) with the critic-only structure. Most of the existing constrained control methods require the use of a certain performance index and only suit for linear or affine nonlinear systems, which is unreasonable in practice. To overcome this problem, the system transformation is first introduced with the general performance index. Then, the constrained optimal control problem is converted to an unconstrained optimal control problem. By introducing the action-state value function, i.e., Q-function, the VIQL algorithm is proposed to learn the optimal Q-function of the data-based unconstrained optimal control problem. The convergence results of the VIQL algorithm are established with an easy-to-realize initial condition . To implement the VIQL algorithm, the critic-only structure is developed, where only one neural network is required to approximate the Q-function. The converged Q-function obtained from the critic-only VIQL method is employed to design the adaptive constrained optimal controller based on the gradient descent scheme. Finally, the effectiveness of the developed adaptive control method is tested on three examples with computer simulation.
DEFF Research Database (Denmark)
Henrichsen, Søren Randrup; Lindgaard, Esben; Lund, Erik
2015-01-01
Robust buckling optimal design of laminated composite structures is conducted in this work. Optimal designs are obtained by considering geometric imperfections in the optimization procedure. Discrete Material Optimization is applied to obtain optimal laminate designs. The optimal geometric...... imperfection is represented by the “worst” shape imperfection. The two optimization problems are combined through the recurrence optimization. Hereby the imperfection sensitivity of the considered structures can be studied. The recurrence optimization is demonstrated through a U-profile and a cylindrical panel...... example. The imperfection sensitivity of the optimized structure decreases during the recurrence optimization for both examples, hence robust buckling optimal structures are designed....
Toward Optimal Manifold Hashing via Discrete Locally Linear Embedding.
Rongrong Ji; Hong Liu; Liujuan Cao; Di Liu; Yongjian Wu; Feiyue Huang
2017-11-01
Binary code learning, also known as hashing, has received increasing attention in large-scale visual search. By transforming high-dimensional features to binary codes, the original Euclidean distance is approximated via Hamming distance. More recently, it is advocated that it is the manifold distance, rather than the Euclidean distance, that should be preserved in the Hamming space. However, it retains as an open problem to directly preserve the manifold structure by hashing. In particular, it first needs to build the local linear embedding in the original feature space, and then quantize such embedding to binary codes. Such a two-step coding is problematic and less optimized. Besides, the off-line learning is extremely time and memory consuming, which needs to calculate the similarity matrix of the original data. In this paper, we propose a novel hashing algorithm, termed discrete locality linear embedding hashing (DLLH), which well addresses the above challenges. The DLLH directly reconstructs the manifold structure in the Hamming space, which learns optimal hash codes to maintain the local linear relationship of data points. To learn discrete locally linear embeddingcodes, we further propose a discrete optimization algorithm with an iterative parameters updating scheme. Moreover, an anchor-based acceleration scheme, termed Anchor-DLLH, is further introduced, which approximates the large similarity matrix by the product of two low-rank matrices. Experimental results on three widely used benchmark data sets, i.e., CIFAR10, NUS-WIDE, and YouTube Face, have shown superior performance of the proposed DLLH over the state-of-the-art approaches.
A discrete optimization method for nuclear fuel management
International Nuclear Information System (INIS)
Argaud, J.P.
1993-01-01
Nuclear fuel management can be seen as a large discrete optimization problem under constraints, and optimization methods on such problems are numerically costly. After an introduction of the main aspects of nuclear fuel management, this paper presents a new way to treat the combinatorial problem by using information included in the gradient of optimized cost function. A new search process idea is to choose, by direct observation of the gradient, the more interesting changes in fuel loading patterns. An example is then developed to illustrate an operating mode of the method. Finally, connections with classical simulated annealing and genetic algorithms are described as an attempt to improve search processes. 16 refs., 2 figs
Directory of Open Access Journals (Sweden)
Yiming Jiang
2016-01-01
Full Text Available Over the last few decades, the intelligent control methods such as fuzzy logic control (FLC and neural network (NN control have been successfully used in various applications. The rapid development of digital computer based control systems requires control signals to be calculated in a digital or discrete-time form. In this background, the intelligent control methods developed for discrete-time systems have drawn great attentions. This survey aims to present a summary of the state of the art of the design of FLC and NN-based intelligent control for discrete-time systems. For discrete-time FLC systems, numerous remarkable design approaches are introduced and a series of efficient methods to deal with the robustness, stability, and time delay of FLC discrete-time systems are recommended. Techniques for NN-based intelligent control for discrete-time systems, such as adaptive methods and adaptive dynamic programming approaches, are also reviewed. Overall, this paper is devoted to make a brief summary for recent progresses in FLC and NN-based intelligent control design for discrete-time systems as well as to present our thoughts and considerations of recent trends and potential research directions in this area.
Discrete optimization in architecture architectural & urban layout
Zawidzki, Machi
2016-01-01
This book presents three projects that demonstrate the fundamental problems of architectural design and urban composition – the layout design, evaluation and optimization. Part I describes the functional layout design of a residential building, and an evaluation of the quality of a town square (plaza). The algorithm for the functional layout design is based on backtracking using a constraint satisfaction approach combined with coarse grid discretization. The algorithm for the town square evaluation is based on geometrical properties derived directly from its plan. Part II introduces a crowd-simulation application for the analysis of escape routes on floor plans, and optimization of a floor plan for smooth crowd flow. The algorithms presented employ agent-based modeling and cellular automata.
Road maintenance optimization through a discrete-time semi-Markov decision process
International Nuclear Information System (INIS)
Zhang Xueqing; Gao Hui
2012-01-01
Optimization models are necessary for efficient and cost-effective maintenance of a road network. In this regard, road deterioration is commonly modeled as a discrete-time Markov process such that an optimal maintenance policy can be obtained based on the Markov decision process, or as a renewal process such that an optimal maintenance policy can be obtained based on the renewal theory. However, the discrete-time Markov process cannot capture the real time at which the state transits while the renewal process considers only one state and one maintenance action. In this paper, road deterioration is modeled as a semi-Markov process in which the state transition has the Markov property and the holding time in each state is assumed to follow a discrete Weibull distribution. Based on this semi-Markov process, linear programming models are formulated for both infinite and finite planning horizons in order to derive optimal maintenance policies to minimize the life-cycle cost of a road network. A hypothetical road network is used to illustrate the application of the proposed optimization models. The results indicate that these linear programming models are practical for the maintenance of a road network having a large number of road segments and that they are convenient to incorporate various constraints on the decision process, for example, performance requirements and available budgets. Although the optimal maintenance policies obtained for the road network are randomized stationary policies, the extent of this randomness in decision making is limited. The maintenance actions are deterministic for most states and the randomness in selecting actions occurs only for a few states.
Feed Forward Neural Network and Optimal Control Problem with Control and State Constraints
Kmet', Tibor; Kmet'ová, Mária
2009-09-01
A feed forward neural network based optimal control synthesis is presented for solving optimal control problems with control and state constraints. The paper extends adaptive critic neural network architecture proposed by [5] to the optimal control problems with control and state constraints. The optimal control problem is transcribed into a nonlinear programming problem which is implemented with adaptive critic neural network. The proposed simulation method is illustrated by the optimal control problem of nitrogen transformation cycle model. Results show that adaptive critic based systematic approach holds promise for obtaining the optimal control with control and state constraints.
Ceylan, Murat; Ceylan, Rahime; Ozbay, Yüksel; Kara, Sadik
2008-09-01
In biomedical signal classification, due to the huge amount of data, to compress the biomedical waveform data is vital. This paper presents two different structures formed using feature extraction algorithms to decrease size of feature set in training and test data. The proposed structures, named as wavelet transform-complex-valued artificial neural network (WT-CVANN) and complex wavelet transform-complex-valued artificial neural network (CWT-CVANN), use real and complex discrete wavelet transform for feature extraction. The aim of using wavelet transform is to compress data and to reduce training time of network without decreasing accuracy rate. In this study, the presented structures were applied to the problem of classification in carotid arterial Doppler ultrasound signals. Carotid arterial Doppler ultrasound signals were acquired from left carotid arteries of 38 patients and 40 healthy volunteers. The patient group included 22 males and 16 females with an established diagnosis of the early phase of atherosclerosis through coronary or aortofemoropopliteal (lower extremity) angiographies (mean age, 59 years; range, 48-72 years). Healthy volunteers were young non-smokers who seem to not bear any risk of atherosclerosis, including 28 males and 12 females (mean age, 23 years; range, 19-27 years). Sensitivity, specificity and average detection rate were calculated for comparison, after training and test phases of all structures finished. These parameters have demonstrated that training times of CVANN and real-valued artificial neural network (RVANN) were reduced using feature extraction algorithms without decreasing accuracy rate in accordance to our aim.
A Novel adaptative Discrete Cuckoo Search Algorithm for parameter optimization in computer vision
Directory of Open Access Journals (Sweden)
loubna benchikhi
2017-10-01
Full Text Available Computer vision applications require choosing operators and their parameters, in order to provide the best outcomes. Often, the users quarry on expert knowledge and must experiment many combinations to find manually the best one. As performance, time and accuracy are important, it is necessary to automate parameter optimization at least for crucial operators. In this paper, a novel approach based on an adaptive discrete cuckoo search algorithm (ADCS is proposed. It automates the process of algorithms’ setting and provides optimal parameters for vision applications. This work reconsiders a discretization problem to adapt the cuckoo search algorithm and presents the procedure of parameter optimization. Some experiments on real examples and comparisons to other metaheuristic-based approaches: particle swarm optimization (PSO, reinforcement learning (RL and ant colony optimization (ACO show the efficiency of this novel method.
Discrete and Continuous Optimization Based on Hierarchical Artificial Bee Colony Optimizer
Directory of Open Access Journals (Sweden)
Lianbo Ma
2014-01-01
Full Text Available This paper presents a novel optimization algorithm, namely, hierarchical artificial bee colony optimization (HABC, to tackle complex high-dimensional problems. In the proposed multilevel model, the higher-level species can be aggregated by the subpopulations from lower level. In the bottom level, each subpopulation employing the canonical ABC method searches the part-dimensional optimum in parallel, which can be constructed into a complete solution for the upper level. At the same time, the comprehensive learning method with crossover and mutation operator is applied to enhance the global search ability between species. Experiments are conducted on a set of 20 continuous and discrete benchmark problems. The experimental results demonstrate remarkable performance of the HABC algorithm when compared with other six evolutionary algorithms.
Liu, Qingshan; Dang, Chuangyin; Huang, Tingwen
2013-02-01
This paper presents a decision-making model described by a recurrent neural network for dynamic portfolio optimization. The portfolio-optimization problem is first converted into a constrained fractional programming problem. Since the objective function in the programming problem is not convex, the traditional optimization techniques are no longer applicable for solving this problem. Fortunately, the objective function in the fractional programming is pseudoconvex on the feasible region. It leads to a one-layer recurrent neural network modeled by means of a discontinuous dynamic system. To ensure the optimal solutions for portfolio optimization, the convergence of the proposed neural network is analyzed and proved. In fact, the neural network guarantees to get the optimal solutions for portfolio-investment advice if some mild conditions are satisfied. A numerical example with simulation results substantiates the effectiveness and illustrates the characteristics of the proposed neural network.
Qin, Sitian; Yang, Xiudong; Xue, Xiaoping; Song, Jiahui
2017-10-01
Pseudoconvex optimization problem, as an important nonconvex optimization problem, plays an important role in scientific and engineering applications. In this paper, a recurrent one-layer neural network is proposed for solving the pseudoconvex optimization problem with equality and inequality constraints. It is proved that from any initial state, the state of the proposed neural network reaches the feasible region in finite time and stays there thereafter. It is also proved that the state of the proposed neural network is convergent to an optimal solution of the related problem. Compared with the related existing recurrent neural networks for the pseudoconvex optimization problems, the proposed neural network in this paper does not need the penalty parameters and has a better convergence. Meanwhile, the proposed neural network is used to solve three nonsmooth optimization problems, and we make some detailed comparisons with the known related conclusions. In the end, some numerical examples are provided to illustrate the effectiveness of the performance of the proposed neural network.
Predicting recurrent aphthous ulceration using genetic algorithms-optimized neural networks
Directory of Open Access Journals (Sweden)
Najla S Dar-Odeh
2010-05-01
Full Text Available Najla S Dar-Odeh1, Othman M Alsmadi2, Faris Bakri3, Zaer Abu-Hammour2, Asem A Shehabi3, Mahmoud K Al-Omiri1, Shatha M K Abu-Hammad4, Hamzeh Al-Mashni4, Mohammad B Saeed4, Wael Muqbil4, Osama A Abu-Hammad1 1Faculty of Dentistry, 2Faculty of Engineering and Technology, 3Faculty of Medicine, University of Jordan, Amman, Jordan; 4Dental Department, University of Jordan Hospital, Amman, JordanObjective: To construct and optimize a neural network that is capable of predicting the occurrence of recurrent aphthous ulceration (RAU based on a set of appropriate input data.Participants and methods: Artificial neural networks (ANN software employing genetic algorithms to optimize the architecture neural networks was used. Input and output data of 86 participants (predisposing factors and status of the participants with regards to recurrent aphthous ulceration were used to construct and train the neural networks. The optimized neural networks were then tested using untrained data of a further 10 participants.Results: The optimized neural network, which produced the most accurate predictions for the presence or absence of recurrent aphthous ulceration was found to employ: gender, hematological (with or without ferritin and mycological data of the participants, frequency of tooth brushing, and consumption of vegetables and fruits.Conclusions: Factors appearing to be related to recurrent aphthous ulceration and appropriate for use as input data to construct ANNs that predict recurrent aphthous ulceration were found to include the following: gender, hemoglobin, serum vitamin B12, serum ferritin, red cell folate, salivary candidal colony count, frequency of tooth brushing, and the number of fruits or vegetables consumed daily.Keywords: artifical neural networks, recurrent, aphthous ulceration, ulcer
A Framework for the Optimization of Discrete-Event Simulation Models
Joshi, B. D.; Unal, R.; White, N. H.; Morris, W. D.
1996-01-01
With the growing use of computer modeling and simulation, in all aspects of engineering, the scope of traditional optimization has to be extended to include simulation models. Some unique aspects have to be addressed while optimizing via stochastic simulation models. The optimization procedure has to explicitly account for the randomness inherent in the stochastic measures predicted by the model. This paper outlines a general purpose framework for optimization of terminating discrete-event simulation models. The methodology combines a chance constraint approach for problem formulation, together with standard statistical estimation and analyses techniques. The applicability of the optimization framework is illustrated by minimizing the operation and support resources of a launch vehicle, through a simulation model.
Directory of Open Access Journals (Sweden)
Fei Chen
2013-01-01
Full Text Available This paper deals with the finite-time stabilization problem for discrete-time Markov jump nonlinear systems with time delays and norm-bounded exogenous disturbance. The nonlinearities in different jump modes are parameterized by neural networks. Subsequently, a linear difference inclusion state space representation for a class of neural networks is established. Based on this, sufficient conditions are derived in terms of linear matrix inequalities to guarantee stochastic finite-time boundedness and stochastic finite-time stabilization of the closed-loop system. A numerical example is illustrated to verify the efficiency of the proposed technique.
Improved Artificial Fish Algorithm for Parameters Optimization of PID Neural Network
Jing Wang; Yourui Huang
2013-01-01
In order to solve problems such as initial weights are difficult to be determined, training results are easy to trap in local minima in optimization process of PID neural network parameters by traditional BP algorithm, this paper proposed a new method based on improved artificial fish algorithm for parameters optimization of PID neural network. This improved artificial fish algorithm uses a composite adaptive artificial fish algorithm based on optimal artificial fish and nearest artificial fi...
Delay-Dependent Exponential Stability for Discrete-Time BAM Neural Networks with Time-Varying Delays
Directory of Open Access Journals (Sweden)
Yonggang Chen
2008-01-01
Full Text Available This paper considers the delay-dependent exponential stability for discrete-time BAM neural networks with time-varying delays. By constructing the new Lyapunov functional, the improved delay-dependent exponential stability criterion is derived in terms of linear matrix inequality (LMI. Moreover, in order to reduce the conservativeness, some slack matrices are introduced in this paper. Two numerical examples are presented to show the effectiveness and less conservativeness of the proposed method.
Computation of optimal transport and related hedging problems via penalization and neural networks
Eckstein, Stephan; Kupper, Michael
2018-01-01
This paper presents a widely applicable approach to solving (multi-marginal, martingale) optimal transport and related problems via neural networks. The core idea is to penalize the optimization problem in its dual formulation and reduce it to a finite dimensional one which corresponds to optimizing a neural network with smooth objective function. We present numerical examples from optimal transport, martingale optimal transport, portfolio optimization under uncertainty and generative adversa...
International Nuclear Information System (INIS)
Thuburn, J.; Woollings, T.J.
2005-01-01
Accurate representation of different kinds of wave motion is essential for numerical models of the atmosphere, but is sensitive to details of the discretization. In this paper, numerical dispersion relations are computed for different vertical discretizations of the compressible Euler equations and compared with the analytical dispersion relation. A height coordinate, an isentropic coordinate, and a terrain-following mass-based coordinate are considered, and, for each of these, different choices of prognostic variables and grid staggerings are considered. The discretizations are categorized according to whether their dispersion relations are optimal, are near optimal, have a single zero-frequency computational mode, or are problematic in other ways. Some general understanding of the factors that affect the numerical dispersion properties is obtained: heuristic arguments concerning the normal mode structures, and the amount of averaging and coarse differencing in the finite difference scheme, are shown to be useful guides to which configurations will be optimal; the number of degrees of freedom in the discretization is shown to be an accurate guide to the existence of computational modes; there is only minor sensitivity to whether the equations for thermodynamic variables are discretized in advective form or flux form; and an accurate representation of acoustic modes is found to be a prerequisite for accurate representation of inertia-gravity modes, which, in turn, is found to be a prerequisite for accurate representation of Rossby modes
A new criterion for global robust stability of interval neural networks with discrete time delays
International Nuclear Information System (INIS)
Li Chuandong; Chen Jinyu; Huang Tingwen
2007-01-01
This paper further studies global robust stability of a class of interval neural networks with discrete time delays. By introducing an equivalent transformation of interval matrices, a new criterion on global robust stability is established. In comparison with the results reported in the literature, the proposed approach leads to results with less restrictive conditions. Numerical examples are also worked through to illustrate our results
International Nuclear Information System (INIS)
Reifman, J.; Vitela, E.J.; Lee, J.C.
1993-01-01
Two complementary methods, statistical feature selection and nonlinear optimization through conjugate gradients, are used to expedite feedforward neural network training. Statistical feature selection techniques in the form of linear correlation coefficients and information-theoretic entropy are used to eliminate redundant and non-informative plant parameters to reduce the size of the network. The method of conjugate gradients is used to accelerate the network training convergence and to systematically calculate the Teaming and momentum constants at each iteration. The proposed techniques are compared with the backpropagation algorithm using the entire set of plant parameters in the training of neural networks to identify transients simulated with the Midland Nuclear Power Plant Unit 2 simulator. By using 25% of the plant parameters and the conjugate gradients, a 30-fold reduction in CPU time was obtained without degrading the diagnostic ability of the network
Optimal neural networks for protein-structure prediction
International Nuclear Information System (INIS)
Head-Gordon, T.; Stillinger, F.H.
1993-01-01
The successful application of neural-network algorithms for prediction of protein structure is stymied by three problem areas: the sparsity of the database of known protein structures, poorly devised network architectures which make the input-output mapping opaque, and a global optimization problem in the multiple-minima space of the network variables. We present a simplified polypeptide model residing in two dimensions with only two amino-acid types, A and B, which allows the determination of the global energy structure for all possible sequences of pentamer, hexamer, and heptamer lengths. This model simplicity allows us to compile a complete structural database and to devise neural networks that reproduce the tertiary structure of all sequences with absolute accuracy and with the smallest number of network variables. These optimal networks reveal that the three problem areas are convoluted, but that thoughtful network designs can actually deconvolute these detrimental traits to provide network algorithms that genuinely impact on the ability of the network to generalize or learn the desired mappings. Furthermore, the two-dimensional polypeptide model shows sufficient chemical complexity so that transfer of neural-network technology to more realistic three-dimensional proteins is evident
Discrete optimization in architecture extremely modular systems
Zawidzki, Machi
2017-01-01
This book is comprised of two parts, both of which explore modular systems: Pipe-Z (PZ) and Truss-Z (TZ), respectively. It presents several methods of creating PZ and TZ structures subjected to discrete optimization. The algorithms presented employ graph-theoretic and heuristic methods. The underlying idea of both systems is to create free-form structures using the minimal number of types of modular elements. PZ is more conceptual, as it forms single-branch mathematical knots with a single type of module. Conversely, TZ is a skeletal system for creating free-form pedestrian ramps and ramp networks among any number of terminals in space. In physical space, TZ uses two types of modules that are mirror reflections of each other. The optimization criteria discussed include: the minimal number of units, maximal adherence to the given guide paths, etc.
Optimization of neural network architecture for classification of radar jamming FM signals
Soto, Alberto; Mendoza, Ariadna; Flores, Benjamin C.
2017-05-01
The purpose of this study is to investigate several artificial Neural Network (NN) architectures in order to design a cognitive radar system capable of optimally distinguishing linear Frequency-Modulated (FM) signals from bandlimited Additive White Gaussian Noise (AWGN). The goal is to create a theoretical framework to determine an optimal NN architecture to achieve a Probability of Detection (PD) of 95% or higher and a Probability of False Alarm (PFA) of 1.5% or lower at 5 dB Signal to Noise Ratio (SNR). Literature research reveals that the frequency-domain power spectral densities characterize a signal more efficiently than its time-domain counterparts. Therefore, the input data is preprocessed by calculating the magnitude square of the Discrete Fourier Transform of the digitally sampled bandlimited AWGN and linear FM signals to populate a matrix containing N number of samples and M number of spectra. This matrix is used as input for the NN, and the spectra are divided as follows: 70% for training, 15% for validation, and 15% for testing. The study begins by experimentally deducing the optimal number of hidden neurons (1-40 neurons), then the optimal number of hidden layers (1-5 layers), and lastly, the most efficient learning algorithm. The training algorithms examined are: Resilient Backpropagation, Scaled Conjugate Gradient, Conjugate Gradient with Powell/Beale Restarts, Polak-Ribiére Conjugate Gradient, and Variable Learning Rate Backpropagation. We determine that an architecture with ten hidden neurons (or higher), one hidden layer, and a Scaled Conjugate Gradient for training algorithm encapsulates an optimal architecture for our application.
Energy Technology Data Exchange (ETDEWEB)
Ponslet, E.R.; Eldred, M.S. [Sandia National Labs., Albuquerque, NM (United States). Structural Dynamics Dept.
1996-05-17
An analytical and experimental study is conducted to investigate the effect of isolator locations on the effectiveness of vibration isolation systems. The study uses isolators with fixed properties and evaluates potential improvements to the isolation system that can be achieved by optimizing isolator locations. Because the available locations for the isolators are discrete in this application, a Genetic Algorithm (GA) is used as the optimization method. The system is modeled in MATLAB{trademark} and coupled with the GA available in the DAKOTA optimization toolkit under development at Sandia National Laboratories. Design constraints dictated by hardware and experimental limitations are implemented through penalty function techniques. A series of GA runs reveal difficulties in the search on this heavily constrained, multimodal, discrete problem. However, the GA runs provide a variety of optimized designs with predicted performance from 30 to 70 times better than a baseline configuration. An alternate approach is also tested on this problem: it uses continuous optimization, followed by rounding of the solution to neighboring discrete configurations. Results show that this approach leads to either infeasible or poor designs. Finally, a number of optimized designs obtained from the GA searches are tested in the laboratory and compared to the baseline design. These experimental results show a 7 to 46 times improvement in vibration isolation from the baseline configuration.
Yang, Jin; Liu, Fagui; Cao, Jianneng; Wang, Liangming
2016-07-14
Mobile sinks can achieve load-balancing and energy-consumption balancing across the wireless sensor networks (WSNs). However, the frequent change of the paths between source nodes and the sinks caused by sink mobility introduces significant overhead in terms of energy and packet delays. To enhance network performance of WSNs with mobile sinks (MWSNs), we present an efficient routing strategy, which is formulated as an optimization problem and employs the particle swarm optimization algorithm (PSO) to build the optimal routing paths. However, the conventional PSO is insufficient to solve discrete routing optimization problems. Therefore, a novel greedy discrete particle swarm optimization with memory (GMDPSO) is put forward to address this problem. In the GMDPSO, particle's position and velocity of traditional PSO are redefined under discrete MWSNs scenario. Particle updating rule is also reconsidered based on the subnetwork topology of MWSNs. Besides, by improving the greedy forwarding routing, a greedy search strategy is designed to drive particles to find a better position quickly. Furthermore, searching history is memorized to accelerate convergence. Simulation results demonstrate that our new protocol significantly improves the robustness and adapts to rapid topological changes with multiple mobile sinks, while efficiently reducing the communication overhead and the energy consumption.
2010-03-01
EVOLUTIONARY ARTIFICIAL NEURAL NETWORK WEIGHT TUNING TO OPTIMIZE DECISION MAKING FOR AN ABSTRACT...AFIT/GCS/ENG/10-06 EVOLUTIONARY ARTIFICIAL NEURAL NETWORK WEIGHT TUNING TO OPTIMIZE DECISION MAKING FOR AN ABSTRACT GAME THESIS Presented...35 14: Diagram of pLoGANN’s Artificial Neural Network and
DEFF Research Database (Denmark)
Lund, Erik
2017-01-01
This work extends the Discrete Material and Thickness Optimization approach to structural optimization problems where strength considerations in the form of failure criteria are taken into account for laminated composite structures. It takes offset in the density approaches applied for stress...... constrained topology optimization of single-material problems and develops formulations for multi-material topology optimization problems applied for laminated composite structures. The method can be applied for both stress- and strain-based failure criteria. The large number of local constraints is reduced...
Directory of Open Access Journals (Sweden)
Mengjuan Cao
2014-01-01
Full Text Available The linear discrete-time descriptor noncausal multirate system is considered for the presentation of a new design approach for optimal preview control. First, according to the characteristics of causal controllability and causal observability, the descriptor noncausal system is constructed into a descriptor causal closed-loop system. Second, by using the characteristics of the causal system and elementary transformation, the descriptor causal closed-loop system is transformed into a normal system. Then, taking advantage of the discrete lifting technique, the normal multirate system is converted to a single-rate system. By making use of the standard preview control method, we construct the descriptor augmented error system. The quadratic performance index for the multirate system is given, which can be changed into one for the single-rate system. In addition, a new single-rate system is obtained, the optimal control law of which is given. Returning to the original system, the optimal preview controller for linear discrete-time descriptor noncausal multirate systems is derived. The stabilizability and detectability of the lifted single-rate system are discussed in detail. The optimal preview control design techniques are illustrated by simulation results for a simple example.
Neural Model with Particle Swarm Optimization Kalman Learning for Forecasting in Smart Grids
Directory of Open Access Journals (Sweden)
Alma Y. Alanis
2013-01-01
Full Text Available This paper discusses a novel training algorithm for a neural network architecture applied to time series prediction with smart grids applications. The proposed training algorithm is based on an extended Kalman filter (EKF improved using particle swarm optimization (PSO to compute the design parameters. The EKF-PSO-based algorithm is employed to update the synaptic weights of the neural network. The size of the regression vector is determined by means of the Cao methodology. The proposed structure captures more efficiently the complex nature of the wind speed, energy generation, and electrical load demand time series that are constantly monitorated in a smart grid benchmark. The proposed model is trained and tested using real data values in order to show the applicability of the proposed scheme.
Application of particle swarm optimization to identify gamma spectrum with neural network
International Nuclear Information System (INIS)
Shi Dongsheng; Di Yuming; Zhou Chunlin
2007-01-01
In applying neural network to identification of gamma spectra back propagation (BP) algorithm is usually trapped to a local optimum and has a low speed of convergence, whereas particle swarm optimization (PSO) is advantageous in terms of globe optimal searching. In this paper, we propose a new algorithm for neural network training, i.e. combined BP and PSO optimization, or PSO-BP algorithm. Practical example shows that the new algorithm can overcome shortcomings of BP algorithm and the neural network trained by it has a high ability of generalization with identification result of 100% correctness. It can be used effectively and reliably to identify gamma spectra. (authors)
International Nuclear Information System (INIS)
Bitencourt, Ana Carla P; Prudente, Frederico V; Vianna, Jose David M
2007-01-01
We propose a new numerically optimized discrete variable representation using eigenstates of diabatic Hamiltonians. This procedure provides an efficient method to solve non-adiabatic coupling problems since the generated basis sets take into account information on the diabatic potentials. The method is applied to the B 1 Σ + - D' 1 Σ + Rydberg-valence predissociation interaction in the CO molecule. Here we give an account of the discrete variable representation and present the procedure for the calculation of its optimized version, which we apply to obtain the total photodissociation cross sections of the CO molecule
DEFF Research Database (Denmark)
Stolpe, Mathias; Bendsøe, Martin P.
2007-01-01
This paper present some initial results pertaining to a search for globally optimal solutions to a challenging benchmark example proposed by Zhou and Rozvany. This means that we are dealing with global optimization of the classical single load minimum compliance topology design problem with a fixed...... finite element discretization and with discrete design variables. Global optimality is achieved by the implementation of some specially constructed convergent nonlinear branch and cut methods, based on the use of natural relaxations and by applying strengthening constraints (linear valid inequalities...
Nuclear reactors project optimization based on neural network and genetic algorithm
International Nuclear Information System (INIS)
Pereira, Claudio M.N.A.; Schirru, Roberto; Martinez, Aquilino S.
1997-01-01
This work presents a prototype of a system for nuclear reactor core design optimization based on genetic algorithms and artificial neural networks. A neural network is modeled and trained in order to predict the flux and the neutron multiplication factor values based in the enrichment, network pitch and cladding thickness, with average error less than 2%. The values predicted by the neural network are used by a genetic algorithm in this heuristic search, guided by an objective function that rewards the high flux values and penalizes multiplication factors far from the required value. Associating the quick prediction - that may substitute the reactor physics calculation code - with the global optimization capacity of the genetic algorithm, it was obtained a quick and effective system for nuclear reactor core design optimization. (author). 11 refs., 8 figs., 3 tabs
A Grey Wolf Optimizer for Modular Granular Neural Networks for Human Recognition
Directory of Open Access Journals (Sweden)
Daniela Sánchez
2017-01-01
Full Text Available A grey wolf optimizer for modular neural network (MNN with a granular approach is proposed. The proposed method performs optimal granulation of data and design of modular neural networks architectures to perform human recognition, and to prove its effectiveness benchmark databases of ear, iris, and face biometric measures are used to perform tests and comparisons against other works. The design of a modular granular neural network (MGNN consists in finding optimal parameters of its architecture; these parameters are the number of subgranules, percentage of data for the training phase, learning algorithm, goal error, number of hidden layers, and their number of neurons. Nowadays, there is a great variety of approaches and new techniques within the evolutionary computing area, and these approaches and techniques have emerged to help find optimal solutions to problems or models and bioinspired algorithms are part of this area. In this work a grey wolf optimizer is proposed for the design of modular granular neural networks, and the results are compared against a genetic algorithm and a firefly algorithm in order to know which of these techniques provides better results when applied to human recognition.
Identification of discrete chaotic maps with singular points
Directory of Open Access Journals (Sweden)
P. G. Akishin
2001-01-01
Full Text Available We investigate the ability of artificial neural networks to reconstruct discrete chaotic maps with singular points. We use as a simple test model the Cusp map. We compare the traditional Multilayer Perceptron, the Chebyshev Neural Network and the Wavelet Neural Network. The numerical scheme for the accurate determination of a singular point is also developed. We show that combining a neural network with the numerical algorithm for the determination of the singular point we are able to accurately approximate discrete chaotic maps with singularities.
Bunnoon, Pituk; Chalermyanont, Kusumal; Limsakul, Chusak
2010-02-01
This paper proposed the discrete transform and neural network algorithms to obtain the monthly peak load demand in mid term load forecasting. The mother wavelet daubechies2 (db2) is employed to decomposed, high pass filter and low pass filter signals from the original signal before using feed forward back propagation neural network to determine the forecasting results. The historical data records in 1997-2007 of Electricity Generating Authority of Thailand (EGAT) is used as reference. In this study, historical information of peak load demand(MW), mean temperature(Tmean), consumer price index (CPI), and industrial index (economic:IDI) are used as feature inputs of the network. The experimental results show that the Mean Absolute Percentage Error (MAPE) is approximately 4.32%. This forecasting results can be used for fuel planning and unit commitment of the power system in the future.
Discrete-Time Stable Generalized Self-Learning Optimal Control With Approximation Errors.
Wei, Qinglai; Li, Benkai; Song, Ruizhuo
2018-04-01
In this paper, a generalized policy iteration (GPI) algorithm with approximation errors is developed for solving infinite horizon optimal control problems for nonlinear systems. The developed stable GPI algorithm provides a general structure of discrete-time iterative adaptive dynamic programming algorithms, by which most of the discrete-time reinforcement learning algorithms can be described using the GPI structure. It is for the first time that approximation errors are explicitly considered in the GPI algorithm. The properties of the stable GPI algorithm with approximation errors are analyzed. The admissibility of the approximate iterative control law can be guaranteed if the approximation errors satisfy the admissibility criteria. The convergence of the developed algorithm is established, which shows that the iterative value function is convergent to a finite neighborhood of the optimal performance index function, if the approximate errors satisfy the convergence criterion. Finally, numerical examples and comparisons are presented.
Discrete Adjoint-Based Design Optimization of Unsteady Turbulent Flows on Dynamic Unstructured Grids
Nielsen, Eric J.; Diskin, Boris; Yamaleev, Nail K.
2009-01-01
An adjoint-based methodology for design optimization of unsteady turbulent flows on dynamic unstructured grids is described. The implementation relies on an existing unsteady three-dimensional unstructured grid solver capable of dynamic mesh simulations and discrete adjoint capabilities previously developed for steady flows. The discrete equations for the primal and adjoint systems are presented for the backward-difference family of time-integration schemes on both static and dynamic grids. The consistency of sensitivity derivatives is established via comparisons with complex-variable computations. The current work is believed to be the first verified implementation of an adjoint-based optimization methodology for the true time-dependent formulation of the Navier-Stokes equations in a practical computational code. Large-scale shape optimizations are demonstrated for turbulent flows over a tiltrotor geometry and a simulated aeroelastic motion of a fighter jet.
DEFF Research Database (Denmark)
Stolpe, Mathias; Bendsøe, Martin P.
2007-01-01
This paper present some initial results pertaining to a search for globally optimal solutions to a challenging benchmark example proposed by Zhou and Rozvany. This means that we are dealing with global optimization of the classical single load minimum compliance topology design problem with a fixed...... finite element discretization and with discrete design variables. Global optimality is achieved by the implementation of some specially constructed convergent nonlinear branch and cut methods, based on the use of natural relaxations and by applying strengthening constraints (linear valid inequalities......) and cuts....
Directory of Open Access Journals (Sweden)
Hong-Zhong Huang
2012-02-01
Full Text Available Various uncertainties are inevitable in complex engineered systems and must be carefully treated in design activities. Reliability-Based Multidisciplinary Design Optimization (RBMDO has been receiving increasing attention in the past decades to facilitate designing fully coupled systems but also achieving a desired reliability considering uncertainty. In this paper, a new formulation of multidisciplinary design optimization, namely RFCDV (random/fuzzy/continuous/discrete variables Multidisciplinary Design Optimization (RFCDV-MDO, is developed within the framework of Sequential Optimization and Reliability Assessment (SORA to deal with multidisciplinary design problems in which both aleatory and epistemic uncertainties are present. In addition, a hybrid discrete-continuous algorithm is put forth to efficiently solve problems where both discrete and continuous design variables exist. The effectiveness and computational efficiency of the proposed method are demonstrated via a mathematical problem and a pressure vessel design problem.
Song, Chen; Zhong-Cheng, Wu; Hong, Lv
2018-03-01
Building Energy forecasting plays an important role in energy management and plan. Using mind evolutionary algorithm to find the optimal network weights and threshold, to optimize the BP neural network, can overcome the problem of the BP neural network into a local minimum point. The optimized network is used for time series prediction, and the same month forecast, to get two predictive values. Then two kinds of predictive values are put into neural network, to get the final forecast value. The effectiveness of the method was verified by experiment with the energy value of three buildings in Hefei.
A non-penalty recurrent neural network for solving a class of constrained optimization problems.
Hosseini, Alireza
2016-01-01
In this paper, we explain a methodology to analyze convergence of some differential inclusion-based neural networks for solving nonsmooth optimization problems. For a general differential inclusion, we show that if its right hand-side set valued map satisfies some conditions, then solution trajectory of the differential inclusion converges to optimal solution set of its corresponding in optimization problem. Based on the obtained methodology, we introduce a new recurrent neural network for solving nonsmooth optimization problems. Objective function does not need to be convex on R(n) nor does the new neural network model require any penalty parameter. We compare our new method with some penalty-based and non-penalty based models. Moreover for differentiable cases, we implement circuit diagram of the new neural network. Copyright © 2015 Elsevier Ltd. All rights reserved.
Truss topology optimization with discrete design variables by outer approximation
DEFF Research Database (Denmark)
Stolpe, Mathias
2015-01-01
Several variants of an outer approximation method are proposed to solve truss topology optimization problems with discrete design variables to proven global optimality. The objective is to minimize the volume of the structure while satisfying constraints on the global stiffness of the structure...... for classical outer approximation approaches applied to optimal design problems. A set of two- and three-dimensional benchmark problems are solved and the numerical results suggest that the proposed approaches are competitive with other special-purpose global optimization methods for the considered class...... under the applied loads. We extend the natural problem formulation by adding redundant force variables and force equilibrium constraints. This guarantees that the designs suggested by the relaxed master problems are capable of carrying the applied loads, a property which is generally not satisfied...
Evolutionary Computation and Its Applications in Neural and Fuzzy Systems
Directory of Open Access Journals (Sweden)
Biaobiao Zhang
2011-01-01
Full Text Available Neural networks and fuzzy systems are two soft-computing paradigms for system modelling. Adapting a neural or fuzzy system requires to solve two optimization problems: structural optimization and parametric optimization. Structural optimization is a discrete optimization problem which is very hard to solve using conventional optimization techniques. Parametric optimization can be solved using conventional optimization techniques, but the solution may be easily trapped at a bad local optimum. Evolutionary computation is a general-purpose stochastic global optimization approach under the universally accepted neo-Darwinian paradigm, which is a combination of the classical Darwinian evolutionary theory, the selectionism of Weismann, and the genetics of Mendel. Evolutionary algorithms are a major approach to adaptation and optimization. In this paper, we first introduce evolutionary algorithms with emphasis on genetic algorithms and evolutionary strategies. Other evolutionary algorithms such as genetic programming, evolutionary programming, particle swarm optimization, immune algorithm, and ant colony optimization are also described. Some topics pertaining to evolutionary algorithms are also discussed, and a comparison between evolutionary algorithms and simulated annealing is made. Finally, the application of EAs to the learning of neural networks as well as to the structural and parametric adaptations of fuzzy systems is also detailed.
Global stability and existence of periodic solutions of discrete delayed cellular neural networks
International Nuclear Information System (INIS)
Li Yongkun
2004-01-01
We use the continuation theorem of coincidence degree theory and Lyapunov functions to study the existence and stability of periodic solutions for the discrete cellular neural networks (CNNs) with delays xi(n+1)=xi(n)e-bi(n)h+θi(h)-bar j=1maij(n)fj(xj(n))+θi(h)-bar j=1mbij(n)fj(xj(n- τij(n)))+θi(h)Ii(n),i=1,2,...,m. We obtain some sufficient conditions to ensure that for the networks there exists a unique periodic solution, and all its solutions converge to such a periodic solution
International Nuclear Information System (INIS)
Souza, Fernando O.; Palhares, Reinaldo M.; Ekel, Petr Ya.
2009-01-01
This paper deals with the stability analysis of delayed uncertain Cohen-Grossberg neural networks (CGNN). The proposed methodology consists in obtaining new robust stability criteria formulated as linear matrix inequalities (LMIs) via the Lyapunov-Krasovskii theory. Particularly one stability criterion is derived from the selection of a parameter-dependent Lyapunov-Krasovskii functional, which allied with the Gu's discretization technique and a simple strategy that decouples the system matrices from the functional matrices, assures a less conservative stability condition. Two computer simulations are presented to support the improved theoretical results.
International Nuclear Information System (INIS)
Liu, Xiaolan; Zhou, Mi
2016-01-01
In this paper, a one-layer recurrent network is proposed for solving a non-smooth convex optimization subject to linear inequality constraints. Compared with the existing neural networks for optimization, the proposed neural network is capable of solving more general convex optimization with linear inequality constraints. The convergence of the state variables of the proposed neural network to achieve solution optimality is guaranteed as long as the designed parameters in the model are larger than the derived lower bounds.
International Nuclear Information System (INIS)
Berthe, P.M.
2013-01-01
In the context of nuclear waste repositories, we consider the numerical discretization of the non stationary convection diffusion equation. Discontinuous physical parameters and heterogeneous space and time scales lead us to use different space and time discretizations in different parts of the domain. In this work, we choose the discrete duality finite volume (DDFV) scheme and the discontinuous Galerkin scheme in time, coupled by an optimized Schwarz waveform relaxation (OSWR) domain decomposition method, because this allows the use of non-conforming space-time meshes. The main difficulty lies in finding an upwind discretization of the convective flux which remains local to a sub-domain and such that the multi domain scheme is equivalent to the mono domain one. These difficulties are first dealt with in the one-dimensional context, where different discretizations are studied. The chosen scheme introduces a hybrid unknown on the cell interfaces. The idea of up winding with respect to this hybrid unknown is extended to the DDFV scheme in the two-dimensional setting. The well-posedness of the scheme and of an equivalent multi domain scheme is shown. The latter is solved by an OSWR algorithm, the convergence of which is proved. The optimized parameters in the Robin transmission conditions are obtained by studying the continuous or discrete convergence rates. Several test-cases, one of which inspired by nuclear waste repositories, illustrate these results. (author) [fr
International Conference on Artificial Neural Networks (ICANN)
Mladenov, Valeri; Kasabov, Nikola; Artificial Neural Networks : Methods and Applications in Bio-/Neuroinformatics
2015-01-01
The book reports on the latest theories on artificial neural networks, with a special emphasis on bio-neuroinformatics methods. It includes twenty-three papers selected from among the best contributions on bio-neuroinformatics-related issues, which were presented at the International Conference on Artificial Neural Networks, held in Sofia, Bulgaria, on September 10-13, 2013 (ICANN 2013). The book covers a broad range of topics concerning the theory and applications of artificial neural networks, including recurrent neural networks, super-Turing computation and reservoir computing, double-layer vector perceptrons, nonnegative matrix factorization, bio-inspired models of cell communities, Gestalt laws, embodied theory of language understanding, saccadic gaze shifts and memory formation, and new training algorithms for Deep Boltzmann Machines, as well as dynamic neural networks and kernel machines. It also reports on new approaches to reinforcement learning, optimal control of discrete time-delay systems, new al...
Neural network algorithm for image reconstruction using the grid friendly projections
International Nuclear Information System (INIS)
Cierniak, R.
2011-01-01
Full text: The presented paper describes a development of original approach to the reconstruction problem using a recurrent neural network. Particularly, the 'grid-friendly' angles of performed projections are selected according to the discrete Radon transform (DRT) concept to decrease the number of projections required. The methodology of our approach is consistent with analytical reconstruction algorithms. Reconstruction problem is reformulated in our approach to optimization problem. This problem is solved in present concept using method based on the maximum likelihood methodology. The reconstruction algorithm proposed in this work is consequently adapted for more practical discrete fan beam projections. Computer simulation results show that the neural network reconstruction algorithm designed to work in this way improves obtained results and outperforms conventional methods in reconstructed image quality. (author)
Directory of Open Access Journals (Sweden)
Maria CAPCELEA
2015-12-01
Full Text Available Este elaborat şi argumentat teoretic un algoritm eficient pentru determinarea strategiilor optime staţionare în proble-mele stocastice de control optimal discret cu perioada de dirijare infinită, definite pe reţele decizionale cu multiple clase recurente, în care este aplicat criteriul de optimizare a combinaţiei convexe a costurilor medii în clasele recurente. Sunt examinate probleme în care costurile de tranziţie între stările sistemului dinamic şi probabilităţile de tranziţie, definite în stările necontrolabile, sunt constante independente de timp. Algoritmul elaborat este bazat pe modelul de programare liniară pentru determinarea strategiilor optime în problemele de control definite pe reţele decizionale perfecte [3,4].AN ALGORITHM FOR DETERMINING STATIONARY OPTIMAL STRATEGIES FOR STOCHASTIC DISCRETE OPTIMAL CONTROL PROBLEMS DEFINED ON NETWORKS WITH MULTIPLE RECURRENT CLASSESAn efficient algorithm for determining optimal stationary strategies for the stochastic discrete optimal control problems with infinite time horizon is developed and theoretically justified. The problems are defined on decision networks with multiple recurrent classes. The average costs convex combination optimization criterion is applied. We examine problems in which the costs of transitions between the states of the dynamic system and transition probabilities, defined on the uncontrollable states, are constants independent on time. The algorithm is based on the linear programming model developed for determining optimal strategies in control problems defined on perfect decision networks [3,4].
Shi, Peng; Zhang, Yingqi; Chadli, Mohammed; Agarwal, Ramesh K
2016-04-01
In this brief, the problems of the mixed H-infinity and passivity performance analysis and design are investigated for discrete time-delay neural networks with Markovian jump parameters represented by Takagi-Sugeno fuzzy model. The main purpose of this brief is to design a filter to guarantee that the augmented Markovian jump fuzzy neural networks are stable in mean-square sense and satisfy a prescribed passivity performance index by employing the Lyapunov method and the stochastic analysis technique. Applying the matrix decomposition techniques, sufficient conditions are provided for the solvability of the problems, which can be formulated in terms of linear matrix inequalities. A numerical example is also presented to illustrate the effectiveness of the proposed techniques.
Global robust stability of neural networks with multiple discrete delays and distributed delays
International Nuclear Information System (INIS)
Gao Ming; Cui Baotong
2009-01-01
The problem of global robust stability is investigated for a class of uncertain neural networks with both multiple discrete time-varying delays and distributed time-varying delays. The uncertainties are assumed to be of norm-bounded form and the activation functions are supposed to be bounded and globally Lipschitz continuous. Based on the Lyapunov stability theory and linear matrix inequality technique, some robust stability conditions guaranteeing the global robust convergence of the equilibrium point are derived. The proposed LMI-based criteria are computationally efficient as they can be easily checked by using recently developed algorithms in solving LMIs. Two examples are given to show the effectiveness of the proposed results.
Directory of Open Access Journals (Sweden)
Jie-sheng Wang
2014-01-01
Full Text Available For meeting the forecasting target of key technology indicators in the flotation process, a BP neural network soft-sensor model based on features extraction of flotation froth images and optimized by shuffled cuckoo search algorithm is proposed. Based on the digital image processing technique, the color features in HSI color space, the visual features based on the gray level cooccurrence matrix, and the shape characteristics based on the geometric theory of flotation froth images are extracted, respectively, as the input variables of the proposed soft-sensor model. Then the isometric mapping method is used to reduce the input dimension, the network size, and learning time of BP neural network. Finally, a shuffled cuckoo search algorithm is adopted to optimize the BP neural network soft-sensor model. Simulation results show that the model has better generalization results and prediction accuracy.
Neural network for nonsmooth pseudoconvex optimization with general convex constraints.
Bian, Wei; Ma, Litao; Qin, Sitian; Xue, Xiaoping
2018-05-01
In this paper, a one-layer recurrent neural network is proposed for solving a class of nonsmooth, pseudoconvex optimization problems with general convex constraints. Based on the smoothing method, we construct a new regularization function, which does not depend on any information of the feasible region. Thanks to the special structure of the regularization function, we prove the global existence, uniqueness and "slow solution" character of the state of the proposed neural network. Moreover, the state solution of the proposed network is proved to be convergent to the feasible region in finite time and to the optimal solution set of the related optimization problem subsequently. In particular, the convergence of the state to an exact optimal solution is also considered in this paper. Numerical examples with simulation results are given to show the efficiency and good characteristics of the proposed network. In addition, some preliminary theoretical analysis and application of the proposed network for a wider class of dynamic portfolio optimization are included. Copyright © 2018 Elsevier Ltd. All rights reserved.
Directory of Open Access Journals (Sweden)
Tamer Khatib
2014-01-01
Full Text Available In this research an improved approach for sizing standalone PV system (SAPV is presented. This work is an improved work developed previously by the authors. The previous work is based on the analytical method which faced some concerns regarding the difficulty of finding the model’s coefficients. Therefore, the proposed approach in this research is based on a combination of an analytical method and a machine learning approach for a generalized artificial neural network (GRNN. The GRNN assists to predict the optimal size of a PV system using the geographical coordinates of the targeted site instead of using mathematical formulas. Employing the GRNN facilitates the use of a previously developed method by the authors and avoids some of its drawbacks. The approach has been tested using data from five Malaysian sites. According to the results, the proposed method can be efficiently used for SAPV sizing whereas the proposed GRNN based model predicts the sizing curves of the PV system accurately with a prediction error of 0.6%. Moreover, hourly meteorological and load demand data are used in this research in order to consider the uncertainty of the solar energy and the load demand.
Kubatko, Ethan J.; Yeager, Benjamin A.; Ketcheson, David I.
2013-01-01
Discontinuous Galerkin (DG) spatial discretizations are often used in a method-of-lines approach with explicit strong-stability-preserving (SSP) Runge–Kutta (RK) time steppers for the numerical solution of hyperbolic conservation laws. The time steps that are employed in this type of approach must satisfy Courant–Friedrichs–Lewy stability constraints that are dependent on both the region of absolute stability and the SSP coefficient of the RK method. While existing SSPRK methods have been optimized with respect to the latter, it is in fact the former that gives rise to stricter constraints on the time step in the case of RKDG stability. Therefore, in this work, we present the development of new “DG-optimized” SSPRK methods with stability regions that have been specifically designed to maximize the stable time step size for RKDG methods of a given order in one space dimension. These new methods represent the best available RKDG methods in terms of computational efficiency, with significant improvements over methods using existing SSPRK time steppers that have been optimized with respect to SSP coefficients. Second-, third-, and fourth-order methods with up to eight stages are presented, and their stability properties are verified through application to numerical test cases.
Kubatko, Ethan J.
2013-10-29
Discontinuous Galerkin (DG) spatial discretizations are often used in a method-of-lines approach with explicit strong-stability-preserving (SSP) Runge–Kutta (RK) time steppers for the numerical solution of hyperbolic conservation laws. The time steps that are employed in this type of approach must satisfy Courant–Friedrichs–Lewy stability constraints that are dependent on both the region of absolute stability and the SSP coefficient of the RK method. While existing SSPRK methods have been optimized with respect to the latter, it is in fact the former that gives rise to stricter constraints on the time step in the case of RKDG stability. Therefore, in this work, we present the development of new “DG-optimized” SSPRK methods with stability regions that have been specifically designed to maximize the stable time step size for RKDG methods of a given order in one space dimension. These new methods represent the best available RKDG methods in terms of computational efficiency, with significant improvements over methods using existing SSPRK time steppers that have been optimized with respect to SSP coefficients. Second-, third-, and fourth-order methods with up to eight stages are presented, and their stability properties are verified through application to numerical test cases.
Optimization behavior of brainstem respiratory neurons. A cerebral neural network model.
Poon, C S
1991-01-01
A recent model of respiratory control suggested that the steady-state respiratory responses to CO2 and exercise may be governed by an optimal control law in the brainstem respiratory neurons. It was not certain, however, whether such complex optimization behavior could be accomplished by a realistic biological neural network. To test this hypothesis, we developed a hybrid computer-neural model in which the dynamics of the lung, brain and other tissue compartments were simulated on a digital computer. Mimicking the "controller" was a human subject who pedalled on a bicycle with varying speed (analog of ventilatory output) with a view to minimize an analog signal of the total cost of breathing (chemical and mechanical) which was computed interactively and displayed on an oscilloscope. In this manner, the visuomotor cortex served as a proxy (homolog) of the brainstem respiratory neurons in the model. Results in 4 subjects showed a linear steady-state ventilatory CO2 response to arterial PCO2 during simulated CO2 inhalation and a nearly isocapnic steady-state response during simulated exercise. Thus, neural optimization is a plausible mechanism for respiratory control during exercise and can be achieved by a neural network with cognitive computational ability without the need for an exercise stimulus.
Prediction of Optimal Design and Deflection of Space Structures Using Neural Networks
Directory of Open Access Journals (Sweden)
Reza Kamyab Moghadas
2012-01-01
Full Text Available The main aim of the present work is to determine the optimal design and maximum deflection of double layer grids spending low computational cost using neural networks. The design variables of the optimization problem are cross-sectional area of the elements as well as the length of the span and height of the structures. In this paper, a number of double layer grids with various random values of length and height are selected and optimized by simultaneous perturbation stochastic approximation algorithm. Then, radial basis function (RBF and generalized regression (GR neural networks are trained to predict the optimal design and maximum deflection of the structures. The numerical results demonstrate the efficiency of the proposed methodology.
Tight bounds on the size of neural networks for classification problems
Energy Technology Data Exchange (ETDEWEB)
Beiu, V. [Los Alamos National Lab., NM (United States); Pauw, T. de [Universite Catholique de Louvain, Louvain-la-Neuve (Belgium). Dept. de Mathematique
1997-06-01
This paper relies on the entropy of a data-set (i.e., number-of-bits) to prove tight bounds on the size of neural networks solving a classification problem. First, based on a sequence of geometrical steps, the authors constructively compute an upper bound of O(mn) on the number-of-bits for a given data-set - here m is the number of examples and n is the number of dimensions (i.e., R{sup n}). This result is used further in a nonconstructive way to bound the size of neural networks which correctly classify that data-set.
Li, Zejing
2012-01-01
This dissertation is mainly devoted to the research of two problems - the continuous-time portfolio optimization in different Wishart models and the effects of discrete rebalancing on portfolio wealth distribution and optimal portfolio strategy.
Directory of Open Access Journals (Sweden)
Reddy Sreenivasulu
2015-03-01
Full Text Available This paper presents the influence of cutting parameters like cutting speed, feed rate, drill diameter, point angle and clearance angle on the burr size, surface roughness and circularity deviation of Al 6061 during drilling on CNC vertical machining center. A plan of experiments based on Taguchi technique has been used to acquire the data. An orthogonal array, signal to noise (S/N ratio and analysis of variance (ANOVA are employed to investigate machining characteristics of Al 6061 using HSS twist drill bits of variable tool geometry and maintain constant helix angle of 45 degrees. Confirmation tests have been carried out to predict the optimal setting of process parameters to validate the used approach, obtained the values of 0.2618mm, 0.1821mm, 3.7451µm, 0.0676mm for burr height, burr thickness, surface roughness and circularity deviation respectively. Finally, artificial neural network has been applied to compare the predicted values with the experimental values, good agreement was shown between the predictive model results and the experimental measurements. Normal 0 false false false EN-US X-NONE X-NONE
Directory of Open Access Journals (Sweden)
N. M. Okasha
2016-04-01
Full Text Available In this paper, an approach for conducting a Reliability-Based Design Optimization (RBDO of truss structures with linked-discrete design variables is proposed. The sections of the truss members are selected from the AISC standard tables and thus the design variables that represent the properties of each section are linked. Latin hypercube sampling is used in the evaluation of the structural reliability. The improved firefly algorithm is used for the optimization solution process. It was found that in order to use the improved firefly algorithm for efficiently solving problems of reliability-based design optimization with linked-discrete design variables; it needs to be modified as proposed in this paper to accelerate its convergence.
Santosa, B.; Siswanto, N.; Fiqihesa
2018-04-01
This paper proposes a discrete Particle Swam Optimization (PSO) to solve limited-wait hybrid flowshop scheduing problem with multi objectives. Flow shop schedulimg represents the condition when several machines are arranged in series and each job must be processed at each machine with same sequence. The objective functions are minimizing completion time (makespan), total tardiness time, and total machine idle time. Flow shop scheduling model always grows to cope with the real production system accurately. Since flow shop scheduling is a NP-Hard problem then the most suitable method to solve is metaheuristics. One of metaheuristics algorithm is Particle Swarm Optimization (PSO), an algorithm which is based on the behavior of a swarm. Originally, PSO was intended to solve continuous optimization problems. Since flow shop scheduling is a discrete optimization problem, then, we need to modify PSO to fit the problem. The modification is done by using probability transition matrix mechanism. While to handle multi objectives problem, we use Pareto Optimal (MPSO). The results of MPSO is better than the PSO because the MPSO solution set produced higher probability to find the optimal solution. Besides the MPSO solution set is closer to the optimal solution
Discretizing the transcritical and pitchfork bifurcations – conjugacy results
Lóczi, Lajos
2015-01-07
© 2015 Taylor & Francis. We present two case studies in one-dimensional dynamics concerning the discretization of transcritical (TC) and pitchfork (PF) bifurcations. In the vicinity of a TC or PF bifurcation point and under some natural assumptions on the one-step discretization method of order (Formula presented.) , we show that the time- (Formula presented.) exact and the step-size- (Formula presented.) discretized dynamics are topologically equivalent by constructing a two-parameter family of conjugacies in each case. As a main result, we prove that the constructed conjugacy maps are (Formula presented.) -close to the identity and these estimates are optimal.
DEFF Research Database (Denmark)
Achtziger, Wolfgang; Stolpe, Mathias
2009-01-01
we use the theory developed in Part I to design a convergent nonlinear branch-and-bound method tailored to solve large-scale instances of the original discrete problem. The problem formulation and the needed theoretical results from Part I are repeated such that this paper is self-contained. We focus...... the largest discrete topology design problems solved by means of global optimization....
International Nuclear Information System (INIS)
Ladjevardi, M.; Masoum, M.A.S.; Fuchs, E.F.
2004-01-01
An iterative nonlinear algorithm is generated for optimal sizing and placement of fixed and switched capacitor banks on radial distribution lines in the presence of linear and nonlinear loads. The HARMFLOW algorithm and the maximum sensitivities selection method are used to solve the constrained optimizations problem with discrete variables. To limit the burden of calculations and improve convergence, the problem is decomposed into two subproblems. Objective functions include minimum system losses and capacitor cost while IEEE 519 power quality limits are used as constraints. Results are presented and analyzed for the 18 bus IEEE distorted system. The advantage of the proposed algorithm compared to the previous work is the consideration of harmonic couplings and reactions of actual nonlinear loads of the distribution system
International Nuclear Information System (INIS)
Kefayat, M.; Lashkar Ara, A.; Nabavi Niaki, S.A.
2015-01-01
Highlights: • A probabilistic optimization framework incorporated with uncertainty is proposed. • A hybrid optimization approach combining ACO and ABC algorithms is proposed. • The problem is to deal with technical, environmental and economical aspects. • A fuzzy interactive approach is incorporated to solve the multi-objective problem. • Several strategies are implemented to compare with literature methods. - Abstract: In this paper, a hybrid configuration of ant colony optimization (ACO) with artificial bee colony (ABC) algorithm called hybrid ACO–ABC algorithm is presented for optimal location and sizing of distributed energy resources (DERs) (i.e., gas turbine, fuel cell, and wind energy) on distribution systems. The proposed algorithm is a combined strategy based on the discrete (location optimization) and continuous (size optimization) structures to achieve advantages of the global and local search ability of ABC and ACO algorithms, respectively. Also, in the proposed algorithm, a multi-objective ABC is used to produce a set of non-dominated solutions which store in the external archive. The objectives consist of minimizing power losses, total emissions produced by substation and resources, total electrical energy cost, and improving the voltage stability. In order to investigate the impact of the uncertainty in the output of the wind energy and load demands, a probabilistic load flow is necessary. In this study, an efficient point estimate method (PEM) is employed to solve the optimization problem in a stochastic environment. The proposed algorithm is tested on the IEEE 33- and 69-bus distribution systems. The results demonstrate the potential and effectiveness of the proposed algorithm in comparison with those of other evolutionary optimization methods
Directory of Open Access Journals (Sweden)
Yan-Ke Du
2013-09-01
Full Text Available We study a class of discrete-time bidirectional ring neural network model with delay. We discuss the asymptotic stability of the origin and the existence of Neimark-Sacker bifurcations, by analyzing the corresponding characteristic equation. Employing M-matrix theory and the Lyapunov functional method, global asymptotic stability of the origin is derived. Applying the normal form theory and the center manifold theorem, the direction of the Neimark-Sacker bifurcation and the stability of bifurcating periodic solutions are obtained. Numerical simulations are given to illustrate the main results.
A Particle Swarm Optimization Algorithm for Neural Networks in Recognition of Maize Leaf Diseases
Directory of Open Access Journals (Sweden)
Zhiyong ZHANG
2014-03-01
Full Text Available The neural networks have significance on recognition of crops disease diagnosis? but it has disadvantage of slow convergent speed and shortcoming of local optimum. In order to identify the maize leaf diseases by using machine vision more accurately, we propose an improved particle swarm optimization algorithm for neural networks. With the algorithm, the neural network property is improved. It reasonably confirms threshold and connection weight of neural network, and improves capability of solving problems in the image recognition. At last, an example of the emulation shows that neural network model based on recognizes significantly better than without optimization. Model accuracy has been improved to a certain extent to meet the actual needs of maize leaf diseases recognition.
A stochastic discrete optimization model for designing container terminal facilities
Zukhruf, Febri; Frazila, Russ Bona; Burhani, Jzolanda Tsavalista
2017-11-01
As uncertainty essentially affect the total transportation cost, it remains important in the container terminal that incorporates several modes and transshipments process. This paper then presents a stochastic discrete optimization model for designing the container terminal, which involves the decision of facilities improvement action. The container terminal operation model is constructed by accounting the variation of demand and facilities performance. In addition, for illustrating the conflicting issue that practically raises in the terminal operation, the model also takes into account the possible increment delay of facilities due to the increasing number of equipment, especially the container truck. Those variations expectantly reflect the uncertainty issue in the container terminal operation. A Monte Carlo simulation is invoked to propagate the variations by following the observed distribution. The problem is constructed within the framework of the combinatorial optimization problem for investigating the optimal decision of facilities improvement. A new variant of glow-worm swarm optimization (GSO) is thus proposed for solving the optimization, which is rarely explored in the transportation field. The model applicability is tested by considering the actual characteristics of the container terminal.
A Collaborative Neurodynamic Approach to Multiple-Objective Distributed Optimization.
Yang, Shaofu; Liu, Qingshan; Wang, Jun
2018-04-01
This paper is concerned with multiple-objective distributed optimization. Based on objective weighting and decision space decomposition, a collaborative neurodynamic approach to multiobjective distributed optimization is presented. In the approach, a system of collaborative neural networks is developed to search for Pareto optimal solutions, where each neural network is associated with one objective function and given constraints. Sufficient conditions are derived for ascertaining the convergence to a Pareto optimal solution of the collaborative neurodynamic system. In addition, it is proved that each connected subsystem can generate a Pareto optimal solution when the communication topology is disconnected. Then, a switching-topology-based method is proposed to compute multiple Pareto optimal solutions for discretized approximation of Pareto front. Finally, simulation results are discussed to substantiate the performance of the collaborative neurodynamic approach. A portfolio selection application is also given.
The application of particle swarm optimization to identify gamma spectrum with neural network
International Nuclear Information System (INIS)
Shi Dongsheng; Di Yuming; Zhou Chunlin
2006-01-01
Aiming at the shortcomings that BP algorithm is usually trapped to a local optimum and it has a low speed of convergence in the application of neural network to identify gamma spectrum, according to the advantage of the globe optimal searching of particle swarm optimization, this paper put forward a new algorithm for neural network training by combining BP algorithm and Particle Swarm Optimization-mixed PSO-BP algorithm. In the application to identify gamma spectrum, the new algorithm overcomes the shortcoming that BP algorithm is usually trapped to a local optimum and the neural network trained by it has a high ability of generalization with identification result of one hundred percent correct. Practical example shows that the mixed PSO-BP algorithm can effectively and reliably be used to identify gamma spectrum. (authors)
An Evolutionary Optimization Framework for Neural Networks and Neuromorphic Architectures
Energy Technology Data Exchange (ETDEWEB)
Schuman, Catherine D [ORNL; Plank, James [University of Tennessee (UT); Disney, Adam [University of Tennessee (UT); Reynolds, John [University of Tennessee (UT)
2016-01-01
As new neural network and neuromorphic architectures are being developed, new training methods that operate within the constraints of the new architectures are required. Evolutionary optimization (EO) is a convenient training method for new architectures. In this work, we review a spiking neural network architecture and a neuromorphic architecture, and we describe an EO training framework for these architectures. We present the results of this training framework on four classification data sets and compare those results to other neural network and neuromorphic implementations. We also discuss how this EO framework may be extended to other architectures.
Optimization of operation schemes in boiling water reactors using neural networks
International Nuclear Information System (INIS)
Ortiz S, J. J.; Castillo M, A.; Pelta, D. A.
2012-10-01
In previous works were presented the results of a recurrent neural network to find the best combination of several groups of fuel cells, fuel load and control bars patterns. These solution groups to each problem of Fuel Management were previously optimized by diverse optimization techniques. The neural network chooses the partial solutions so the combination of them, correspond to a good configuration of the reactor according to a function objective. The values of the involved variables in this objective function are obtained through the simulation of the combination of partial solutions by means of Simulate-3. In the present work, a multilayer neural network that learned how to predict some results of Simulate-3 was used so was possible to substitute it in the objective function for the neural network and to accelerate the response time of the whole system of this way. The preliminary results shown in this work are encouraging to continue carrying out efforts in this sense and to improve the response quality of the system. (Author)
Real-time process optimization based on grey-box neural models
Directory of Open Access Journals (Sweden)
F. A. Cubillos
2007-09-01
Full Text Available This paper investigates the feasibility of using grey-box neural models (GNM in Real Time Optimization (RTO. These models are based on a suitable combination of fundamental conservation laws and neural networks, being used in at least two different ways: to complement available phenomenological knowledge with empirical information, or to reduce dimensionality of complex rigorous physical models. We have observed that the benefits of using these simple adaptable models are counteracted by some difficulties associated with the solution of the optimization problem. Nonlinear Programming (NLP algorithms failed in finding the global optimum due to the fact that neural networks can introduce multimodal objective functions. One alternative considered to solve this problem was the use of some kind of evolutionary algorithms, like Genetic Algorithms (GA. Although these algorithms produced better results in terms of finding the appropriate region, they took long periods of time to reach the global optimum. It was found that a combination of genetic and nonlinear programming algorithms can be use to fast obtain the optimum solution. The proposed approach was applied to the Williams-Otto reactor, considering three different GNM models of increasing complexity. Results demonstrated that the use of GNM models and mixed GA/NLP optimization algorithms is a promissory approach for solving dynamic RTO problems.
BEST-4, Fuel Cycle and Cost Optimization for Discrete Power Levels
International Nuclear Information System (INIS)
1973-01-01
1 - Nature of physical problem solved: Determination of optimal power strategy for a fuel cycle, for discrete power levels and n temporal stages, taking into account replacement energy costs and de-rating. 2 - Method of solution: Dynamic programming. 3 - Restrictions on the complexity of the problem: Restrictions may arise from number of power levels and temporal stages, due to machine limitations
Cheng, Long; Hou, Zeng-Guang; Lin, Yingzi; Tan, Min; Zhang, Wenjun Chris; Wu, Fang-Xiang
2011-05-01
A recurrent neural network is proposed for solving the non-smooth convex optimization problem with the convex inequality and linear equality constraints. Since the objective function and inequality constraints may not be smooth, the Clarke's generalized gradients of the objective function and inequality constraints are employed to describe the dynamics of the proposed neural network. It is proved that the equilibrium point set of the proposed neural network is equivalent to the optimal solution of the original optimization problem by using the Lagrangian saddle-point theorem. Under weak conditions, the proposed neural network is proved to be stable, and the state of the neural network is convergent to one of its equilibrium points. Compared with the existing neural network models for non-smooth optimization problems, the proposed neural network can deal with a larger class of constraints and is not based on the penalty method. Finally, the proposed neural network is used to solve the identification problem of genetic regulatory networks, which can be transformed into a non-smooth convex optimization problem. The simulation results show the satisfactory identification accuracy, which demonstrates the effectiveness and efficiency of the proposed approach.
Directory of Open Access Journals (Sweden)
Ram Verma
2016-02-01
Full Text Available This paper deals with mainly establishing numerous sets of generalized second order paramertic sufficient optimality conditions for a semiinfinite discrete minmax fractional programming problem, while the results on semiinfinite discrete minmax fractional programming problem achieved based on some partitioning schemes under various types of generalized second order univexity assumptions.
Optimal Formation of Multirobot Systems Based on a Recurrent Neural Network.
Wang, Yunpeng; Cheng, Long; Hou, Zeng-Guang; Yu, Junzhi; Tan, Min
2016-02-01
The optimal formation problem of multirobot systems is solved by a recurrent neural network in this paper. The desired formation is described by the shape theory. This theory can generate a set of feasible formations that share the same relative relation among robots. An optimal formation means that finding one formation from the feasible formation set, which has the minimum distance to the initial formation of the multirobot system. Then, the formation problem is transformed into an optimization problem. In addition, the orientation, scale, and admissible range of the formation can also be considered as the constraints in the optimization problem. Furthermore, if all robots are identical, their positions in the system are exchangeable. Then, each robot does not necessarily move to one specific position in the formation. In this case, the optimal formation problem becomes a combinational optimization problem, whose optimal solution is very hard to obtain. Inspired by the penalty method, this combinational optimization problem can be approximately transformed into a convex optimization problem. Due to the involvement of the Euclidean norm in the distance, the objective function of these optimization problems are nonsmooth. To solve these nonsmooth optimization problems efficiently, a recurrent neural network approach is employed, owing to its parallel computation ability. Finally, some simulations and experiments are given to validate the effectiveness and efficiency of the proposed optimal formation approach.
Design of an optimal preview controller for linear discrete-time descriptor systems with state delay
Cao, Mengjuan; Liao, Fucheng
2015-04-01
In this paper, the linear discrete-time descriptor system with state delay is studied, and a design method for an optimal preview controller is proposed. First, by using the discrete lifting technique, the original system is transformed into a general descriptor system without state delay in form. Then, taking advantage of the first-order forward difference operator, we construct a descriptor augmented error system, including the state vectors of the lifted system, error vectors, and desired target signals. Rigorous mathematical proofs are given for the regularity, stabilisability, causal controllability, and causal observability of the descriptor augmented error system. Based on these, the optimal preview controller with preview feedforward compensation for the original system is obtained by using the standard optimal regulator theory of the descriptor system. The effectiveness of the proposed method is shown by numerical simulation.
Optimal control of LQR for discrete time-varying systems with input delays
Yin, Yue-Zhu; Yang, Zhong-Lian; Yin, Zhi-Xiang; Xu, Feng
2018-04-01
In this work, we consider the optimal control problem of linear quadratic regulation for discrete time-variant systems with single input and multiple input delays. An innovative and simple method to derive the optimal controller is given. The studied problem is first equivalently converted into a problem subject to a constraint condition. Last, with the established duality, the problem is transformed into a static mathematical optimisation problem without input delays. The optimal control input solution to minimise performance index function is derived by solving this optimisation problem with two methods. A numerical simulation example is carried out and its results show that our two approaches are both feasible and very effective.
Application of neural network to CT
International Nuclear Information System (INIS)
Ma, Xiao-Feng; Takeda, Tatsuoki
1999-01-01
This paper presents a new method for two-dimensional image reconstruction by using a multilayer neural network. Multilayer neural networks are extensively investigated and practically applied to solution of various problems such as inverse problems or time series prediction problems. From learning an input-output mapping from a set of examples, neural networks can be regarded as synthesizing an approximation of multidimensional function (that is, solving the problem of hypersurface reconstruction, including smoothing and interpolation). From this viewpoint, neural networks are well suited to the solution of CT image reconstruction. Though a conventionally used object function of a neural network is composed of a sum of squared errors of the output data, we can define an object function composed of a sum of residue of an integral equation. By employing an appropriate line integral for this integral equation, we can construct a neural network that can be used for CT. We applied this method to some model problems and obtained satisfactory results. As it is not necessary to discretized the integral equation using this reconstruction method, therefore it is application to the problem of complicated geometrical shapes is also feasible. Moreover, in neural networks, interpolation is performed quite smoothly, as a result, inverse mapping can be achieved smoothly even in case of including experimental and numerical errors, However, use of conventional back propagation technique for optimization leads to an expensive computation cost. To overcome this drawback, 2nd order optimization methods or parallel computing will be applied in future. (J.P.N.)
International Nuclear Information System (INIS)
Mellit, A.; Benghanem, M.; Hadj Arab, A.; Guessoum, G.
2004-07-01
In this paper we investigate, by using an adaptive Artificial Neural Network (ANN), in order to find a suitable model for sizing Stand-Alone Photovoltaic (SAPV) systems, based on a minimum of input data. This model combines Radial Basis Function (RBF) network and Infinite Impulse Response (IIR) filter in order to accelerate the convergence of the network. For the sizing of a photovoltaic (PV) system, we need to determine the optimal sizing coefficients (K PV , K B . These coefficients allow us to determine the number of solar panels and storage batteries necessary to satisfy a given consumption, especially in isolated sites where the global solar radiation data is not always available and which are considered the most important parameters for sizing a PV system. Obtained results by classical models (analytical, numerical, analytical- numerical, B-spline function) and new models like feed-forward (MLP), radial basis function (RBF), MLP-IIR and RBF-IIR have been compared with experimental sizing coefficients in order to illustrate the accuracy of the results of the new developed model. This model has been trained by using 200 known optimal sizing coefficients corresponding to 200 locations in Algeria. In this way, the adaptive model was trained to accept and even handle a number of unusual cases, the unknown validation sizing coefficients set produced very set accurate estimation and a correlation coefficient of 98% was obtained between the calculated and that estimated by the RBF-IIR model. This result indicates that the proposed method can be successfully used for the estimation of optimal sizing coefficients of SAPV systems for any locations in Algeria, but the methodology can be generalized using different locations over the world. (author)
Analysis and optimization of gas-centrifugal separation of uranium isotopes by neural networks
Directory of Open Access Journals (Sweden)
Migliavacca S.C.P.
2002-01-01
Full Text Available Neural networks are an attractive alternative for modeling complex problems with too many difficulties to be solved by a phenomenological model. A feed-forward neural network was used to model a gas-centrifugal separation of uranium isotopes. The prediction showed good agreement with the experimental data. An optimization study was carried out. The optimal operational condition was tested by a new experiment and a difference of less than 1% was found.
DEFF Research Database (Denmark)
Evgrafov, Anton; Gregersen, Misha Marie; Sørensen, Mads Peter
2011-01-01
We present a convergence analysis of a cell-based finite volume (FV) discretization scheme applied to a problem of control in the coefficients of a generalized Laplace equation modelling, for example, a steady state heat conduction. Such problems arise in applications dealing with geometric optimal......, whereas the convergence of the coefficients happens only with respect to the "volumetric" Lebesgue measure. Additionally, depending on whether the stationarity conditions are stated for the discretized or the original continuous problem, two distinct concepts of stationarity at a discrete level arise. We...... provide characterizations of limit points, with respect to FV mesh size, of globally optimal solutions and two types of stationary points to the discretized problems. We illustrate the practical behaviour of our cell-based FV discretization algorithm on a numerical example....
International Nuclear Information System (INIS)
Song, Qiankun; Wang, Zidong
2007-01-01
In this Letter, the analysis problem for the existence and stability of periodic solutions is investigated for a class of general discrete-time recurrent neural networks with time-varying delays. For the neural networks under study, a generalized activation function is considered, and the traditional assumptions on the boundedness, monotony and differentiability of the activation functions are removed. By employing the latest free-weighting matrix method, an appropriate Lyapunov-Krasovskii functional is constructed and several sufficient conditions are established to ensure the existence, uniqueness, and globally exponential stability of the periodic solution for the addressed neural network. The conditions are dependent on both the lower bound and upper bound of the time-varying time delays. Furthermore, the conditions are expressed in terms of the linear matrix inequalities (LMIs), which can be checked numerically using the effective LMI toolbox in MATLAB. Two simulation examples are given to show the effectiveness and less conservatism of the proposed criteria
International Nuclear Information System (INIS)
Liang Jinling; Cao Jinde
2004-01-01
First, convergence of continuous-time Bidirectional Associative Memory (BAM) neural networks are studied. By using Lyapunov functionals and some analysis technique, the delay-independent sufficient conditions are obtained for the networks to converge exponentially toward the equilibrium associated with the constant input sources. Second, discrete-time analogues of the continuous-time BAM networks are formulated and studied. It is shown that the convergence characteristics of the continuous-time systems are preserved by the discrete-time analogues without any restriction imposed on the uniform discretionary step size. An illustrative example is given to demonstrate the effectiveness of the obtained results
Energy Technology Data Exchange (ETDEWEB)
Mellit, A. [Medea Univ., Medea (Algeria). Inst. of Science Engineering, Dept. of Electronics
2007-07-01
Stand-alone photovoltaic (PV) power supply systems are regarded as reliable and economical sources of electricity in rural remote areas, particularly in developing countries. However, the sizing of stand-alone photovoltaic (PV) systems is an important part of the system design. Choosing the optimal number of solar cell panels and the size of the storage battery to be used for a certain application at a particular site is an important economical problem. In this paper, a genetic algorithm (GA) and an adaptive neuro-fuzzy inference scheme (ANFIS) were proposed as a means for determining the optimal size of PV system, particularly, in isolated areas. The GA-ANFIS model was shown to be suitable for modelling the optimal sizing parameters of PVS systems. The GA was used to determine the PV-array capacity and the storage capacity for 60 sites. From this database, 56 pairs relative to 56 sites were used for training the network. Four pairs were used for testing and validating the ANFIS model. A correlation of 99 per cent was achieved when complete unknown data parameters were presented to the model. The proposed technique provided more accurate results than the alternative artificial neural network (ANN) with GA. The advantage of this model was that it could estimate the PV-array area and the useful capacity of the battery from only geographical coordinates. Although the technique was applied and tested in Algeria, it can be generalized for any location in the world. 15 refs., 4 tabs., 8 figs.
Complex dynamics of a delayed discrete neural network of two nonidentical neurons.
Chen, Yuanlong; Huang, Tingwen; Huang, Yu
2014-03-01
In this paper, we discover that a delayed discrete Hopfield neural network of two nonidentical neurons with self-connections and no self-connections can demonstrate chaotic behaviors. To this end, we first transform the model, by a novel way, into an equivalent system which has some interesting properties. Then, we identify the chaotic invariant set for this system and show that the dynamics of this system within this set is topologically conjugate to the dynamics of the full shift map with two symbols. This confirms chaos in the sense of Devaney. Our main results generalize the relevant results of Huang and Zou [J. Nonlinear Sci. 15, 291-303 (2005)], Kaslik and Balint [J. Nonlinear Sci. 18, 415-432 (2008)] and Chen et al. [Sci. China Math. 56(9), 1869-1878 (2013)]. We also give some numeric simulations to verify our theoretical results.
Optimization of neural network algorithm of the land market description
Directory of Open Access Journals (Sweden)
M. A. Karpovich
2016-01-01
Full Text Available The advantages of neural network technology is shown in comparison of traditional descriptions of dynamically changing systems, which include a modern land market. The basic difficulty arising in the practical implementation of neural network models of the land market and construction products is revealed It is the formation of a representative set of training and test examples. The requirements which are necessary for the correct description of the current economic situation has been determined, it consists in the fact that Train-paid-set in the feature space should not has the ranges with a low density of observations. The methods of optimization of empirical array, which allow to avoid the long-range extrapolation of data from range of concentration of the set of examples are formulated. It is shown that a radical method of optimization a set of training and test examples enclosing to collect supplemantary information, is associated with significant costs time and resources for the economic problems and the ratio of cost / efficiency is less efficient than an algorithm optimization neural network models the earth market fixed set of empirical data. Algorithm of optimization based on the transformation of arrays of information which represents the expansion of the ranges of concentration of the set of examples and compression the ranges of low density of observations is analyzed in details. The significant reduction in the relative error of land price description is demonstrated on the specific example of Voronezh region market of lands which intend for road construction, it makes the using of radical method of empirical optimization of the array costeffective with accounting the significant absolute value of the land. The high economic efficiency of the proposed algorithms is demonstrated.
Huang, Daizheng; Wu, Zhihui
2017-01-01
Accurately predicting the trend of outpatient visits by mathematical modeling can help policy makers manage hospitals effectively, reasonably organize schedules for human resources and finances, and appropriately distribute hospital material resources. In this study, a hybrid method based on empirical mode decomposition and back-propagation artificial neural networks optimized by particle swarm optimization is developed to forecast outpatient visits on the basis of monthly numbers. The data outpatient visits are retrieved from January 2005 to December 2013 and first obtained as the original time series. Second, the original time series is decomposed into a finite and often small number of intrinsic mode functions by the empirical mode decomposition technique. Third, a three-layer back-propagation artificial neural network is constructed to forecast each intrinsic mode functions. To improve network performance and avoid falling into a local minimum, particle swarm optimization is employed to optimize the weights and thresholds of back-propagation artificial neural networks. Finally, the superposition of forecasting results of the intrinsic mode functions is regarded as the ultimate forecasting value. Simulation indicates that the proposed method attains a better performance index than the other four methods.
International Nuclear Information System (INIS)
Onomi, T; Nakajima, K
2014-01-01
We have proposed a superconducting Hopfield-type neural network for solving the N-Queens problem which is one of combinatorial optimization problems. The sigmoid-shape function of a neuron output is represented by the output of coupled SQUIDs gate consisting of a single-junction and a double-junction SQUIDs. One of the important factors for an improvement of the network performance is an improvement of a threshold characteristic of a neuron circuit. In this paper, we report an improved design of coupled SQUID gates for a superconducting neural network. A step-like function with a steep threshold at a rising edge is desirable for a neuron circuit to solve a combinatorial optimization problem. A neuron circuit is composed of two coupled SQUIDs gates with a cascade connection in order to obtain such characteristics. The designed neuron circuit is fabricated by a 2.5 kA/cm 2 Nb/AlOx/Nb process. The operation of a fabricated neuron circuit is experimentally demonstrated. Moreover, we discuss about the performance of the neural network using the improved neuron circuits and delayed negative self-connections.
Directory of Open Access Journals (Sweden)
P.-Y. Chen
2009-01-01
Full Text Available This study proposes a neural network-family competition genetic algorithm (NN-FCGA for solving the electromagnetic (EM optimization and other general-purpose optimization problems. The NN-FCGA is a hybrid evolutionary-based algorithm, combining the good approximation performance of neural network (NN and the robust and effective optimum search ability of the family competition genetic algorithms (FCGA to accelerate the optimization process. In this study, the NN-FCGA is used to extract a set of optimal design parameters for two representative design examples: the multiple section low-pass filter and the polygonal electromagnetic absorber. Our results demonstrate that the optimal electromagnetic properties given by the NN-FCGA are comparable to those of the FCGA, but reducing a large amount of computation time and a well-trained NN model that can serve as a nonlinear approximator was developed during the optimization process of the NN-FCGA.
Calculating Optimal Inventory Size
Directory of Open Access Journals (Sweden)
Ruby Perez
2010-01-01
Full Text Available The purpose of the project is to find the optimal value for the Economic Order Quantity Model and then use a lean manufacturing Kanban equation to find a numeric value that will minimize the total cost and the inventory size.
Optimization of a neural network model for signal-to-background prediction in gamma-ray spectrometry
International Nuclear Information System (INIS)
Dragovic, S.; Onjia, A. . E-mail address of corresponding author: sdragovic@inep.co.yu; Dragovic, S.)
2005-01-01
The artificial neural network (ANN) model was optimized for the prediction of signal-to-background (SBR) ratio as a function of the measurement time in gamma-ray spectrometry. The network parameters: learning rate (α), momentum (μ), number of epochs (E) and number of nodes in hidden layer (N) were optimized simultaneously employing variable-size simplex method. The most accurate model with the root mean square (RMS) error of 0.073 was obtained using ANN with online backpropagation randomized (OBPR) algorithm with α = 0.27, μ 0.36, E = 14800 and N = 9. Most of the predicted and experimental SBR values for the eight radionuclides ( 226 Ra, 214 Bi, 235 U, 40 K, 232 Th, 134 Cs, 137 Cs and 7 Be), studied in this work, reasonably agreed to within 15 %, which was satisfactory accuracy. (author)
2016-06-12
Particle Size in Discrete Element Method to Particle Gas Method (DEM_PGM) Coupling in Underbody Blast Simulations Venkatesh Babu, Kumar Kulkarni, Sanjay...buried in soil viz., (1) coupled discrete element & particle gas methods (DEM-PGM) and (2) Arbitrary Lagrangian-Eulerian (ALE), are investigated. The...DEM_PGM and identify the limitations/strengths compared to the ALE method. Discrete Element Method (DEM) can model individual particle directly, and
A new approach to self-organizing fuzzy polynomial neural networks guided by genetic optimization
International Nuclear Information System (INIS)
Oh, Sung-Kwun; Pedrycz, Witold
2005-01-01
In this study, we introduce a new topology of Fuzzy Polynomial Neural Networks (FPNN) that is based on a genetically optimized multilayer perceptron with fuzzy polynomial neurons (FPNs) and discuss its comprehensive design methodology. The underlying methodology involves mechanisms of genetic optimization, especially genetic algorithms (GAs). Let us recall that the design of the 'conventional' FPNNs uses an extended Group Method of Data Handling (GMDH) and exploits a fixed fuzzy inference type located at each FPN of the FPNN as well as considers a fixed number of input nodes at FPNs (or nodes) located in each layer. The proposed FPNN gives rise to a structurally optimized structure and comes with a substantial level of flexibility in comparison to the one we encounter in conventional FPNNs. The structural optimization is realized via GAs whereas in the case of the parametric optimization we proceed with a standard least square method based learning. Through the consecutive process of such structural and parametric optimization, an optimized and flexible fuzzy neural network is generated in a dynamic fashion. The performance of the proposed gFPNN is quantified through experimentation that exploits standard data already being used in fuzzy modeling. The results reveal superiority of the proposed networks over the existing fuzzy and neural models
Smolensky, Paul; Goldrick, Matthew; Mathis, Donald
2014-08-01
Mental representations have continuous as well as discrete, combinatorial properties. For example, while predominantly discrete, phonological representations also vary continuously; this is reflected by gradient effects in instrumental studies of speech production. Can an integrated theoretical framework address both aspects of structure? The framework we introduce here, Gradient Symbol Processing, characterizes the emergence of grammatical macrostructure from the Parallel Distributed Processing microstructure (McClelland, Rumelhart, & The PDP Research Group, 1986) of language processing. The mental representations that emerge, Distributed Symbol Systems, have both combinatorial and gradient structure. They are processed through Subsymbolic Optimization-Quantization, in which an optimization process favoring representations that satisfy well-formedness constraints operates in parallel with a distributed quantization process favoring discrete symbolic structures. We apply a particular instantiation of this framework, λ-Diffusion Theory, to phonological production. Simulations of the resulting model suggest that Gradient Symbol Processing offers a way to unify accounts of grammatical competence with both discrete and continuous patterns in language performance. Copyright © 2013 Cognitive Science Society, Inc.
Optimizing a neural network for detection of moving vehicles in video
Fischer, Noëlle M.; Kruithof, Maarten C.; Bouma, Henri
2017-10-01
In the field of security and defense, it is extremely important to reliably detect moving objects, such as cars, ships, drones and missiles. Detection and analysis of moving objects in cameras near borders could be helpful to reduce illicit trading, drug trafficking, irregular border crossing, trafficking in human beings and smuggling. Many recent benchmarks have shown that convolutional neural networks are performing well in the detection of objects in images. Most deep-learning research effort focuses on classification or detection on single images. However, the detection of dynamic changes (e.g., moving objects, actions and events) in streaming video is extremely relevant for surveillance and forensic applications. In this paper, we combine an end-to-end feedforward neural network for static detection with a recurrent Long Short-Term Memory (LSTM) network for multi-frame analysis. We present a practical guide with special attention to the selection of the optimizer and batch size. The end-to-end network is able to localize and recognize the vehicles in video from traffic cameras. We show an efficient way to collect relevant in-domain data for training with minimal manual labor. Our results show that the combination with LSTM improves performance for the detection of moving vehicles.
Using neural networks to speed up optimization algorithms
Bazan, M
2000-01-01
The paper presents the application of radial-basis-function (RBF) neural networks to speed up deterministic search algorithms used for the design and optimization of superconducting LHC magnets. The optimization of the iron yoke of the main dipoles requires a number of numerical field computations per trial solution as the field quality depends on the excitation of the magnets. This results in computation times of about 30 minutes for each objective function evaluation (on a DEC-Alpha 600/333) and only the most robust (deterministic) optimization algorithms can be applied. Using a RBF function approximator, the achieved speed-up of the search algorithm is in the order of 25% for problems with two parameters and about 18% for problems with three and five design variables. (13 refs).
Discrete Optimization in Chemical Space Reference Manual
2012-10-01
includes instructions on setting up constrained optimizations of substitutional frameworks and the full application programming interface ( API ) necessary...space size • bool space size computed • ulong bits • bool bits computed • string Nam 4.26.1 Detailed Description This class provides the API that...1, 0) 1102 (O, 0, 1.4, -3, 120, -2, 180) 1103 (C, 1, 1.5, 0, 120, -3, -30(150)) 1104 (H, 2, 1.1, 1, 109.47, 0,180) 1105 (H, 2, 1.1, 1, 109.47, 3, 120
Liu, Qingshan; Wang, Jun
2011-04-01
This paper presents a one-layer recurrent neural network for solving a class of constrained nonsmooth optimization problems with piecewise-linear objective functions. The proposed neural network is guaranteed to be globally convergent in finite time to the optimal solutions under a mild condition on a derived lower bound of a single gain parameter in the model. The number of neurons in the neural network is the same as the number of decision variables of the optimization problem. Compared with existing neural networks for optimization, the proposed neural network has a couple of salient features such as finite-time convergence and a low model complexity. Specific models for two important special cases, namely, linear programming and nonsmooth optimization, are also presented. In addition, applications to the shortest path problem and constrained least absolute deviation problem are discussed with simulation results to demonstrate the effectiveness and characteristics of the proposed neural network.
International Nuclear Information System (INIS)
Gurcan, Metin N.; Sahiner, Berkman; Chan Heangping; Hadjiiski, Lubomir; Petrick, Nicholas
2001-01-01
Many computer-aided diagnosis (CAD) systems use neural networks (NNs) for either detection or classification of abnormalities. Currently, most NNs are 'optimized' by manual search in a very limited parameter space. In this work, we evaluated the use of automated optimization methods for selecting an optimal convolution neural network (CNN) architecture. Three automated methods, the steepest descent (SD), the simulated annealing (SA), and the genetic algorithm (GA), were compared. We used as an example the CNN that classifies true and false microcalcifications detected on digitized mammograms by a prescreening algorithm. Four parameters of the CNN architecture were considered for optimization, the numbers of node groups and the filter kernel sizes in the first and second hidden layers, resulting in a search space of 432 possible architectures. The area A z under the receiver operating characteristic (ROC) curve was used to design a cost function. The SA experiments were conducted with four different annealing schedules. Three different parent selection methods were compared for the GA experiments. An available data set was split into two groups with approximately equal number of samples. By using the two groups alternately for training and testing, two different cost surfaces were evaluated. For the first cost surface, the SD method was trapped in a local minimum 91% (392/432) of the time. The SA using the Boltzman schedule selected the best architecture after evaluating, on average, 167 architectures. The GA achieved its best performance with linearly scaled roulette-wheel parent selection; however, it evaluated 391 different architectures, on average, to find the best one. The second cost surface contained no local minimum. For this surface, a simple SD algorithm could quickly find the global minimum, but the SA with the very fast reannealing schedule was still the most efficient. The same SA scheme, however, was trapped in a local minimum on the first cost
Energy Technology Data Exchange (ETDEWEB)
Ortiz S, J. J.; Castillo, A. [ININ, Carretera Mexico-Toluca s/n, 52750 Ocoyoacac, Estado de Mexico (Mexico); Alejandro P, D., E-mail: juanjose.ortiz@inin.gob.mx [Universidad de Granada, ETS de Ingenierias, Informatica y de Telecomunicacion, C/Daniel Saucedo Aranda s/n, 18071 Granada (Spain)
2011-11-15
The first results of a system for the optimization of operation cycles in boiling water reactors by means of a multi state recurrent neural network are present in this work. The neural network finds the best combination of fuel cells; fuel reloads and control bars patterns previously designed, according to an energy function that qualifies the performance of the three partial solutions for the solution of the whole problem. The partial solutions are designed by means of optimization systems non couple among them and that can use any optimization technique. The phase of the fuel axial design is not made and the size of the axial areas is fixed during the optimization process. The methodology was applied to design a balance cycle of 18 months for the reactors of the nuclear power station of Laguna Verde. The results show that is possible to find combinations of partial solutions that in set represent good solutions to the complete design problem of an operation cycle of a nuclear reactor. The results are compared with others obtained previously by other techniques. This system was developed in platform Li nux and programmed in Fortran 95 taking advantage of the 8 nuclei of a work station Dell Precision T7400. (Author)
Particle swarm optimization of a neural network model in a ...
Indian Academy of Sciences (India)
. Since tool life is critically affected by the tool wear, accurate prediction of this wear ... In their work, they established an improvement in the quality ... objective optimization of hard turning using neural network modelling and swarm intelligence ...
Discrete Neural Signatures of Basic Emotions.
Saarimäki, Heini; Gotsopoulos, Athanasios; Jääskeläinen, Iiro P; Lampinen, Jouko; Vuilleumier, Patrik; Hari, Riitta; Sams, Mikko; Nummenmaa, Lauri
2016-06-01
Categorical models of emotions posit neurally and physiologically distinct human basic emotions. We tested this assumption by using multivariate pattern analysis (MVPA) to classify brain activity patterns of 6 basic emotions (disgust, fear, happiness, sadness, anger, and surprise) in 3 experiments. Emotions were induced with short movies or mental imagery during functional magnetic resonance imaging. MVPA accurately classified emotions induced by both methods, and the classification generalized from one induction condition to another and across individuals. Brain regions contributing most to the classification accuracy included medial and inferior lateral prefrontal cortices, frontal pole, precentral and postcentral gyri, precuneus, and posterior cingulate cortex. Thus, specific neural signatures across these regions hold representations of different emotional states in multimodal fashion, independently of how the emotions are induced. Similarity of subjective experiences between emotions was associated with similarity of neural patterns for the same emotions, suggesting a direct link between activity in these brain regions and the subjective emotional experience. © The Author 2015. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.
Complex dynamics of a delayed discrete neural network of two nonidentical neurons
Energy Technology Data Exchange (ETDEWEB)
Chen, Yuanlong [Mathematics Department, GuangDong University of Finance, Guangzhou 510521 (China); Huang, Tingwen [Mathematics Department, Texas A and M University at Qatar, P. O. Box 23874, Doha (Qatar); Huang, Yu, E-mail: stshyu@mail.sysu.edu.cn [Mathematics Department, Sun Yat-Sen University, Guangzhou 510275, People' s Republic China (China)
2014-03-15
In this paper, we discover that a delayed discrete Hopfield neural network of two nonidentical neurons with self-connections and no self-connections can demonstrate chaotic behaviors. To this end, we first transform the model, by a novel way, into an equivalent system which has some interesting properties. Then, we identify the chaotic invariant set for this system and show that the dynamics of this system within this set is topologically conjugate to the dynamics of the full shift map with two symbols. This confirms chaos in the sense of Devaney. Our main results generalize the relevant results of Huang and Zou [J. Nonlinear Sci. 15, 291–303 (2005)], Kaslik and Balint [J. Nonlinear Sci. 18, 415–432 (2008)] and Chen et al. [Sci. China Math. 56(9), 1869–1878 (2013)]. We also give some numeric simulations to verify our theoretical results.
Complex dynamics of a delayed discrete neural network of two nonidentical neurons
International Nuclear Information System (INIS)
Chen, Yuanlong; Huang, Tingwen; Huang, Yu
2014-01-01
In this paper, we discover that a delayed discrete Hopfield neural network of two nonidentical neurons with self-connections and no self-connections can demonstrate chaotic behaviors. To this end, we first transform the model, by a novel way, into an equivalent system which has some interesting properties. Then, we identify the chaotic invariant set for this system and show that the dynamics of this system within this set is topologically conjugate to the dynamics of the full shift map with two symbols. This confirms chaos in the sense of Devaney. Our main results generalize the relevant results of Huang and Zou [J. Nonlinear Sci. 15, 291–303 (2005)], Kaslik and Balint [J. Nonlinear Sci. 18, 415–432 (2008)] and Chen et al. [Sci. China Math. 56(9), 1869–1878 (2013)]. We also give some numeric simulations to verify our theoretical results
A New Approach for Optimal Sizing of Standalone Photovoltaic Systems
Khatib, Tamer; Mohamed, Azah; Sopian, K.; Mahmoud, M.
2012-01-01
This paper presents a new method for determining the optimal sizing of standalone photovoltaic (PV) system in terms of optimal sizing of PV array and battery storage. A standalone PV system energy flow is first analysed, and the MATLAB fitting tool is used to fit the resultant sizing curves in order to derive general formulas for optimal sizing of PV array and battery. In deriving the formulas for optimal sizing of PV array and battery, the data considered are based on five sites in Malaysia...
A New Approach for Optimal Sizing of Standalone Photovoltaic Systems
Directory of Open Access Journals (Sweden)
Tamer Khatib
2012-01-01
Full Text Available This paper presents a new method for determining the optimal sizing of standalone photovoltaic (PV system in terms of optimal sizing of PV array and battery storage. A standalone PV system energy flow is first analysed, and the MATLAB fitting tool is used to fit the resultant sizing curves in order to derive general formulas for optimal sizing of PV array and battery. In deriving the formulas for optimal sizing of PV array and battery, the data considered are based on five sites in Malaysia, which are Kuala Lumpur, Johor Bharu, Ipoh, Kuching, and Alor Setar. Based on the results of the designed example for a PV system installed in Kuala Lumpur, the proposed method gives satisfactory optimal sizing results.
Directory of Open Access Journals (Sweden)
O. M. Kwon
2012-01-01
Full Text Available The purpose of this paper is to investigate the delay-dependent stability analysis for discrete-time neural networks with interval time-varying delays. Based on Lyapunov method, improved delay-dependent criteria for the stability of the networks are derived in terms of linear matrix inequalities (LMIs by constructing a suitable Lyapunov-Krasovskii functional and utilizing reciprocally convex approach. Also, a new activation condition which has not been considered in the literature is proposed and utilized for derivation of stability criteria. Two numerical examples are given to illustrate the effectiveness of the proposed method.
International Nuclear Information System (INIS)
Abdulaal, Ahmed; Moghaddass, Ramin; Asfour, Shihab
2017-01-01
Highlights: •Two-stage model links discrete-optimization to real-time system dynamics operation. •The solutions obtained are non-dominated Pareto optimal solutions. •Computationally efficient GA solver through customized chromosome coding. •Modest to considerable savings are achieved depending on the consumer’s preference. -- Abstract: In the wake of today’s highly dynamic and competitive energy markets, optimal dispatching of energy sources requires effective demand responsiveness. Suppliers have adopted a dynamic pricing strategy in efforts to control the downstream demand. This method however requires consumer awareness, flexibility, and timely responsiveness. While residential activities are more flexible and schedulable, larger commercial consumers remain an obstacle due to the impacts on industrial performance. This paper combines methods from quadratic, stochastic, and evolutionary programming with multi-objective optimization and continuous simulation, to propose a two-stage discrete-continuous multi-objective load optimization (DiCoMoLoOp) autonomous approach for industrial consumer demand response (DR). Stage 1 defines discrete-event load shifting targets. Accordingly, controllable loads are continuously optimized in stage 2 while considering the consumer’s utility. Utility functions, which measure the loads’ time value to the consumer, are derived and weights are assigned through an analytical hierarchy process (AHP). The method is demonstrated for an industrial building model using real data. The proposed method integrates with building energy management system and solves in real-time with autonomous and instantaneous load shifting in the hour-ahead energy price (HAP) market. The simulation shows the occasional existence of multiple load management options on the Pareto frontier. Finally, the computed savings, based on the simulation analysis with real consumption, climate, and price data, ranged from modest to considerable amounts
Estimation of mean grain size of seafloor sediments using neural network
Digital Repository Service at National Institute of Oceanography (India)
De, C.; Chakraborty, B.
The feasibility of an artificial neural network based approach is investigated to estimate the values of mean grain size of seafloor sediments using four dominant echo features, extracted from acoustic backscatter data. The acoustic backscatter data...
Evaluation of a proposed optimization method for discrete-event simulation models
Directory of Open Access Journals (Sweden)
Alexandre Ferreira de Pinho
2012-12-01
Full Text Available Optimization methods combined with computer-based simulation have been utilized in a wide range of manufacturing applications. However, in terms of current technology, these methods exhibit low performance levels which are only able to manipulate a single decision variable at a time. Thus, the objective of this article is to evaluate a proposed optimization method for discrete-event simulation models based on genetic algorithms which exhibits more efficiency in relation to computational time when compared to software packages on the market. It should be emphasized that the variable's response quality will not be altered; that is, the proposed method will maintain the solutions' effectiveness. Thus, the study draws a comparison between the proposed method and that of a simulation instrument already available on the market and has been examined in academic literature. Conclusions are presented, confirming the proposed optimization method's efficiency.
Energy Technology Data Exchange (ETDEWEB)
Pereira, Claudio M.N.A. [Instituto de Engenharia Nuclear (IEN), Rio de Janeiro, RJ (Brazil); Schirru, Roberto; Martinez, Aquilino S. [Universidade Federal, Rio de Janeiro, RJ (Brazil). Coordenacao dos Programas de Pos-graduacao de Engenharia
1997-12-01
This work presents a prototype of a system for nuclear reactor core design optimization based on genetic algorithms and artificial neural networks. A neural network is modeled and trained in order to predict the flux and the neutron multiplication factor values based in the enrichment, network pitch and cladding thickness, with average error less than 2%. The values predicted by the neural network are used by a genetic algorithm in this heuristic search, guided by an objective function that rewards the high flux values and penalizes multiplication factors far from the required value. Associating the quick prediction - that may substitute the reactor physics calculation code - with the global optimization capacity of the genetic algorithm, it was obtained a quick and effective system for nuclear reactor core design optimization. (author). 11 refs., 8 figs., 3 tabs.
Fault Diagnosis of Hydraulic Servo Valve Based on Genetic Optimization RBF-BP Neural Network
Directory of Open Access Journals (Sweden)
Li-Ping FAN
2014-04-01
Full Text Available Electro-hydraulic servo valves are core components of the hydraulic servo system of rolling mills. It is necessary to adopt an effective fault diagnosis method to keep the hydraulic servo valve in a good work state. In this paper, RBF and BP neural network are integrated effectively to build a double hidden layers RBF-BP neural network for fault diagnosis. In the process of training the neural network, genetic algorithm (GA is used to initialize and optimize the connection weights and thresholds of the network. Several typical fault states are detected by the constructed GA-optimized fault diagnosis scheme. Simulation results shown that the proposed fault diagnosis scheme can give satisfactory effect.
Fixed-time synchronization of memristor-based BAM neural networks with time-varying discrete delay.
Chen, Chuan; Li, Lixiang; Peng, Haipeng; Yang, Yixian
2017-12-01
This paper is devoted to studying the fixed-time synchronization of memristor-based BAM neural networks (MBAMNNs) with discrete delay. Fixed-time synchronization means that synchronization can be achieved in a fixed time for any initial values of the considered systems. In the light of the double-layer structure of MBAMNNs, we design two similar feedback controllers. Based on Lyapunov stability theories, several criteria are established to guarantee that the drive and response MBAMNNs can realize synchronization in a fixed time. In particular, by changing the parameters of controllers, this fixed time can be adjusted to some desired value in advance, irrespective of the initial values of MBAMNNs. Numerical simulations are included to validate the derived results. Copyright © 2017 Elsevier Ltd. All rights reserved.
Xi, Jun; Xue, Yujing; Xu, Yinxiang; Shen, Yuhong
2013-11-01
In this study, the ultrahigh pressure extraction of green tea polyphenols was modeled and optimized by a three-layer artificial neural network. A feed-forward neural network trained with an error back-propagation algorithm was used to evaluate the effects of pressure, liquid/solid ratio and ethanol concentration on the total phenolic content of green tea extracts. The neural network coupled with genetic algorithms was also used to optimize the conditions needed to obtain the highest yield of tea polyphenols. The obtained optimal architecture of artificial neural network model involved a feed-forward neural network with three input neurons, one hidden layer with eight neurons and one output layer including single neuron. The trained network gave the minimum value in the MSE of 0.03 and the maximum value in the R(2) of 0.9571, which implied a good agreement between the predicted value and the actual value, and confirmed a good generalization of the network. Based on the combination of neural network and genetic algorithms, the optimum extraction conditions for the highest yield of green tea polyphenols were determined as follows: 498.8 MPa for pressure, 20.8 mL/g for liquid/solid ratio and 53.6% for ethanol concentration. The total phenolic content of the actual measurement under the optimum predicated extraction conditions was 582.4 ± 0.63 mg/g DW, which was well matched with the predicted value (597.2mg/g DW). This suggests that the artificial neural network model described in this work is an efficient quantitative tool to predict the extraction efficiency of green tea polyphenols. Crown Copyright © 2013. Published by Elsevier Ltd. All rights reserved.
The choice of optimal Discrete Interaction Approximation to the kinetic integral for ocean waves
Directory of Open Access Journals (Sweden)
V. G. Polnikov
2003-01-01
Full Text Available A lot of discrete configurations for the four-wave nonlinear interaction processes have been calculated and tested by the method proposed earlier in the frame of the concept of Fast Discrete Interaction Approximation to the Hasselmann's kinetic integral (Polnikov and Farina, 2002. It was found that there are several simple configurations, which are more efficient than the one proposed originally in Hasselmann et al. (1985. Finally, the optimal multiple Discrete Interaction Approximation (DIA to the kinetic integral for deep-water waves was found. Wave spectrum features have been intercompared for a number of different configurations of DIA, applied to a long-time solution of kinetic equation. On the basis of this intercomparison the better efficiency of the configurations proposed was confirmed. Certain recommendations were given for implementation of new approximations to the wave forecast practice.
Experiments in Neural-Network Control of a Free-Flying Space Robot
Wilson, Edward
1995-01-01
Four important generic issues are identified and addressed in some depth in this thesis as part of the development of an adaptive neural network based control system for an experimental free flying space robot prototype. The first issue concerns the importance of true system level design of the control system. A new hybrid strategy is developed here, in depth, for the beneficial integration of neural networks into the total control system. A second important issue in neural network control concerns incorporating a priori knowledge into the neural network. In many applications, it is possible to get a reasonably accurate controller using conventional means. If this prior information is used purposefully to provide a starting point for the optimizing capabilities of the neural network, it can provide much faster initial learning. In a step towards addressing this issue, a new generic Fully Connected Architecture (FCA) is developed for use with backpropagation. A third issue is that neural networks are commonly trained using a gradient based optimization method such as backpropagation; but many real world systems have Discrete Valued Functions (DVFs) that do not permit gradient based optimization. One example is the on-off thrusters that are common on spacecraft. A new technique is developed here that now extends backpropagation learning for use with DVFs. The fourth issue is that the speed of adaptation is often a limiting factor in the implementation of a neural network control system. This issue has been strongly resolved in the research by drawing on the above new contributions.
DEFF Research Database (Denmark)
Sørensen, John Aasted
2010-01-01
The introduction of the mathematics needed for analysis, design and verification of discrete systems, including applications within programming languages for computer systems. Course sessions and project work. Semester: Spring 2010 Ectent: 5 ects Class size: 18......The introduction of the mathematics needed for analysis, design and verification of discrete systems, including applications within programming languages for computer systems. Course sessions and project work. Semester: Spring 2010 Ectent: 5 ects Class size: 18...
DEFF Research Database (Denmark)
Sørensen, John Aasted
2010-01-01
The introduction of the mathematics needed for analysis, design and verification of discrete systems, including applications within programming languages for computer systems. Course sessions and project work. Semester: Autumn 2010 Ectent: 5 ects Class size: 15......The introduction of the mathematics needed for analysis, design and verification of discrete systems, including applications within programming languages for computer systems. Course sessions and project work. Semester: Autumn 2010 Ectent: 5 ects Class size: 15...
Hybrid chaotic ant swarm optimization
International Nuclear Information System (INIS)
Li Yuying; Wen Qiaoyan; Li Lixiang; Peng Haipeng
2009-01-01
Chaotic ant swarm optimization (CASO) is a powerful chaos search algorithm that is used to find the global optimum solution in search space. However, the CASO algorithm has some disadvantages, such as lower solution precision and longer computational time, when solving complex optimization problems. To resolve these problems, an improved CASO, called hybrid chaotic swarm optimization (HCASO), is proposed in this paper. The new algorithm introduces preselection operator and discrete recombination operator into the CASO; meanwhile it replaces the best position found by own and its neighbors' ants with the best position found by preselection operator and discrete recombination operator in evolution equation. Through testing five benchmark functions with large dimensionality, the experimental results show the new method enhances the solution accuracy and stability greatly, as well as reduces the computational time and computer memory significantly when compared to the CASO. In addition, we observe the results can become better with swarm size increasing from the sensitivity study to swarm size. And we gain some relations between problem dimensions and swam size according to scalability study.
Numerical sedimentation particle-size analysis using the Discrete Element Method
Bravo, R.; Pérez-Aparicio, J. L.; Gómez-Hernández, J. J.
2015-12-01
Sedimentation tests are widely used to determine the particle size distribution of a granular sample. In this work, the Discrete Element Method interacts with the simulation of flow using the well known one-way-coupling method, a computationally affordable approach for the time-consuming numerical simulation of the hydrometer, buoyancy and pipette sedimentation tests. These tests are used in the laboratory to determine the particle-size distribution of fine-grained aggregates. Five samples with different particle-size distributions are modeled by about six million rigid spheres projected on two-dimensions, with diameters ranging from 2.5 ×10-6 m to 70 ×10-6 m, forming a water suspension in a sedimentation cylinder. DEM simulates the particle's movement considering laminar flow interactions of buoyant, drag and lubrication forces. The simulation provides the temporal/spatial distributions of densities and concentrations of the suspension. The numerical simulations cannot replace the laboratory tests since they need the final granulometry as initial data, but, as the results show, these simulations can identify the strong and weak points of each method and eventually recommend useful variations and draw conclusions on their validity, aspects very difficult to achieve in the laboratory.
Discrete-time recurrent neural networks with time-varying delays: Exponential stability analysis
International Nuclear Information System (INIS)
Liu, Yurong; Wang, Zidong; Serrano, Alan; Liu, Xiaohui
2007-01-01
This Letter is concerned with the analysis problem of exponential stability for a class of discrete-time recurrent neural networks (DRNNs) with time delays. The delay is of the time-varying nature, and the activation functions are assumed to be neither differentiable nor strict monotonic. Furthermore, the description of the activation functions is more general than the recently commonly used Lipschitz conditions. Under such mild conditions, we first prove the existence of the equilibrium point. Then, by employing a Lyapunov-Krasovskii functional, a unified linear matrix inequality (LMI) approach is developed to establish sufficient conditions for the DRNNs to be globally exponentially stable. It is shown that the delayed DRNNs are globally exponentially stable if a certain LMI is solvable, where the feasibility of such an LMI can be easily checked by using the numerically efficient Matlab LMI Toolbox. A simulation example is presented to show the usefulness of the derived LMI-based stability condition
Theoretical properties of the global optimizer of two layer neural network
Boob, Digvijay; Lan, Guanghui
2017-01-01
In this paper, we study the problem of optimizing a two-layer artificial neural network that best fits a training dataset. We look at this problem in the setting where the number of parameters is greater than the number of sampled points. We show that for a wide class of differentiable activation functions (this class involves "almost" all functions which are not piecewise linear), we have that first-order optimal solutions satisfy global optimality provided the hidden layer is non-singular. ...
Optimal sizing method for stand-alone photovoltaic power systems
Energy Technology Data Exchange (ETDEWEB)
Groumpos, P P; Papageorgiou, G
1987-01-01
The total life-cycle cost of stand-alone photovoltaic (SAPV) power systems is mathematically formulated. A new optimal sizing algorithm for the solar array and battery capacity is developed. The optimum value of a balancing parameter, M, for the optimal sizing of SAPV system components is derived. The proposed optimal sizing algorithm is used in an illustrative example, where a more economical life-cycle cost has bene obtained. The question of cost versus reliability is briefly discussed.
Tekoglu, Cihan; Onck, Patrick R.
2008-01-01
In view of size effects in cellular solids, we critically compare the analytical results of generalized continuum theories with the computation a I results of discrete models. Representatives are studied from two classes of generalized continuum theories: the strain divergence theory from the class
Directory of Open Access Journals (Sweden)
Miriam eZacksenhouse
2015-05-01
Full Text Available Recent experiments with brain-machine-interfaces (BMIs indicate that the extent of neural modulations increased abruptly upon starting to operate the interface, and especially after the monkey stopped moving its hand. In contrast, neural modulations that are correlated with the kinematics of the movement remained relatively unchanged. Here we demonstrate that similar changes are produced by simulated neurons that encode the relevant signals generated by an optimal feedback controller during simulated BMI experiments. The optimal feedback controller relies on state estimation that integrates both visual and proprioceptive feedback with prior estimations from an internal model. The processing required for optimal state estimation and control were conducted in the state-space, and neural recording was simulated by modeling two populations of neurons that encode either only the estimated state or also the control signal. Spike counts were generated as realizations of doubly stochastic Poisson processes with linear tuning curves. The model successfully reconstructs the main features of the kinematics and neural activity during regular reaching movements. Most importantly, the activity of the simulated neurons successfully reproduces the observed changes in neural modulations upon switching to brain control. Further theoretical analysis and simulations indicate that increasing the process noise during normal reaching movement results in similar changes in neural modulations. Thus we conclude that the observed changes in neural modulations during BMI experiments can be attributed to increasing process noise associated with the imperfect BMI ﬁlter, and, more directly, to the resulting increase in the variance of the encoded signals associated with state estimation and the required control signal.
Benyamini, Miri; Zacksenhouse, Miriam
2015-01-01
Recent experiments with brain-machine-interfaces (BMIs) indicate that the extent of neural modulations increased abruptly upon starting to operate the interface, and especially after the monkey stopped moving its hand. In contrast, neural modulations that are correlated with the kinematics of the movement remained relatively unchanged. Here we demonstrate that similar changes are produced by simulated neurons that encode the relevant signals generated by an optimal feedback controller during simulated BMI experiments. The optimal feedback controller relies on state estimation that integrates both visual and proprioceptive feedback with prior estimations from an internal model. The processing required for optimal state estimation and control were conducted in the state-space, and neural recording was simulated by modeling two populations of neurons that encode either only the estimated state or also the control signal. Spike counts were generated as realizations of doubly stochastic Poisson processes with linear tuning curves. The model successfully reconstructs the main features of the kinematics and neural activity during regular reaching movements. Most importantly, the activity of the simulated neurons successfully reproduces the observed changes in neural modulations upon switching to brain control. Further theoretical analysis and simulations indicate that increasing the process noise during normal reaching movement results in similar changes in neural modulations. Thus, we conclude that the observed changes in neural modulations during BMI experiments can be attributed to increasing process noise associated with the imperfect BMI filter, and, more directly, to the resulting increase in the variance of the encoded signals associated with state estimation and the required control signal.
Patnaik, Surya N.; Guptill, James D.; Hopkins, Dale A.; Lavelle, Thomas M.
2000-01-01
The NASA Engine Performance Program (NEPP) can configure and analyze almost any type of gas turbine engine that can be generated through the interconnection of a set of standard physical components. In addition, the code can optimize engine performance by changing adjustable variables under a set of constraints. However, for engine cycle problems at certain operating points, the NEPP code can encounter difficulties: nonconvergence in the currently implemented Powell's optimization algorithm and deficiencies in the Newton-Raphson solver during engine balancing. A project was undertaken to correct these deficiencies. Nonconvergence was avoided through a cascade optimization strategy, and deficiencies associated with engine balancing were eliminated through neural network and linear regression methods. An approximation-interspersed cascade strategy was used to optimize the engine's operation over its flight envelope. Replacement of Powell's algorithm by the cascade strategy improved the optimization segment of the NEPP code. The performance of the linear regression and neural network methods as alternative engine analyzers was found to be satisfactory. This report considers two examples-a supersonic mixed-flow turbofan engine and a subsonic waverotor-topped engine-to illustrate the results, and it discusses insights gained from the improved version of the NEPP code.
Energy Technology Data Exchange (ETDEWEB)
Djukanovic, M.; Novicevic, M.; Dobrijevic, D.; Babic, B. [Electrical Engineering Inst. Nikola Tesla, Belgrade (Yugoslavia); Sobajic, D.J. [Electric Power Research Inst., Palo Alto, CA (United States); Pao, Y.H. [Case Western Reserve Univ., Cleveland, OH (United States)]|[AI WARE, Inc., Cleveland, OH (United States)
1995-12-01
This paper presents a design technique of a new adaptive optimal controller of the low head hydropower plant using artificial neural networks (ANN). The adaptive controller is to operate in real time to improve the generating unit transients through the exciter input, the guide vane position and the runner blade position. The new design procedure is based on self-organization and the predictive estimation capabilities of neural-nets implemented through the cluster-wise segmented associative memory scheme. The developed neural-net based controller (NNC) whose control signals are adjusted using the on-line measurements, can offer better damping effects for generator oscillations over a wide range of operating conditions than conventional controllers. Digital simulations of hydropower plant equipped with low head Kaplan turbine are performed and the comparisons of conventional excitation-governor control, state-space optimal control and neural-net based control are presented. Results obtained on the non-linear mathematical model demonstrate that the effects of the NNC closely agree with those obtained using the state-space multivariable discrete-time optimal controllers.
International Nuclear Information System (INIS)
Poursalehi, N.; Zolfaghari, A.; Minuchehr, A.
2015-01-01
Highlights: • An advanced version of firefly algorithm, EDFA, is proposed for the core pattern optimization problem. • The movement of each firefly toward the best firefly with a dynamic probability is the major improvement of EDFA. • LPO results represent the faster convergence and better performance of EDFA in comparison to CFA and DFA. - Abstract: Inspired by fireflies behavior in nature, a firefly algorithm has been developed for solving optimization problems. In this approach, each firefly movement is based on absorption of the other one. For enhancing the performance of firefly algorithm in the optimization process of nuclear reactor loading pattern optimization (LPO), we introduce a new variant of firefly algorithm, i.e. Effective Discrete Firefly Algorithm (EDFA). In EDFA, a new behavior is the movement of fireflies to current global best position with a dynamic probability, i.e. the movement of each firefly can be determined to be toward the brighter or brightest firefly’s position in any iteration of the algorithm. In this paper, our optimization objectives for the LPO are the maximization of K eff along with the minimization of the power peaking factor (PPF). In order to represent the increase of convergence speed of EDFA, basic firefly algorithms including the continuous firefly algorithm (CFA) and the discrete firefly algorithm (DFA) also have been implemented. Loading pattern optimization results of two well-known problems confirm better performance of EDFA in obtaining nearly optimized fuel arrangements in comparison to CFA and DFA. All in all, we can suggest applying the EDFA to other optimization problems of nuclear engineering field in order to investigate its performance in gaining considered objectives
International Nuclear Information System (INIS)
Balasubramaniam, P.; Lakshmanan, S.; Manivannan, A.
2012-01-01
Highlights: ► Robust stability analysis for Markovian jumping interval neural networks is considered. ► Both linear fractional and interval uncertainties are considered. ► A new LKF is constructed with triple integral terms. ► MATLAB LMI control toolbox is used to validate theoretical results. ► Numerical examples are given to illustrate the effectiveness of the proposed method. - Abstract: This paper investigates robust stability analysis for Markovian jumping interval neural networks with discrete and distributed time-varying delays. The parameter uncertainties are assumed to be bounded in given compact sets. The delay is assumed to be time-varying and belong to a given interval, which means that the lower and upper bounds of interval time-varying delays are available. Based on the new Lyapunov–Krasovskii functional (LKF), some inequality techniques and stochastic stability theory, new delay-dependent stability criteria have been obtained in terms of linear matrix inequalities (LMIs). Finally, two numerical examples are given to illustrate the less conservative and effectiveness of our theoretical results.
EEG signal classification using PSO trained RBF neural network for epilepsy identification
Directory of Open Access Journals (Sweden)
Sandeep Kumar Satapathy
Full Text Available The electroencephalogram (EEG is a low amplitude signal generated in the brain, as a result of information flow during the communication of several neurons. Hence, careful analysis of these signals could be useful in understanding many human brain disorder diseases. One such disease topic is epileptic seizure identification, which can be identified via a classification process of the EEG signal after preprocessing with the discrete wavelet transform (DWT. To classify the EEG signal, we used a radial basis function neural network (RBFNN. As shown herein, the network can be trained to optimize the mean square error (MSE by using a modified particle swarm optimization (PSO algorithm. The key idea behind the modification of PSO is to introduce a method to overcome the problem of slow searching in and around the global optimum solution. The effectiveness of this procedure was verified by an experimental analysis on a benchmark dataset which is publicly available. The result of our experimental analysis revealed that the improvement in the algorithm is significant with respect to RBF trained by gradient descent and canonical PSO. Here, two classes of EEG signals were considered: the first being an epileptic and the other being non-epileptic. The proposed method produced a maximum accuracy of 99% as compared to the other techniques. Keywords: Electroencephalography, Radial basis function neural network, Particle swarm optimization, Discrete wavelet transform, Machine learning
Optimization of composite panels using neural networks and genetic algorithms
Ruijter, W.; Spallino, R.; Warnet, Laurent; de Boer, Andries
2003-01-01
The objective of this paper is to present first results of a running study on optimization of aircraft components (composite panels of a typical vertical tail plane) by using Genetic Algorithms (GA) and Neural Networks (NN). The panels considered are standardized to some extent but still there is a
FE, JORGE DEOLINDO; Aliaga Varea, Ramón José; Gadea Gironés, Rafael
2015-01-01
In the optimization of artificial neural networks (ANNs) via evolutionary algorithms and the implementation of the necessary training for the objective function, there is often a trade-off between efficiency and flexibility. Pure software solutions on general-purpose processors tend to be slow because they do not take advantage of the inherent parallelism, whereas hardware realizations usually rely on optimizations that reduce the range of applicable network topologies, or they...
Using a multi-state recurrent neural network to optimize loading patterns in BWRs
International Nuclear Information System (INIS)
Ortiz, Juan Jose; Requena, Ignacio
2004-01-01
A Multi-State Recurrent Neural Network is used to optimize Loading Patterns (LP) in BWRs. We have proposed an energy function that depends on fuel assembly positions and their nuclear cross sections to carry out optimisation. Multi-State Recurrent Neural Networks creates LPs that satisfy the Radial Power Peaking Factor and maximize the effective multiplication factor at the Beginning of the Cycle, and also satisfy the Minimum Critical Power Ratio and Maximum Linear Heat Generation Rate at the End of the Cycle, thereby maximizing the effective multiplication factor. In order to evaluate the LPs, we have used a trained back-propagation neural network to predict the parameter values, instead of using a reactor core simulator, which saved considerable computation time in the search process. We applied this method to find optimal LPs for five cycles of Laguna Verde Nuclear Power Plant (LVNPP) in Mexico
Rajkumar, T.; Bardina, Jorge; Clancy, Daniel (Technical Monitor)
2002-01-01
Wind tunnels use scale models to characterize aerodynamic coefficients, Wind tunnel testing can be slow and costly due to high personnel overhead and intensive power utilization. Although manual curve fitting can be done, it is highly efficient to use a neural network to define the complex relationship between variables. Numerical simulation of complex vehicles on the wide range of conditions required for flight simulation requires static and dynamic data. Static data at low Mach numbers and angles of attack may be obtained with simpler Euler codes. Static data of stalled vehicles where zones of flow separation are usually present at higher angles of attack require Navier-Stokes simulations which are costly due to the large processing time required to attain convergence. Preliminary dynamic data may be obtained with simpler methods based on correlations and vortex methods; however, accurate prediction of the dynamic coefficients requires complex and costly numerical simulations. A reliable and fast method of predicting complex aerodynamic coefficients for flight simulation I'S presented using a neural network. The training data for the neural network are derived from numerical simulations and wind-tunnel experiments. The aerodynamic coefficients are modeled as functions of the flow characteristics and the control surfaces of the vehicle. The basic coefficients of lift, drag and pitching moment are expressed as functions of angles of attack and Mach number. The modeled and training aerodynamic coefficients show good agreement. This method shows excellent potential for rapid development of aerodynamic models for flight simulation. Genetic Algorithms (GA) are used to optimize a previously built Artificial Neural Network (ANN) that reliably predicts aerodynamic coefficients. Results indicate that the GA provided an efficient method of optimizing the ANN model to predict aerodynamic coefficients. The reliability of the ANN using the GA includes prediction of aerodynamic
International Nuclear Information System (INIS)
Vanderbei, Robert J.; Pınar, Mustafa Ç.; Bozkaya, Efe B.
2013-01-01
An American option (or, warrant) is the right, but not the obligation, to purchase or sell an underlying equity at any time up to a predetermined expiration date for a predetermined amount. A perpetual American option differs from a plain American option in that it does not expire. In this study, we solve the optimal stopping problem of a perpetual American option (both call and put) in discrete time using linear programming duality. Under the assumption that the underlying stock price follows a discrete time and discrete state Markov process, namely a geometric random walk, we formulate the pricing problem as an infinite dimensional linear programming (LP) problem using the excessive-majorant property of the value function. This formulation allows us to solve complementary slackness conditions in closed-form, revealing an optimal stopping strategy which highlights the set of stock-prices where the option should be exercised. The analysis for the call option reveals that such a critical value exists only in some cases, depending on a combination of state-transition probabilities and the economic discount factor (i.e., the prevailing interest rate) whereas it ceases to be an issue for the put.
Energy Technology Data Exchange (ETDEWEB)
Vanderbei, Robert J., E-mail: rvdb@princeton.edu [Princeton University, Department of Operations Research and Financial Engineering (United States); P Latin-Small-Letter-Dotless-I nar, Mustafa C., E-mail: mustafap@bilkent.edu.tr [Bilkent University, Department of Industrial Engineering (Turkey); Bozkaya, Efe B. [Sabanc Latin-Small-Letter-Dotless-I University, Faculty of Administrative Sciences (Turkey)
2013-02-15
An American option (or, warrant) is the right, but not the obligation, to purchase or sell an underlying equity at any time up to a predetermined expiration date for a predetermined amount. A perpetual American option differs from a plain American option in that it does not expire. In this study, we solve the optimal stopping problem of a perpetual American option (both call and put) in discrete time using linear programming duality. Under the assumption that the underlying stock price follows a discrete time and discrete state Markov process, namely a geometric random walk, we formulate the pricing problem as an infinite dimensional linear programming (LP) problem using the excessive-majorant property of the value function. This formulation allows us to solve complementary slackness conditions in closed-form, revealing an optimal stopping strategy which highlights the set of stock-prices where the option should be exercised. The analysis for the call option reveals that such a critical value exists only in some cases, depending on a combination of state-transition probabilities and the economic discount factor (i.e., the prevailing interest rate) whereas it ceases to be an issue for the put.
Andrei, Alexandru; Welkenhuysen, Marleen; Ameye, Lieveke; Nuttin, Bart; Eberle, Wolfgang
2011-01-01
Understanding the mechanical interactions between implants and the surrounding tissue is known to have an important role for improving the bio-compatibility of such devices. Using a recently developed model, a particular micro-machined neural implant design aiming the reduction of insertion forces dependence on the insertion speed was optimized. Implantations with 10 and 100 μm/s insertion speeds showed excellent agreement with the predicted behavior. Lesion size, gliosis (GFAP), inflammation (ED1) and neuronal cells density (NeuN) was evaluated after 6 week of chronic implantation showing no insertion speed dependence.
Discrete and mesoscopic regimes of finite-size wave turbulence
International Nuclear Information System (INIS)
L'vov, V. S.; Nazarenko, S.
2010-01-01
Bounding volume results in discreteness of eigenmodes in wave systems. This leads to a depletion or complete loss of wave resonances (three-wave, four-wave, etc.), which has a strong effect on wave turbulence (WT) i.e., on the statistical behavior of broadband sets of weakly nonlinear waves. This paper describes three different regimes of WT realizable for different levels of the wave excitations: discrete, mesoscopic and kinetic WT. Discrete WT comprises chaotic dynamics of interacting wave 'clusters' consisting of discrete (often finite) number of connected resonant wave triads (or quarters). Kinetic WT refers to the infinite-box theory, described by well-known wave-kinetic equations. Mesoscopic WT is a regime in which either the discrete and the kinetic evolutions alternate or when none of these two types is purely realized. We argue that in mesoscopic systems the wave spectrum experiences a sandpile behavior. Importantly, the mesoscopic regime is realized for a broad range of wave amplitudes which typically spans over several orders on magnitude, and not just for a particular intermediate level.
Determination of crack size around rivet hole through neural network using ultrasonic Lamb wave
International Nuclear Information System (INIS)
Choi, Sang Woo; Lee, Joon Hyun
1998-01-01
Rivets are typical structural features that are potential initiation sites for fatigue crack due to combination of local stress concentration around rivet hole and moisture trapping. For the viewpoint of structural assurance, it is crucial to evaluate the size of crack around rivets by appropriate nondestructive techniques. Guided waves, which direct wave energy along the plate, carry information about the material in their path and offer a potentially more efficient tool for nondestructive inspection of structural material. Neural network that is considered to be the most suitable for pattern recognition and has been used by researchers in NDE field to classify different types of flaws and flaw size. In this study, crack size determination around rivet through a neural network based on the back-propagation algorithm has been done by extracting some feature from time-domain waveforms of ultrasonic Lamb wave for Al 2024-T3 skin panel of aircraft. Special attention was paid to reduce the coupling effect between transducer and specimen by extracting some features related to only time component data in ultrasonic waveform. It was demonstrated clearly that features extraction based on time component data of the time-domain waveform of Lamb wave was very useful to determine crack size initiated from rivet hole through neural network.
The neural optimal control hierarchy for motor control
DeWolf, T.; Eliasmith, C.
2011-10-01
Our empirical, neuroscientific understanding of biological motor systems has been rapidly growing in recent years. However, this understanding has not been systematically mapped to a quantitative characterization of motor control based in control theory. Here, we attempt to bridge this gap by describing the neural optimal control hierarchy (NOCH), which can serve as a foundation for biologically plausible models of neural motor control. The NOCH has been constructed by taking recent control theoretic models of motor control, analyzing the required processes, generating neurally plausible equivalent calculations and mapping them on to the neural structures that have been empirically identified to form the anatomical basis of motor control. We demonstrate the utility of the NOCH by constructing a simple model based on the identified principles and testing it in two ways. First, we perturb specific anatomical elements of the model and compare the resulting motor behavior with clinical data in which the corresponding area of the brain has been damaged. We show that damaging the assigned functions of the basal ganglia and cerebellum can cause the movement deficiencies seen in patients with Huntington's disease and cerebellar lesions. Second, we demonstrate that single spiking neuron data from our model's motor cortical areas explain major features of single-cell responses recorded from the same primate areas. We suggest that together these results show how NOCH-based models can be used to unify a broad range of data relevant to biological motor control in a quantitative, control theoretic framework.
Potential usefulness of an artificial neural network for assessing ventricular size
International Nuclear Information System (INIS)
Fukuda, Haruyuki; Nakajima, Hideyuki; Usuki, Noriaki; Saiwai, Shigeo; Miyamoto, Takeshi; Inoue, Yuichi; Onoyama, Yasuto.
1995-01-01
An artificial neural network approach was applied to assess ventricular size from computed tomograms. Three layer, feed-forward neural networks with a back propagation algorithm were designed to distinguish between three degree of enlargement of the ventricles on the basis of patient's age and six items of computed tomographic information. Data for training and testing the neural network were created with computed tomograms of the brains selected at random from daily examinations. Four radiologists decided by mutual consent subjectively based on their experience whether the ventricles were within normal limits, slightly enlarged, or enlarged for the patient's age. The data for training was obtained from 38 patients. The data for testing was obtained from 47 other patients. The performance of the neural network trained using the data for training was evaluated by the rate of correct answers to the data for testing. The valid solution ratio to response of the test data obtained from the trained neural networks was more than 90% for all conditions in this study. The solutions were completely valid in the neural networks with two or three units at the hidden layer with 2,200 learning iterations, and with two units at the hidden layer with 11,000 learning iterations. The squared error decreased remarkably in the range from 0 to 500 learning iterations, and was close to a contrast over two thousand learning iterations. The neural network with a hidden layer having two or three units showed high decision performance. The preliminary results strongly suggest that the neural network approach has potential utility in computer-aided estimation of enlargement of the ventricles. (author)
Linear programming based on neural networks for radiotherapy treatment planning
International Nuclear Information System (INIS)
Xingen Wu; Limin Luo
2000-01-01
In this paper, we propose a neural network model for linear programming that is designed to optimize radiotherapy treatment planning (RTP). This kind of neural network can be easily implemented by using a kind of 'neural' electronic system in order to obtain an optimization solution in real time. We first give an introduction to the RTP problem and construct a non-constraint objective function for the neural network model. We adopt a gradient algorithm to minimize the objective function and design the structure of the neural network for RTP. Compared to traditional linear programming methods, this neural network model can reduce the time needed for convergence, the size of problems (i.e., the number of variables to be searched) and the number of extra slack and surplus variables needed. We obtained a set of optimized beam weights that result in a better dose distribution as compared to that obtained using the simplex algorithm under the same initial condition. The example presented in this paper shows that this model is feasible in three-dimensional RTP. (author)
Papagiannis, P.; Azariadis, P.; Papanikos, P.
2017-10-01
Footwear is subject to bending and torsion deformations that affect comfort perception. Following review of Finite Element Analysis studies of sole rigidity and comfort, a three-dimensional, linear multi-material finite element sole model for quasi-static bending and torsion simulation, overcoming boundary and optimisation limitations, is described. Common footwear materials properties and boundary conditions from gait biomechanics are used. The use of normalised strain energy for product benchmarking is demonstrated along with comfort level determination through strain energy density stratification. Sensitivity of strain energy against material thickness is greater for bending than for torsion, with results of both deformations showing positive correlation. Optimization for a targeted performance level and given layer thickness is demonstrated with bending simulations sufficing for overall comfort assessment. An algorithm for comfort optimization w.r.t. bending is presented, based on a discrete approach with thickness values set in line with practical manufacturing accuracy. This work illustrates the potential of the developed finite element analysis applications to offer viable and proven aids to modern footwear sole design assessment and optimization.
Yu, Lianchun; Liu, Liwei
2014-03-01
The generation and conduction of action potentials (APs) represents a fundamental means of communication in the nervous system and is a metabolically expensive process. In this paper, we investigate the energy efficiency of neural systems in transferring pulse signals with APs. By analytically solving a bistable neuron model that mimics the AP generation with a particle crossing the barrier of a double well, we find the optimal number of ion channels that maximizes the energy efficiency of a neuron. We also investigate the energy efficiency of a neuron population in which the input pulse signals are represented with synchronized spikes and read out with a downstream coincidence detector neuron. We find an optimal number of neurons in neuron population, as well as the number of ion channels in each neuron that maximizes the energy efficiency. The energy efficiency also depends on the characters of the input signals, e.g., the pulse strength and the interpulse intervals. These results are confirmed by computer simulation of the stochastic Hodgkin-Huxley model with a detailed description of the ion channel random gating. We argue that the tradeoff between signal transmission reliability and energy cost may influence the size of the neural systems when energy use is constrained.
Scale economies and optimal size in the Swiss gas distribution sector
International Nuclear Information System (INIS)
Alaeifar, Mozhgan; Farsi, Mehdi; Filippini, Massimo
2014-01-01
This paper studies the cost structure of Swiss gas distribution utilities. Several econometric models are applied to a panel of 26 companies over 1996–2000. Our main objective is to estimate the optimal size and scale economies of the industry and to study their possible variation with respect to network characteristics. The results indicate the presence of unexploited scale economies. However, very large companies in the sample and companies with a disproportionate mixture of output and density present an exception. Furthermore, the estimated optimal size for majority of companies in the sample has shown a value far greater than the actual size, suggesting remarkable efficiency gains by reorganization of the industry. The results also highlight the effect of customer density on optimal size. Networks with higher density or greater complexity have a lower optimal size. - highlights: • Presence of unexploited scale economies for small and medium sized companies. • Scale economies vary considerably with customer density. • Higher density or greater complexity is associated with lower optimal size. • Optimal size varies across the companies through unobserved heterogeneity. • Firms with low density can gain more from expanding firm size
Neural nets for massively parallel optimization
Dixon, Laurence C. W.; Mills, David
1992-07-01
To apply massively parallel processing systems to the solution of large scale optimization problems it is desirable to be able to evaluate any function f(z), z (epsilon) Rn in a parallel manner. The theorem of Cybenko, Hecht Nielsen, Hornik, Stinchcombe and White, and Funahasi shows that this can be achieved by a neural network with one hidden layer. In this paper we address the problem of the number of nodes required in the layer to achieve a given accuracy in the function and gradient values at all points within a given n dimensional interval. The type of activation function needed to obtain nonsingular Hessian matrices is described and a strategy for obtaining accurate minimal networks presented.
International Nuclear Information System (INIS)
Silva, P.V.M. da; Seixas, J.M. de; Damazio, D.O.; Ferreira, B.C.
2004-01-01
For LHC, the hadronic calorimetry of the ATLAS detector is performed by Tilecal, a scintillating tile calorimeter. For calibration purposes, a fraction of the Tilecal modules is placed in particle beam lines. Despite beam high quality, experimental beam contamination is observed and this masks the actual performance of the calorimeter. For optimizing the calibration task, an online neural particle classifier was developed for Tilecal. Envisaging a neural trigger for incoming particles, a neural process runs integrated to the data acquisition task and performs online training for particle identification. The neural classification performance is evaluated by correlating the neural response to classical methodology, confirming an ability for outsider identification at levels as high as 99.3%
Da Silva, P V M; De Seixas, J M; Ferreira, B C
2004-01-01
For LHC, the hadronic calorimetry of the ATLAS detector is performed by Tilecal, a scintillating tile calorimeter. For calibration purposes, a fraction of the Tilecal modules is placed in particle beam lines. Despite beam high quality, experimental beam contamination is observed and this masks the actual performance of the calorimeter. For optimizing the calibration task, an online neural particle classifier was developed for Tilecal. Envisaging a neural trigger for incoming particles, a neural process runs integrated to the data acquisition task and performs online training for particle identification. The neural classification performance is evaluated by correlating the neural response to classical methodology, confirming an ability for outsider identification at levels as high as 99.3%.
A Simulation Framework for Optimal Energy Storage Sizing
Directory of Open Access Journals (Sweden)
Carlos Suazo-Martínez
2014-05-01
Full Text Available Despite the increasing interest in Energy Storage Systems (ESS, quantification of their technical and economical benefits remains a challenge. To assess the use of ESS, a simulation approach for ESS optimal sizing is presented. The algorithm is based on an adapted Unit Commitment, including ESS operational constraints, and the use of high performance computing (HPC. Multiple short-term simulations are carried out within a multiple year horizon. Evaluation is performed for Chile's Northern Interconnected Power System (SING. The authors show that a single year evaluation could lead to sub-optimal results when evaluating optimal ESS size. Hence, it is advisable to perform long-term evaluations of ESS. Additionally, the importance of detailed simulation for adequate assessment of ESS contributions and to fully capture storage value is also discussed. Furthermore, the robustness of the optimal sizing approach is evaluated by means of a sensitivity analyses. The results suggest that regulatory frameworks should recognize multiple value streams from storage in order to encourage greater ESS integration.
Artificial Neural Networks in Evaluation and Optimization of Modified Release Solid Dosage Forms
Directory of Open Access Journals (Sweden)
Zorica Djurić
2012-10-01
Full Text Available Implementation of the Quality by Design (QbD approach in pharmaceutical development has compelled researchers in the pharmaceutical industry to employ Design of Experiments (DoE as a statistical tool, in product development. Among all DoE techniques, response surface methodology (RSM is the one most frequently used. Progress of computer science has had an impact on pharmaceutical development as well. Simultaneous with the implementation of statistical methods, machine learning tools took an important place in drug formulation. Twenty years ago, the first papers describing application of artificial neural networks in optimization of modified release products appeared. Since then, a lot of work has been done towards implementation of new techniques, especially Artificial Neural Networks (ANN in modeling of production, drug release and drug stability of modified release solid dosage forms. The aim of this paper is to review artificial neural networks in evaluation and optimization of modified release solid dosage forms.
DMTO – a method for Discrete Material and Thickness Optimization of laminated composite structures
DEFF Research Database (Denmark)
Sørensen, Søren Nørgaard; Sørensen, Rene; Lund, Erik
2014-01-01
This paper presents a gradient based topology optimization method for Discrete Material and Thickness Optimization of laminated composite structures, labelled the DMTOmethod. The capabilities of the proposed method are demonstrated on mass minimization, subject to constraints on the structural...... criteria; buckling load factors, eigenfrequencies, and limited displacements. Furthermore, common design guidelines or rules, referred to as manufacturing constraints, are included explicitly in the optimization problem as series of linear inequalities. The material selection and thickness variation...... to manufacturability. The results will thus give insight into the relation between potential weight saving and design complexity. The results show that the DMTO method is capable of solving the problems robustly with only few intermediate valued design variables....
Directory of Open Access Journals (Sweden)
Fushing Hsieh
2016-11-01
Full Text Available Discrete combinatorial optimization problems in real world are typically defined via an ensemble of potentially high dimensional measurements pertaining to all subjects of a system under study. We point out that such a data ensemble in fact embeds with system's information content that is not directly used in defining the combinatorial optimization problems. Can machine learning algorithms extract such information content and make combinatorial optimizing tasks more efficient? Would such algorithmic computations bring new perspectives into this classic topic of Applied Mathematics and Theoretical Computer Science? We show that answers to both questions are positive. One key reason is due to permutation invariance. That is, the data ensemble of subjects' measurement vectors is permutation invariant when it is represented through a subject-vs-measurement matrix. An unsupervised machine learning algorithm, called Data Mechanics (DM, is applied to find optimal permutations on row and column axes such that the permuted matrix reveals coupled deterministic and stochastic structures as the system's information content. The deterministic structures are shown to facilitate geometry-based divide-and-conquer scheme that helps optimizing task, while stochastic structures are used to generate an ensemble of mimicries retaining the deterministic structures, and then reveal the robustness pertaining to the original version of optimal solution. Two simulated systems, Assignment problem and Traveling Salesman problem, are considered. Beyond demonstrating computational advantages and intrinsic robustness in the two systems, we propose brand new robust optimal solutions. We believe such robust versions of optimal solutions are potentially more realistic and practical in real world settings.
Locally optimal extracellular stimulation for chaotic desynchronization of neural populations.
Wilson, Dan; Moehlis, Jeff
2014-10-01
We use optimal control theory to design a methodology to find locally optimal stimuli for desynchronization of a model of neurons with extracellular stimulation. This methodology yields stimuli which lead to positive Lyapunov exponents, and hence desynchronizes a neural population. We analyze this methodology in the presence of interneuron coupling to make predictions about the strength of stimulation required to overcome synchronizing effects of coupling. This methodology suggests a powerful alternative to pulsatile stimuli for deep brain stimulation as it uses less energy than pulsatile stimuli, and could eliminate the time consuming tuning process.
DEFF Research Database (Denmark)
Vidal, Rene Victor Valqui
1994-01-01
The paper studies the problem of determining the number and dimensions of sizes of apparel so as to maximize profits. It develops a simple one-variable bisection search algorithm that gives the optimal solution. An example is solved interactively using a Macintosh LC and Math CAD, a mathematical...
The role of stochasticity in an information-optimal neural population code
International Nuclear Information System (INIS)
Stocks, N G; Nikitin, A P; McDonnell, M D; Morse, R P
2009-01-01
In this paper we consider the optimisation of Shannon mutual information (MI) in the context of two model neural systems. The first is a stochastic pooling network (population) of McCulloch-Pitts (MP) type neurons (logical threshold units) subject to stochastic forcing; the second is (in a rate coding paradigm) a population of neurons that each displays Poisson statistics (the so called 'Poisson neuron'). The mutual information is optimised as a function of a parameter that characterises the 'noise level'-in the MP array this parameter is the standard deviation of the noise; in the population of Poisson neurons it is the window length used to determine the spike count. In both systems we find that the emergent neural architecture and, hence, code that maximises the MI is strongly influenced by the noise level. Low noise levels leads to a heterogeneous distribution of neural parameters (diversity), whereas, medium to high noise levels result in the clustering of neural parameters into distinct groups that can be interpreted as subpopulations. In both cases the number of subpopulations increases with a decrease in noise level. Our results suggest that subpopulations are a generic feature of an information optimal neural population.
Prediction of energy demands using neural network with model identification by global optimization
Energy Technology Data Exchange (ETDEWEB)
Yokoyama, Ryohei; Wakui, Tetsuya; Satake, Ryoichi [Department of Mechanical Engineering, Osaka Prefecture University, 1-1 Gakuen-cho, Naka-ku, Sakai, Osaka 599-8531 (Japan)
2009-02-15
To operate energy supply plants properly from the viewpoints of stable energy supply, and energy and cost savings, it is important to predict energy demands accurately as basic conditions. Several methods of predicting energy demands have been proposed, and one of them is to use neural networks. Although local optimization methods such as gradient ones have conventionally been adopted in the back propagation procedure to identify the values of model parameters, they have the significant drawback that they can derive only local optimal solutions. In this paper, a global optimization method called ''Modal Trimming Method'' proposed for non-linear programming problems is adopted to identify the values of model parameters. In addition, the trend and periodic change are first removed from time series data on energy demand, and the converted data is used as the main input to a neural network. Furthermore, predicted values of air temperature and relative humidity are considered as additional inputs to the neural network, and their effect on the prediction of energy demand is investigated. This approach is applied to the prediction of the cooling demand in a building used for a bench mark test of a variety of prediction methods, and its validity and effectiveness are clarified. (author)
International Nuclear Information System (INIS)
Meo, Santolo; Zohoori, Alireza; Vahedi, Abolfazl
2016-01-01
Highlights: • A new optimal design of flux switching permanent magnet generator is developed. • A prototype is employed to validate numerical data used for optimization. • A novel hybrid multi-objective particle swarm optimization approach is proposed. • Optimization targets are weight, cost, voltage and its total harmonic distortion. • The hybrid approach preference is proved compared with other optimization methods. - Abstract: In this paper a new hybrid approach obtained combining a multi-objective particle swarm optimization and artificial neural network is proposed for the design optimization of a direct-drive permanent magnet flux switching generators for low power wind applications. The targets of the proposed multi-objective optimization are to reduce the costs and weight of the machine while maximizing the amplitude of the induced voltage as well as minimizing its total harmonic distortion. The permanent magnet width, the stator and rotor tooth width, the rotor teeth number and stator pole number of the machine define the search space for the optimization problem. Four supervised artificial neural networks are designed for modeling the complex relationships among the weight, the cost, the amplitude and the total harmonic distortion of the output voltage respect to the quantities of the search space. Finite element analysis is adopted to generate training dataset for the artificial neural networks. Finite element analysis based model is verified by experimental results with a 1.5 kW permanent magnet flux switching generator prototype suitable for renewable energy applications, having 6/19 stator poles/rotor teeth. Finally the effectiveness of the proposed hybrid procedure is compared with the results given by conventional multi-objective optimization algorithms. The obtained results show the soundness of the proposed multi objective optimization technique and its feasibility to be adopted as suitable methodology for optimal design of permanent
Energy Complexity of Recurrent Neural Networks
Czech Academy of Sciences Publication Activity Database
Šíma, Jiří
2014-01-01
Roč. 26, č. 5 (2014), s. 953-973 ISSN 0899-7667 R&D Projects: GA ČR GAP202/10/1333 Institutional support: RVO:67985807 Keywords : neural network * finite automaton * energy complexity * optimal size Subject RIV: IN - Informatics, Computer Science Impact factor: 2.207, year: 2014
Optimal Sizing and Control Strategy Design for Heavy Hybrid Electric Truck
Directory of Open Access Journals (Sweden)
Yuan Zou
2012-01-01
Full Text Available Due to the complexity of the hybrid powertrain, the control is highly involved to improve the collaborations of the different components. For the specific powertrain, the components' sizing just gives the possibility to propel the vehicle and the control will realize the function of the propulsion. Definitely the components' sizing also gives the constraints to the control design, which cause a close coupling between the sizing and control strategy design. This paper presents a parametric study focused on sizing of the powertrain components and optimization of the power split between the engine and electric motor for minimizing the fuel consumption. A framework is put forward to accomplish the optimal sizing and control design for a heavy parallel pre-AMT hybrid truck under the natural driving schedule. The iterative plant-controller combined optimization methodology is adopted to optimize the key parameters of the plant and control strategy simultaneously. A scalable powertrain model based on a bilevel optimization framework is built. Dynamic programming is applied to find the optimal control in the inner loop with a prescribed cycle. The parameters are optimized in the outer loop. The results are analysed and the optimal sizing and control strategy are achieved simultaneously.
Directory of Open Access Journals (Sweden)
Nicholas O Fischer
Full Text Available BACKGROUND: Nanolipoprotein particles (NLPs are discoidal, nanometer-sized particles comprised of self-assembled phospholipid membranes and apolipoproteins. NLPs assembled with human apolipoproteins have been used for myriad biotechnology applications, including membrane protein solubilization, drug delivery, and diagnostic imaging. To expand the repertoire of lipoproteins for these applications, insect apolipophorin-III (apoLp-III was evaluated for the ability to form discretely-sized, homogeneous, and stable NLPs. METHODOLOGY: Four NLP populations distinct with regards to particle diameters (ranging in size from 10 nm to >25 nm and lipid-to-apoLp-III ratios were readily isolated to high purity by size exclusion chromatography. Remodeling of the purified NLP species over time at 4 degrees C was monitored by native gel electrophoresis, size exclusion chromatography, and atomic force microscopy. Purified 20 nm NLPs displayed no remodeling and remained stable for over 1 year. Purified NLPs with 10 nm and 15 nm diameters ultimately remodeled into 20 nm NLPs over a period of months. Intra-particle chemical cross-linking of apoLp-III stabilized NLPs of all sizes. CONCLUSIONS: ApoLp-III-based NLPs can be readily prepared, purified, characterized, and stabilized, suggesting their utility for biotechnological applications.
A Global Network Alignment Method Using Discrete Particle Swarm Optimization.
Huang, Jiaxiang; Gong, Maoguo; Ma, Lijia
2016-10-19
Molecular interactions data increase exponentially with the advance of biotechnology. This makes it possible and necessary to comparatively analyse the different data at a network level. Global network alignment is an important network comparison approach to identify conserved subnetworks and get insight into evolutionary relationship across species. Network alignment which is analogous to subgraph isomorphism is known to be an NP-hard problem. In this paper, we introduce a novel heuristic Particle-Swarm-Optimization based Network Aligner (PSONA), which optimizes a weighted global alignment model considering both protein sequence similarity and interaction conservations. The particle statuses and status updating rules are redefined in a discrete form by using permutation. A seed-and-extend strategy is employed to guide the searching for the superior alignment. The proposed initialization method "seeds" matches with high sequence similarity into the alignment, which guarantees the functional coherence of the mapping nodes. A greedy local search method is designed as the "extension" procedure to iteratively optimize the edge conservations. PSONA is compared with several state-of-art methods on ten network pairs combined by five species. The experimental results demonstrate that the proposed aligner can map the proteins with high functional coherence and can be used as a booster to effectively refine the well-studied aligners.
DEFF Research Database (Denmark)
Rasmussen, Marie-Louise Højlund; Stolpe, Mathias
2008-01-01
the physics, and the cuts (Combinatorial Benders’ and projected Chvátal–Gomory) come from an understanding of the particular mathematical structure of the reformulation. The impact of a stronger representation is investigated on several truss topology optimization problems in two and three dimensions.......The subject of this article is solving discrete truss topology optimization problems with local stress and displacement constraints to global optimum. We consider a formulation based on the Simultaneous ANalysis and Design (SAND) approach. This intrinsically non-convex problem is reformulated...
Nikelshpur, Dmitry O.
2014-01-01
Similar to mammalian brains, Artificial Neural Networks (ANN) are universal approximators, capable of yielding near-optimal solutions to a wide assortment of problems. ANNs are used in many fields including medicine, internet security, engineering, retail, robotics, warfare, intelligence control, and finance. "ANNs have a tendency to get…
Optimal Search Strategy of Robotic Assembly Based on Neural Vibration Learning
Directory of Open Access Journals (Sweden)
Lejla Banjanovic-Mehmedovic
2011-01-01
Full Text Available This paper presents implementation of optimal search strategy (OSS in verification of assembly process based on neural vibration learning. The application problem is the complex robot assembly of miniature parts in the example of mating the gears of one multistage planetary speed reducer. Assembly of tube over the planetary gears was noticed as the most difficult problem of overall assembly. The favourable influence of vibration and rotation movement on compensation of tolerance was also observed. With the proposed neural-network-based learning algorithm, it is possible to find extended scope of vibration state parameter. Using optimal search strategy based on minimal distance path between vibration parameter stage sets (amplitude and frequencies of robots gripe vibration and recovery parameter algorithm, we can improve the robot assembly behaviour, that is, allow the fastest possible way of mating. We have verified by using simulation programs that search strategy is suitable for the situation of unexpected events due to uncertainties.
An improved genetic algorithm for designing optimal temporal patterns of neural stimulation
Cassar, Isaac R.; Titus, Nathan D.; Grill, Warren M.
2017-12-01
Objective. Electrical neuromodulation therapies typically apply constant frequency stimulation, but non-regular temporal patterns of stimulation may be more effective and more efficient. However, the design space for temporal patterns is exceedingly large, and model-based optimization is required for pattern design. We designed and implemented a modified genetic algorithm (GA) intended for design optimal temporal patterns of electrical neuromodulation. Approach. We tested and modified standard GA methods for application to designing temporal patterns of neural stimulation. We evaluated each modification individually and all modifications collectively by comparing performance to the standard GA across three test functions and two biophysically-based models of neural stimulation. Main results. The proposed modifications of the GA significantly improved performance across the test functions and performed best when all were used collectively. The standard GA found patterns that outperformed fixed-frequency, clinically-standard patterns in biophysically-based models of neural stimulation, but the modified GA, in many fewer iterations, consistently converged to higher-scoring, non-regular patterns of stimulation. Significance. The proposed improvements to standard GA methodology reduced the number of iterations required for convergence and identified superior solutions.
Huang, Darong; Bai, Xing-Rong
Based on wavelet transform and neural network theory, a traffic-flow prediction model, which was used in optimal control of Intelligent Traffic system, is constructed. First of all, we have extracted the scale coefficient and wavelet coefficient from the online measured raw data of traffic flow via wavelet transform; Secondly, an Artificial Neural Network model of Traffic-flow Prediction was constructed and trained using the coefficient sequences as inputs and raw data as outputs; Simultaneous, we have designed the running principium of the optimal control system of traffic-flow Forecasting model, the network topological structure and the data transmitted model; Finally, a simulated example has shown that the technique is effectively and exactly. The theoretical results indicated that the wavelet neural network prediction model and algorithms have a broad prospect for practical application.
Design of Optimal Hybrid Position/Force Controller for a Robot Manipulator Using Neural Networks
Directory of Open Access Journals (Sweden)
Vikas Panwar
2007-01-01
Full Text Available The application of quadratic optimization and sliding-mode approach is considered for hybrid position and force control of a robot manipulator. The dynamic model of the manipulator is transformed into a state-space model to contain two sets of state variables, where one describes the constrained motion and the other describes the unconstrained motion. The optimal feedback control law is derived solving matrix differential Riccati equation, which is obtained using Hamilton Jacobi Bellman optimization. The optimal feedback control law is shown to be globally exponentially stable using Lyapunov function approach. The dynamic model uncertainties are compensated with a feedforward neural network. The neural network requires no preliminary offline training and is trained with online weight tuning algorithms that guarantee small errors and bounded control signals. The application of the derived control law is demonstrated through simulation with a 4-DOF robot manipulator to track an elliptical planar constrained surface while applying the desired force on the surface.
Directory of Open Access Journals (Sweden)
Deyu Cui
2018-04-01
Full Text Available State of charge (SOC estimation is becoming increasingly important, along with electric vehicle (EV rapid development, while SOC is one of the most significant parameters for the battery management system, indicating remaining energy and ensuring the safety and reliability of EV. In this paper, a hybrid wavelet neural network (WNN model combining the discrete wavelet transform (DWT method and adaptive WNN is proposed to estimate the SOC of lithium-ion batteries. The WNN model is trained by Levenberg-Marquardt (L-M algorithm, whose inputs are processed by discrete wavelet decomposition and reconstitution. Compared with back-propagation neural network (BPNN, L-M based BPNN (LMBPNN, L-M based WNN (LMWNN, DWT with L-M based BPNN (DWTLMBPNN and extend Kalman filter (EKF, the proposed intelligent SOC estimation method is validated and proved to be effective. Under the New European Driving Cycle (NEDC, the mean absolute error and maximum error can be reduced to 0.59% and 3.13%, respectively. The characteristics of high accuracy and strong robustness of the proposed method are verified by comparison study and robustness evaluation results (e.g., measurement noise test and untrained driving cycle test.
2012-01-01
Background Synchronized bursting activity (SBA) is a remarkable dynamical behavior in both ex vivo and in vivo neural networks. Investigations of the underlying structural characteristics associated with SBA are crucial to understanding the system-level regulatory mechanism of neural network behaviors. Results In this study, artificial pulsed neural networks were established using spike response models to capture fundamental dynamics of large scale ex vivo cortical networks. Network simulations with synaptic parameter perturbations showed the following two findings. (i) In a network with an excitatory ratio (ER) of 80-90%, its connective ratio (CR) was within a range of 10-30% when the occurrence of SBA reached the highest expectation. This result was consistent with the experimental observation in ex vivo neuronal networks, which were reported to possess a matured inhibitory synaptic ratio of 10-20% and a CR of 10-30%. (ii) No SBA occurred when a network does not contain any all-positive-interaction feedback loop (APFL) motif. In a neural network containing APFLs, the number of APFLs presented an optimal range corresponding to the maximal occurrence of SBA, which was very similar to the optimal CR. Conclusions In a neural network, the evolutionarily selected CR (10-30%) optimizes the occurrence of SBA, and APFL serves a pivotal network motif required to maximize the occurrence of SBA. PMID:22462685
Ant colony optimization and neural networks applied to nuclear power plant monitoring
International Nuclear Information System (INIS)
Santos, Gean Ribeiro dos; Andrade, Delvonei Alves de; Pereira, Iraci Martinez
2015-01-01
A recurring challenge in production processes is the development of monitoring and diagnosis systems. Those systems help on detecting unexpected changes and interruptions, preventing losses and mitigating risks. Artificial Neural Networks (ANNs) have been extensively used in creating monitoring systems. Usually the ANNs created to solve this kind of problem are created by taking into account only parameters as the number of inputs, outputs, and hidden layers. The result networks are generally fully connected and have no improvements in its topology. This work intends to use an Ant Colony Optimization (ACO) algorithm to create a tuned neural network. The ACO search algorithm will use Back Error Propagation (BP) to optimize the network topology by suggesting the best neuron connections. The result ANN will be applied to monitoring the IEA-R1 research reactor at IPEN. (author)
Ant colony optimization and neural networks applied to nuclear power plant monitoring
Energy Technology Data Exchange (ETDEWEB)
Santos, Gean Ribeiro dos; Andrade, Delvonei Alves de; Pereira, Iraci Martinez, E-mail: gean@usp.br, E-mail: delvonei@ipen.br, E-mail: martinez@ipen.br [Instituto de Pesquisas Energeticas e Nucleares (IPEN/CNEN-SP), Sao Paulo, SP (Brazil)
2015-07-01
A recurring challenge in production processes is the development of monitoring and diagnosis systems. Those systems help on detecting unexpected changes and interruptions, preventing losses and mitigating risks. Artificial Neural Networks (ANNs) have been extensively used in creating monitoring systems. Usually the ANNs created to solve this kind of problem are created by taking into account only parameters as the number of inputs, outputs, and hidden layers. The result networks are generally fully connected and have no improvements in its topology. This work intends to use an Ant Colony Optimization (ACO) algorithm to create a tuned neural network. The ACO search algorithm will use Back Error Propagation (BP) to optimize the network topology by suggesting the best neuron connections. The result ANN will be applied to monitoring the IEA-R1 research reactor at IPEN. (author)
International Nuclear Information System (INIS)
Chao Luo-Meng; Bao Li-Hong; Tegus, O.
2015-01-01
The discrete dipole approximation is used to investigate the optical response of CeB_6 nanoparticles with different sizes and different shapes. The extinction valley in the visible light range becomes narrower and the extinction peak at the near infrared region (NIR) is red-shifted with the increasing particle size. In addition, the extinction peak value of the spherical particle decreases more rapidly than that of cubic-shaped particle with an increase in the particle size, and the cubic-shaped particles exhibit better performance on blocking NIR radiation than spherical-shaped particles. The calculation results coincide well with the reported experimental results. (paper)
Optimization of neural networks for time-domain simulation of mooring lines
DEFF Research Database (Denmark)
Christiansen, Niels Hørbye; Voie, Per Erlend Torbergsen; Winther, Ole
2016-01-01
, they also can be used to rank the importance of the various network inputs. The dynamic response of slender marine structures often depends on several external load components, and by applying the optimization procedures to a trained artificial neural network, it is possible to classify the external force...
International Nuclear Information System (INIS)
Li, Chunlong; Zhou, Jianzhong; Ouyang, Shuo; Ding, Xiaoling; Chen, Lu
2014-01-01
Highlights: • Optimization of large-scale hydropower system in the Yangtze River basin. • Improved decomposition–coordination and discrete differential dynamic programming. • Generating initial solution randomly to reduce generation time. • Proposing relative coefficient for more power generation. • Proposing adaptive bias corridor technology to enhance convergence speed. - Abstract: With the construction of major hydro plants, more and more large-scale hydropower systems are taking shape gradually, which brings up a challenge to optimize these systems. Optimization of large-scale hydropower system (OLHS), which is to determine water discharges or water levels of overall hydro plants for maximizing total power generation when subjecting to lots of constrains, is a high dimensional, nonlinear and coupling complex problem. In order to solve the OLHS problem effectively, an improved decomposition–coordination and discrete differential dynamic programming (IDC–DDDP) method is proposed in this paper. A strategy that initial solution is generated randomly is adopted to reduce generation time. Meanwhile, a relative coefficient based on maximum output capacity is proposed for more power generation. Moreover, an adaptive bias corridor technology is proposed to enhance convergence speed. The proposed method is applied to long-term optimal dispatches of large-scale hydropower system (LHS) in the Yangtze River basin. Compared to other methods, IDC–DDDP has competitive performances in not only total power generation but also convergence speed, which provides a new method to solve the OLHS problem
BWR fuel cycle optimization using neural networks
International Nuclear Information System (INIS)
Ortiz-Servin, Juan Jose; Castillo, Jose Alejandro; Pelta, David Alejandro
2011-01-01
Highlights: → OCONN a new system to optimize all nuclear fuel management steps in a coupled way. → OCON is based on an artificial recurrent neural network to find the best combination of partial solutions to each fuel management step. → OCONN works with a fuel lattices' stock, a fuel reloads' stock and a control rod patterns' stock, previously obtained with different heuristic techniques. → Results show OCONN is able to find good combinations according the global objective function. - Abstract: In nuclear fuel management activities for BWRs, four combinatorial optimization problems are solved: fuel lattice design, axial fuel bundle design, fuel reload design and control rod patterns design. Traditionally, these problems have been solved in separated ways due to their complexity and the required computational resources. In the specialized literature there are some attempts to solve fuel reloads and control rod patterns design or fuel lattice and axial fuel bundle design in a coupled way. In this paper, the system OCONN to solve all of these problems in a coupled way is shown. This system is based on an artificial recurrent neural network to find the best combination of partial solutions to each problem, in order to maximize a global objective function. The new system works with a fuel lattices' stock, a fuel reloads' stock and a control rod patterns' stock, previously obtained with different heuristic techniques. The system was tested to design an equilibrium cycle with a cycle length of 18 months. Results show that the new system is able to find good combinations. Cycle length is reached and safety parameters are fulfilled.
Zhu, Bofan
Biocompatible scaffolds mimicking the locally aligned fibrous structure of native extracellular matrix (ECM) are in high demand in tissue engineering. In this thesis research, unidirectionally aligned fibers were generated via a home-built electrospinning system. Collagen type I, as a major ECM component, was chosen in this study due to its support of cell proliferation and promotion of neuroectodermal commitment in stem cell differentiation. Synthetic dragline silk proteins, as biopolymers with remarkable tensile strength and superior elasticity, were also used as a model material. Good alignment, controllable fiber size and morphology, as well as a desirable deposition density of fibers were achieved via the optimization of solution and electrospinning parameters. The incorporation of silk proteins into collagen was found to significantly enhance mechanical properties and stability of electrospun fibers. Glutaraldehyde (GA) vapor post-treatment was demonstrated as a simple and effective way to tune the properties of collagen/silk fibers without changing their chemical composition. With 6-12 hours GA treatment, electrospun collagen/silk fibers were not only biocompatible, but could also effectively induce the polarization and neural commitment of stem cells, which were optimized on collagen rich fibers due to the unique combination of biochemical and biophysical cues imposed to cells. Taken together, electrospun collagen rich composite fibers are mechanically strong, stable and provide excellent cell adhesion. The unidirectionally aligned fibers can accelerate neural differentiation of stem cells, representing a promising therapy for neural tissue degenerative diseases and nerve injuries.
Zakary, Omar; Rachik, Mostafa; Elmouki, Ilias
2017-08-01
First, we devise in this paper, a multi-regions discrete-time model which describes the spatial-temporal spread of an epidemic which starts from one region and enters to regions which are connected with their neighbors by any kind of anthropological movement. We suppose homogeneous Susceptible-Infected-Removed (SIR) populations, and we consider in our simulations, a grid of colored cells, which represents the whole domain affected by the epidemic while each cell can represent a sub-domain or region. Second, in order to minimize the number of infected individuals in one region, we propose an optimal control approach based on a travel-blocking vicinity strategy which aims to control only one cell by restricting movements of infected people coming from all neighboring cells. Thus, we show the influence of the optimal control approach on the controlled cell. We should also note that the cellular modeling approach we propose here, can also describes infection dynamics of regions which are not necessarily attached one to an other, even if no empty space can be viewed between cells. The theoretical method we follow for the characterization of the travel-locking optimal controls, is based on a discrete version of Pontryagin's maximum principle while the numerical approach applied to the multi-points boundary value problems we obtain here, is based on discrete progressive-regressive iterative schemes. We illustrate our modeling and control approaches by giving an example of 100 regions.
DECISION WITH ARTIFICIAL NEURAL NETWORKS IN DISCRETE EVENT SIMULATION MODELS ON A TRAFFIC SYSTEM
Directory of Open Access Journals (Sweden)
Marília Gonçalves Dutra da Silva
2016-04-01
Full Text Available ABSTRACT This work aims to demonstrate the use of a mechanism to be applied in the development of the discrete-event simulation models that perform decision operations through the implementation of an artificial neural network. Actions that involve complex operations performed by a human agent in a process, for example, are often modeled in simplified form with the usual mechanisms of simulation software. Therefore, it was chosen a traffic system controlled by a traffic officer with a flow of vehicles and pedestrians to demonstrate the proposed solution. From a module built in simulation software itself, it was possible to connect the algorithm for intelligent decision to the simulation model. The results showed that the model elaborated responded as expected when it was submitted to actions, which required different decisions to maintain the operation of the system with changes in the flow of people and vehicles.
Determination of the optimal sample size for a clinical trial accounting for the population size.
Stallard, Nigel; Miller, Frank; Day, Simon; Hee, Siew Wan; Madan, Jason; Zohar, Sarah; Posch, Martin
2017-07-01
The problem of choosing a sample size for a clinical trial is a very common one. In some settings, such as rare diseases or other small populations, the large sample sizes usually associated with the standard frequentist approach may be infeasible, suggesting that the sample size chosen should reflect the size of the population under consideration. Incorporation of the population size is possible in a decision-theoretic approach either explicitly by assuming that the population size is fixed and known, or implicitly through geometric discounting of the gain from future patients reflecting the expected population size. This paper develops such approaches. Building on previous work, an asymptotic expression is derived for the sample size for single and two-arm clinical trials in the general case of a clinical trial with a primary endpoint with a distribution of one parameter exponential family form that optimizes a utility function that quantifies the cost and gain per patient as a continuous function of this parameter. It is shown that as the size of the population, N, or expected size, N∗ in the case of geometric discounting, becomes large, the optimal trial size is O(N1/2) or O(N∗1/2). The sample size obtained from the asymptotic expression is also compared with the exact optimal sample size in examples with responses with Bernoulli and Poisson distributions, showing that the asymptotic approximations can also be reasonable in relatively small sample sizes. © 2016 The Author. Biometrical Journal published by WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.
The role of stochasticity in an information-optimal neural population code
Energy Technology Data Exchange (ETDEWEB)
Stocks, N G; Nikitin, A P [School of Engineering, University of Warwick, Coventry CV4 7AL (United Kingdom); McDonnell, M D [Institute for Telecommunications Research, University of South Australia, SA 5095 (Australia); Morse, R P, E-mail: n.g.stocks@warwick.ac.u [School of Life and Health Sciences, Aston University, Birmingham B4 7ET (United Kingdom)
2009-12-01
In this paper we consider the optimisation of Shannon mutual information (MI) in the context of two model neural systems. The first is a stochastic pooling network (population) of McCulloch-Pitts (MP) type neurons (logical threshold units) subject to stochastic forcing; the second is (in a rate coding paradigm) a population of neurons that each displays Poisson statistics (the so called 'Poisson neuron'). The mutual information is optimised as a function of a parameter that characterises the 'noise level'-in the MP array this parameter is the standard deviation of the noise; in the population of Poisson neurons it is the window length used to determine the spike count. In both systems we find that the emergent neural architecture and, hence, code that maximises the MI is strongly influenced by the noise level. Low noise levels leads to a heterogeneous distribution of neural parameters (diversity), whereas, medium to high noise levels result in the clustering of neural parameters into distinct groups that can be interpreted as subpopulations. In both cases the number of subpopulations increases with a decrease in noise level. Our results suggest that subpopulations are a generic feature of an information optimal neural population.
Optimal weights for circle fitting with discrete granular data
International Nuclear Information System (INIS)
Chernov, N.; Kolganova, E.; Ososkov, G.
1995-01-01
The problem of the data approximation measured along a circle by modern detectors in high energy physics, as for example, RICH (Ring Imaging Cherenkov) is considered. Such detectors having the discrete cell structure register the energy dissipation produced by a passing elementary particle not in a single point, but in several adjacent cells where all this energy is distributed. The presence of background hits makes inapplicable circle fitting methods based on the least square fit due to their noise sensitivity. In this paper it's shown that the efficient way to overcome these problems of the curve fitting is the robust fitting technique based on a reweighted least square method with optimally chosen weights, obtained by the use of maximum likelihood estimates. Results of numerical experiments are given proving the high efficiency of the suggested method. 9 refs., 5 figs., 1 tab
Identification of parameters of discrete-continuous models
International Nuclear Information System (INIS)
Cekus, Dawid; Warys, Pawel
2015-01-01
In the paper, the parameters of a discrete-continuous model have been identified on the basis of experimental investigations and formulation of optimization problem. The discrete-continuous model represents a cantilever stepped Timoshenko beam. The mathematical model has been formulated and solved according to the Lagrange multiplier formalism. Optimization has been based on the genetic algorithm. The presented proceeding’s stages make the identification of any parameters of discrete-continuous systems possible
Identification of parameters of discrete-continuous models
Energy Technology Data Exchange (ETDEWEB)
Cekus, Dawid, E-mail: cekus@imipkm.pcz.pl; Warys, Pawel, E-mail: warys@imipkm.pcz.pl [Institute of Mechanics and Machine Design Foundations, Czestochowa University of Technology, Dabrowskiego 73, 42-201 Czestochowa (Poland)
2015-03-10
In the paper, the parameters of a discrete-continuous model have been identified on the basis of experimental investigations and formulation of optimization problem. The discrete-continuous model represents a cantilever stepped Timoshenko beam. The mathematical model has been formulated and solved according to the Lagrange multiplier formalism. Optimization has been based on the genetic algorithm. The presented proceeding’s stages make the identification of any parameters of discrete-continuous systems possible.
Iterative free-energy optimization for recurrent neural networks (INFERNO)
2017-01-01
The intra-parietal lobe coupled with the Basal Ganglia forms a working memory that demonstrates strong planning capabilities for generating robust yet flexible neuronal sequences. Neurocomputational models however, often fails to control long range neural synchrony in recurrent spiking networks due to spontaneous activity. As a novel framework based on the free-energy principle, we propose to see the problem of spikes’ synchrony as an optimization problem of the neurons sub-threshold activity for the generation of long neuronal chains. Using a stochastic gradient descent, a reinforcement signal (presumably dopaminergic) evaluates the quality of one input vector to move the recurrent neural network to a desired activity; depending on the error made, this input vector is strengthened to hill-climb the gradient or elicited to search for another solution. This vector can be learned then by one associative memory as a model of the basal-ganglia to control the recurrent neural network. Experiments on habit learning and on sequence retrieving demonstrate the capabilities of the dual system to generate very long and precise spatio-temporal sequences, above two hundred iterations. Its features are applied then to the sequential planning of arm movements. In line with neurobiological theories, we discuss its relevance for modeling the cortico-basal working memory to initiate flexible goal-directed neuronal chains of causation and its relation to novel architectures such as Deep Networks, Neural Turing Machines and the Free-Energy Principle. PMID:28282439
Directory of Open Access Journals (Sweden)
Ahmed R. Abas
2012-07-01
Full Text Available In this paper, a new algorithm is presented for unsupervised learning of finite mixture models (FMMs using data set with missing values. This algorithm overcomes the local optima problem of the Expectation-Maximization (EM algorithm via integrating the EM algorithm with Particle Swarm Optimization (PSO. In addition, the proposed algorithm overcomes the problem of biased estimation due to overlapping clusters in estimating missing values in the input data set by integrating locally-tuned general regression neural networks with Optimal Completion Strategy (OCS. A comparison study shows the superiority of the proposed algorithm over other algorithms commonly used in the literature in unsupervised learning of FMM parameters that result in minimum mis-classification errors when used in clustering incomplete data set that is generated from overlapping clusters and these clusters are largely different in their sizes.
Dreifuss, Tamar; Betzer, Oshra; Barnoy, Eran; Motiei, Menachem; Popovtzer, Rachela
2018-02-01
Theranostics is an emerging field, defined as combination of therapeutic and diagnostic capabilities in the same material. Nanoparticles are considered as an efficient platform for theranostics, particularly in cancer treatment, as they offer substantial advantages over both common imaging contrast agents and chemotherapeutic drugs. However, the development of theranostic nanoplatforms raises an important question: Is the optimal particle for imaging also optimal for therapy? Are the specific parameters required for maximal drug delivery, similar to those required for imaging applications? Herein, we examined this issue by investigating the effect of nanoparticle size on tumor uptake and imaging. Anti-epidermal growth factor receptor (EGFR)-conjugated gold nanoparticles (GNPs) in different sizes (diameter range: 20-120 nm) were injected to tumor bearing mice and their uptake by tumors was measured, as well as their tumor visualization capabilities as tumor-targeted CT contrast agent. Interestingly, the results showed that different particles led to highest tumor uptake or highest contrast enhancement, meaning that the optimal particle size for drug delivery is not necessarily optimal for tumor imaging. These results have important implications on the design of theranostic nanoplatforms.
LQR-Based Optimal Distributed Cooperative Design for Linear Discrete-Time Multiagent Systems.
Zhang, Huaguang; Feng, Tao; Liang, Hongjing; Luo, Yanhong
2017-03-01
In this paper, a novel linear quadratic regulator (LQR)-based optimal distributed cooperative design method is developed for synchronization control of general linear discrete-time multiagent systems on a fixed, directed graph. Sufficient conditions are derived for synchronization, which restrict the graph eigenvalues into a bounded circular region in the complex plane. The synchronizing speed issue is also considered, and it turns out that the synchronizing region reduces as the synchronizing speed becomes faster. To obtain more desirable synchronizing capacity, the weighting matrices are selected by sufficiently utilizing the guaranteed gain margin of the optimal regulators. Based on the developed LQR-based cooperative design framework, an approximate dynamic programming technique is successfully introduced to overcome the (partially or completely) model-free cooperative design for linear multiagent systems. Finally, two numerical examples are given to illustrate the effectiveness of the proposed design methods.
Optimized low-order explicit Runge-Kutta schemes for high- order spectral difference method
Parsani, Matteo
2012-01-01
Optimal explicit Runge-Kutta (ERK) schemes with large stable step sizes are developed for method-of-lines discretizations based on the spectral difference (SD) spatial discretization on quadrilateral grids. These methods involve many stages and provide the optimal linearly stable time step for a prescribed SD spectrum and the minimum leading truncation error coefficient, while admitting a low-storage implementation. Using a large number of stages, the new ERK schemes lead to efficiency improvements larger than 60% over standard ERK schemes for 4th- and 5th-order spatial discretization.
Selection and storage of perceptual groups is constrained by a discrete resource in working memory.
Anderson, David E; Vogel, Edward K; Awh, Edward
2013-06-01
Perceptual grouping can lead observers to perceive a multielement scene as a smaller number of hierarchical units. Past work has shown that grouping enables more elements to be stored in visual working memory (WM). Although this may appear to contradict so-called discrete resource models that argue for fixed item limits in WM storage, it is also possible that grouping reduces the effective number of "items" in the display. To test this hypothesis, we examined how mnemonic resolution declined as the number of items to be stored increased. Discrete resource models predict that precision will reach a stable plateau at relatively early set sizes, because no further items can be stored once putative item limits are exceeded. Thus, we examined whether the precision by set size function was bilinear when storage was enhanced via perceptual grouping. In line with the hypothesis that each perceptual group counted as a single "item," precision still reached a clear plateau at a set size determined by the number of stored groups. Moreover, the maximum number of elements stored was doubled, and electrophysiological measures showed that selection and storage-related neural responses were the same for a single element and a multielement perceptual group. Thus, perceptual grouping allows more elements to be held in working memory while storage is still constrained by a discrete item limit.
Bansal, Ravi; Hao, Xuejun; Peterson, Bradley S
2015-05-01
We hypothesize that coordinated functional activity within discrete neural circuits induces morphological organization and plasticity within those circuits. Identifying regions of morphological covariation that are independent of morphological covariation in other regions therefore may therefore allow us to identify discrete neural systems within the brain. Comparing the magnitude of these variations in individuals who have psychiatric disorders with the magnitude of variations in healthy controls may allow us to identify aberrant neural pathways in psychiatric illnesses. We measured surface morphological features by applying nonlinear, high-dimensional warping algorithms to manually defined brain regions. We transferred those measures onto the surface of a unit sphere via conformal mapping and then used spherical wavelets and their scaling coefficients to simplify the data structure representing these surface morphological features of each brain region. We used principal component analysis (PCA) to calculate covariation in these morphological measures, as represented by their scaling coefficients, across several brain regions. We then assessed whether brain subregions that covaried in morphology, as identified by large eigenvalues in the PCA, identified specific neural pathways of the brain. To do so, we spatially registered the subnuclei for each eigenvector into the coordinate space of a Diffusion Tensor Imaging dataset; we used these subnuclei as seed regions to track and compare fiber pathways with known fiber pathways identified in neuroanatomical atlases. We applied these procedures to anatomical MRI data in a cohort of 82 healthy participants (42 children, 18 males, age 10.5 ± 2.43 years; 40 adults, 22 males, age 32.42 ± 10.7 years) and 107 participants with Tourette's Syndrome (TS) (71 children, 59 males, age 11.19 ± 2.2 years; 36 adults, 21 males, age 37.34 ± 10.9 years). We evaluated the construct validity of the identified covariation in morphology
International Nuclear Information System (INIS)
Kaslik, E.; Balint, St.
2009-01-01
In this paper, a bifurcation analysis is undertaken for a discrete-time Hopfield neural network of two neurons with two different delays and self-connections. Conditions ensuring the asymptotic stability of the null solution are found, with respect to two characteristic parameters of the system. It is shown that for certain values of these parameters, Fold or Neimark-Sacker bifurcations occur, but Flip and codimension 2 (Fold-Neimark-Sacker, double Neimark-Sacker, resonance 1:1 and Flip-Neimark-Sacker) bifurcations may also be present. The direction and the stability of the Neimark-Sacker bifurcations are investigated by applying the center manifold theorem and the normal form theory
Zamani, Majid; Demosthenous, Andreas
2014-07-01
Next generation neural interfaces for upper-limb (and other) prostheses aim to develop implantable interfaces for one or more nerves, each interface having many neural signal channels that work reliably in the stump without harming the nerves. To achieve real-time multi-channel processing it is important to integrate spike sorting on-chip to overcome limitations in transmission bandwidth. This requires computationally efficient algorithms for feature extraction and clustering suitable for low-power hardware implementation. This paper describes a new feature extraction method for real-time spike sorting based on extrema analysis (namely positive peaks and negative peaks) of spike shapes and their discrete derivatives at different frequency bands. Employing simulation across different datasets, the accuracy and computational complexity of the proposed method are assessed and compared with other methods. The average classification accuracy of the proposed method in conjunction with online sorting (O-Sort) is 91.6%, outperforming all the other methods tested with the O-Sort clustering algorithm. The proposed method offers a better tradeoff between classification error and computational complexity, making it a particularly strong choice for on-chip spike sorting.
Behavior and neural basis of near-optimal visual search
Ma, Wei Ji; Navalpakkam, Vidhya; Beck, Jeffrey M; van den Berg, Ronald; Pouget, Alexandre
2013-01-01
The ability to search efficiently for a target in a cluttered environment is one of the most remarkable functions of the nervous system. This task is difficult under natural circumstances, as the reliability of sensory information can vary greatly across space and time and is typically a priori unknown to the observer. In contrast, visual-search experiments commonly use stimuli of equal and known reliability. In a target detection task, we randomly assigned high or low reliability to each item on a trial-by-trial basis. An optimal observer would weight the observations by their trial-to-trial reliability and combine them using a specific nonlinear integration rule. We found that humans were near-optimal, regardless of whether distractors were homogeneous or heterogeneous and whether reliability was manipulated through contrast or shape. We present a neural-network implementation of near-optimal visual search based on probabilistic population coding. The network matched human performance. PMID:21552276
Schwalger, Tilo; Deger, Moritz; Gerstner, Wulfram
2017-04-01
Neural population equations such as neural mass or field models are widely used to study brain activity on a large scale. However, the relation of these models to the properties of single neurons is unclear. Here we derive an equation for several interacting populations at the mesoscopic scale starting from a microscopic model of randomly connected generalized integrate-and-fire neuron models. Each population consists of 50-2000 neurons of the same type but different populations account for different neuron types. The stochastic population equations that we find reveal how spike-history effects in single-neuron dynamics such as refractoriness and adaptation interact with finite-size fluctuations on the population level. Efficient integration of the stochastic mesoscopic equations reproduces the statistical behavior of the population activities obtained from microscopic simulations of a full spiking neural network model. The theory describes nonlinear emergent dynamics such as finite-size-induced stochastic transitions in multistable networks and synchronization in balanced networks of excitatory and inhibitory neurons. The mesoscopic equations are employed to rapidly integrate a model of a cortical microcircuit consisting of eight neuron types, which allows us to predict spontaneous population activities as well as evoked responses to thalamic input. Our theory establishes a general framework for modeling finite-size neural population dynamics based on single cell and synapse parameters and offers an efficient approach to analyzing cortical circuits and computations.
Combined Simulated Annealing Algorithm for the Discrete Facility Location Problem
Directory of Open Access Journals (Sweden)
Jin Qin
2012-01-01
Full Text Available The combined simulated annealing (CSA algorithm was developed for the discrete facility location problem (DFLP in the paper. The method is a two-layer algorithm, in which the external subalgorithm optimizes the decision of the facility location decision while the internal subalgorithm optimizes the decision of the allocation of customer's demand under the determined location decision. The performance of the CSA is tested by 30 instances with different sizes. The computational results show that CSA works much better than the previous algorithm on DFLP and offers a new reasonable alternative solution method to it.
Liu, Tao; Huang, Jie
2017-04-17
This paper presents a discrete-time recurrent neural network approach to solving systems of linear equations with two features. First, the system of linear equations may not have a unique solution. Second, the system matrix is not known precisely, but a sequence of matrices that converges to the unknown system matrix exponentially is known. The problem is motivated from solving the output regulation problem for linear systems. Thus, an application of our main result leads to an online solution to the output regulation problem for linear systems.
Social network size relates to developmental neural sensitivity to biological motion
Directory of Open Access Journals (Sweden)
L.A. Kirby
2018-04-01
Full Text Available The ability to perceive others’ actions and goals from human motion (i.e., biological motion perception is a critical component of social perception and may be linked to the development of real-world social relationships. Adult research demonstrates two key nodes of the brain’s biological motion perception system—amygdala and posterior superior temporal sulcus (pSTS—are linked to variability in social network properties. The relation between social perception and social network properties, however, has not yet been investigated in middle childhood—a time when individual differences in social experiences and social perception are growing. The aims of this study were to (1 replicate past work showing amygdala and pSTS sensitivity to biological motion in middle childhood; (2 examine age-related changes in the neural sensitivity for biological motion, and (3 determine whether neural sensitivity for biological motion relates to social network characteristics in children. Consistent with past work, we demonstrate a significant relation between social network size and neural sensitivity for biological motion in left pSTS, but do not find age-related change in biological motion perception. This finding offers evidence for the interplay between real-world social experiences and functional brain development and has important implications for understanding disorders of atypical social experience. Keywords: Biological motion, Social networks, Middle childhood, Neural specialization, Brain-behavior relations, pSTS
Takiyama, Ken
2017-12-01
How neural adaptation affects neural information processing (i.e. the dynamics and equilibrium state of neural activities) is a central question in computational neuroscience. In my previous works, I analytically clarified the dynamics and equilibrium state of neural activities in a ring-type neural network model that is widely used to model the visual cortex, motor cortex, and several other brain regions. The neural dynamics and the equilibrium state in the neural network model corresponded to a Bayesian computation and statistically optimal multiple information integration, respectively, under a biologically inspired condition. These results were revealed in an analytically tractable manner; however, adaptation effects were not considered. Here, I analytically reveal how the dynamics and equilibrium state of neural activities in a ring neural network are influenced by spike-frequency adaptation (SFA). SFA is an adaptation that causes gradual inhibition of neural activity when a sustained stimulus is applied, and the strength of this inhibition depends on neural activities. I reveal that SFA plays three roles: (1) SFA amplifies the influence of external input in neural dynamics; (2) SFA allows the history of the external input to affect neural dynamics; and (3) the equilibrium state corresponds to the statistically optimal multiple information integration independent of the existence of SFA. In addition, the equilibrium state in a ring neural network model corresponds to the statistically optimal integration of multiple information sources under biologically inspired conditions, independent of the existence of SFA.
Directory of Open Access Journals (Sweden)
Haibo Zhang
2016-08-01
Full Text Available The security incidents ion networks are sudden and uncertain, it is very hard to precisely predict the network security situation by traditional methods. In order to improve the prediction accuracy of the network security situation, we build a network security situation prediction model based on Wavelet Neural Network (WNN with optimized parameters by the Improved Niche Genetic Algorithm (INGA. The proposed model adopts WNN which has strong nonlinear ability and fault-tolerance performance. Also, the parameters for WNN are optimized through the adaptive genetic algorithm (GA so that WNN searches more effectively. Considering the problem that the adaptive GA converges slowly and easily turns to the premature problem, we introduce a novel niche technology with a dynamic fuzzy clustering and elimination mechanism to solve the premature convergence of the GA. Our final simulation results show that the proposed INGA-WNN prediction model is more reliable and effective, and it achieves faster convergence-speed and higher prediction accuracy than the Genetic Algorithm-Wavelet Neural Network (GA-WNN, Genetic Algorithm-Back Propagation Neural Network (GA-BPNN and WNN.
Chen, Jian; Matuttis, Hans-Georg
2013-02-01
We report our experiences with the optimization and parallelization of a discrete element code for convex polyhedra on multi-core machines and introduce a novel variant of the sort-and-sweep neighborhood algorithm. While in theory the whole code in itself parallelizes ideally, in practice the results on different architectures with different compilers and performance measurement tools depend very much on the particle number and optimization of the code. After difficulties with the interpretation of the data for speedup and efficiency are overcome, respectable parallelization speedups could be obtained.
An L∞/L1-Constrained Quadratic Optimization Problem with Applications to Neural Networks
International Nuclear Information System (INIS)
Leizarowitz, Arie; Rubinstein, Jacob
2003-01-01
Pattern formation in associative neural networks is related to a quadratic optimization problem. Biological considerations imply that the functional is constrained in the L ∞ norm and in the L 1 norm. We consider such optimization problems. We derive the Euler-Lagrange equations, and construct basic properties of the maximizers. We study in some detail the case where the kernel of the quadratic functional is finite-dimensional. In this case the optimization problem can be fully characterized by the geometry of a certain convex and compact finite-dimensional set
Efficiency optimized control of medium-size induction motor drives
DEFF Research Database (Denmark)
Abrahamsen, F.; Blaabjerg, Frede; Pedersen, John Kim
2000-01-01
The efficiency of a variable speed induction motor drive can be optimized by adaption of the motor flux level to the load torque. In small drives (<10 kW) this can be done without considering the relatively small converter losses, but for medium-size drives (10-1000 kW) the losses can not be disr......The efficiency of a variable speed induction motor drive can be optimized by adaption of the motor flux level to the load torque. In small drives (... not be disregarded without further analysis. The importance of the converter losses on efficiency optimization in medium-size drives is analyzed in this paper. Based on the experiments with a 90 kW drive it is found that it is not critical if the converter losses are neglected in the control, except...... that the robustness towards load disturbances may unnecessarily be reduced. Both displacement power factor and model-based efficiency optimizing control methods perform well in medium-size drives. The last strategy is also tested on a 22 kW drive with good results....
Briaire, Jeroen J; Frijns, Johan H M
2006-04-01
Cochlear implant research endeavors to optimize the spatial selectivity, threshold and dynamic range with the objective of improving the speech perception performance of the implant user. One of the ways to achieve some of these goals is by electrode design. New cochlear implant electrode designs strive to bring the electrode contacts into close proximity to the nerve fibers in the modiolus: this is done by placing the contacts on the medial side of the array and positioning the implant against the medial wall of scala tympani. The question remains whether this is the optimal position for a cochlea with intact neural fibers and, if so, whether it is also true for a cochlea with degenerated neural fibers. In this study a computational model of the implanted human cochlea is used to investigate the optimal position of the array with respect to threshold, dynamic range and spatial selectivity for a cochlea with intact nerve fibers and for degenerated nerve fibers. In addition, the model is used to evaluate the predictive value of eCAP measurements for obtaining peri-operative information on the neural status. The model predicts improved threshold, dynamic range and spatial selectivity for the peri-modiolar position at the basal end of the cochlea, with minimal influence of neural degeneration. At the apical end of the array (1.5 cochlear turns), the dynamic range and the spatial selectivity are limited due to the occurrence of cross-turn stimulation, with the exception of the condition without neural degeneration and with the electrode array along the lateral wall of scala tympani. The eCAP simulations indicate that a large P(0) peak occurs before the N(1)P(1) complex when the fibers are not degenerated. The absence of this peak might be used as an indicator for neural degeneration.
Tuning Recurrent Neural Networks for Recognizing Handwritten Arabic Words
Qaralleh, Esam
2013-10-01
Artificial neural networks have the abilities to learn by example and are capable of solving problems that are hard to solve using ordinary rule-based programming. They have many design parameters that affect their performance such as the number and sizes of the hidden layers. Large sizes are slow and small sizes are generally not accurate. Tuning the neural network size is a hard task because the design space is often large and training is often a long process. We use design of experiments techniques to tune the recurrent neural network used in an Arabic handwriting recognition system. We show that best results are achieved with three hidden layers and two subsampling layers. To tune the sizes of these five layers, we use fractional factorial experiment design to limit the number of experiments to a feasible number. Moreover, we replicate the experiment configuration multiple times to overcome the randomness in the training process. The accuracy and time measurements are analyzed and modeled. The two models are then used to locate network sizes that are on the Pareto optimal frontier. The approach described in this paper reduces the label error from 26.2% to 19.8%.
Schmitt, Oliver; Steinmann, Paul
2017-09-01
We introduce a manufacturing constraint for controlling the minimum member size in structural shape optimization problems, which is for example of interest for components fabricated in a molding process. In a parameter-free approach, whereby the coordinates of the FE boundary nodes are used as design variables, the challenging task is to find a generally valid definition for the thickness of non-parametric geometries in terms of their boundary nodes. Therefore we use the medial axis, which is the union of all points with at least two closest points on the boundary of the domain. Since the effort for the exact computation of the medial axis of geometries given by their FE discretization highly increases with the number of surface elements we use the distance function instead to approximate the medial axis by a cloud of points. The approximation is demonstrated on three 2D examples. Moreover, the formulation of a minimum thickness constraint is applied to a sensitivity-based shape optimization problem of one 2D and one 3D model.
Optimal capacitor placement and sizing using combined fuzzy ...
African Journals Online (AJOL)
Then the sizing of the capacitors is modeled as an optimization problem and the objective function (loss minimization) is solved using Hybrid Particle Swarm Optimization (HPSO) technique. A case study with an IEEE 34 bus distribution feeder is presented to illustrate the applicability of the algorithm. A comparison is made ...
Fast particle characterization using digital holography and neural networks.
Schneider, B; Dambre, J; Bienstman, P
2016-01-01
We propose using a neural network approach in conjunction with digital holographic microscopy in order to rapidly determine relevant parameters such as the core and shell diameter of coated, non-absorbing spheres. We do so without requiring a time-consuming reconstruction of the cell image. In contrast to previous approaches, we are able to obtain a continuous value for parameters such as size, as opposed to binning into a discrete number of categories. Also, we are able to separately determine both core and shell diameter. For simulated particle sizes ranging between 7 and 20 μm, we obtain accuracies of (4.4±0.2)% and (0.74±0.01)% for the core and shell diameter, respectively.
Neural Networks for Optimal Control
DEFF Research Database (Denmark)
Sørensen, O.
1995-01-01
Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process.......Two neural networks are trained to act as an observer and a controller, respectively, to control a non-linear, multi-variable process....
Liu, Yan-Jun; Gao, Ying; Tong, Shaocheng; Chen, C L Philip
2016-01-01
In this paper, an effective adaptive control approach is constructed to stabilize a class of nonlinear discrete-time systems, which contain unknown functions, unknown dead-zone input, and unknown control direction. Different from linear dead zone, the dead zone, in this paper, is a kind of nonlinear dead zone. To overcome the noncausal problem, which leads to the control scheme infeasible, the systems can be transformed into a m -step-ahead predictor. Due to nonlinear dead-zone appearance, the transformed predictor still contains the nonaffine function. In addition, it is assumed that the gain function of dead-zone input and the control direction are unknown. These conditions bring about the difficulties and the complicacy in the controller design. Thus, the implicit function theorem is applied to deal with nonaffine dead-zone appearance, the problem caused by the unknown control direction can be resolved through applying the discrete Nussbaum gain, and the neural networks are used to approximate the unknown function. Based on the Lyapunov theory, all the signals of the resulting closed-loop system are proved to be semiglobal uniformly ultimately bounded. Moreover, the tracking error is proved to be regulated to a small neighborhood around zero. The feasibility of the proposed approach is demonstrated by a simulation example.
Deng, Lei; Jiao, Peng; Pei, Jing; Wu, Zhenzhi; Li, Guoqi
2018-04-01
Although deep neural networks (DNNs) are being a revolutionary power to open up the AI era, the notoriously huge hardware overhead has challenged their applications. Recently, several binary and ternary networks, in which the costly multiply-accumulate operations can be replaced by accumulations or even binary logic operations, make the on-chip training of DNNs quite promising. Therefore there is a pressing need to build an architecture that could subsume these networks under a unified framework that achieves both higher performance and less overhead. To this end, two fundamental issues are yet to be addressed. The first one is how to implement the back propagation when neuronal activations are discrete. The second one is how to remove the full-precision hidden weights in the training phase to break the bottlenecks of memory/computation consumption. To address the first issue, we present a multi-step neuronal activation discretization method and a derivative approximation technique that enable the implementing the back propagation algorithm on discrete DNNs. While for the second issue, we propose a discrete state transition (DST) methodology to constrain the weights in a discrete space without saving the hidden weights. Through this way, we build a unified framework that subsumes the binary or ternary networks as its special cases, and under which a heuristic algorithm is provided at the website https://github.com/AcrossV/Gated-XNOR. More particularly, we find that when both the weights and activations become ternary values, the DNNs can be reduced to sparse binary networks, termed as gated XNOR networks (GXNOR-Nets) since only the event of non-zero weight and non-zero activation enables the control gate to start the XNOR logic operations in the original binary networks. This promises the event-driven hardware design for efficient mobile intelligence. We achieve advanced performance compared with state-of-the-art algorithms. Furthermore, the computational sparsity
Estimation of LOCA break size using cascaded Fuzzy neural networks
Energy Technology Data Exchange (ETDEWEB)
Choi, Geon Pil; Yoo, Kwae Hwan; Back, Ju Hyun; Na, Man Gyun [Dept. of Nuclear Engineering, Chosun University, Gwangju (Korea, Republic of)
2017-04-15
Operators of nuclear power plants may not be equipped with sufficient information during a loss-of-coolant accident (LOCA), which can be fatal, or they may not have sufficient time to analyze the information they do have, even if this information is adequate. It is not easy to predict the progression of LOCAs in nuclear power plants. Therefore, accurate information on the LOCA break position and size should be provided to efficiently manage the accident. In this paper, the LOCA break size is predicted using a cascaded fuzzy neural network (CFNN) model. The input data of the CFNN model are the time-integrated values of each measurement signal for an initial short-time interval after a reactor scram. The training of the CFNN model is accomplished by a hybrid method combined with a genetic algorithm and a least squares method. As a result, LOCA break size is estimated exactly by the proposed CFNN model.
Gerstner, Wulfram
2017-01-01
Neural population equations such as neural mass or field models are widely used to study brain activity on a large scale. However, the relation of these models to the properties of single neurons is unclear. Here we derive an equation for several interacting populations at the mesoscopic scale starting from a microscopic model of randomly connected generalized integrate-and-fire neuron models. Each population consists of 50–2000 neurons of the same type but different populations account for different neuron types. The stochastic population equations that we find reveal how spike-history effects in single-neuron dynamics such as refractoriness and adaptation interact with finite-size fluctuations on the population level. Efficient integration of the stochastic mesoscopic equations reproduces the statistical behavior of the population activities obtained from microscopic simulations of a full spiking neural network model. The theory describes nonlinear emergent dynamics such as finite-size-induced stochastic transitions in multistable networks and synchronization in balanced networks of excitatory and inhibitory neurons. The mesoscopic equations are employed to rapidly integrate a model of a cortical microcircuit consisting of eight neuron types, which allows us to predict spontaneous population activities as well as evoked responses to thalamic input. Our theory establishes a general framework for modeling finite-size neural population dynamics based on single cell and synapse parameters and offers an efficient approach to analyzing cortical circuits and computations. PMID:28422957
Combined Optimal Sizing and Control for a Hybrid Tracked Vehicle
Directory of Open Access Journals (Sweden)
Huei Peng
2012-11-01
Full Text Available The optimal sizing and control of a hybrid tracked vehicle is presented and solved in this paper. A driving schedule obtained from field tests is used to represent typical tracked vehicle operations. Dynamics of the diesel engine-permanent magnetic AC synchronous generator set, the lithium-ion battery pack, and the power split between them are modeled and validated through experiments. Two coupled optimizations, one for the plant parameters, forming the outer optimization loop and one for the control strategy, forming the inner optimization loop, are used to achieve minimum fuel consumption under the selected driving schedule. The dynamic programming technique is applied to find the optimal controller in the inner loop while the component parameters are optimized iteratively in the outer loop. The results are analyzed, and the relationship between the key parameters is observed to keep the optimal sizing and control simultaneously.
Positivity for Convective Semi-discretizations
Fekete, Imre
2017-04-19
We propose a technique for investigating stability properties like positivity and forward invariance of an interval for method-of-lines discretizations, and apply the technique to study positivity preservation for a class of TVD semi-discretizations of 1D scalar hyperbolic conservation laws. This technique is a generalization of the approach suggested in Khalsaraei (J Comput Appl Math 235(1): 137–143, 2010). We give more relaxed conditions on the time-step for positivity preservation for slope-limited semi-discretizations integrated in time with explicit Runge–Kutta methods. We show that the step-size restrictions derived are sharp in a certain sense, and that many higher-order explicit Runge–Kutta methods, including the classical 4th-order method and all non-confluent methods with a negative Butcher coefficient, cannot generally maintain positivity for these semi-discretizations under any positive step size. We also apply the proposed technique to centered finite difference discretizations of scalar hyperbolic and parabolic problems.
Linear Model for Optimal Distributed Generation Size Predication
Directory of Open Access Journals (Sweden)
Ahmed Al Ameri
2017-01-01
Full Text Available This article presents a linear model predicting optimal size of Distributed Generation (DG that addresses the minimum power loss. This method is based fundamentally on strong coupling between active power and voltage angle as well as between reactive power and voltage magnitudes. This paper proposes simplified method to calculate the total power losses in electrical grid for different distributed generation sizes and locations. The method has been implemented and tested on several IEEE bus test systems. The results show that the proposed method is capable of predicting approximate optimal size of DG when compared with precision calculations. The method that linearizes a complex model showed a good result, which can actually reduce processing time required. The acceptable accuracy with less time and memory required can help the grid operator to assess power system integrated within large-scale distribution generation.
Beneficial role of noise in artificial neural networks
International Nuclear Information System (INIS)
Monterola, Christopher; Saloma, Caesar; Zapotocky, Martin
2008-01-01
We demonstrate enhancement of neural networks efficacy to recognize frequency encoded signals and/or to categorize spatial patterns of neural activity as a result of noise addition. For temporal information recovery, noise directly added to the receiving neurons allow instantaneous improvement of signal-to-noise ratio [Monterola and Saloma, Phys. Rev. Lett. 2002]. For spatial patterns however, recurrence is necessary to extend and homogenize the operating range of a feed-forward neural network [Monterola and Zapotocky, Phys. Rev. E 2005]. Finally, using the size of the basin of attraction of the networks learned patterns (dynamical fixed points), a procedure for estimating the optimal noise is demonstrated
Design of a centrifugal compressor impeller using multi-objective optimization algorithm
International Nuclear Information System (INIS)
Kim, Jin Hyuk; Husain, Afzal; Kim, Kwang Yong; Choi, Jae Ho
2009-01-01
This paper presents a design optimization of a centrifugal compressor impeller with hybrid multi-objective evolutionary algorithm (hybrid MOEA). Reynolds-averaged Navier-Stokes equations with shear stress transport turbulence model are discretized by finite volume approximations and solved on hexahedral grids for flow analyses. Two objectives, i.e., isentropic efficiency and total pressure ratio are selected with four design variables defining impeller hub and shroud contours in meridional contours to optimize the system. Non-dominated Sorting of Genetic Algorithm (NSGA-II) with ε-constraint strategy for local search coupled with Radial Basis Neural Network model is used for multi-objective optimization. The optimization results show that isentropic efficiencies and total pressure ratios of the five cluster points at the Pareto-optimal solutions are enhanced by multi-objective optimization.
Design of a centrifugal compressor impeller using multi-objective optimization algorithm
Energy Technology Data Exchange (ETDEWEB)
Kim, Jin Hyuk; Husain, Afzal; Kim, Kwang Yong [Inha University, Incheon (Korea, Republic of); Choi, Jae Ho [Samsung Techwin Co., Ltd., Changwon (Korea, Republic of)
2009-07-01
This paper presents a design optimization of a centrifugal compressor impeller with hybrid multi-objective evolutionary algorithm (hybrid MOEA). Reynolds-averaged Navier-Stokes equations with shear stress transport turbulence model are discretized by finite volume approximations and solved on hexahedral grids for flow analyses. Two objectives, i.e., isentropic efficiency and total pressure ratio are selected with four design variables defining impeller hub and shroud contours in meridional contours to optimize the system. Non-dominated Sorting of Genetic Algorithm (NSGA-II) with {epsilon}-constraint strategy for local search coupled with Radial Basis Neural Network model is used for multi-objective optimization. The optimization results show that isentropic efficiencies and total pressure ratios of the five cluster points at the Pareto-optimal solutions are enhanced by multi-objective optimization.
International Nuclear Information System (INIS)
Taraglio, S.; Zanela, A.
1997-03-01
An optimization method for some of the CNN's (Cellular Neural Network) parameters, based on evolutionary strategies, is proposed. The new class of feedback template found is more effective in extracting features from the images that an autonomous vehicle acquires, than in the previous CNN's literature
Multiobjective optimization of building design using genetic algorithm and artificial neural network
Energy Technology Data Exchange (ETDEWEB)
Magnier, L.; Zhou, L.; Haghighat, F. [Concordia Univ., Centre for Building Studies, Montreal, PQ (Canada). Dept. of Building, Civil and Environmental Engineering
2008-07-01
This paper addressed the challenge of designing modern buildings that are energy efficient, affordable, environmentally sound and comfortable for occupants. Building optimization is a time consuming process when so many objectives must be met. In particular, the use of genetic algorithm (GA) for building design has limitations due to the high number of simulations required. This paper presented an efficient approach to overcome the limitations of GA for building design. The approach expanded the GA methodology to multiobjective optimization. The GA integrating neural network (GAINN) approach first uses a simulation-based artificial neural network (ANN) to characterize building behaviour, and then combines it with a GA for optimization. The process was shown to provide fast and reliable optimization. GAINN was further improved by integrating multiobjective evolutionary algorithms (MOEAs). Two new MOEAs named NSGAINN and PLAGUE were designed for the proposed methodology. The purpose of creating a new MOEA was to take advantage of GAINN fast evaluations. This paper presented bench test results and compared them with with NSGA-2. A previous case study using GAINN methodology was re-optimized with the newly developed MOEA. The design to be optimized was a ventilation system of a standard office room in the summer, with 2 occupants and 4 underfloor air distribution diffusers. The objectives included thermal comfort, indoor air quality, and energy conservation for cooling. The control variables were temperature of the air supply, speed of air supply, distance from the diffuser to the occupant, and the distance from the return grill to the contaminant source. The results showed that the newly presented GAINN methodology was better in both convergence and range of choices compared to a weighted sum GA. 13 refs., 2 tabs., 9 figs.
Mohanty, Itishree; Chintha, Appa Rao; Kundu, Saurabh
2018-06-01
The optimization of process parameters and composition is essential to achieve the desired properties with minimal additions of alloying elements in microalloyed steels. In some cases, it may be possible to substitute such steels for those which are more richly alloyed. However, process control involves a larger number of parameters, making the relationship between structure and properties difficult to assess. In this work, neural network models have been developed to estimate the mechanical properties of steels containing Nb + V or Nb + Ti. The outcomes have been validated by thermodynamic calculations and plant data. It has been shown that subtle thermodynamic trends can be captured by the neural network model. Some experimental rolling data have also been used to support the model, which in addition has been applied to calculate the costs of optimizing microalloyed steel. The generated pareto fronts identify many combinations of strength and elongation, making it possible to select composition and process parameters for a range of applications. The ANN model and the optimization model are being used for prediction of properties in a running plant and for development of new alloys, respectively.
An optimization-based framework for anisotropic simplex mesh adaptation
Yano, Masayuki; Darmofal, David L.
2012-09-01
We present a general framework for anisotropic h-adaptation of simplex meshes. Given a discretization and any element-wise, localizable error estimate, our adaptive method iterates toward a mesh that minimizes error for a given degrees of freedom. Utilizing mesh-metric duality, we consider a continuous optimization problem of the Riemannian metric tensor field that provides an anisotropic description of element sizes. First, our method performs a series of local solves to survey the behavior of the local error function. This information is then synthesized using an affine-invariant tensor manipulation framework to reconstruct an approximate gradient of the error function with respect to the metric tensor field. Finally, we perform gradient descent in the metric space to drive the mesh toward optimality. The method is first demonstrated to produce optimal anisotropic meshes minimizing the L2 projection error for a pair of canonical problems containing a singularity and a singular perturbation. The effectiveness of the framework is then demonstrated in the context of output-based adaptation for the advection-diffusion equation using a high-order discontinuous Galerkin discretization and the dual-weighted residual (DWR) error estimate. The method presented provides a unified framework for optimizing both the element size and anisotropy distribution using an a posteriori error estimate and enables efficient adaptation of anisotropic simplex meshes for high-order discretizations.
Craft, David
2010-10-01
A discrete set of points and their convex combinations can serve as a sparse representation of the Pareto surface in multiple objective convex optimization. We develop a method to evaluate the quality of such a representation, and show by example that in multiple objective radiotherapy planning, the number of Pareto optimal solutions needed to represent Pareto surfaces of up to five dimensions grows at most linearly with the number of objectives. The method described is also applicable to the representation of convex sets. Copyright © 2009 Associazione Italiana di Fisica Medica. Published by Elsevier Ltd. All rights reserved.
Liu, Hongjian; Wang, Zidong; Shen, Bo; Huang, Tingwen; Alsaadi, Fuad E
2018-06-01
This paper is concerned with the globally exponential stability problem for a class of discrete-time stochastic memristive neural networks (DSMNNs) with both leakage delays as well as probabilistic time-varying delays. For the probabilistic delays, a sequence of Bernoulli distributed random variables is utilized to determine within which intervals the time-varying delays fall at certain time instant. The sector-bounded activation function is considered in the addressed DSMNN. By taking into account the state-dependent characteristics of the network parameters and choosing an appropriate Lyapunov-Krasovskii functional, some sufficient conditions are established under which the underlying DSMNN is globally exponentially stable in the mean square. The derived conditions are made dependent on both the leakage and the probabilistic delays, and are therefore less conservative than the traditional delay-independent criteria. A simulation example is given to show the effectiveness of the proposed stability criterion. Copyright © 2018 Elsevier Ltd. All rights reserved.
On the dynamic rounding-off in analogue and RF optimal circuit sizing
Kotti, Mouna; Fakhfakh, Mourad; Fino, Maria Helena
2014-04-01
Frequently used approaches to solve discrete multivariable optimisation problems consist of computing solutions using a continuous optimisation technique. Then, using heuristics, the variables are rounded-off to their nearest available discrete values to obtain a discrete solution. Indeed, in many engineering problems, and particularly in analogue circuit design, component values, such as the geometric dimensions of the transistors, the number of fingers in an integrated capacitor or the number of turns in an integrated inductor, cannot be chosen arbitrarily since they have to obey to some technology sizing constraints. However, rounding-off the variables values a posteriori and can lead to infeasible solutions (solutions that are located too close to the feasible solution frontier) or degradation of the obtained results (expulsion from the neighbourhood of a 'sharp' optimum) depending on how the added perturbation affects the solution. Discrete optimisation techniques, such as the dynamic rounding-off technique (DRO) are, therefore, needed to overcome the previously mentioned situation. In this paper, we deal with an improvement of the DRO technique. We propose a particle swarm optimisation (PSO)-based DRO technique, and we show, via some analog and RF-examples, the necessity to implement such a routine into continuous optimisation algorithms.
Energy Technology Data Exchange (ETDEWEB)
Taraglio, S. [ENEA, Centro Ricerche Casaccia, Rome (Italy). Dipt. Innovazione; Zanela, A. [Rome Univ. `La Sapienza` (Italy). Dipt. di Fisica
1997-03-01
An optimization method for some of the CNN`s (Cellular Neural Network) parameters, based on evolutionary strategies, is proposed. The new class of feedback template found is more effective in extracting features from the images that an autonomous vehicle acquires, than in the previous CNN`s literature.
Directory of Open Access Journals (Sweden)
Xiaofeng Lv
2018-01-01
Full Text Available Sensor data-based test selection optimization is the basis for designing a test work, which ensures that the system is tested under the constraint of the conventional indexes such as fault detection rate (FDR and fault isolation rate (FIR. From the perspective of equipment maintenance support, the ambiguity isolation has a significant effect on the result of test selection. In this paper, an improved test selection optimization model is proposed by considering the ambiguity degree of fault isolation. In the new model, the fault test dependency matrix is adopted to model the correlation between the system fault and the test group. The objective function of the proposed model is minimizing the test cost with the constraint of FDR and FIR. The improved chaotic discrete particle swarm optimization (PSO algorithm is adopted to solve the improved test selection optimization model. The new test selection optimization model is more consistent with real complicated engineering systems. The experimental result verifies the effectiveness of the proposed method.
Alfa, Attahiru S
2016-01-01
This book introduces the theoretical fundamentals for modeling queues in discrete-time, and the basic procedures for developing queuing models in discrete-time. There is a focus on applications in modern telecommunication systems. It presents how most queueing models in discrete-time can be set up as discrete-time Markov chains. Techniques such as matrix-analytic methods (MAM) that can used to analyze the resulting Markov chains are included. This book covers single node systems, tandem system and queueing networks. It shows how queues with time-varying parameters can be analyzed, and illustrates numerical issues associated with computations for the discrete-time queueing systems. Optimal control of queues is also covered. Applied Discrete-Time Queues targets researchers, advanced-level students and analysts in the field of telecommunication networks. It is suitable as a reference book and can also be used as a secondary text book in computer engineering and computer science. Examples and exercises are includ...
Poultangari, Iman; Shahnazi, Reza; Sheikhan, Mansour
2012-09-01
In order to control the pitch angle of blades in wind turbines, commonly the proportional and integral (PI) controller due to its simplicity and industrial usability is employed. The neural networks and evolutionary algorithms are tools that provide a suitable ground to determine the optimal PI gains. In this paper, a radial basis function (RBF) neural network based PI controller is proposed for collective pitch control (CPC) of a 5-MW wind turbine. In order to provide an optimal dataset to train the RBF neural network, particle swarm optimization (PSO) evolutionary algorithm is used. The proposed method does not need the complexities, nonlinearities and uncertainties of the system under control. The simulation results show that the proposed controller has satisfactory performance. Copyright © 2012 ISA. Published by Elsevier Ltd. All rights reserved.
Offspring fitness and individual optimization of clutch size
Both, C.; Tinbergen, J. M.; Noordwijk, A. J. van
1998-01-01
Within-year variation in clutch size has been claimed to be an adaptation to variation in the individual capacity to raise offspring. We tested this hypothesis by manipulating brood size to one common size, and predicted that if clutch size is individually optimized, then birds with originally large clutches have a higher fitness than birds with originally small clutches. No evidence was found that fitness was related to the original clutch size, and in this population clutch size is thus not related to the parental capacity to raise offspring. However, offspring from larger original clutches recruited better than their nest mates that came from smaller original clutches. This suggests that early maternal or genetic variation in viability is related to clutch size.
Inverse Reliability Task: Artificial Neural Networks and Reliability-Based Optimization Approaches
Lehký , David; Slowik , Ondřej; Novák , Drahomír
2014-01-01
Part 7: Genetic Algorithms; International audience; The paper presents two alternative approaches to solve inverse reliability task – to determine the design parameters to achieve desired target reliabilities. The first approach is based on utilization of artificial neural networks and small-sample simulation Latin hypercube sampling. The second approach considers inverse reliability task as reliability-based optimization task using double-loop method and also small-sample simulation. Efficie...
Introductory discrete mathematics
Balakrishnan, V K
2010-01-01
This concise text offers an introduction to discrete mathematics for undergraduate students in computer science and mathematics. Mathematics educators consider it vital that their students be exposed to a course in discrete methods that introduces them to combinatorial mathematics and to algebraic and logical structures focusing on the interplay between computer science and mathematics. The present volume emphasizes combinatorics, graph theory with applications to some stand network optimization problems, and algorithms to solve these problems.Chapters 0-3 cover fundamental operations involv
Lin, Albert; Fu, Sze-Ming; Chung, Yen-Kai; Lai, Shih-Yun; Tseng, Chi-Wei
2013-01-14
Surface plasmon enhancement has been proposed as a way to achieve higher absorption for thin-film photovoltaics, where surface plasmon polariton(SPP) and localized surface plasmon (LSP) are shown to provide dense near field and far field light scattering. Here it is shown that controlled far-field light scattering can be achieved using successive coupling between surface plasmonic (SP) nano-particles. Through genetic algorithm (GA) optimization, energy transfer between discrete nano-particles (ETDNP) is identified, which enhances solar cell efficiency. The optimized energy transfer structure acts like lumped-element transmission line and can properly alter the direction of photon flow. Increased in-plane component of wavevector is thus achieved and photon path length is extended. In addition, Wood-Rayleigh anomaly, at which transmission minimum occurs, is avoided through GA optimization. Optimized energy transfer structure provides 46.95% improvement over baseline planar cell. It achieves larger angular scattering capability compared to conventional surface plasmon polariton back reflector structure and index-guided structure due to SP energy transfer through mode coupling. Via SP mediated energy transfer, an alternative way to control the light flow inside thin-film is proposed, which can be more efficient than conventional index-guided mode using total internal reflection (TIR).
Yu, Chaoyin; Yuan, Zhengwu; Wu, Yuanfeng
2017-10-01
Hyperspectral image unmixing is an important part of hyperspectral data analysis. The mixed pixel decomposition consists of two steps, endmember (the unique signatures of pure ground components) extraction and abundance (the proportion of each endmember in each pixel) estimation. Recently, a Discrete Particle Swarm Optimization algorithm (DPSO) was proposed for accurately extract endmembers with high optimal performance. However, the DPSO algorithm shows very high computational complexity, which makes the endmember extraction procedure very time consuming for hyperspectral image unmixing. Thus, in this paper, the DPSO endmember extraction algorithm was parallelized, implemented on the CUDA (GPU K20) platform, and evaluated by real hyperspectral remote sensing data. The experimental results show that with increasing the number of particles the parallelized version obtained much higher computing efficiency while maintain the same endmember exaction accuracy.
Delay-area trade-off for MPRM circuits based on hybrid discrete particle swarm optimization
International Nuclear Information System (INIS)
Jiang Zhidi; Wang Zhenhai; Wang Pengjun
2013-01-01
Polarity optimization for mixed polarity Reed—Muller (MPRM) circuits is a combinatorial issue. Based on the study on discrete particle swarm optimization (DPSO) and mixed polarity, the corresponding relation between particle and mixed polarity is established, and the delay-area trade-off of large-scale MPRM circuits is proposed. Firstly, mutation operation and elitist strategy in genetic algorithm are incorporated into DPSO to further develop a hybrid DPSO (HDPSO). Then the best polarity for delay and area trade-off is searched for large-scale MPRM circuits by combining the HDPSO and a delay estimation model. Finally, the proposed algorithm is testified by MCNC Benchmarks. Experimental results show that HDPSO achieves a better convergence than DPSO in terms of search capability for large-scale MPRM circuits. (semiconductor integrated circuits)
Development of neural basis for chinese orthographic neighborhood size effect.
Zhao, Jing; Li, Qing-Lin; Ding, Guo-Sheng; Bi, Hong-Yan
2016-02-01
The brain activity of orthographic neighborhood size (N size) effect in Chinese character naming has been studied in adults, meanwhile behavioral studies have revealed a developmental trend of Chinese N-size effect in developing readers. However, it is unclear whether and how the neural mechanism of N-size effect changes in Chinese children along with development. Here we address this issue using functional magnetic resonance imaging. Forty-four students from the 3(rd) , 5(th) , and 7(th) grades were scanned during silent naming of Chinese characters. After scanning, all participants took part in an overt naming test outside the scanner, and results of the naming task showed that the 3(rd) graders named characters from large neighborhoods faster than those from small neighborhoods, revealing a facilitatory N-size effect; the 5(th) graders showed null N-size effect while the 7(th) graders showed an inhibitory N-size effect. Neuroimaging results revealed that only the 3(rd) graders exhibited a significant N-size effect in the left middle occipital activity, with greater activation for large N-size characters. Results of 5(th) and 7(th) graders showed significant N-size effects in the left middle frontal gyrus, in which 5(th) graders induced greater activation in large N-size condition than in small N-size condition, while 7(th) graders exhibited an opposite effect which was similar to the adult pattern reported in a previous study. The current findings suggested the transition from broadly tuned to finely tuned orthographic representation with reading development, and the inhibition from neighbors' phonology for higher graders. Hum Brain Mapp 37:632-647, 2016. © 2015 Wiley Periodicals, Inc. © 2015 Wiley Periodicals, Inc.
International Nuclear Information System (INIS)
Rao, S.I.; Dimiduk, D.M.; Parthasarathy, T.A.; Uchic, M.D.; Tang, M.; Woodward, C.
2008-01-01
Recent experimental studies have revealed that micrometer-scale face-centered cubic (fcc) crystals show strong strengthening effects, even at high initial dislocation densities. We use large-scale three-dimensional discrete dislocation simulations (DDS) to explicitly model the deformation behavior of fcc Ni microcrystals in the size range of 0.5-20 μm. This study shows that two size-sensitive athermal hardening processes, beyond forest hardening, are sufficient to develop the dimensional scaling of the flow stress, stochastic stress variation, flow intermittency and high initial strain-hardening rates, similar to experimental observations for various materials. One mechanism, source-truncation hardening, is especially potent in micrometer-scale volumes. A second mechanism, termed exhaustion hardening, results from a breakdown of the mean-field conditions for forest hardening in small volumes, thus biasing the statistics of ordinary dislocation processes
PID control design for chaotic synchronization using a tribes optimization approach
Energy Technology Data Exchange (ETDEWEB)
Santos Coelho, Leandro dos [Industrial and Systems Engineering Graduate Program, LAS/PPGEPS, Pontifical Catholic University of Parana, PUCPR, Imaculada Conceicao, 1155, 80215-901 Curitiba, Parana (Brazil)], E-mail: leandro.coelho@pucpr.br; Andrade Bernert, Diego Luis de [Industrial and Systems Engineering Graduate Program, LAS/PPGEPS, Pontifical Catholic University of Parana, PUCPR, Imaculada Conceicao, 1155, 80215-901 Curitiba, Parana (Brazil)], E-mail: dbernert@gmail.com
2009-10-15
Recently, the investigation of synchronization and control problems for discrete chaotic systems has stimulated a wide range of research activity including both theoretical studies and practical applications. This paper deals with the tuning of a proportional-integral-derivative (PID) controller using a modified Tribes optimization algorithm based on truncated chaotic Zaslavskii map (MTribes) for synchronization of two identical discrete chaotic systems subject the different initial conditions. The Tribes algorithm is inspired by the social behavior of bird flocking and is also an optimization adaptive procedure that does not require sociometric or swarm size parameter tuning. Numerical simulations are given to show the effectiveness of the proposed synchronization method. In addition, some comparisons of the MTribes optimization algorithm with other continuous optimization methods, including classical Tribes algorithm and particle swarm optimization approaches, are presented.
PID control design for chaotic synchronization using a tribes optimization approach
International Nuclear Information System (INIS)
Santos Coelho, Leandro dos; Andrade Bernert, Diego Luis de
2009-01-01
Recently, the investigation of synchronization and control problems for discrete chaotic systems has stimulated a wide range of research activity including both theoretical studies and practical applications. This paper deals with the tuning of a proportional-integral-derivative (PID) controller using a modified Tribes optimization algorithm based on truncated chaotic Zaslavskii map (MTribes) for synchronization of two identical discrete chaotic systems subject the different initial conditions. The Tribes algorithm is inspired by the social behavior of bird flocking and is also an optimization adaptive procedure that does not require sociometric or swarm size parameter tuning. Numerical simulations are given to show the effectiveness of the proposed synchronization method. In addition, some comparisons of the MTribes optimization algorithm with other continuous optimization methods, including classical Tribes algorithm and particle swarm optimization approaches, are presented.
Landscape encodings enhance optimization.
Directory of Open Access Journals (Sweden)
Konstantin Klemm
Full Text Available Hard combinatorial optimization problems deal with the search for the minimum cost solutions (ground states of discrete systems under strong constraints. A transformation of state variables may enhance computational tractability. It has been argued that these state encodings are to be chosen invertible to retain the original size of the state space. Here we show how redundant non-invertible encodings enhance optimization by enriching the density of low-energy states. In addition, smooth landscapes may be established on encoded state spaces to guide local search dynamics towards the ground state.
Landscape Encodings Enhance Optimization
Klemm, Konstantin; Mehta, Anita; Stadler, Peter F.
2012-01-01
Hard combinatorial optimization problems deal with the search for the minimum cost solutions (ground states) of discrete systems under strong constraints. A transformation of state variables may enhance computational tractability. It has been argued that these state encodings are to be chosen invertible to retain the original size of the state space. Here we show how redundant non-invertible encodings enhance optimization by enriching the density of low-energy states. In addition, smooth landscapes may be established on encoded state spaces to guide local search dynamics towards the ground state. PMID:22496860
International Nuclear Information System (INIS)
Moosavi, K.; Setayeshi, S.; Maragheh, M.Gh.; Ahmadi, S.J.; Kardan, M.R.; Banaem, L.M.
2009-01-01
In this study, an experimental design using artificial neural networks for an optimization on the strontium separation model for fission products (inactive trace elements) is investigated. The goal is to optimize the separation parameters to achieve maximum amount of strontium that is separated from the fission products. The result of the optimization method causes a proper purity of Strontium-89 that was separated from the fission products. It is also shown that ANN may be establish a method to optimize the separation model.
International Nuclear Information System (INIS)
Wang Jun; Liu Mingzhe; Li Zhe; Li Lei; Shi Rui; Tuo Xianguo
2015-01-01
The quantitative elemental content analysis is difficult due to the uniform effect, particle effect and the element matrix effect, etc, when using energy dispersive X-ray fluorescence (EDXRF) technique. In this paper, a hybrid approach of genetic algorithm (GA) and back propagation (BP) neural network was proposed without considering the complex relationship between the concentration and intensity. The aim of GA optimized BP was to get better network initial weights and thresholds. The basic idea was that the reciprocal of the mean square error of the initialization BP neural network was set as the fitness value of the individual in GA, and the initial weights and thresholds were replaced by individuals, and then the optimal individual was sought by selection, crossover and mutation operations, finally a new BP neural network model was created with the optimal initial weights and thresholds. The calculation results of quantitative analysis of titanium and iron contents for five types of ore bodies in Panzhihua Mine show that the results of classification prediction are far better than that of overall forecasting, and relative errors of 76.7% samples are less than 2% compared with chemical analysis values, which demonstrates the effectiveness of the proposed method. (authors)
Designing Artificial Neural Networks Using Particle Swarm Optimization Algorithms.
Garro, Beatriz A; Vázquez, Roberto A
2015-01-01
Artificial Neural Network (ANN) design is a complex task because its performance depends on the architecture, the selected transfer function, and the learning algorithm used to train the set of synaptic weights. In this paper we present a methodology that automatically designs an ANN using particle swarm optimization algorithms such as Basic Particle Swarm Optimization (PSO), Second Generation of Particle Swarm Optimization (SGPSO), and a New Model of PSO called NMPSO. The aim of these algorithms is to evolve, at the same time, the three principal components of an ANN: the set of synaptic weights, the connections or architecture, and the transfer functions for each neuron. Eight different fitness functions were proposed to evaluate the fitness of each solution and find the best design. These functions are based on the mean square error (MSE) and the classification error (CER) and implement a strategy to avoid overtraining and to reduce the number of connections in the ANN. In addition, the ANN designed with the proposed methodology is compared with those designed manually using the well-known Back-Propagation and Levenberg-Marquardt Learning Algorithms. Finally, the accuracy of the method is tested with different nonlinear pattern classification problems.
Genetic algorithm for neural networks optimization
Setyawati, Bina R.; Creese, Robert C.; Sahirman, Sidharta
2004-11-01
This paper examines the forecasting performance of multi-layer feed forward neural networks in modeling a particular foreign exchange rates, i.e. Japanese Yen/US Dollar. The effects of two learning methods, Back Propagation and Genetic Algorithm, in which the neural network topology and other parameters fixed, were investigated. The early results indicate that the application of this hybrid system seems to be well suited for the forecasting of foreign exchange rates. The Neural Networks and Genetic Algorithm were programmed using MATLAB«.
Lin, Na; Chen, Hanning; Jing, Shikai; Liu, Fang; Liang, Xiaodan
2017-03-01
In recent years, symbiosis as a rich source of potential engineering applications and computational model has attracted more and more attentions in the adaptive complex systems and evolution computing domains. Inspired by different symbiotic coevolution forms in nature, this paper proposed a series of multi-swarm particle swarm optimizers called PS 2 Os, which extend the single population particle swarm optimization (PSO) algorithm to interacting multi-swarms model by constructing hierarchical interaction topologies and enhanced dynamical update equations. According to different symbiotic interrelationships, four versions of PS 2 O are initiated to mimic mutualism, commensalism, predation, and competition mechanism, respectively. In the experiments, with five benchmark problems, the proposed algorithms are proved to have considerable potential for solving complex optimization problems. The coevolutionary dynamics of symbiotic species in each PS 2 O version are also studied respectively to demonstrate the heterogeneity of different symbiotic interrelationships that effect on the algorithm's performance. Then PS 2 O is used for solving the radio frequency identification (RFID) network planning (RNP) problem with a mixture of discrete and continuous variables. Simulation results show that the proposed algorithm outperforms the reference algorithms for planning RFID networks, in terms of optimization accuracy and computation robustness.
Sizing Optimization and Strength Analysis for Spread-type Gear Reducers
Directory of Open Access Journals (Sweden)
Wei-Hsuan Hsu
2014-08-01
Full Text Available A reducer is now developed towards the trend of customization service and cost-saving. In this study, a sizing program for the reducer has been developed in order to replace the manual sizing process. We aim at the total center distance of the gear reducer for optimization to reduce gear volume and weight. Also, we checked constrains such as, tooth root bending, tooth contact strength, gear shaft endangered cross-section, bearing life, gear shaft deflection, and torsion angle deformation, etc., to obtain reliable drive strength. Comparisons of sizes and weights before and after optimization confirm that the purpose for reducing production cost is achieved.
A neural network approach to job-shop scheduling.
Zhou, D N; Cherkassky, V; Baldwin, T R; Olson, D E
1991-01-01
A novel analog computational network is presented for solving NP-complete constraint satisfaction problems, i.e. job-shop scheduling. In contrast to most neural approaches to combinatorial optimization based on quadratic energy cost function, the authors propose to use linear cost functions. As a result, the network complexity (number of neurons and the number of resistive interconnections) grows only linearly with problem size, and large-scale implementations become possible. The proposed approach is related to the linear programming network described by D.W. Tank and J.J. Hopfield (1985), which also uses a linear cost function for a simple optimization problem. It is shown how to map a difficult constraint-satisfaction problem onto a simple neural net in which the number of neural processors equals the number of subjobs (operations) and the number of interconnections grows linearly with the total number of operations. Simulations show that the authors' approach produces better solutions than existing neural approaches to job-shop scheduling, i.e. the traveling salesman problem-type Hopfield approach and integer linear programming approach of J.P.S. Foo and Y. Takefuji (1988), in terms of the quality of the solution and the network complexity.
International Nuclear Information System (INIS)
Amanifard, N.; Nariman-Zadeh, N.; Borji, M.; Khalkhali, A.; Habibdoust, A.
2008-01-01
Three-dimensional heat transfer characteristics and pressure drop of water flow in a set of rectangular microchannels are numerically investigated using Fluent and compared with those of experimental results. Two metamodels based on the evolved group method of data handling (GMDH) type neural networks are then obtained for modelling of both pressure drop (ΔP) and Nusselt number (Nu) with respect to design variables such as geometrical parameters of microchannels, the amount of heat flux and the Reynolds number. Using such obtained polynomial neural networks, multi-objective genetic algorithms (GAs) (non-dominated sorting genetic algorithm, NSGA-II) with a new diversity preserving mechanism is then used for Pareto based optimization of microchannels considering two conflicting objectives such as (ΔP) and (Nu). It is shown that some interesting and important relationships as useful optimal design principles involved in the performance of microchannels can be discovered by Pareto based multi-objective optimization of the obtained polynomial metamodels representing their heat transfer and flow characteristics. Such important optimal principles would not have been obtained without the use of both GMDH type neural network modelling and the Pareto optimization approach
Optimal neural computations require analog processors
Energy Technology Data Exchange (ETDEWEB)
Beiu, V.
1998-12-31
This paper discusses some of the limitations of hardware implementations of neural networks. The authors start by presenting neural structures and their biological inspirations, while mentioning the simplifications leading to artificial neural networks. Further, the focus will be on hardware imposed constraints. They will present recent results for three different alternatives of parallel implementations of neural networks: digital circuits, threshold gate circuits, and analog circuits. The area and the delay will be related to the neurons` fan-in and to the precision of their synaptic weights. The main conclusion is that hardware-efficient solutions require analog computations, and suggests the following two alternatives: (i) cope with the limitations imposed by silicon, by speeding up the computation of the elementary silicon neurons; (2) investigate solutions which would allow the use of the third dimension (e.g. using optical interconnections).
International Nuclear Information System (INIS)
Wei, F.; Wu, Q.H.; Jing, Z.X.; Chen, J.J.; Zhou, X.X.
2016-01-01
This paper proposes a comprehensive framework including a multi-objective interval optimization model and evidential reasoning (ER) approach to solve the unit sizing problem of small-scale integrated energy systems, with uncertain wind and solar energies integrated. In the multi-objective interval optimization model, interval variables are introduced to tackle the uncertainties of the optimization problem. Aiming at simultaneously considering the cost and risk of a business investment, the average and deviation of life cycle cost (LCC) of the integrated energy system are formulated. In order to solve the problem, a novel multi-objective optimization algorithm, MGSOACC (multi-objective group search optimizer with adaptive covariance matrix and chaotic search), is developed, employing adaptive covariance matrix to make the search strategy adaptive and applying chaotic search to maintain the diversity of group. Furthermore, ER approach is applied to deal with multiple interests of an investor at the business decision making stage and to determine the final unit sizing solution from the Pareto-optimal solutions. This paper reports on the simulation results obtained using a small-scale direct district heating system (DH) and a small-scale district heating and cooling system (DHC) optimized by the proposed framework. The results demonstrate the superiority of the multi-objective interval optimization model and ER approach in tackling the unit sizing problem of integrated energy systems considering the integration of uncertian wind and solar energies. - Highlights: • Cost and risk of investment in small-scale integrated energy systems are considered. • A multi-objective interval optimization model is presented. • A novel multi-objective optimization algorithm (MGSOACC) is proposed. • The evidential reasoning (ER) approach is used to obtain the final optimal solution. • The MGSOACC and ER can tackle the unit sizing problem efficiently.
AHP-Based Optimal Selection of Garment Sizes for Online Shopping
Institute of Scientific and Technical Information of China (English)
无
2007-01-01
Garment online shopping has been accepted by more and more consumers in recent years. In online shopping, a buyer only chooses the garment size judged by his own experience without trying-on, so the selected garment may not be the fittest one for the buyer due to the variety of body's figures. Thus, we propose a method of optimal selection of garment sizes for online shopping based on Analytic Hierarchy Process (AHP). The hierarchical structure model for optimal selection of garment sizes is structured and the fittest garment for a buyer is found by calculating the matching degrees between individual's measurements and the corresponding key-part values of ready-to-wear clothing sizes. In order to demonstrate its feasibility, we provide an example of selecting the fittest sizes of men's bottom. The result shows that the proposed method is useful in online clothing sales application.
Neural substrate of body size: illusory feeling of shrinking of the waist.
Directory of Open Access Journals (Sweden)
H Henrik Ehrsson
2005-12-01
Full Text Available The perception of the size and shape of one's body (body image is a fundamental aspect of how we experience ourselves. We studied the neural correlates underlying perceived changes in the relative size of body parts by using a perceptual illusion in which participants felt that their waist was shrinking. We scanned the brains of the participants using functional magnetic resonance imaging. We found that activity in the cortices lining the left postcentral sulcus and the anterior part of the intraparietal sulcus reflected the illusion of waist shrinking, and that this activity was correlated with the reported degree of shrinking. These results suggest that the perceived changes in the size and shape of body parts are mediated by hierarchically higher-order somatosensory areas in the parietal cortex. Based on this finding we suggest that relative size of body parts is computed by the integration of more elementary somatic signals from different body segments.
Modeling and optimization of wet sizing process
International Nuclear Information System (INIS)
Thai Ba Cau; Vu Thanh Quang and Nguyen Ba Tien
2004-01-01
Mathematical simulation on basis of Stock law has been done for wet sizing process on cylinder equipment of laboratory and semi-industrial scale. The model consists of mathematical equations describing relations between variables, such as: - Resident time distribution function of emulsion particles in the separating zone of the equipment depending on flow-rate, height, diameter and structure of the equipment. - Size-distribution function in the fine and coarse parts depending on resident time distribution function of emulsion particles, characteristics of the material being processed, such as specific density, shapes, and characteristics of the environment of classification, such as specific density, viscosity. - Experimental model was developed on data collected from an experimental cylindrical equipment with diameter x height of sedimentation chamber equal to 50 x 40 cm for an emulsion of zirconium silicate in water. - Using this experimental model allows to determine optimal flow-rate in order to obtain product with desired grain size in term of average size or size distribution function. (author)
Genetic Algorithm Optimized Neural Networks Ensemble as ...
African Journals Online (AJOL)
NJD
Improvements in neural network calibration models by a novel approach using neural network ensemble (NNE) for the simultaneous ... process by training a number of neural networks. .... Matlab® version 6.1 was employed for building principal component ... provide a fair simulation of calibration data set with some degree.
Directory of Open Access Journals (Sweden)
Yu-Tzu Chang
2012-01-01
Full Text Available This paper aims to find the optimal set of initial weights to enhance the accuracy of artificial neural networks (ANNs by using genetic algorithms (GA. The sample in this study included 228 patients with first low-trauma hip fracture and 215 patients without hip fracture, both of them were interviewed with 78 questions. We used logistic regression to select 5 important factors (i.e., bone mineral density, experience of fracture, average hand grip strength, intake of coffee, and peak expiratory flow rate for building artificial neural networks to predict the probabilities of hip fractures. Three-layer (one hidden layer ANNs models with back-propagation training algorithms were adopted. The purpose in this paper is to find the optimal initial weights of neural networks via genetic algorithm to improve the predictability. Area under the ROC curve (AUC was used to assess the performance of neural networks. The study results showed the genetic algorithm obtained an AUC of 0.858±0.00493 on modeling data and 0.802 ± 0.03318 on testing data. They were slightly better than the results of our previous study (0.868±0.00387 and 0.796±0.02559, resp.. Thus, the preliminary study for only using simple GA has been proved to be effective for improving the accuracy of artificial neural networks.
Generation of artificial accelerograms using neural networks for data of Iran
International Nuclear Information System (INIS)
Bargi, Kh.; Loux, C.; Rohani, H.
2002-01-01
A new method for generation of artificial earthquake accelerograms from response spectra is proposed by Ghaboussi and Lin in 1997 using neural networks. In this paper the methodology has been extended and enhanced for data of Iran. For this purpose, first 40 records of Iran acceleration is chosen, then an RBF neural network which called generalized regression neural network learn the inverse mapping directly from the response spectrum to the Discrete Cosine Transform of accelerograms. Discrete Cosine Transform has been used as an assisting device to extract the content of frequency domain. Learning of network is reasonable and a generalized regression neural network learns it in a few second. Outputs are presented to demonstrate the performance of this method and show its capabilities
An application of multigrid methods for a discrete elastic model for epitaxial systems
International Nuclear Information System (INIS)
Caflisch, R.E.; Lee, Y.-J.; Shu, S.; Xiao, Y.-X.; Xu, J.
2006-01-01
We apply an efficient and fast algorithm to simulate the atomistic strain model for epitaxial systems, recently introduced by Schindler et al. [Phys. Rev. B 67, 075316 (2003)]. The discrete effects in this lattice statics model are crucial for proper simulation of the influence of strain for thin film epitaxial growth, but the size of the atomistic systems of interest is in general quite large and hence the solution of the discrete elastic equations is a considerable numerical challenge. In this paper, we construct an algebraic multigrid method suitable for efficient solution of the large scale discrete strain model. Using this method, simulations are performed for several representative physical problems, including an infinite periodic step train, a layered nanocrystal, and a system of quantum dots. The results demonstrate the effectiveness and robustness of the method and show that the method attains optimal convergence properties, regardless of the problem size, the geometry and the physical parameters. The effects of substrate depth and of invariance due to traction-free boundary conditions are assessed. For a system of quantum dots, the simulated strain energy density supports the observations that trench formation near the dots provides strain relief
Directory of Open Access Journals (Sweden)
Petr Maca
2014-01-01
Full Text Available The presented paper aims to analyze the influence of the selection of transfer function and training algorithms on neural network flood runoff forecast. Nine of the most significant flood events, caused by the extreme rainfall, were selected from 10 years of measurement on small headwater catchment in the Czech Republic, and flood runoff forecast was investigated using the extensive set of multilayer perceptrons with one hidden layer of neurons. The analyzed artificial neural network models with 11 different activation functions in hidden layer were trained using 7 local optimization algorithms. The results show that the Levenberg-Marquardt algorithm was superior compared to the remaining tested local optimization methods. When comparing the 11 nonlinear transfer functions, used in hidden layer neurons, the RootSig function was superior compared to the rest of analyzed activation functions.
A chaos wolf optimization algorithm with self-adaptive variable step-size
Zhu, Yong; Jiang, Wanlu; Kong, Xiangdong; Quan, Lingxiao; Zhang, Yongshun
2017-10-01
To explore the problem of parameter optimization for complex nonlinear function, a chaos wolf optimization algorithm (CWOA) with self-adaptive variable step-size was proposed. The algorithm was based on the swarm intelligence of wolf pack, which fully simulated the predation behavior and prey distribution way of wolves. It possessed three intelligent behaviors such as migration, summons and siege. And the competition rule as "winner-take-all" and the update mechanism as "survival of the fittest" were also the characteristics of the algorithm. Moreover, it combined the strategies of self-adaptive variable step-size search and chaos optimization. The CWOA was utilized in parameter optimization of twelve typical and complex nonlinear functions. And the obtained results were compared with many existing algorithms, including the classical genetic algorithm, the particle swarm optimization algorithm and the leader wolf pack search algorithm. The investigation results indicate that CWOA possess preferable optimization ability. There are advantages in optimization accuracy and convergence rate. Furthermore, it demonstrates high robustness and global searching ability.
Bernico, Michael
2018-01-01
This book is a practical guide to applying deep neural networks including MLPs, CNNs, LSTMs, and more in Keras and TensorFlow. Packed with useful hacks to solve real-world challenges along with the supported math and theory around each topic, this book will be a quick reference for training and optimize your deep neural networks.
International Nuclear Information System (INIS)
Abdel-Aal, M.M.Z.
2004-01-01
Automation in large, complex systems such as chemical plants, electrical power generation, aerospace and nuclear plants has been steadily increasing in the recent past. automated diagnosis and control forms a necessary part of these systems,this contains thousands of alarms processing in every component, subsystem and system. so the accurate and speed of diagnosis of faults is an important factors in operation and maintaining their health and continued operation and in reducing of repair and recovery time. using of artificial intelligence facilitates the alarm classifications and faults diagnosis to control any abnormal events during the operation cycle of the plant. thesis work uses the artificial neural network as a powerful classification tool. the work basically is has two components, the first is to effectively train the neural network using particle swarm optimization, which non-derivative based technique. to achieve proper training of the neural network to fault classification problem and comparing this technique to already existing techniques
A methodology for optimal sizing of autonomous hybrid PV/wind system
International Nuclear Information System (INIS)
Diaf, S.; Diaf, D.; Belhamel, M.; Haddadi, M.; Louche, A.
2007-01-01
The present paper presents a methodology to perform the optimal sizing of an autonomous hybrid PV/wind system. The methodology aims at finding the configuration, among a set of systems components, which meets the desired system reliability requirements, with the lowest value of levelized cost of energy. Modelling a hybrid PV/wind system is considered as the first step in the optimal sizing procedure. In this paper, more accurate mathematical models for characterizing PV module, wind generator and battery are proposed. The second step consists to optimize the sizing of a system according to the loss of power supply probability (LPSP) and the levelized cost of energy (LCE) concepts. Considering various types and capacities of system devices, the configurations, which can meet the desired system reliability, are obtained by changing the type and size of the devices systems. The configuration with the lowest LCE gives the optimal choice. Applying this method to an assumed PV/wind hybrid system to be installed at Corsica Island, the simulation results show that the optimal configuration, which meet the desired system reliability requirements (LPSP=0) with the lowest LCE, is obtained for a system comprising a 125 W photovoltaic module, one wind generator (600 W) and storage batteries (using 253 Ah). On the other hand, the device system choice plays an important role in cost reduction as well as in energy production
Marcar, Valentine L; Baselgia, Silvana; Lüthi-Eisenegger, Barbara; Jäncke, Lutz
2018-03-01
Retinal input processing in the human visual system involves a phasic and tonic neural response. We investigated the role of the magno- and parvocellular systems by comparing the influence of the active neural population size and its discharge activity on the amplitude and latency of four VEP components. We recorded the scalp electric potential of 20 human volunteers viewing a series of dartboard images presented as a pattern reversing and pattern on-/offset stimulus. These patterns were designed to vary both neural population size coding the temporal- and spatial luminance contrast property and the discharge activity of the population involved in a systematic manner. When the VEP amplitude reflected the size of the neural population coding the temporal luminance contrast property of the image, the influence of luminance contrast followed the contrast response function of the parvocellular system. When the VEP amplitude reflected the size of the neural population responding to the spatial luminance contrast property the image, the influence of luminance contrast followed the contrast response function of the magnocellular system. The latencies of the VEP components examined exhibited the same behavior across our stimulus series. This investigation demonstrates the complex interplay of the magno- and parvocellular systems on the neural response as captured by the VEP. It also demonstrates a linear relationship between stimulus property, neural response, and the VEP and reveals the importance of feedback projections in modulating the ongoing neural response. In doing so, it corroborates the conclusions of our previous study.
Distributed Optimal Consensus Control for Multiagent Systems With Input Delay.
Zhang, Huaipin; Yue, Dong; Zhao, Wei; Hu, Songlin; Dou, Chunxia; Huaipin Zhang; Dong Yue; Wei Zhao; Songlin Hu; Chunxia Dou; Hu, Songlin; Zhang, Huaipin; Dou, Chunxia; Yue, Dong; Zhao, Wei
2018-06-01
This paper addresses the problem of distributed optimal consensus control for a continuous-time heterogeneous linear multiagent system subject to time varying input delays. First, by discretization and model transformation, the continuous-time input-delayed system is converted into a discrete-time delay-free system. Two delicate performance index functions are defined for these two systems. It is shown that the performance index functions are equivalent and the optimal consensus control problem of the input-delayed system can be cast into that of the delay-free system. Second, by virtue of the Hamilton-Jacobi-Bellman (HJB) equations, an optimal control policy for each agent is designed based on the delay-free system and a novel value iteration algorithm is proposed to learn the solutions to the HJB equations online. The proposed adaptive dynamic programming algorithm is implemented on the basis of a critic-action neural network (NN) structure. Third, it is proved that local consensus errors of the two systems and weight estimation errors of the critic-action NNs are uniformly ultimately bounded while the approximated control policies converge to their target values. Finally, two simulation examples are presented to illustrate the effectiveness of the developed method.
Sur, Chiranjib; Shukla, Anupam
2018-03-01
Bacteria Foraging Optimisation Algorithm is a collective behaviour-based meta-heuristics searching depending on the social influence of the bacteria co-agents in the search space of the problem. The algorithm faces tremendous hindrance in terms of its application for discrete problems and graph-based problems due to biased mathematical modelling and dynamic structure of the algorithm. This had been the key factor to revive and introduce the discrete form called Discrete Bacteria Foraging Optimisation (DBFO) Algorithm for discrete problems which exceeds the number of continuous domain problems represented by mathematical and numerical equations in real life. In this work, we have mainly simulated a graph-based road multi-objective optimisation problem and have discussed the prospect of its utilisation in other similar optimisation problems and graph-based problems. The various solution representations that can be handled by this DBFO has also been discussed. The implications and dynamics of the various parameters used in the DBFO are illustrated from the point view of the problems and has been a combination of both exploration and exploitation. The result of DBFO has been compared with Ant Colony Optimisation and Intelligent Water Drops Algorithms. Important features of DBFO are that the bacteria agents do not depend on the local heuristic information but estimates new exploration schemes depending upon the previous experience and covered path analysis. This makes the algorithm better in combination generation for graph-based problems and combination generation for NP hard problems.
Mohamed, Mamdouh S.
2016-02-11
A conservative discretization of incompressible Navier–Stokes equations is developed based on discrete exterior calculus (DEC). A distinguishing feature of our method is the use of an algebraic discretization of the interior product operator and a combinatorial discretization of the wedge product. The governing equations are first rewritten using the exterior calculus notation, replacing vector calculus differential operators by the exterior derivative, Hodge star and wedge product operators. The discretization is then carried out by substituting with the corresponding discrete operators based on the DEC framework. Numerical experiments for flows over surfaces reveal a second order accuracy for the developed scheme when using structured-triangular meshes, and first order accuracy for otherwise unstructured meshes. By construction, the method is conservative in that both mass and vorticity are conserved up to machine precision. The relative error in kinetic energy for inviscid flow test cases converges in a second order fashion with both the mesh size and the time step.
Mohamed, Mamdouh S.; Hirani, Anil N.; Samtaney, Ravi
2016-05-01
A conservative discretization of incompressible Navier-Stokes equations is developed based on discrete exterior calculus (DEC). A distinguishing feature of our method is the use of an algebraic discretization of the interior product operator and a combinatorial discretization of the wedge product. The governing equations are first rewritten using the exterior calculus notation, replacing vector calculus differential operators by the exterior derivative, Hodge star and wedge product operators. The discretization is then carried out by substituting with the corresponding discrete operators based on the DEC framework. Numerical experiments for flows over surfaces reveal a second order accuracy for the developed scheme when using structured-triangular meshes, and first order accuracy for otherwise unstructured meshes. By construction, the method is conservative in that both mass and vorticity are conserved up to machine precision. The relative error in kinetic energy for inviscid flow test cases converges in a second order fashion with both the mesh size and the time step.
Energy Technology Data Exchange (ETDEWEB)
Sousa, Sergio H.G. de; Madeira, Marcelo G. [Halliburton Servicos Ltda., Rio de Janeiro, RJ (Brazil)
2008-07-01
In the classical operations research arena, there is the notion that the search for optimized solutions in continuous solution spaces is easier than on discrete solution spaces, even when the latter is a subset of the first. On the upstream oil industry, there is an additional complexity in the optimization problems because there usually are no analytical expressions for the objective function, which require some form of simulation in order to be evaluated. Thus, the use of meta heuristic optimizers like scatter search, tabu search and genetic algorithms is common. In this meta heuristic context, there are advantages in transforming continuous solution spaces in equivalent discrete ones; the goal to do so usually is to speed up the search for optimized solutions. However, these advantages can be masked when the problem has restrictions formed by linear combinations of its decision variables. In order to study these aspects of meta heuristic optimization, two optimization problems are proposed and solved with both continuous and discrete solution spaces: assisted history matching and injection rates optimization. Both cases operate on a model of the Wytch Farm onshore oil filed located in England. (author)
Economic Optimization of Component Sizing for Residential Battery Storage Systems
Directory of Open Access Journals (Sweden)
Holger C. Hesse
2017-06-01
Full Text Available Battery energy storage systems (BESS coupled with rooftop-mounted residential photovoltaic (PV generation, designated as PV-BESS, draw increasing attention and market penetration as more and more such systems become available. The manifold BESS deployed to date rely on a variety of different battery technologies, show a great variation of battery size, and power electronics dimensioning. However, given today’s high investment costs of BESS, a well-matched design and adequate sizing of the storage systems are prerequisites to allow profitability for the end-user. The economic viability of a PV-BESS depends also on the battery operation, storage technology, and aging of the system. In this paper, a general method for comprehensive PV-BESS techno-economic analysis and optimization is presented and applied to the state-of-art PV-BESS to determine its optimal parameters. Using a linear optimization method, a cost-optimal sizing of the battery and power electronics is derived based on solar energy availability and local demand. At the same time, the power flow optimization reveals the best storage operation patterns considering a trade-off between energy purchase, feed-in remuneration, and battery aging. Using up to date technology-specific aging information and the investment cost of battery and inverter systems, three mature battery chemistries are compared; a lead-acid (PbA system and two lithium-ion systems, one with lithium-iron-phosphate (LFP and another with lithium-nickel-manganese-cobalt (NMC cathode. The results show that different storage technology and component sizing provide the best economic performances, depending on the scenario of load demand and PV generation.
Hortensius, Ruud; de Gelder, Beatrice
2014-06-01
Naturalistic observation and experimental studies in humans and other primates show that observing an individual in need automatically triggers helping behavior. The aim of the present study is to clarify the neurofunctional basis of social influences on individual helping behavior. We investigate whether when participants witness an emergency, while performing an unrelated color-naming task in an fMRI scanner, the number of bystanders present at the emergency influences neural activity in regions related to action preparation. The results show a decrease in activity with the increase in group size in the left pre- and postcentral gyri and left medial frontal gyrus. In contrast, regions related to visual perception and attention show an increase in activity. These results demonstrate the neural mechanisms of social influence on automatic action preparation that is at the core of helping behavior when witnessing an emergency. Copyright © 2014 Elsevier Inc. All rights reserved.
Stochastic Neural Field Theory and the System-Size Expansion
Bressloff, Paul C.
2010-01-01
We analyze a master equation formulation of stochastic neurodynamics for a network of synaptically coupled homogeneous neuronal populations each consisting of N identical neurons. The state of the network is specified by the fraction of active or spiking neurons in each population, and transition rates are chosen so that in the thermodynamic or deterministic limit (N → ∞) we recover standard activity-based or voltage-based rate models. We derive the lowest order corrections to these rate equations for large but finite N using two different approximation schemes, one based on the Van Kampen system-size expansion and the other based on path integral methods. Both methods yield the same series expansion of the moment equations, which at O(1/N) can be truncated to form a closed system of equations for the first-and second-order moments. Taking a continuum limit of the moment equations while keeping the system size N fixed generates a system of integrodifferential equations for the mean and covariance of the corresponding stochastic neural field model. We also show how the path integral approach can be used to study large deviation or rare event statistics underlying escape from the basin of attraction of a stable fixed point of the mean-field dynamics; such an analysis is not possible using the system-size expansion since the latter cannot accurately determine exponentially small transitions. © by SIAM.
Directory of Open Access Journals (Sweden)
Na Lin
2017-03-01
Full Text Available In recent years, symbiosis as a rich source of potential engineering applications and computational model has attracted more and more attentions in the adaptive complex systems and evolution computing domains. Inspired by different symbiotic coevolution forms in nature, this paper proposed a series of multi-swarm particle swarm optimizers called PS2Os, which extend the single population particle swarm optimization (PSO algorithm to interacting multi-swarms model by constructing hierarchical interaction topologies and enhanced dynamical update equations. According to different symbiotic interrelationships, four versions of PS2O are initiated to mimic mutualism, commensalism, predation, and competition mechanism, respectively. In the experiments, with five benchmark problems, the proposed algorithms are proved to have considerable potential for solving complex optimization problems. The coevolutionary dynamics of symbiotic species in each PS2O version are also studied respectively to demonstrate the heterogeneity of different symbiotic interrelationships that effect on the algorithm’s performance. Then PS2O is used for solving the radio frequency identification (RFID network planning (RNP problem with a mixture of discrete and continuous variables. Simulation results show that the proposed algorithm outperforms the reference algorithms for planning RFID networks, in terms of optimization accuracy and computation robustness.
Statistical process control using optimized neural networks: a case study.
Addeh, Jalil; Ebrahimzadeh, Ata; Azarbad, Milad; Ranaee, Vahid
2014-09-01
The most common statistical process control (SPC) tools employed for monitoring process changes are control charts. A control chart demonstrates that the process has altered by generating an out-of-control signal. This study investigates the design of an accurate system for the control chart patterns (CCPs) recognition in two aspects. First, an efficient system is introduced that includes two main modules: feature extraction module and classifier module. In the feature extraction module, a proper set of shape features and statistical feature are proposed as the efficient characteristics of the patterns. In the classifier module, several neural networks, such as multilayer perceptron, probabilistic neural network and radial basis function are investigated. Based on an experimental study, the best classifier is chosen in order to recognize the CCPs. Second, a hybrid heuristic recognition system is introduced based on cuckoo optimization algorithm (COA) algorithm to improve the generalization performance of the classifier. The simulation results show that the proposed algorithm has high recognition accuracy. Copyright © 2013 ISA. Published by Elsevier Ltd. All rights reserved.
A Transistor Sizing Tool for Optimization of Analog CMOS Circuits: TSOp
Y.C.Wong; Syafeeza A. R; N. A. Hamid
2015-01-01
Optimization of a circuit by transistor sizing is often a slow, tedious and iterative manual process which relies on designer intuition. It is highly desirable to automate the transistor sizing process towards being able to rapidly design high performance integrated circuit. Presented here is a simple but effective algorithm for automatically optimizing the circuit parameters by exploiting the relationships among the genetic algorithm's coefficient values derived from the analog circuit desig...
Automatic analog IC sizing and optimization constrained with PVT corners and layout effects
Lourenço, Nuno; Horta, Nuno
2017-01-01
This book introduces readers to a variety of tools for automatic analog integrated circuit (IC) sizing and optimization. The authors provide a historical perspective on the early methods proposed to tackle automatic analog circuit sizing, with emphasis on the methodologies to size and optimize the circuit, and on the methodologies to estimate the circuit’s performance. The discussion also includes robust circuit design and optimization and the most recent advances in layout-aware analog sizing approaches. The authors describe a methodology for an automatic flow for analog IC design, including details of the inputs and interfaces, multi-objective optimization techniques, and the enhancements made in the base implementation by using machine leaning techniques. The Gradient model is discussed in detail, along with the methods to include layout effects in the circuit sizing. The concepts and algorithms of all the modules are thoroughly described, enabling readers to reproduce the methodologies, improve the qual...
Directory of Open Access Journals (Sweden)
Norman Josephy
2011-01-01
Full Text Available We present a method of optimal hedging and pricing of equity-linked life insurance products in an incomplete discrete-time financial market. A pure endowment life insurance contract with guarantee is used as an example. The financial market incompleteness is caused by the assumption that the underlying risky asset price ratios are distributed in a compact interval, generalizing the assumptions of multinomial incomplete market models. For a range of initial hedging capitals for the embedded financial option, we numerically solve an optimal hedging problem and determine a risk-return profile of each optimal non-self-financing hedging strategy. The fair price of the insurance contract is determined according to the insurer's risk-return preferences. Illustrative numerical results of testing our algorithm on hypothetical insurance contracts are documented. A discussion and a test of a hedging strategy recalibration technique for long-term contracts are presented.
Kulkarni, Shruti R; Rajendran, Bipin
2018-07-01
We demonstrate supervised learning in Spiking Neural Networks (SNNs) for the problem of handwritten digit recognition using the spike triggered Normalized Approximate Descent (NormAD) algorithm. Our network that employs neurons operating at sparse biological spike rates below 300Hz achieves a classification accuracy of 98.17% on the MNIST test database with four times fewer parameters compared to the state-of-the-art. We present several insights from extensive numerical experiments regarding optimization of learning parameters and network configuration to improve its accuracy. We also describe a number of strategies to optimize the SNN for implementation in memory and energy constrained hardware, including approximations in computing the neuronal dynamics and reduced precision in storing the synaptic weights. Experiments reveal that even with 3-bit synaptic weights, the classification accuracy of the designed SNN does not degrade beyond 1% as compared to the floating-point baseline. Further, the proposed SNN, which is trained based on the precise spike timing information outperforms an equivalent non-spiking artificial neural network (ANN) trained using back propagation, especially at low bit precision. Thus, our study shows the potential for realizing efficient neuromorphic systems that use spike based information encoding and learning for real-world applications. Copyright © 2018 Elsevier Ltd. All rights reserved.
A chaos wolf optimization algorithm with self-adaptive variable step-size
Directory of Open Access Journals (Sweden)
Yong Zhu
2017-10-01
Full Text Available To explore the problem of parameter optimization for complex nonlinear function, a chaos wolf optimization algorithm (CWOA with self-adaptive variable step-size was proposed. The algorithm was based on the swarm intelligence of wolf pack, which fully simulated the predation behavior and prey distribution way of wolves. It possessed three intelligent behaviors such as migration, summons and siege. And the competition rule as “winner-take-all” and the update mechanism as “survival of the fittest” were also the characteristics of the algorithm. Moreover, it combined the strategies of self-adaptive variable step-size search and chaos optimization. The CWOA was utilized in parameter optimization of twelve typical and complex nonlinear functions. And the obtained results were compared with many existing algorithms, including the classical genetic algorithm, the particle swarm optimization algorithm and the leader wolf pack search algorithm. The investigation results indicate that CWOA possess preferable optimization ability. There are advantages in optimization accuracy and convergence rate. Furthermore, it demonstrates high robustness and global searching ability.
International Nuclear Information System (INIS)
Kim, Jae Hwan; Park, Soon Ho; Na, Man Gyun
2014-01-01
Highlights: • A model predictive controller for load-following operation was developed. • Genetic algorithm optimizes the five nonlinear discrete control rod speeds. • The boron concentration is adjusted with automatic adjustment logic. • The proposed controller reflects the realistic control rod drive mechanism movement. • The performance was confirmed to be satisfactory by simulation from BOC to EOC. - Abstract: Currently, most existing nuclear power plants alter the reactor power by adjusting the boron concentration in the coolant because it has a smaller effect on the reactor power distribution. Frequent control rod movements for load-following operation induce xenon-oscillation. Therefore, a controller that can subdue this phenomenon effectively is needed. At an APR1400 nuclear power plant which is a pressurized water reactor (PWR), the reactor power is controlled automatically using a Reactor Regulating System (RRS) but the power distribution is controlled manually by operators. Therefore, for APR+ nuclear power plants which is an improved version of APR1400 nuclear reactor, a new concept of a reactor controller is needed to control both the reactor power and power distribution automatically. The model predictive control (MPC) method is applicable to multiple-input multiple-output control, and can be applied for complex and nonlinear systems, such as the nuclear power plants. In this study, an MPC controller was developed by applying a genetic algorithm to optimize the discrete control rod speeds and by reflecting the realistic movement of the control rod drive mechanism that moves at only five discrete speeds. The performance of the proposed controller was confirmed to be satisfactory by simulating the load-following operation of an APR+ nuclear power plant through interface with KISPAC-1D code
Discrete-State Simulated Annealing For Traveling-Wave Tube Slow-Wave Circuit Optimization
Wilson, Jeffrey D.; Bulson, Brian A.; Kory, Carol L.; Williams, W. Dan (Technical Monitor)
2001-01-01
Algorithms based on the global optimization technique of simulated annealing (SA) have proven useful in designing traveling-wave tube (TWT) slow-wave circuits for high RF power efficiency. The characteristic of SA that enables it to determine a globally optimized solution is its ability to accept non-improving moves in a controlled manner. In the initial stages of the optimization, the algorithm moves freely through configuration space, accepting most of the proposed designs. This freedom of movement allows non-intuitive designs to be explored rather than restricting the optimization to local improvement upon the initial configuration. As the optimization proceeds, the rate of acceptance of non-improving moves is gradually reduced until the algorithm converges to the optimized solution. The rate at which the freedom of movement is decreased is known as the annealing or cooling schedule of the SA algorithm. The main disadvantage of SA is that there is not a rigorous theoretical foundation for determining the parameters of the cooling schedule. The choice of these parameters is highly problem dependent and the designer needs to experiment in order to determine values that will provide a good optimization in a reasonable amount of computational time. This experimentation can absorb a large amount of time especially when the algorithm is being applied to a new type of design. In order to eliminate this disadvantage, a variation of SA known as discrete-state simulated annealing (DSSA), was recently developed. DSSA provides the theoretical foundation for a generic cooling schedule which is problem independent, Results of similar quality to SA can be obtained, but without the extra computational time required to tune the cooling parameters. Two algorithm variations based on DSSA were developed and programmed into a Microsoft Excel spreadsheet graphical user interface (GUI) to the two-dimensional nonlinear multisignal helix traveling-wave amplifier analysis program TWA3
International Nuclear Information System (INIS)
Sengupta, A.; Ranjan, P.
2001-01-01
In this paper, we examine the possibility of using a multilayered feedforward neural network to extract tokamak plasma parameters from magnetic measurements as an improvement over the traditional methodology of function parametrization. It is also used to optimize the number and locations of the magnetic diagnostics designed for the tokamak. This work has been undertaken with the specific purpose of application of the neural network technique to the newly designed (and currently under fabrication) Superconducting Steady-State Tokamak-1 (SST-1). The magnetic measurements will be utilized to achieve real-time control of plasma shape, position, and some global profiles. A trained neural network is tested, and the results of parameter identification are compared with function parametrization. Both techniques appear well suited for the purpose, but a definite improvement with neural networks is observed. Although simulated measurements are used in this work, confidence regarding the network performance with actual experimental data is ensured by testing the network's noise tolerance with Gaussian noise of up to 10%. Finally, three possible methods of ranking the diagnostics in decreasing order of importance are suggested, and the neural network is used to optimize the number and locations of the magnetic sensors designed for SST-1. The results from the three methods are compared with one another and also with function parametrization. Magnetic probes within the plasma-facing side of the outboard limiter have been ranked high. Function parametrization and one of the neural network methods show a distinct tendency to favor the probes in the remote regions of the vacuum vessel, proving the importance of redundancy. Fault tolerance of the optimized network is tested. The results obtained should, in the long run, help in the decision regarding the final effective set of magnetic diagnostics to be used in SST-1 for reconstruction of the control parameters
Optimizing Markovian modeling of chaotic systems with recurrent neural networks
International Nuclear Information System (INIS)
Cechin, Adelmo L.; Pechmann, Denise R.; Oliveira, Luiz P.L. de
2008-01-01
In this paper, we propose a methodology for optimizing the modeling of an one-dimensional chaotic time series with a Markov Chain. The model is extracted from a recurrent neural network trained for the attractor reconstructed from the data set. Each state of the obtained Markov Chain is a region of the reconstructed state space where the dynamics is approximated by a specific piecewise linear map, obtained from the network. The Markov Chain represents the dynamics of the time series in its statistical essence. An application to a time series resulted from Lorenz system is included
A discrete optimization method for nuclear fuel management
International Nuclear Information System (INIS)
Argaud, J.P.
1993-04-01
Nuclear loading pattern elaboration can be seen as a combinational optimization problem of tremendous size and with non-linear cost-functions, and search are always numerically expensive. After a brief introduction of the main aspects of nuclear fuel management, this paper presents a new idea to treat the combinational problem by using informations included in the gradient of a cost function. The method is to choose, by direct observation of the gradient, the more interesting changes in fuel loading patterns. An example is then developed to illustrate an operating mode of the method, and finally, connections with simulated annealing and genetic algorithms are described as an attempt to improve search processes
Elements of an algorithm for optimizing a parameter-structural neural network
Mrówczyńska, Maria
2016-06-01
The field of processing information provided by measurement results is one of the most important components of geodetic technologies. The dynamic development of this field improves classic algorithms for numerical calculations in the aspect of analytical solutions that are difficult to achieve. Algorithms based on artificial intelligence in the form of artificial neural networks, including the topology of connections between neurons have become an important instrument connected to the problem of processing and modelling processes. This concept results from the integration of neural networks and parameter optimization methods and makes it possible to avoid the necessity to arbitrarily define the structure of a network. This kind of extension of the training process is exemplified by the algorithm called the Group Method of Data Handling (GMDH), which belongs to the class of evolutionary algorithms. The article presents a GMDH type network, used for modelling deformations of the geometrical axis of a steel chimney during its operation.
International Nuclear Information System (INIS)
Atashkari, K.; Nariman-Zadeh, N.; Goelcue, M.; Khalkhali, A.; Jamali, A.
2007-01-01
The main reason for the efficiency decrease at part load conditions for four-stroke spark-ignition (SI) engines is the flow restriction at the cross-sectional area of the intake system. Traditionally, valve-timing has been designed to optimize operation at high engine-speed and wide open throttle conditions. Several investigations have demonstrated that improvements at part load conditions in engine performance can be accomplished if the valve-timing is variable. Controlling valve-timing can be used to improve the torque and power curve as well as to reduce fuel consumption and emissions. In this paper, a group method of data handling (GMDH) type neural network and evolutionary algorithms (EAs) are firstly used for modelling the effects of intake valve-timing (V t ) and engine speed (N) of a spark-ignition engine on both developed engine torque (T) and fuel consumption (Fc) using some experimentally obtained training and test data. Using such obtained polynomial neural network models, a multi-objective EA (non-dominated sorting genetic algorithm, NSGA-II) with a new diversity preserving mechanism are secondly used for Pareto based optimization of the variable valve-timing engine considering two conflicting objectives such as torque (T) and fuel consumption (Fc). The comparison results demonstrate the superiority of the GMDH type models over feedforward neural network models in terms of the statistical measures in the training data, testing data and the number of hidden neurons. Further, it is shown that some interesting and important relationships, as useful optimal design principles, involved in the performance of the variable valve-timing four-stroke spark-ignition engine can be discovered by the Pareto based multi-objective optimization of the polynomial models. Such important optimal principles would not have been obtained without the use of both the GMDH type neural network modelling and the multi-objective Pareto optimization approach
Wuensche, Andrew
DDLab is interactive graphics software for creating, visualizing, and analyzing many aspects of Cellular Automata, Random Boolean Networks, and Discrete Dynamical Networks in general and studying their behavior, both from the time-series perspective — space-time patterns, and from the state-space perspective — attractor basins. DDLab is relevant to research, applications, and education in the fields of complexity, self-organization, emergent phenomena, chaos, collision-based computing, neural networks, content addressable memory, genetic regulatory networks, dynamical encryption, generative art and music, and the study of the abstract mathematical/physical/dynamical phenomena in their own right.
Alternating optimization method based on nonnegative matrix factorizations for deep neural networks
Sakurai, Tetsuya; Imakura, Akira; Inoue, Yuto; Futamura, Yasunori
2016-01-01
The backpropagation algorithm for calculating gradients has been widely used in computation of weights for deep neural networks (DNNs). This method requires derivatives of objective functions and has some difficulties finding appropriate parameters such as learning rate. In this paper, we propose a novel approach for computing weight matrices of fully-connected DNNs by using two types of semi-nonnegative matrix factorizations (semi-NMFs). In this method, optimization processes are performed b...
Optimal sizing of a run-of-river small hydropower plant
International Nuclear Information System (INIS)
Anagnostopoulos, John S.; Papantonis, Dimitris E.
2007-01-01
The sizing of a small hydropower plant of the run-of-river type is very critical for the cost effectiveness of the investment. In the present work, a numerical method is used for the optimal sizing of such a plant that comprises two hydraulic turbines operating in parallel, which can be of different type and size in order to improve its efficiency. The study and analysis of the plant performance is conducted using a newly developed evaluation algorithm that simulates in detail the plant operation during the year and computes its production results and economic indices. A parametric study is performed first in order to quantify the impact of some important construction and operation factors. Next, a stochastic evolutionary algorithm is implemented for the optimization process. The examined optimization problem uses data of a specific site and is solved in the single and two-objective modes, considering, together with economic, some additional objectives, as maximization of the produced energy and the best exploitation of the water stream potential. Analyzing the results of various optimizations runs, it becomes possible to identify the most advantageous design alternatives to realize the project. It was found that the use of two turbines of different size can enhance sufficiently both the energy production of the plant and the economic results of the investment. Finally, the sensitivity of the plant performance to other external parameters can be easily studied with the present method, and some indicative results are given for different financial or hydrologic conditions
Adhikari, Shyam Prasad; Yang, Changju; Slot, Krzysztof; Kim, Hyongsuk
2018-01-10
This paper presents a vision sensor-based solution to the challenging problem of detecting and following trails in highly unstructured natural environments like forests, rural areas and mountains, using a combination of a deep neural network and dynamic programming. The deep neural network (DNN) concept has recently emerged as a very effective tool for processing vision sensor signals. A patch-based DNN is trained with supervised data to classify fixed-size image patches into "trail" and "non-trail" categories, and reshaped to a fully convolutional architecture to produce trail segmentation map for arbitrary-sized input images. As trail and non-trail patches do not exhibit clearly defined shapes or forms, the patch-based classifier is prone to misclassification, and produces sub-optimal trail segmentation maps. Dynamic programming is introduced to find an optimal trail on the sub-optimal DNN output map. Experimental results showing accurate trail detection for real-world trail datasets captured with a head mounted vision system are presented.
International Nuclear Information System (INIS)
Sauget, M.
2007-12-01
This research is about the application of neural networks used in the external radiotherapy domain. The goal is to elaborate a new evaluating system for the radiation dose distributions in heterogeneous environments. The al objective of this work is to build a complete tool kit to evaluate the optimal treatment planning. My st research point is about the conception of an incremental learning algorithm. The interest of my work is to combine different optimizations specialized in the function interpolation and to propose a new algorithm allowing to change the neural network architecture during the learning phase. This algorithm allows to minimise the al size of the neural network while keeping a good accuracy. The second part of my research is to parallelize the previous incremental learning algorithm. The goal of that work is to increase the speed of the learning step as well as the size of the learned dataset needed in a clinical case. For that, our incremental learning algorithm presents an original data decomposition with overlapping, together with a fault tolerance mechanism. My last research point is about a fast and accurate algorithm computing the radiation dose deposit in any heterogeneous environment. At the present time, the existing solutions used are not optimal. The fast solution are not accurate and do not give an optimal treatment planning. On the other hand, the accurate solutions are far too slow to be used in a clinical context. Our algorithm answers to this problem by bringing rapidity and accuracy. The concept is to use a neural network adequately learned together with a mechanism taking into account the environment changes. The advantages of this algorithm is to avoid the use of a complex physical code while keeping a good accuracy and reasonable computation times. (author)
Energy Minimization of Discrete Protein Titration State Models Using Graph Theory
Purvine, Emilie; Monson, Kyle; Jurrus, Elizabeth; Star, Keith; Baker, Nathan A.
2016-01-01
There are several applications in computational biophysics which require the optimization of discrete interacting states; e.g., amino acid titration states, ligand oxidation states, or discrete rotamer angles. Such optimization can be very time-consuming as it scales exponentially in the number of sites to be optimized. In this paper, we describe a new polynomial-time algorithm for optimization of discrete states in macromolecular systems. This algorithm was adapted from image processing and uses techniques from discrete mathematics and graph theory to restate the optimization problem in terms of “maximum flow-minimum cut” graph analysis. The interaction energy graph, a graph in which vertices (amino acids) and edges (interactions) are weighted with their respective energies, is transformed into a flow network in which the value of the minimum cut in the network equals the minimum free energy of the protein, and the cut itself encodes the state that achieves the minimum free energy. Because of its deterministic nature and polynomial-time performance, this algorithm has the potential to allow for the ionization state of larger proteins to be discovered. PMID:27089174
Energy Minimization of Discrete Protein Titration State Models Using Graph Theory.
Purvine, Emilie; Monson, Kyle; Jurrus, Elizabeth; Star, Keith; Baker, Nathan A
2016-08-25
There are several applications in computational biophysics that require the optimization of discrete interacting states, for example, amino acid titration states, ligand oxidation states, or discrete rotamer angles. Such optimization can be very time-consuming as it scales exponentially in the number of sites to be optimized. In this paper, we describe a new polynomial time algorithm for optimization of discrete states in macromolecular systems. This algorithm was adapted from image processing and uses techniques from discrete mathematics and graph theory to restate the optimization problem in terms of "maximum flow-minimum cut" graph analysis. The interaction energy graph, a graph in which vertices (amino acids) and edges (interactions) are weighted with their respective energies, is transformed into a flow network in which the value of the minimum cut in the network equals the minimum free energy of the protein and the cut itself encodes the state that achieves the minimum free energy. Because of its deterministic nature and polynomial time performance, this algorithm has the potential to allow for the ionization state of larger proteins to be discovered.
Electrical Energy Forecasting and Optimal Allocation of ESS in a Hybrid Wind-Diesel Power System
Directory of Open Access Journals (Sweden)
Hai Lan
2017-02-01
Full Text Available Due to the increasingly serious energy crisis and environmental pollution problem, traditional fossil energy is gradually being replaced by renewable energy in recent years. However, the introduction of renewable energy into power systems will lead to large voltage fluctuations and high capital costs. To solve these problems, an energy storage system (ESS is employed into a power system to reduce total costs and greenhouse gas emissions. Hence, this paper proposes a two-stage method based on a back-propagation neural network (BPNN and hybrid multi-objective particle swarm optimization (HMOPSO to determine the optimal placements and sizes of ESSs in a transmission system. Owing to the uncertainties of renewable energy, a BPNN is utilized to forecast the outputs of the wind power and load demand based on historic data in the city of Madison, USA. Furthermore, power-voltage (P-V sensitivity analysis is conducted in this paper to improve the converge speed of the proposed algorithm, and continuous wind distribution is discretized by a three-point estimation method. The Institute of Electrical and Electronic Engineers (IEEE 30-bus system is adopted to perform case studies. The simulation results of each case clearly demonstrate the necessity for optimal storage allocation and the efficiency of the proposed method.
A parallel neural network training algorithm for control of discrete dynamical systems.
Energy Technology Data Exchange (ETDEWEB)
Gordillo, J. L.; Hanebutte, U. R.; Vitela, J. E.
1998-01-20
In this work we present a parallel neural network controller training code, that uses MPI, a portable message passing environment. A comprehensive performance analysis is reported which compares results of a performance model with actual measurements. The analysis is made for three different load assignment schemes: block distribution, strip mining and a sliding average bin packing (best-fit) algorithm. Such analysis is crucial since optimal load balance can not be achieved because the work load information is not available a priori. The speedup results obtained with the above schemes are compared with those corresponding to the bin packing load balance scheme with perfect load prediction based on a priori knowledge of the computing effort. Two multiprocessor platforms: a SGI/Cray Origin 2000 and a IBM SP have been utilized for this study. It is shown that for the best load balance scheme a parallel efficiency of over 50% for the entire computation is achieved by 17 processors of either parallel computers.
Narasimhan, Seetharam; Chiel, Hillel J; Bhunia, Swarup
2009-01-01
For implantable neural interface applications, it is important to compress data and analyze spike patterns across multiple channels in real time. Such a computational task for online neural data processing requires an innovative circuit-architecture level design approach for low-power, robust and area-efficient hardware implementation. Conventional microprocessor or Digital Signal Processing (DSP) chips would dissipate too much power and are too large in size for an implantable system. In this paper, we propose a novel hardware design approach, referred to as "Preferential Design" that exploits the nature of the neural signal processing algorithm to achieve a low-voltage, robust and area-efficient implementation using nanoscale process technology. The basic idea is to isolate the critical components with respect to system performance and design them more conservatively compared to the noncritical ones. This allows aggressive voltage scaling for low power operation while ensuring robustness and area efficiency. We have applied the proposed approach to a neural signal processing algorithm using the Discrete Wavelet Transform (DWT) and observed significant improvement in power and robustness over conventional design.
Simplified Method of Optimal Sizing of a Renewable Energy Hybrid System for Schools
Directory of Open Access Journals (Sweden)
Jiyeon Kim
2016-11-01
Full Text Available Schools are a suitable public building for renewable energy systems. Renewable energy hybrid systems (REHSs have recently been introduced in schools following a new national regulation that mandates renewable energy utilization. An REHS combines the common renewable-energy sources such as geothermal heat pumps, solar collectors for water heating, and photovoltaic systems with conventional energy systems (i.e., boilers and air-source heat pumps. Optimal design of an REHS by adequate sizing is not a trivial task because it usually requires intensive work including detailed simulation and demand/supply analysis. This type of simulation-based approach for optimization is difficult to implement in practice. To address this, this paper proposes simplified sizing equations for renewable-energy systems of REHSs. A conventional optimization process is used to calculate the optimal combinations of an REHS for cases of different numbers of classrooms and budgets. On the basis of the results, simplified sizing equations that use only the number of classrooms as the input are proposed by regression analysis. A verification test was carried out using an initial conventional optimization process. The results show that the simplified sizing equations predict similar sizing results to the initial process, consequently showing similar capital costs within a 2% error.
A new approach for sizing stand alone photovoltaic systems based in neural networks
Energy Technology Data Exchange (ETDEWEB)
Hontoria, L.; Aguilera, J. [Universidad de Jaen, Dept. de Electronica, Jaen (Spain); Zufiria, P. [UPM Ciudad Universitaria, Dept. de Matematica Aplicada a las Tecnologias de la Informacion, Madrid (Spain)
2005-02-01
Several methods for sizing stand alone photovoltaic (pv) systems has been developed. The more simplistic are called intuitive methods. They are a useful tool for a first approach in sizing stand alone photovoltaic systems. Nevertheless they are very inaccurate. Analytical methods use equations to describe the pv system size as a function of reliability. These ones are more accurate than the previous ones but they are also not accurate enough for sizing of high reliability. In a third group there are methods which use system simulations. These ones are called numerical methods. Many of the analytical methods employ the concept of reliability of the system or the complementary term: loss of load probability (LOLP). In this paper an improvement for obtaining LOLP curves based on the neural network called Multilayer Perceptron (MLP) is presented. A unique MLP for many locations of Spain has been trained and after the training, the MLP is able to generate LOLP curves for any value and location. (Author)
Optimal placement and sizing of multiple distributed generating units in distribution
Directory of Open Access Journals (Sweden)
D. Rama Prabha
2016-06-01
Full Text Available Distributed generation (DG is becoming more important due to the increase in the demands for electrical energy. DG plays a vital role in reducing real power losses, operating cost and enhancing the voltage stability which is the objective function in this problem. This paper proposes a multi-objective technique for optimally determining the location and sizing of multiple distributed generation (DG units in the distribution network with different load models. The loss sensitivity factor (LSF determines the optimal placement of DGs. Invasive weed optimization (IWO is a population based meta-heuristic algorithm based on the behavior of weeds. This algorithm is used to find optimal sizing of the DGs. The proposed method has been tested for different load models on IEEE-33 bus and 69 bus radial distribution systems. This method has been compared with other nature inspired optimization methods. The simulated results illustrate the good applicability and performance of the proposed method.
A hybrid neural network – world cup optimization algorithm for melanoma detection
Directory of Open Access Journals (Sweden)
Razmjooy Navid
2018-03-01
Full Text Available One of the most dangerous cancers in humans is Melanoma. However, early detection of melanoma can help us to cure it completely. This paper presents a new efficient method to detect malignancy in melanoma via images. At first, the extra scales are eliminated by using edge detection and smoothing. Afterwards, the proposed method can be utilized to segment the cancer images. Finally, the extra information is eliminated by morphological operations and used to focus on the area which melanoma boundary potentially exists. To do this, World Cup Optimization algorithm is utilized to optimize an MLP neural Networks (ANN. World Cup Optimization algorithm is a new meta-heuristic algorithm which is recently presented and has a good performance in some optimization problems. WCO is a derivative-free, Meta-Heuristic algorithm, mimicking the world’s FIFA competitions. World cup Optimization algorithm is a global search algorithm while gradient-based back propagation method is local search. In this proposed algorithm, multi-layer perceptron network (MLP employs the problem’s constraints and WCO algorithm attempts to minimize the root mean square error. Experimental results show that the proposed method can develop the performance of the standard MLP algorithm significantly.
Finite time synchronization of memristor-based Cohen-Grossberg neural networks with mixed delays
Chen, Chuan; Li, Lixiang; Peng, Haipeng; Yang, Yixian
2017-01-01
Finite time synchronization, which means synchronization can be achieved in a settling time, is desirable in some practical applications. However, most of the published results on finite time synchronization don't include delays or only include discrete delays. In view of the fact that distributed delays inevitably exist in neural networks, this paper aims to investigate the finite time synchronization of memristor-based Cohen-Grossberg neural networks (MCGNNs) with both discrete delay and di...
Energy Technology Data Exchange (ETDEWEB)
Wan, Xiaodong; Wang, Yuanxun; Zhao, Dawei [Huazhong University of Science and Technology, Wuhan (China)
2016-06-15
The prediction and optimization of weld quality characteristics in small scale resistance spot welding of TC2 titanium alloy were investigated. Grey relational analysis, neural network and genetic algorithm were applied separately. Quality characteristics were selected as nugget diameter, failure load, failure displacement and failure energy. Welding parameters to be optimized were set as electrode force, welding current and welding time. Grey relational analysis was conducted for a rough estimation of the optimum welding parameters. Results showed that welding current played a key role in weld quality improvement. Different back propagation neural network architectures were then arranged to predict multiple quality characteristics. Interaction effects of welding parameters were analyzed with the proposed neural network. Failure load was found more sensitive to the change of welding parameters than nugget diameter. Optimum welding parameters were determined by genetic algorithm. The predicted responses showed good agreement with confirmation experiments.
Jiang, Guangli; Liu, Leibo; Zhu, Wenping; Yin, Shouyi; Wei, Shaojun
2015-09-04
This paper proposes a real-time feature extraction VLSI architecture for high-resolution images based on the accelerated KAZE algorithm. Firstly, a new system architecture is proposed. It increases the system throughput, provides flexibility in image resolution, and offers trade-offs between speed and scaling robustness. The architecture consists of a two-dimensional pipeline array that fully utilizes computational similarities in octaves. Secondly, a substructure (block-serial discrete-time cellular neural network) that can realize a nonlinear filter is proposed. This structure decreases the memory demand through the removal of data dependency. Thirdly, a hardware-friendly descriptor is introduced in order to overcome the hardware design bottleneck through the polar sample pattern; a simplified method to realize rotation invariance is also presented. Finally, the proposed architecture is designed in TSMC 65 nm CMOS technology. The experimental results show a performance of 127 fps in full HD resolution at 200 MHz frequency. The peak performance reaches 181 GOPS and the throughput is double the speed of other state-of-the-art architectures.
Directory of Open Access Journals (Sweden)
Guangli Jiang
2015-09-01
Full Text Available This paper proposes a real-time feature extraction VLSI architecture for high-resolution images based on the accelerated KAZE algorithm. Firstly, a new system architecture is proposed. It increases the system throughput, provides flexibility in image resolution, and offers trade-offs between speed and scaling robustness. The architecture consists of a two-dimensional pipeline array that fully utilizes computational similarities in octaves. Secondly, a substructure (block-serial discrete-time cellular neural network that can realize a nonlinear filter is proposed. This structure decreases the memory demand through the removal of data dependency. Thirdly, a hardware-friendly descriptor is introduced in order to overcome the hardware design bottleneck through the polar sample pattern; a simplified method to realize rotation invariance is also presented. Finally, the proposed architecture is designed in TSMC 65 nm CMOS technology. The experimental results show a performance of 127 fps in full HD resolution at 200 MHz frequency. The peak performance reaches 181 GOPS and the throughput is double the speed of other state-of-the-art architectures.
Energy Technology Data Exchange (ETDEWEB)
Baroni, Douglas B.; Lamy, Carlos A.; Bittencourt, Marcelo S.Q.; Pereira, Claudio M.N.A., E-mail: douglasbaroni@ien.gov.b, E-mail: lamy@ien.gov.b, E-mail: bittenc@ien.gov.b, E-mail: cmnap@ien.gov.b [Instituto de Engenharia Nuclear (IEN/CNEN-RJ), Rio de Janeiro, RJ (Brazil); Cunha Filho, Jurandyr S. [Escola Tecnica Estadual Visconde de Maua (ETEVM/RJ), Rio de Janeiro, RJ (Brazil); Motta, Mauricio S., E-mail: mmotta@cefet-rj.b [Centro Federal de Educacao Tecnologica Celso Suckow da Fonseca (CEFET/RJ), Rio de Janeiro, RJ (Brazil)
2011-07-01
The development of advanced nuclear reactor conceptions depends largely on the amount of available data to the designer. Non invasive ultrasonic techniques can contribute to the evaluation of gas-liquid two-phase regimes in the nuclear thermo-hydraulic circuits. A key-point for success of those techniques is the interpretation of the ultrasonic signal. In this work, a methodology based in artificial neural networks (ANN) is proposed to predict size distribution of bubbles in a bubbly flow. To accomplish that, an air feed system control was used to obtain specific bubbly flows in an experimental system utilizing a Plexiglas vertical bubbly column. Four different size distribution of bubbles were generated. The bubbles were photographed and measured. To evaluate the different size distribution of bubbles it was used the ultrasonic reflected echo on the opposite wall of the column. Then, an ANN has been developed for predicting size distribution of bubbles by using the frequency spectra of the ultrasonic signal as input. A trained artificial neural network using ultrasonic signal in the frequency domain can evaluate with a good precision the size distribution of bubbles generated in this system. (author)
International Nuclear Information System (INIS)
Baroni, Douglas B.; Lamy, Carlos A.; Bittencourt, Marcelo S.Q.; Pereira, Claudio M.N.A.; Cunha Filho, Jurandyr S.; Motta, Mauricio S.
2011-01-01
The development of advanced nuclear reactor conceptions depends largely on the amount of available data to the designer. Non invasive ultrasonic techniques can contribute to the evaluation of gas-liquid two-phase regimes in the nuclear thermo-hydraulic circuits. A key-point for success of those techniques is the interpretation of the ultrasonic signal. In this work, a methodology based in artificial neural networks (ANN) is proposed to predict size distribution of bubbles in a bubbly flow. To accomplish that, an air feed system control was used to obtain specific bubbly flows in an experimental system utilizing a Plexiglas vertical bubbly column. Four different size distribution of bubbles were generated. The bubbles were photographed and measured. To evaluate the different size distribution of bubbles it was used the ultrasonic reflected echo on the opposite wall of the column. Then, an ANN has been developed for predicting size distribution of bubbles by using the frequency spectra of the ultrasonic signal as input. A trained artificial neural network using ultrasonic signal in the frequency domain can evaluate with a good precision the size distribution of bubbles generated in this system. (author)
A discrete optimization method for nuclear fuel management
International Nuclear Information System (INIS)
Argaud, J.P.
1993-04-01
Nuclear loading pattern elaboration can be seen as a combinational optimization problem, of tremendous size and with non-linear cost-functions, and search are always numerically expensive. After a brief introduction of the main aspects of nuclear fuel management, this note presents a new idea to treat the combinational problem by using informations included in the gradient of a cost function. The method is to choose, by direct observation of the gradient, the more interesting changes in fuel loading patterns. An example is then developed to illustrate an operating mode of the method, and finally, connections with simulated annealing and genetic algorithms are described as an attempt to improve search processes. (author). 1 fig., 16 refs
Maschio, Célio; José Schiozer, Denis
2015-01-01
In this article, a new optimization framework to reduce uncertainties in petroleum reservoir attributes using artificial intelligence techniques (neural network and genetic algorithm) is proposed. Instead of using the deterministic values of the reservoir properties, as in a conventional process, the parameters of the probability density function of each uncertain attribute are set as design variables in an optimization process using a genetic algorithm. The objective function (OF) is based on the misfit of a set of models, sampled from the probability density function, and a symmetry factor (which represents the distribution of curves around the history) is used as weight in the OF. Artificial neural networks are trained to represent the production curves of each well and the proxy models generated are used to evaluate the OF in the optimization process. The proposed method was applied to a reservoir with 16 uncertain attributes and promising results were obtained.
ASOP, Shield Calculation, 1-D, Discrete Ordinates Transport
International Nuclear Information System (INIS)
1993-01-01
1 - Nature of physical problem solved: ASOP is a shield optimization calculational system based on the one-dimensional discrete ordinates transport program ANISN. It has been used to design optimum shields for space applications of SNAP zirconium-hydride-uranium- fueled reactors and uranium-oxide fueled thermionic reactors and to design beam stops for the ORELA facility. 2 - Method of solution: ASOP generates coefficients of linear equations describing the logarithm of the dose and dose-weight derivatives as functions of position from data obtained in an automated sequence of ANISN calculations. With the dose constrained to a design value and all dose-weight derivatives required to be equal, the linear equations may be solved for a new set of shield dimensions. Since changes in the shield dimensions may cause the linear functions to change, the entire procedure is repeated until convergence is obtained. The detailed calculations of the radiation transport through shield configurations for every step in the procedure distinguish ASOP from other shield optimization computer code systems which rely on multiple component sources and attenuation coefficients to describe the transport. 3 - Restrictions on the complexity of the problem: Problem size is limited only by machine size
Guaranteed Discrete Energy Optimization on Large Protein Design Problems.
Simoncini, David; Allouche, David; de Givry, Simon; Delmas, Céline; Barbe, Sophie; Schiex, Thomas
2015-12-08
In Computational Protein Design (CPD), assuming a rigid backbone and amino-acid rotamer library, the problem of finding a sequence with an optimal conformation is NP-hard. In this paper, using Dunbrack's rotamer library and Talaris2014 decomposable energy function, we use an exact deterministic method combining branch and bound, arc consistency, and tree-decomposition to provenly identify the global minimum energy sequence-conformation on full-redesign problems, defining search spaces of size up to 10(234). This is achieved on a single core of a standard computing server, requiring a maximum of 66GB RAM. A variant of the algorithm is able to exhaustively enumerate all sequence-conformations within an energy threshold of the optimum. These proven optimal solutions are then used to evaluate the frequencies and amplitudes, in energy and sequence, at which an existing CPD-dedicated simulated annealing implementation may miss the optimum on these full redesign problems. The probability of finding an optimum drops close to 0 very quickly. In the worst case, despite 1,000 repeats, the annealing algorithm remained more than 1 Rosetta unit away from the optimum, leading to design sequences that could differ from the optimal sequence by more than 30% of their amino acids.
Directory of Open Access Journals (Sweden)
Zhenhua Wang
2016-04-01
Full Text Available In this article, the cutting parameters optimization method for aluminum alloy AlMn1Cu in high-speed milling was studied in order to properly select the high-speed cutting parameters. First, a back propagation neural network model for predicting surface roughness of AlMn1Cu was proposed. The prediction model can improve the prediction accuracy and well work out the higher-order nonlinear relationship between surface roughness and cutting parameters. Second, considering the constraints of technical requirements on surface roughness, a mathematical model for optimizing cutting parameters based on the Bayesian neural network prediction model of surface roughness was established so as to obtain the maximum machining efficiency. The genetic algorithm adopting the homogeneous design to initialize population as well as steady-state reproduction without duplicates was also presented. The application indicates that the algorithm can effectively avoid precocity, strengthen global optimization, and increase the calculation efficiency. Finally, a case was presented on the application of the proposed cutting parameters optimization algorithm to optimize the cutting parameters.
Finite-size effect on optimal efficiency of heat engines.
Tajima, Hiroyasu; Hayashi, Masahito
2017-07-01
The optimal efficiency of quantum (or classical) heat engines whose heat baths are n-particle systems is given by the strong large deviation. We give the optimal work extraction process as a concrete energy-preserving unitary time evolution among the heat baths and the work storage. We show that our optimal work extraction turns the disordered energy of the heat baths to the ordered energy of the work storage, by evaluating the ratio of the entropy difference to the energy difference in the heat baths and the work storage, respectively. By comparing the statistical mechanical optimal efficiency with the macroscopic thermodynamic bound, we evaluate the accuracy of the macroscopic thermodynamics with finite-size heat baths from the statistical mechanical viewpoint. We also evaluate the quantum coherence effect on the optimal efficiency of the cycle processes without restricting their cycle time by comparing the classical and quantum optimal efficiencies.
Crop Classification by Forward Neural Network with Adaptive Chaotic Particle Swarm Optimization
Directory of Open Access Journals (Sweden)
Yudong Zhang
2011-05-01
Full Text Available This paper proposes a hybrid crop classifier for polarimetric synthetic aperture radar (SAR images. The feature sets consisted of span image, the H/A/α decomposition, and the gray-level co-occurrence matrix (GLCM based texture features. Then, the features were reduced by principle component analysis (PCA. Finally, a two-hidden-layer forward neural network (NN was constructed and trained by adaptive chaotic particle swarm optimization (ACPSO. K-fold cross validation was employed to enhance generation. The experimental results on Flevoland sites demonstrate the superiority of ACPSO to back-propagation (BP, adaptive BP (ABP, momentum BP (MBP, Particle Swarm Optimization (PSO, and Resilient back-propagation (RPROP methods. Moreover, the computation time for each pixel is only 1.08 × 10−7 s.
Hong, Xia
2006-07-01
In this letter, a Box-Cox transformation-based radial basis function (RBF) neural network is introduced using the RBF neural network to represent the transformed system output. Initially a fixed and moderate sized RBF model base is derived based on a rank revealing orthogonal matrix triangularization (QR decomposition). Then a new fast identification algorithm is introduced using Gauss-Newton algorithm to derive the required Box-Cox transformation, based on a maximum likelihood estimator. The main contribution of this letter is to explore the special structure of the proposed RBF neural network for computational efficiency by utilizing the inverse of matrix block decomposition lemma. Finally, the Box-Cox transformation-based RBF neural network, with good generalization and sparsity, is identified based on the derived optimal Box-Cox transformation and a D-optimality-based orthogonal forward regression algorithm. The proposed algorithm and its efficacy are demonstrated with an illustrative example in comparison with support vector machine regression.
Discrete Optimal Multirate Techniques for Excitation Controller Design of a Synchronous Machine
Directory of Open Access Journals (Sweden)
D. I. Pappas
2016-02-01
Full Text Available An optimal control strategy based on Two-Point-Multirate Controllers (TPMRCs, is used to design a desirable excitation controller of a hydrogenerator system, in order to enhance its dynamic stability characteristics. In the TPMRCs based scheme, the control is constrained to a certain piecewise constant signal, while each of the controlled plant outputs is detected many times over a fundamental sampling period T0. On the basis on this strategy, the original problem is reduced to an associate discrete-time linear quadratic (LQ regulation problem for the performance index with cross product terms, for which a fictitious static state feedback controller is needed to be computed. Simulation results for the actual 117 MVA synchronous generator with conventional exciter supplying line to an infinite grid show the effectiveness of the proposed method which has a quite satisfactory performance.
Layout Optimization of Structures with Finite-size Features using Multiresolution Analysis
DEFF Research Database (Denmark)
Chellappa, S.; Diaz, A. R.; Bendsøe, Martin P.
2004-01-01
A scheme for layout optimization in structures with multiple finite-sized heterogeneities is presented. Multiresolution analysis is used to compute reduced operators (stiffness matrices) representing the elastic behavior of material distributions with heterogeneities of sizes that are comparable...
Neural network-based optimal adaptive output feedback control of a helicopter UAV.
Nodland, David; Zargarzadeh, Hassan; Jagannathan, Sarangapani
2013-07-01
Helicopter unmanned aerial vehicles (UAVs) are widely used for both military and civilian operations. Because the helicopter UAVs are underactuated nonlinear mechanical systems, high-performance controller design for them presents a challenge. This paper introduces an optimal controller design via an output feedback for trajectory tracking of a helicopter UAV, using a neural network (NN). The output-feedback control system utilizes the backstepping methodology, employing kinematic and dynamic controllers and an NN observer. The online approximator-based dynamic controller learns the infinite-horizon Hamilton-Jacobi-Bellman equation in continuous time and calculates the corresponding optimal control input by minimizing a cost function, forward-in-time, without using the value and policy iterations. Optimal tracking is accomplished by using a single NN utilized for the cost function approximation. The overall closed-loop system stability is demonstrated using Lyapunov analysis. Finally, simulation results are provided to demonstrate the effectiveness of the proposed control design for trajectory tracking.
Performance Optimization of Irreversible Air Heat Pumps Considering Size Effect
Bi, Yuehong; Chen, Lingen; Ding, Zemin; Sun, Fengrui
2018-06-01
Considering the size of an irreversible air heat pump (AHP), heating load density (HLD) is taken as thermodynamic optimization objective by using finite-time thermodynamics. Based on an irreversible AHP with infinite reservoir thermal-capacitance rate model, the expression of HLD of AHP is put forward. The HLD optimization processes are studied analytically and numerically, which consist of two aspects: (1) to choose pressure ratio; (2) to distribute heat-exchanger inventory. Heat reservoir temperatures, heat transfer performance of heat exchangers as well as irreversibility during compression and expansion processes are important factors influencing on the performance of an irreversible AHP, which are characterized with temperature ratio, heat exchanger inventory as well as isentropic efficiencies, respectively. Those impacts of parameters on the maximum HLD are thoroughly studied. The research results show that HLD optimization can make the size of the AHP system smaller and improve the compactness of system.
International Nuclear Information System (INIS)
Olcan, Ceyda
2015-01-01
Highlights: • An analytical optimal sizing model is proposed for PV water pumping systems. • The objectives are chosen as deficiency of power supply and life-cycle costs. • The crop water requirements are estimated for a citrus tree yard in Antalya. • The optimal tilt angles are calculated for fixed, seasonal and monthly changes. • The sizing results showed the validity of the proposed analytical model. - Abstract: Stand-alone photovoltaic (PV) water pumping systems effectively use solar energy for irrigation purposes in remote areas. However the random variability and unpredictability of solar energy makes difficult the penetration of PV implementations and complicate the system design. An optimal sizing of these systems proves to be essential. This paper recommends a techno-economic optimization model to determine optimally the capacity of the components of PV water pumping system using a water storage tank. The proposed model is developed regarding the reliability and cost indicators, which are the deficiency of power supply probability and life-cycle costs, respectively. The novelty is that the proposed optimization model is analytically defined for two-objectives and it is able to find a compromise solution. The sizing of a stand-alone PV water pumping system comprises a detailed analysis of crop water requirements and optimal tilt angles. Besides the necessity of long solar radiation and temperature time series, the accurate forecasts of water supply needs have to be determined. The calculation of the optimal tilt angle for yearly, seasonally and monthly frequencies results in higher system efficiency. It is, therefore, suggested to change regularly the tilt angle in order to maximize solar energy output. The proposed optimal sizing model incorporates all these improvements and can accomplish a comprehensive optimization of PV water pumping systems. A case study is conducted considering the irrigation of citrus trees yard located in Antalya, Turkey
Distinct timing mechanisms produce discrete and continuous movements.
Directory of Open Access Journals (Sweden)
Raoul Huys
2008-04-01
Full Text Available The differentiation of discrete and continuous movement is one of the pillars of motor behavior classification. Discrete movements have a definite beginning and end, whereas continuous movements do not have such discriminable end points. In the past decade there has been vigorous debate whether this classification implies different control processes. This debate up until the present has been empirically based. Here, we present an unambiguous non-empirical classification based on theorems in dynamical system theory that sets discrete and continuous movements apart. Through computational simulations of representative modes of each class and topological analysis of the flow in state space, we show that distinct control mechanisms underwrite discrete and fast rhythmic movements. In particular, we demonstrate that discrete movements require a time keeper while fast rhythmic movements do not. We validate our computational findings experimentally using a behavioral paradigm in which human participants performed finger flexion-extension movements at various movement paces and under different instructions. Our results demonstrate that the human motor system employs different timing control mechanisms (presumably via differential recruitment of neural subsystems to accomplish varying behavioral functions such as speed constraints.
Optimal Multi-Level Lot Sizing for Requirements Planning Systems
Earle Steinberg; H. Albert Napier
1980-01-01
The wide spread use of advanced information systems such as Material Requirements Planning (MRP) has significantly altered the practice of dependent demand inventory management. Recent research has focused on development of multi-level lot sizing heuristics for such systems. In this paper, we develop an optimal procedure for the multi-period, multi-product, multi-level lot sizing problem by modeling the system as a constrained generalized network with fixed charge arcs and side constraints. T...
Bayesian estimation of the discrete coefficient of determination.
Chen, Ting; Braga-Neto, Ulisses M
2016-12-01
The discrete coefficient of determination (CoD) measures the nonlinear interaction between discrete predictor and target variables and has had far-reaching applications in Genomic Signal Processing. Previous work has addressed the inference of the discrete CoD using classical parametric and nonparametric approaches. In this paper, we introduce a Bayesian framework for the inference of the discrete CoD. We derive analytically the optimal minimum mean-square error (MMSE) CoD estimator, as well as a CoD estimator based on the Optimal Bayesian Predictor (OBP). For the latter estimator, exact expressions for its bias, variance, and root-mean-square (RMS) are given. The accuracy of both Bayesian CoD estimators with non-informative and informative priors, under fixed or random parameters, is studied via analytical and numerical approaches. We also demonstrate the application of the proposed Bayesian approach in the inference of gene regulatory networks, using gene-expression data from a previously published study on metastatic melanoma.
Convergence of posteriors for discretized log Gaussian Cox processes
DEFF Research Database (Denmark)
Waagepetersen, Rasmus Plenge
2004-01-01
In Markov chain Monte Carlo posterior computation for log Gaussian Cox processes (LGCPs) a discretization of the continuously indexed Gaussian field is required. It is demonstrated that approximate posterior expectations computed from discretized LGCPs converge to the exact posterior expectations...... when the cell sizes of the discretization tends to zero. The effect of discretization is studied in a data example....
Rajkumar, T.; Aragon, Cecilia; Bardina, Jorge; Britten, Roy
2002-01-01
A fast, reliable way of predicting aerodynamic coefficients is produced using a neural network optimized by a genetic algorithm. Basic aerodynamic coefficients (e.g. lift, drag, pitching moment) are modelled as functions of angle of attack and Mach number. The neural network is first trained on a relatively rich set of data from wind tunnel tests of numerical simulations to learn an overall model. Most of the aerodynamic parameters can be well-fitted using polynomial functions. A new set of data, which can be relatively sparse, is then supplied to the network to produce a new model consistent with the previous model and the new data. Because the new model interpolates realistically between the sparse test data points, it is suitable for use in piloted simulations. The genetic algorithm is used to choose a neural network architecture to give best results, avoiding over-and under-fitting of the test data.
Energy Technology Data Exchange (ETDEWEB)
Wijayasekara, Dumidu, E-mail: wija2589@vandals.uidaho.edu [Department of Computer Science, University of Idaho, 1776 Science Center Drive, Idaho Falls, ID 83402 (United States); Manic, Milos [Department of Computer Science, University of Idaho, 1776 Science Center Drive, Idaho Falls, ID 83402 (United States); Sabharwall, Piyush [Idaho National Laboratory, Idaho Falls, ID (United States); Utgikar, Vivek [Department of Chemical Engineering, University of Idaho, Idaho Falls, ID 83402 (United States)
2011-07-15
Highlights: > Performance prediction of PCHE using artificial neural networks. > Evaluating artificial neural network performance for PCHE modeling. > Selection of over-training resilient artificial neural networks. > Artificial neural network architecture selection for modeling problems with small data sets. - Abstract: Artificial Neural Networks (ANN) have been used in the past to predict the performance of printed circuit heat exchangers (PCHE) with satisfactory accuracy. Typically published literature has focused on optimizing ANN using a training dataset to train the network and a testing dataset to evaluate it. Although this may produce outputs that agree with experimental results, there is a risk of over-training or over-learning the network rather than generalizing it, which should be the ultimate goal. An over-trained network is able to produce good results with the training dataset but fails when new datasets with subtle changes are introduced. In this paper we present EBaLM-OTR (error back propagation and Levenberg-Marquardt algorithms for over training resilience) technique, which is based on a previously discussed method of selecting neural network architecture that uses a separate validation set to evaluate different network architectures based on mean square error (MSE), and standard deviation of MSE. The method uses k-fold cross validation. Therefore in order to select the optimal architecture for the problem, the dataset is divided into three parts which are used to train, validate and test each network architecture. Then each architecture is evaluated according to their generalization capability and capability to conform to original data. The method proved to be a comprehensive tool in identifying the weaknesses and advantages of different network architectures. The method also highlighted the fact that the architecture with the lowest training error is not always the most generalized and therefore not the optimal. Using the method the testing
International Nuclear Information System (INIS)
Wijayasekara, Dumidu; Manic, Milos; Sabharwall, Piyush; Utgikar, Vivek
2011-01-01
Highlights: → Performance prediction of PCHE using artificial neural networks. → Evaluating artificial neural network performance for PCHE modeling. → Selection of over-training resilient artificial neural networks. → Artificial neural network architecture selection for modeling problems with small data sets. - Abstract: Artificial Neural Networks (ANN) have been used in the past to predict the performance of printed circuit heat exchangers (PCHE) with satisfactory accuracy. Typically published literature has focused on optimizing ANN using a training dataset to train the network and a testing dataset to evaluate it. Although this may produce outputs that agree with experimental results, there is a risk of over-training or over-learning the network rather than generalizing it, which should be the ultimate goal. An over-trained network is able to produce good results with the training dataset but fails when new datasets with subtle changes are introduced. In this paper we present EBaLM-OTR (error back propagation and Levenberg-Marquardt algorithms for over training resilience) technique, which is based on a previously discussed method of selecting neural network architecture that uses a separate validation set to evaluate different network architectures based on mean square error (MSE), and standard deviation of MSE. The method uses k-fold cross validation. Therefore in order to select the optimal architecture for the problem, the dataset is divided into three parts which are used to train, validate and test each network architecture. Then each architecture is evaluated according to their generalization capability and capability to conform to original data. The method proved to be a comprehensive tool in identifying the weaknesses and advantages of different network architectures. The method also highlighted the fact that the architecture with the lowest training error is not always the most generalized and therefore not the optimal. Using the method the
Component sizing optimization of plug-in hybrid electric vehicles
International Nuclear Information System (INIS)
Wu, Xiaolan; Cao, Binggang; Li, Xueyan; Xu, Jun; Ren, Xiaolong
2011-01-01
Plug-in hybrid electric vehicles (PHEVs) are considered as one of the most promising means to improve the near-term sustainability of the transportation and stationary energy sectors. This paper describes a methodology for the optimization of PHEVs component sizing using parallel chaos optimization algorithm (PCOA). In this approach, the objective function is defined so as to minimize the drivetrain cost. In addition, the driving performance requirements are considered as constraints. Finally, the optimization process is performed over three different all electric range (AER) and two types of batteries. The results from computer simulation show the effectiveness of the approach and the reduction in drivetrian cost while ensuring the vehicle performance.
Adaptive Control of Nonlinear Discrete-Time Systems by Using OS-ELM Neural Networks
Directory of Open Access Journals (Sweden)
Xiao-Li Li
2014-01-01
Full Text Available As a kind of novel feedforward neural network with single hidden layer, ELM (extreme learning machine neural networks are studied for the identification and control of nonlinear dynamic systems. The property of simple structure and fast convergence of ELM can be shown clearly. In this paper, we are interested in adaptive control of nonlinear dynamic plants by using OS-ELM (online sequential extreme learning machine neural networks. Based on data scope division, the problem that training process of ELM neural network is sensitive to the initial training data is also solved. According to the output range of the controlled plant, the data corresponding to this range will be used to initialize ELM. Furthermore, due to the drawback of conventional adaptive control, when the OS-ELM neural network is used for adaptive control of the system with jumping parameters, the topological structure of the neural network can be adjusted dynamically by using multiple model switching strategy, and an MMAC (multiple model adaptive control will be used to improve the control performance. Simulation results are included to complement the theoretical results.
International Nuclear Information System (INIS)
Rong Bao; Rui Xiaoting; Tao Ling
2012-01-01
In this paper, a dynamic modeling method and an active vibration control scheme for a smart flexible four-bar linkage mechanism featuring piezoelectric actuators and strain gauge sensors are presented. The dynamics of this smart mechanism is described by the Discrete Time Transfer Matrix Method of Multibody System (MS-DTTMM). Then a nonlinear fuzzy neural network control is employed to suppress the vibration of this smart mechanism. For improving the dynamic performance of the fuzzy neural network, a genetic algorithm based on the MS-DTTMM is designed offline to tune the initial parameters of the fuzzy neural network. The MS-DTTMM avoids the global dynamics equations of the system, which results in the matrices involved are always very small, so the computational efficiency of the dynamic analysis and control system optimization can be greatly improved. Formulations of the method as well as a numerical simulation are given to demonstrate the proposed dynamic method and control scheme.
Calibration of neural networks using genetic algorithms, with application to optimal path planning
Smith, Terence R.; Pitney, Gilbert A.; Greenwood, Daniel
1987-01-01
Genetic algorithms (GA) are used to search the synaptic weight space of artificial neural systems (ANS) for weight vectors that optimize some network performance function. GAs do not suffer from some of the architectural constraints involved with other techniques and it is straightforward to incorporate terms into the performance function concerning the metastructure of the ANS. Hence GAs offer a remarkably general approach to calibrating ANS. GAs are applied to the problem of calibrating an ANS that finds optimal paths over a given surface. This problem involves training an ANS on a relatively small set of paths and then examining whether the calibrated ANS is able to find good paths between arbitrary start and end points on the surface.
Zhang, Qing; Beard, Daniel A; Schlick, Tamar
2003-12-01
Salt-mediated electrostatics interactions play an essential role in biomolecular structures and dynamics. Because macromolecular systems modeled at atomic resolution contain thousands of solute atoms, the electrostatic computations constitute an expensive part of the force and energy calculations. Implicit solvent models are one way to simplify the model and associated calculations, but they are generally used in combination with standard atomic models for the solute. To approximate electrostatics interactions in models on the polymer level (e.g., supercoiled DNA) that are simulated over long times (e.g., milliseconds) using Brownian dynamics, Beard and Schlick have developed the DiSCO (Discrete Surface Charge Optimization) algorithm. DiSCO represents a macromolecular complex by a few hundred discrete charges on a surface enclosing the system modeled by the Debye-Hückel (screened Coulombic) approximation to the Poisson-Boltzmann equation, and treats the salt solution as continuum solvation. DiSCO can represent the nucleosome core particle (>12,000 atoms), for example, by 353 discrete surface charges distributed on the surfaces of a large disk for the nucleosome core particle and a slender cylinder for the histone tail; the charges are optimized with respect to the Poisson-Boltzmann solution for the electric field, yielding a approximately 5.5% residual. Because regular surfaces enclosing macromolecules are not sufficiently general and may be suboptimal for certain systems, we develop a general method to construct irregular models tailored to the geometry of macromolecules. We also compare charge optimization based on both the electric field and electrostatic potential refinement. Results indicate that irregular surfaces can lead to a more accurate approximation (lower residuals), and the refinement in terms of the electric field is more robust. We also show that surface smoothing for irregular models is important, that the charge optimization (by the TNPACK
Optimizing Semantic Pointer Representations for Symbol-Like Processing in Spiking Neural Networks.
Gosmann, Jan; Eliasmith, Chris
2016-01-01
The Semantic Pointer Architecture (SPA) is a proposal of specifying the computations and architectural elements needed to account for cognitive functions. By means of the Neural Engineering Framework (NEF) this proposal can be realized in a spiking neural network. However, in any such network each SPA transformation will accumulate noise. By increasing the accuracy of common SPA operations, the overall network performance can be increased considerably. As well, the representations in such networks present a trade-off between being able to represent all possible values and being only able to represent the most likely values, but with high accuracy. We derive a heuristic to find the near-optimal point in this trade-off. This allows us to improve the accuracy of common SPA operations by up to 25 times. Ultimately, it allows for a reduction of neuron number and a more efficient use of both traditional and neuromorphic hardware, which we demonstrate here.
Wang, Zhongqi; Yang, Bo; Kang, Yonggang; Yang, Yuan
2016-01-01
Fixture plays an important part in constraining excessive sheet metal part deformation at machining, assembly, and measuring stages during the whole manufacturing process. However, it is still a difficult and nontrivial task to design and optimize sheet metal fixture locating layout at present because there is always no direct and explicit expression describing sheet metal fixture locating layout and responding deformation. To that end, an RBF neural network prediction model is proposed in this paper to assist design and optimization of sheet metal fixture locating layout. The RBF neural network model is constructed by training data set selected by uniform sampling and finite element simulation analysis. Finally, a case study is conducted to verify the proposed method.
Effect of the size of an artificial neural network used as pattern identifier
International Nuclear Information System (INIS)
Reynoso V, M.R.; Vega C, J.J.
2003-01-01
A novel way to extract relevant parameters associated with the outgoing ions from nuclear reactions, obtained by digitizing the signals provided by a Bragg curve spectrometer (BCS) is presented. This allowed the implementation of a more thorough pulse-shape analysis. Due to the complexity of this task, it was required to take advantage of new and more powerful computational paradigms. This was fulfilled using a back-propagation artificial neural network (ANN) as a pattern identifier. Over training of ANNs is a common problem during the training stage. In the performance of the ANN there is a compromise between its size and the size of the training set. Here, this effect will be illustrated in relation to the problem of Bragg Curve (BC) identification. (Author)
Effect of the size of an artificial neural network used as pattern identifier
Energy Technology Data Exchange (ETDEWEB)
Reynoso V, M.R.; Vega C, J.J. [ININ, 52045 Ocoyoacac, Estado de Mexico (Mexico)
2003-07-01
A novel way to extract relevant parameters associated with the outgoing ions from nuclear reactions, obtained by digitizing the signals provided by a Bragg curve spectrometer (BCS) is presented. This allowed the implementation of a more thorough pulse-shape analysis. Due to the complexity of this task, it was required to take advantage of new and more powerful computational paradigms. This was fulfilled using a back-propagation artificial neural network (ANN) as a pattern identifier. Over training of ANNs is a common problem during the training stage. In the performance of the ANN there is a compromise between its size and the size of the training set. Here, this effect will be illustrated in relation to the problem of Bragg Curve (BC) identification. (Author)
Multi-objective optimization design method of radiation shielding
International Nuclear Information System (INIS)
Yang Shouhai; Wang Weijin; Lu Daogang; Chen Yixue
2012-01-01
Due to the shielding design goals of diversification and uncertain process of many factors, it is necessary to develop an optimization design method of intelligent shielding by which the shielding scheme selection will be achieved automatically and the uncertainties of human impact will be reduced. For economical feasibility to achieve a radiation shielding design for automation, the multi-objective genetic algorithm optimization of screening code which combines the genetic algorithm and discrete-ordinate method was developed to minimize the costs, size, weight, and so on. This work has some practical significance for gaining the optimization design of shielding. (authors)
Energy Technology Data Exchange (ETDEWEB)
Larson, David B. [Stanford University School of Medicine, Department of Radiology, Stanford, CA (United States)
2014-10-15
The principle of ALARA (dose as low as reasonably achievable) calls for dose optimization rather than dose reduction, per se. Optimization of CT radiation dose is accomplished by producing images of acceptable diagnostic image quality using the lowest dose method available. Because it is image quality that constrains the dose, CT dose optimization is primarily a problem of image quality rather than radiation dose. Therefore, the primary focus in CT radiation dose optimization should be on image quality. However, no reliable direct measure of image quality has been developed for routine clinical practice. Until such measures become available, size-specific dose estimates (SSDE) can be used as a reasonable image-quality estimate. The SSDE method of radiation dose optimization for CT abdomen and pelvis consists of plotting SSDE for a sample of examinations as a function of patient size, establishing an SSDE threshold curve based on radiologists' assessment of image quality, and modifying protocols to consistently produce doses that are slightly above the threshold SSDE curve. Challenges in operationalizing CT radiation dose optimization include data gathering and monitoring, managing the complexities of the numerous protocols, scanners and operators, and understanding the relationship of the automated tube current modulation (ATCM) parameters to image quality. Because CT manufacturers currently maintain their ATCM algorithms as secret for proprietary reasons, prospective modeling of SSDE for patient populations is not possible without reverse engineering the ATCM algorithm and, hence, optimization by this method requires a trial-and-error approach. (orig.)
Discrete Bose-Einstein spectra
International Nuclear Information System (INIS)
Vlad, Valentin I.; Ionescu-Pallas, Nicholas
2001-03-01
The Bose-Einstein energy spectrum of a quantum gas, confined in a rigid cubic box, is shown to become discrete and strongly dependent on the box geometry (size L), temperature, T and atomic mass number, A at , in the region of small γ=A at TV 1/3 . This behavior is the consequence of the random state degeneracy in the box. Furthermore, we demonstrate that the total energy does not obey the conventional law any longer, but a new law, which depends on γ and on the quantum gas fugacity. This energy law imposes a faster decrease to zero than it is classically expected, for γ→0. The lighter the gas atoms, the higher the temperatures or the box size, for the same effects in the discrete Bose-Einstein regime. (author)
Particle Swarm Optimization-based BP Neural Network for UHV DC Insulator Pollution Forecasting
Directory of Open Access Journals (Sweden)
Fangcheng Lü
2014-02-01
Full Text Available In order to realize the forecasting of the UHV DC insulator's pollution conditions, we introduced a PSOBP algorithm. A BP neural network (BPNN with leakage current, temperature, relative humidity and dew point as input neurons, and ESDD as output neuron was built to forecast the ESDD. The PSO was used to optimize the the BPNN, which had great improved the convergence rate of the BP neural network. The dew point as a brand new input unit has improved the iteration speed of the PSOBP algorithm in this study. It was the first time that the PSOBP algorithm was applied to the UHV DC insulator pollution forecasting. The experiment results showed that the method had great advantages in accuracy and speed of convergence. The research showed that this algorithm was suitable for the UHV DC insulator pollution forecasting.
Optimizing the maximum reported cluster size in the spatial scan statistic for ordinal data.
Kim, Sehwi; Jung, Inkyung
2017-01-01
The spatial scan statistic is an important tool for spatial cluster detection. There have been numerous studies on scanning window shapes. However, little research has been done on the maximum scanning window size or maximum reported cluster size. Recently, Han et al. proposed to use the Gini coefficient to optimize the maximum reported cluster size. However, the method has been developed and evaluated only for the Poisson model. We adopt the Gini coefficient to be applicable to the spatial scan statistic for ordinal data to determine the optimal maximum reported cluster size. Through a simulation study and application to a real data example, we evaluate the performance of the proposed approach. With some sophisticated modification, the Gini coefficient can be effectively employed for the ordinal model. The Gini coefficient most often picked the optimal maximum reported cluster sizes that were the same as or smaller than the true cluster sizes with very high accuracy. It seems that we can obtain a more refined collection of clusters by using the Gini coefficient. The Gini coefficient developed specifically for the ordinal model can be useful for optimizing the maximum reported cluster size for ordinal data and helpful for properly and informatively discovering cluster patterns.
Naikwad, S. N.; Dudul, S. V.
2009-01-01
A focused time lagged recurrent neural network (FTLR NN) with gamma memory filter is designed to learn the subtle complex dynamics of a typical CSTR process. Continuous stirred tank reactor exhibits complex nonlinear operations where reaction is exothermic. It is noticed from literature review that process control of CSTR using neuro-fuzzy systems was attempted by many, but optimal neural network model for identification of CSTR process is not yet available. As CSTR process includes tempora...
Optimizing the crystal size and habit of beta-sitosterol in suspension
DEFF Research Database (Denmark)
von Bonsdorff-Nikander, Anna; Rantanen, Jukka; Christiansen, Leena
2003-01-01
surfactant, polysorbate 80, has on crystal size distribution and the polymorphic form. This study describes the optimization of the crystallization process, with the object of preparing crystals as small as possible. Particle size distribution and habit were analyzed using optical microscopy, and the crystal...
Discrete variational Hamiltonian mechanics
International Nuclear Information System (INIS)
Lall, S; West, M
2006-01-01
The main contribution of this paper is to present a canonical choice of a Hamiltonian theory corresponding to the theory of discrete Lagrangian mechanics. We make use of Lagrange duality and follow a path parallel to that used for construction of the Pontryagin principle in optimal control theory. We use duality results regarding sensitivity and separability to show the relationship between generating functions and symplectic integrators. We also discuss connections to optimal control theory and numerical algorithms
Genetic algorithms used to optimize an artificial neural network design used in neutron spectrometry
International Nuclear Information System (INIS)
Arteaga A, T.; Ortiz R, J. M.; Vega C, H. R.
2016-10-01
Artificial neural networks (Ann) are widely used; it which consist of an input layer, one or more hidden layers and an output layer; these layers contain neurons and each has connections called weights, where the knowledge are allowed and let to Ann solve problems proposed. These Ann is used to reconstruction of the energy spectrum of neutrons from count rates and develop Bonner sphere neutron dosimetry. Currently, we have developed Ann with high performance and generalization ability. Determine your optimal architecture is usually a difficult task, an exhaustive search of all possible combinations of parameters is rarely possible further training of the neural network with random initial weights can cause two major drawbacks: it can stuck in local minima or converge very slowly. In this project it will be used Genetic Algorithms (Ga); which are based on the principle or analogy of evolution through natural selection and has shown to be very effective in optimizing complex search functions and large spaces or to find a near optimal overall efficiency. The aim is to decrease the architecture in number of hidden neurons and therefore the total number of connections is reducing. The benefits obtained by optimizing the network are that the number of connections would be considerably smaller and thus the computational complexity, hardware integration, resources will be lower such that will allow to be even more viable implemented. To use the Ga three problems must be solve: 1) coding the problem into chromosomes. 2) Construct a fitness function. 3) Proper selection of genetic operators; crossover, selection, mutation. As a result, the scientific knowledge obtained can to be applied to similar problems having a reference parameters used and their impact on the optimization would to be generated. It concluded that the input layer and output are subject to the problem; the Ga propose the optimal number of neurons in the hidden layer without losing the quality of the
International Nuclear Information System (INIS)
Kucuksari, Sadik; Khaleghi, Amirreza M.; Hamidi, Maryam; Zhang, Ye; Szidarovszky, Ferenc; Bayraksan, Guzin; Son, Young-Jun
2014-01-01
Highlights: • The optimal size and locations for PV units for campus environments are achieved. • The GIS module finds the suitable rooftops and their panel capacity. • The optimization module maximizes the long-term profit of PV installations. • The simulation module evaluates the voltage profile of the distribution network. • The proposed work has been successfully demonstrated for a real university campus. - Abstract: Finding the optimal size and locations for Photovoltaic (PV) units has been a major challenge for distribution system planners and researchers. In this study, a framework is proposed to integrate Geographical Information Systems (GIS), mathematical optimization, and simulation modules to obtain the annual optimal placement and size of PV units for the next two decades in a campus area environment. First, a GIS module is developed to find the suitable rooftops and their panel capacity considering the amount of solar radiation, slope, elevation, and aspect. The optimization module is then used to maximize the long-term net profit of PV installations considering various costs of investment, inverter replacement, operation, and maintenance as well as savings from consuming less conventional energy. A voltage profile of the electricity distribution network is then investigated in the simulation module. In the case of voltage limit violation by intermittent PV generations or load fluctuations, two mitigation strategies, reallocation of the PV units or installation of a local storage unit, are suggested. The proposed framework has been implemented in a real campus area, and the results show that it can effectively be used for long-term installation planning of PV panels considering both the cost and power quality
A discrete-space urban model with environmental amenities
Liaila Tajibaeva; Robert G. Haight; Stephen Polasky
2008-01-01
This paper analyzes the effects of providing environmental amenities associated with open space in a discrete-space urban model and characterizes optimal provision of open space across a metropolitan area. The discrete-space model assumes distinct neighborhoods in which developable land is homogeneous within a neighborhood but heterogeneous across neighborhoods. Open...
Directory of Open Access Journals (Sweden)
T.E. Müller
Full Text Available Abstract There are typically three broad categories of structural optimization namely size, shape and topology. Over the past few decades various researchers have focused on developing techniques for optimizing structures by considering either one or a combination of these aspects. In this paper the efficiency of these techniques are investigated in an effort to quantify the improvement of the result obtained by utilizing a more complex optimization routine. The percentage of the structural weight saved and computational effort required are used as measures to compare these techniques. The well-known genetic algorithm with elitism is used to perform these tests on various benchmark structures found in literature. Some of the results that are obtained include that a simultaneous approach produces, on average, a 22 % better solution than a simple size optimization and a 12 % improvement when compared to a staged approach where the size, shape and topology of the structure is considered sequentially. From these results, it is concluded that a significant saving can be made by using a more complex optimization routine, such as a simultaneous approach.
An Improved Genetic Algorithm for Optimal Stationary Energy Storage System Locating and Sizing
Directory of Open Access Journals (Sweden)
Bin Wang
2014-10-01
Full Text Available The application of a stationary ultra-capacitor energy storage system (ESS in urban rail transit allows for the recuperation of vehicle braking energy for increasing energy savings as well as for a better vehicle voltage profile. This paper aims to obtain the best energy savings and voltage profile by optimizing the location and size of ultra-capacitors. This paper firstly raises the optimization objective functions from the perspectives of energy savings, regenerative braking cancellation and installation cost, respectively. Then, proper mathematical models of the DC (direct current traction power supply system are established to simulate the electrical load-flow of the traction supply network, and the optimization objections are evaluated in the example of a Chinese metro line. Ultimately, a methodology for optimal ultra-capacitor energy storage system locating and sizing is put forward based on the improved genetic algorithm. The optimized result shows that certain preferable and compromised schemes of ESSs’ location and size can be obtained, acting as a compromise between satisfying better energy savings, voltage profile and lower installation cost.
Directory of Open Access Journals (Sweden)
Hao Yin
2014-01-01
Full Text Available For SLA-aware service composition problem (SSC, an optimization model for this algorithm is built, and a hybrid multiobjective discrete particle swarm optimization algorithm (HMDPSO is also proposed in this paper. According to the characteristic of this problem, a particle updating strategy is designed by introducing crossover operator. In order to restrain particle swarm’s premature convergence and increase its global search capacity, the swarm diversity indicator is introduced and a particle mutation strategy is proposed to increase the swarm diversity. To accelerate the process of obtaining the feasible particle position, a local search strategy based on constraint domination is proposed and incorporated into the proposed algorithm. At last, some parameters in the algorithm HMDPSO are analyzed and set with relative proper values, and then the algorithm HMDPSO and the algorithm HMDPSO+ incorporated by local search strategy are compared with the recently proposed related algorithms on different scale cases. The results show that algorithm HMDPSO+ can solve the SSC problem more effectively.
Optimal Investment Timing and Size of a Logistics Park: A Real Options Perspective
Directory of Open Access Journals (Sweden)
Dezhi Zhang
2017-01-01
Full Text Available This paper uses a real options approach to address optimal timing and size of a logistics park investment with logistics demand volatility. Two important problems are examined: when should an investment be introduced, and what size should it be? A real option model is proposed to explicitly incorporate the effect of government subsidies on logistics park investment. Logistic demand that triggers the threshold for investment in a logistics park project is explored analytically. Comparative static analyses of logistics park investment are also carried out. Our analytical results show that (1 investors will select smaller sized logistics parks and prepone the investment if government subsidies are considered; (2 the real option will postpone the optimal investment timing of logistics parks compared with net present value approach; and (3 logistic demands can significantly affect the optimal investment size and timing of logistics park investment.
Component sizing optimization of plug-in hybrid electric vehicles
Energy Technology Data Exchange (ETDEWEB)
Wu, Xiaolan; Cao, Binggang; Li, Xueyan; Xu, Jun; Ren, Xiaolong [School of Mechanical Engineering, Xi' an Jiaotong University, Xi' an, 710049 (China)
2011-03-15
Plug-in hybrid electric vehicles (PHEVs) are considered as one of the most promising means to improve the near-term sustainability of the transportation and stationary energy sectors. This paper describes a methodology for the optimization of PHEVs component sizing using parallel chaos optimization algorithm (PCOA). In this approach, the objective function is defined so as to minimize the drivetrain cost. In addition, the driving performance requirements are considered as constraints. Finally, the optimization process is performed over three different all electric range (AER) and two types of batteries. The results from computer simulation show the effectiveness of the approach and the reduction in drivetrian cost while ensuring the vehicle performance. (author)
Approximating the constellation constrained capacity of the MIMO channel with discrete input
DEFF Research Database (Denmark)
Yankov, Metodi Plamenov; Forchhammer, Søren; Larsen, Knud J.
2015-01-01
In this paper the capacity of a Multiple Input Multiple Output (MIMO) channel is considered, subject to average power constraint, for multi-dimensional discrete input, in the case when no channel state information is available at the transmitter. We prove that when the constellation size grows, t...... for the equivalent orthogonal channel, obtained by the singular value decomposition. Furthermore, lower bounds on the constrained capacity are derived for the cases of square and tall MIMO matrix, by optimizing the constellation for the equivalent channel, obtained by QR decomposition....
Global optimization of truss topology with discrete bar areas—Part I: Theory of relaxed problems
DEFF Research Database (Denmark)
Achtziger, Wolfgang; Stolpe, Mathias
2008-01-01
the case of discrete areas. This problem is of major practical relevance if the truss must be built from pre-produced bars with given areas. As a special case, we consider the design problem for a single bar area, i.e., a 0/1-problem. In contrast to heuristic methods considered in other approaches, Part I....... The main issue of the paper and of the approach lies in the fact that the relaxed nonlinear optimization problem can be formulated as a quadratic program (QP). Here the paper generalizes and extends the available theory from the literature. Although the Hessian of this QP is indefinite, it is possible...
Huang, Si-Da; Shang, Cheng; Zhang, Xiao-Jie; Liu, Zhi-Pan
2017-09-01
While the underlying potential energy surface (PES) determines the structure and other properties of a material, it has been frustrating to predict new materials from theory even with the advent of supercomputing facilities. The accuracy of the PES and the efficiency of PES sampling are two major bottlenecks, not least because of the great complexity of the material PES. This work introduces a "Global-to-Global" approach for material discovery by combining for the first time a global optimization method with neural network (NN) techniques. The novel global optimization method, named the stochastic surface walking (SSW) method, is carried out massively in parallel for generating a global training data set, the fitting of which by the atom-centered NN produces a multi-dimensional global PES; the subsequent SSW exploration of large systems with the analytical NN PES can provide key information on the thermodynamics and kinetics stability of unknown phases identified from global PESs. We describe in detail the current implementation of the SSW-NN method with particular focuses on the size of the global data set and the simultaneous energy/force/stress NN training procedure. An important functional material, TiO 2 , is utilized as an example to demonstrate the automated global data set generation, the improved NN training procedure and the application in material discovery. Two new TiO 2 porous crystal structures are identified, which have similar thermodynamics stability to the common TiO 2 rutile phase and the kinetics stability for one of them is further proved from SSW pathway sampling. As a general tool for material simulation, the SSW-NN method provides an efficient and predictive platform for large-scale computational material screening.
Optimal path-finding through mental exploration based on neural energy field gradients.
Wang, Yihong; Wang, Rubin; Zhu, Yating
2017-02-01
Rodent animal can accomplish self-locating and path-finding task by forming a cognitive map in the hippocampus representing the environment. In the classical model of the cognitive map, the system (artificial animal) needs large amounts of physical exploration to study spatial environment to solve path-finding problems, which costs too much time and energy. Although Hopfield's mental exploration model makes up for the deficiency mentioned above, the path is still not efficient enough. Moreover, his model mainly focused on the artificial neural network, and clear physiological meanings has not been addressed. In this work, based on the concept of mental exploration, neural energy coding theory has been applied to the novel calculation model to solve the path-finding problem. Energy field is constructed on the basis of the firing power of place cell clusters, and the energy field gradient can be used in mental exploration to solve path-finding problems. The study shows that the new mental exploration model can efficiently find the optimal path, and present the learning process with biophysical meaning as well. We also analyzed the parameters of the model which affect the path efficiency. This new idea verifies the importance of place cell and synapse in spatial memory and proves that energy coding is effective to study cognitive activities. This may provide the theoretical basis for the neural dynamics mechanism of spatial memory.
Directory of Open Access Journals (Sweden)
Golmohammadi Hassan
2013-01-01
Full Text Available A quantitative structure-property relationship (QSPR study based on partial least squares (PLS and artificial neural network (ANN was developed for the prediction of ferric iron precipitation in bioleaching process. The leaching temperature, initial pH, oxidation/reduction potential (ORP, ferrous concentration and particle size of ore were used as inputs to the network. The output of the model was ferric iron precipitation. The optimal condition of the neural network was obtained by adjusting various parameters by trial-and-error. After optimization and training of the network according to back-propagation algorithm, a 5-5-1 neural network was generated for prediction of ferric iron precipitation. The root mean square error for the neural network calculated ferric iron precipitation for training, prediction and validation set are 32.860, 40.739 and 35.890, respectively, which are smaller than those obtained by PLS model (180.972, 165.047 and 149.950, respectively. Results obtained reveal the reliability and good predictivity of neural network model for the prediction of ferric iron precipitation in bioleaching process.
Directory of Open Access Journals (Sweden)
Zhongqi Wang
2016-01-01
Full Text Available Fixture plays an important part in constraining excessive sheet metal part deformation at machining, assembly, and measuring stages during the whole manufacturing process. However, it is still a difficult and nontrivial task to design and optimize sheet metal fixture locating layout at present because there is always no direct and explicit expression describing sheet metal fixture locating layout and responding deformation. To that end, an RBF neural network prediction model is proposed in this paper to assist design and optimization of sheet metal fixture locating layout. The RBF neural network model is constructed by training data set selected by uniform sampling and finite element simulation analysis. Finally, a case study is conducted to verify the proposed method.
Genetic optimization of neural network architecture
International Nuclear Information System (INIS)
Harp, S.A.; Samad, T.
1994-03-01
Neural networks are now a popular technology for a broad variety of application domains, including the electric utility industry. Yet, as the technology continues to gain increasing acceptance, it is also increasingly apparent that the power that neural networks provide is not an unconditional blessing. Considerable care must be exercised during application development if the full benefit of the technology is to be realized. At present, no fully general theory or methodology for neural network design is available, and application development is a trial-and-error process that is time-consuming and expertise-intensive. Each application demands appropriate selections of the network input space, the network structure, and values of learning algorithm parameters-design choices that are closely coupled in ways that largely remain a mystery. This EPRI-funded exploratory research project was initiated to take the key next step in this research program: the validation of the approach on a realistic problem. We focused on the problem of modeling the thermal performance of the TVA Sequoyah nuclear power plant (units 1 and 2)
Fuel economy and torque tracking in camless engines through optimization of neural networks
International Nuclear Information System (INIS)
Ashhab, Moh'd Sami S.
2008-01-01
The feed forward controller of a camless internal combustion engine is modeled by inverting a multi-input multi-output feed forward artificial neural network (ANN) model of the engine. The engine outputs, pumping loss and cylinder air charge, are related to the inputs, intake valve lift and closing timing, by the artificial neural network model, which is trained with historical input-output data. The controller selects the intake valve lift and closing timing that will mimimize the pumping loss and achieve engine torque tracking. Lower pumping loss means better fuel economy, whereas engine torque tracking gurantees the driver's torque demand. The inversion of the ANN is performed with the complex method constrained optimization. How the camless engine inverse controller can be augmented with adaptive techniques to maintain accuracy even when the engine parts degrade is discussed. The simulation results demonstrate the effectiveness of the developed camless engine controller
Allmendinger, Richard; Simaria, Ana S; Turner, Richard; Farid, Suzanne S
2014-10-01
This paper considers a real-world optimization problem involving the identification of cost-effective equipment sizing strategies for the sequence of chromatography steps employed to purify biopharmaceuticals. Tackling this problem requires solving a combinatorial optimization problem subject to multiple constraints, uncertain parameters, and time-consuming fitness evaluations. An industrially-relevant case study is used to illustrate that evolutionary algorithms can identify chromatography sizing strategies with significant improvements in performance criteria related to process cost, time and product waste over the base case. The results demonstrate also that evolutionary algorithms perform best when infeasible solutions are repaired intelligently, the population size is set appropriately, and elitism is combined with a low number of Monte Carlo trials (needed to account for uncertainty). Adopting this setup turns out to be more important for scenarios where less time is available for the purification process. Finally, a data-visualization tool is employed to illustrate how user preferences can be accounted for when it comes to selecting a sizing strategy to be implemented in a real industrial setting. This work demonstrates that closed-loop evolutionary optimization, when tuned properly and combined with a detailed manufacturing cost model, acts as a powerful decisional tool for the identification of cost-effective purification strategies. © 2013 The Authors. Journal of Chemical Technology & Biotechnology published by John Wiley & Sons Ltd on behalf of Society of Chemical Industry.
DEFF Research Database (Denmark)
Petersen, Lennart; Iov, Florin; Tarnowski, German Claudio
2018-01-01
The paper focusses on the optimal sizing of off-grid hybrid power plants including wind power generation. A modular and scalable system topology as well as an optimal sizing algorithm for the HPP has been presented in a previous publication. In this paper, the sizing process is evaluated by means...... of assessment studies. The aim is to address the impact of renewable resource data, the required power supply availability and reactive power load demand on the optimal sizing of wind integrated off-grid HPPs....
Discretization-dependent model for weakly connected excitable media
Arroyo, Pedro André; Alonso, Sergio; Weber dos Santos, Rodrigo
2018-03-01
Pattern formation has been widely observed in extended chemical and biological processes. Although the biochemical systems are highly heterogeneous, homogenized continuum approaches formed by partial differential equations have been employed frequently. Such approaches are usually justified by the difference of scales between the heterogeneities and the characteristic spatial size of the patterns. Under different conditions, for example, under weak coupling, discrete models are more adequate. However, discrete models may be less manageable, for instance, in terms of numerical implementation and mesh generation, than the associated continuum models. Here we study a model to approach discreteness which permits the computer implementation on general unstructured meshes. The model is cast as a partial differential equation but with a parameter that depends not only on heterogeneities sizes, as in the case of quasicontinuum models, but also on the discretization mesh. Therefore, we refer to it as a discretization-dependent model. We validate the approach in a generic excitable media that simulates three different phenomena: the propagation of action membrane potential in cardiac tissue, in myelinated axons of neurons, and concentration waves in chemical microemulsions.