Structural changes in surface layer of steel 08Kh18N10T during machining

International Nuclear Information System (INIS)

Palenik, J.; Vodarek, V.

1989-01-01

The results are reported of a study of the surface layer of steel 08Kh18N10T affected by machining. Structural changes were studied caused by finish turning and by additional roller burnishing. Multiple deformation bands were observed to occur under the given cutting conditions; they mainly consisted of deformation doublets and only in isolated cases of ε-martensite. The presence of α'-martensite was not shown in the specimen surface layer following finish turning. The deformation shear bands in the roller-burnished specimen consisted of both ε-martensite and of deformation doublets. The amount of ε-martensite in the structure was significantly higher than in the specimen worked by turning. Local presence of α'-martensite formations was observed inside the deformation bands. It thus follows that roller burnishing is unsuitable as part of the manufacture of components from steel 08Kh18N10T. (J.B.). 5 figs., 1 tab., 9 refs

Precipitation behavior and grain refinement of burnishing Al-Zn-Mg alloy

Directory of Open Access Journals (Sweden)

Ce Pang

2018-02-01

Full Text Available Burnishing is a unique strengthening approach to improve the strength of surface layer and remains the ductility of the interior of metallic materials. In this work, burnishing treatment was employed to improve the surface microstructure of naturally aged Al-Zn-Mg alloys after solid solution. Transmission electron microscopy, high-resolution transmission electron microscopy, X-ray diffraction and nano-indentation were used to characterize the effects of the burnishing on the microstructures of surface layer and Guinier-Preston (GP zones. It was indicated that GP zones uniformly distributed and dispersed in the matrix before burnishing, and the amount of GP zones decreased dramatically after burnishing processing. Additionally, the grains in the surficial layer were refined into nano-crystals with an average grain size of 78 nm. Burnishing treatment not only led to formation of large number of dislocation substructures in the sub-surface and near-matrix surface, but also promoted the precipitation of metastable η' phase at grain boundaries. The synergistic effects of the grain refinement, dislocation multiplication and the precipitation of η' phase strengthen the burnished layer of Al-Zn-Mg alloy. Keywords: Al-Zn-Mg alloy, Burnishing, Nano-crystal, Precipitation, Grain refinement

Fault Diagnosis Method of Polymerization Kettle Equipment Based on Rough Sets and BP Neural Network

Directory of Open Access Journals (Sweden)

Shu-zhi Gao

2013-01-01

Full Text Available Polyvinyl chloride (PVC polymerizing production process is a typical complex controlled object, with complexity features, such as nonlinear, multivariable, strong coupling, and large time-delay. Aiming at the real-time fault diagnosis and optimized monitoring requirements of the large-scale key polymerization equipment of PVC production process, a real-time fault diagnosis strategy is proposed based on rough sets theory with the improved discernibility matrix and BP neural networks. The improved discernibility matrix is adopted to reduct the attributes of rough sets in order to decrease the input dimensionality of fault characteristics effectively. Levenberg-Marquardt BP neural network is trained to diagnose the polymerize faults according to the reducted decision table, which realizes the nonlinear mapping from fault symptom set to polymerize fault set. Simulation experiments are carried out combining with the industry history datum to show the effectiveness of the proposed rough set neural networks fault diagnosis method. The proposed strategy greatly increased the accuracy rate and efficiency of the polymerization fault diagnosis system.

Effect of surface roughness on drying speed of drying lamellas in ...

African Journals Online (AJOL)

Lamellas, which are defined as top layers of multilayer parquet and favourable to wood veneer can be dried in jet ventilated automatic veneer roller dryer due to short drying period. The objective of this study is to determine the effect of surface roughness on the drying speed of the veneer roller dryer. Quercus spp.

Prediction of the surface roughness of AA6082 flow-formed tubes by design of experiments

International Nuclear Information System (INIS)

Srinivasulu, M.; Komaraiah, M.; Rao, C. S. Krishna Prasada

2013-01-01

Flow forming is a modern, chipless metal forming process that is employed for the production of thin-walled seamless tubes. Experiments are conducted on AA6082 alloy pre-forms to flow form into thin-walled tubes on a CNC flow-forming machine with a single roller. Design of experiments is used to predict the surface roughness of flow-formed tubes. The process parameters selected for this study are the roller axial feed, mandrel speed, and roller radius. A standard response surface methodology (RSM) called the Box Behnken design is used to perform the experimental runs. The regression model developed by RSM successfully predicts the surface roughness of AA6082 flow-formed tubes within the range of the selected process parameters.

Prediction of the surface roughness of AA6082 flow-formed tubes by design of experiments

Energy Technology Data Exchange (ETDEWEB)

Srinivasulu, M. [Government Polytechnic for Women Badangpet, Hyderabad (India); Komaraiah, M. [Sreenidhi Institute of Science and Technology, Hyderabad (India); Rao, C. S. Krishna Prasada [Bharat Dynamics Limited, Hyderabad (India)

2013-06-15

Flow forming is a modern, chipless metal forming process that is employed for the production of thin-walled seamless tubes. Experiments are conducted on AA6082 alloy pre-forms to flow form into thin-walled tubes on a CNC flow-forming machine with a single roller. Design of experiments is used to predict the surface roughness of flow-formed tubes. The process parameters selected for this study are the roller axial feed, mandrel speed, and roller radius. A standard response surface methodology (RSM) called the Box Behnken design is used to perform the experimental runs. The regression model developed by RSM successfully predicts the surface roughness of AA6082 flow-formed tubes within the range of the selected process parameters.

Noncontact Surface Roughness Estimation Using 2D Complex Wavelet Enhanced ResNet for Intelligent Evaluation of Milled Metal Surface Quality

Directory of Open Access Journals (Sweden)

Weifang Sun

2018-03-01

Full Text Available Machined surfaces are rough from a microscopic perspective no matter how finely they are finished. Surface roughness is an important factor to consider during production quality control. Using modern techniques, surface roughness measurements are beneficial for improving machining quality. With optical imaging of machined surfaces as input, a convolutional neural network (CNN can be utilized as an effective way to characterize hierarchical features without prior knowledge. In this paper, a novel method based on CNN is proposed for making intelligent surface roughness identifications. The technical scheme incorporates there elements: texture skew correction, image filtering, and intelligent neural network learning. Firstly, a texture skew correction algorithm, based on an improved Sobel operator and Hough transform, is applied such that surface texture directions can be adjusted. Secondly, two-dimensional (2D dual tree complex wavelet transform (DTCWT is employed to retrieve surface topology information, which is more effective for feature classifications. In addition, residual network (ResNet is utilized to ensure automatic recognition of the filtered texture features. The proposed method has verified its feasibility as well as its effectiveness in actual surface roughness estimation experiments using the material of spheroidal graphite cast iron 500-7 in an agricultural machinery manufacturing company. Testing results demonstrate the proposed method has achieved high-precision surface roughness estimation.

Optimization of Burr size, Surface Roughness and Circularity Deviation during Drilling of Al 6061 using Taguchi Design Method and Artificial Neural Network

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

Study on intelligence fault diagnosis method for nuclear power plant equipment based on rough set and fuzzy neural network

International Nuclear Information System (INIS)

Liu Yongkuo; Xia Hong; Xie Chunli; Chen Zhihui; Chen Hongxia

2007-01-01

Rough set theory and fuzzy neural network are combined, to take full advantages of the two of them. Based on the reduction technology to knowledge of Rough set method, and by drawing the simple rule from a large number of initial data, the fuzzy neural network was set up, which was with better topological structure, improved study speed, accurate judgment, strong fault-tolerant ability, and more practical. In order to test the validity of the method, the inverted U-tubes break accident of Steam Generator and etc are used as examples, and many simulation experiments are performed. The test result shows that it is feasible to incorporate the fault intelligence diagnosis method based on rough set and fuzzy neural network in the nuclear power plant equipment, and the method is simple and convenience, with small calculation amount and reliable result. (authors)

Investigations on the Effect of Ball Burnishing Parameters on ...

African Journals Online (AJOL)

Surface finish has a vital influence on most functional properties of a component, such as fatigue strength, wear resistance and corrosion resistance. This has led to processes such as lapping, honing, and burnishing. Burnishing is a fine finishing operation involving the cold working and plastic deformation of surface layers ...

Nano-topography Enhances Communication in Neural Cells Networks

KAUST Repository

Onesto, V.

2017-08-23

Neural cells are the smallest building blocks of the central and peripheral nervous systems. Information in neural networks and cell-substrate interactions have been heretofore studied separately. Understanding whether surface nano-topography can direct nerve cells assembly into computational efficient networks may provide new tools and criteria for tissue engineering and regenerative medicine. In this work, we used information theory approaches and functional multi calcium imaging (fMCI) techniques to examine how information flows in neural networks cultured on surfaces with controlled topography. We found that substrate roughness Sa affects networks topology. In the low nano-meter range, S-a = 0-30 nm, information increases with Sa. Moreover, we found that energy density of a network of cells correlates to the topology of that network. This reinforces the view that information, energy and surface nano-topography are tightly inter-connected and should not be neglected when studying cell-cell interaction in neural tissue repair and regeneration.

Experimental Investigation of the Effect of Burnishing Force on Service Properties of AISI 1010 Steel Plates

Science.gov (United States)

Gharbi, F.; Sghaier, S.; Morel, F.; Benameur, T.

2015-02-01

This paper presents the results obtained with a new ball burnishing tool developed for the mechanical treatment of large flat surfaces. Several parameters can affect the mechanical behavior and fatigue of workpiece. Our study focused on the effect of the burnishing force on the surface quality and on the service properties (mechanical behavior, fatigue) of AISI 1010 steel hot-rolled plates. Experimental results assert that burnishing force not exceeding 300 N causes an increase in the ductility. In addition, results indicated that the effect of the burnishing force on the residual surface stress was greater in the direction of advance than in the cross-feed direction. Furthermore, the flat burnishing surfaces did not improve the fatigue strength of AISI 1010 steel flat specimens.

Reconstruction of road defects and road roughness classification using vehicle responses with artificial neural networks simulation

CSIR Research Space (South Africa)

Ngwangwa, HM

2010-04-01

Full Text Available -1 Journal of Terramechanics Volume 47, Issue 2, April 2010, Pages 97-111 Reconstruction of road defects and road roughness classification using vehicle responses with artificial neural networks simulation H.M. Ngwangwaa, P.S. Heynsa, , , F...

Decoding small surface codes with feedforward neural networks

Science.gov (United States)

Varsamopoulos, Savvas; Criger, Ben; Bertels, Koen

2018-01-01

Surface codes reach high error thresholds when decoded with known algorithms, but the decoding time will likely exceed the available time budget, especially for near-term implementations. To decrease the decoding time, we reduce the decoding problem to a classification problem that a feedforward neural network can solve. We investigate quantum error correction and fault tolerance at small code distances using neural network-based decoders, demonstrating that the neural network can generalize to inputs that were not provided during training and that they can reach similar or better decoding performance compared to previous algorithms. We conclude by discussing the time required by a feedforward neural network decoder in hardware.

Correlation between Surface Roughness Characteristics in CO2 Laser Cutting of Mild Steel

Directory of Open Access Journals (Sweden)

M. Radovanović

2012-12-01

Full Text Available CO2 laser oxygen cutting of mild steel is widely used industrial application. Cut surface quality is a very important characteristic of laser cutting that ensures an advantage over other contour cutting processes. In this paper mathematical models for estimating characteristics of surface quality such as average surface roughness and ten-point mean roughness in CO2 laser cutting of mild steel based on laser cutting parameters were developed. Empirical models were developed using artificial neural networks and experimental data collected. Taguchi’s orthogonal array was implemented for experimental plan. From the analysis of the developed mathematical models it was observed that functional dependence between laser cutting parameters, their interactions and surface roughness characteristics is complex and non-linear. It was also observed that there exist region of minimal average surface roughness to ten-point mean roughness ratio. The relationship between average surface roughness and ten-point mean roughness was found to be nonlinear and can be expressed with a second degree polynomial.

Experimental and numerical researches of duplex burnishing process in aspect of achieved productive quality of the product

Science.gov (United States)

Patyk, Radoslaw; Kukielka, Leon; Kaldunski, Pawel; Bohdal, Lukasz; Chodor, Jaroslaw; Kulakowska, Agnieszka; Kukielka, Krzysztof; Nagnajewicz, Slawomir

2018-05-01

The paper presents the results of experimental researches and numerical simulations of the duplex burnishing process. During duplex burnishing process the treatment is carry out in two stages. In the first stage - on the semi-fabrication surface, the regular asperities are embossed with triangular, symmetrical, periodic outline. In the second stage the asperities are burnished (smooth burnishing) till the needed asperities equalized, resulting in a smooth and strengthened surface layer. The implementation of such technology results in receiving of a new surface layer characterized by favorable functional properties, particularly increased resistance to fatigue wear.

Optimisation of milling parameters using neural network

Directory of Open Access Journals (Sweden)

Lipski Jerzy

2017-01-01

Full Text Available The purpose of this study was to design and test an intelligent computer software developed with the purpose of increasing average productivity of milling not compromising the design features of the final product. The developed system generates optimal milling parameters based on the extent of tool wear. The introduced optimisation algorithm employs a multilayer model of a milling process developed in the artificial neural network. The input parameters for model training are the following: cutting speed vc, feed per tooth fz and the degree of tool wear measured by means of localised flank wear (VB3. The output parameter is the surface roughness of a machined surface Ra. Since the model in the neural network exhibits good approximation of functional relationships, it was applied to determine optimal milling parameters in changeable tool wear conditions (VB3 and stabilisation of surface roughness parameter Ra. Our solution enables constant control over surface roughness parameters and productivity of milling process after each assessment of tool condition. The recommended parameters, i.e. those which applied in milling ensure desired surface roughness and maximal productivity, are selected from all the parameters generated by the model. The developed software may constitute an expert system supporting a milling machine operator. In addition, the application may be installed on a mobile device (smartphone, connected to a tool wear diagnostics instrument and the machine tool controller in order to supply updated optimal parameters of milling. The presented solution facilitates tool life optimisation and decreasing tool change costs, particularly during prolonged operation.

A STUDY ON THE PROPERTIES OF SURFACE – ACTIVE FLUIDS USED IN BURNISHING AND SHOT PEENING PROCESSES

Directory of Open Access Journals (Sweden)

Kazmierz Zaleski

2016-09-01

Full Text Available A method is presented for the study of surface-active properties of a fluids, in burnishing and shot peening processes used, which consists in comparing mean plastic strains of thin metal foil subjected to tensile tests in the examined fluid and in air. As a surface-active additive to the fluid (mineral oil, methyl polymethacrylate solution was used. It was found that the surfactant activity coefficient depended on the type of examined fluid as well as on the thickness of the foil being stretched. Results of analyses of the surface-active properties of a fluid can be compared only when metal foils of equal thickness made from one specific material are used. It can be supposed that the introduction of methyl polymethacrylate solution as an additive to the metalworking fluid will have a beneficial effect on the course and the results of burnishing and shot peening of metals.

Modeling and optimization of kerf taper and surface roughness in laser cutting of titanium alloy sheet

Energy Technology Data Exchange (ETDEWEB)

Pandey, Arun Kumar; Dubey, Avanish Kumar [Motilal Nehru National Institute of Technology Allahabad, Uttar Pradesh (India)

2013-07-15

Laser cutting of titanium and its alloys is difficult due to it's poor thermal conductivity and chemical reactivity at elevated temperatures. But demand of these materials in different advanced industries such as aircraft, automobile and space research, require accurate geometry with high surface quality. The present research investigates the laser cutting process behavior of titanium alloy sheet (Ti-6Al-4V) with the aim to improve geometrical accuracy and surface quality by minimizing the kerf taper and surface roughness. The data obtained from L{sub 27} orthogonal array experiments have been used for developing neural network (NN) based models of kerf taper and surface roughness. A hybrid approach of neural network and genetic algorithm has been proposed and applied for the optimization of different quality characteristics. The optimization results show considerable improvements in both the quality characteristics. The results predicted by NN models are well in agreement with the experimental data.

AN ARTIFICIAL INTELLIGENCE APPROACH FOR THE PREDICTION OF SURFACE ROUGHNESS IN CO2 LASER CUTTING

Directory of Open Access Journals (Sweden)

MILOŠ MADIĆ

2012-12-01

Full Text Available In laser cutting, the cut quality is of great importance. Multiple non-linear effects of process parameters and their interactions make very difficult to predict cut quality. In this paper, artificial intelligence (AI approach was applied to predict the surface roughness in CO2 laser cutting. To this aim, artificial neural network (ANN model of surface roughness was developed in terms of cutting speed, laser power and assist gas pressure. The experimental results obtained from Taguchi’s L25 orthogonal array were used to develop ANN model. The ANN mathematical model of surface roughness was expressed as explicit nonlinear function of the selected input parameters. Statistical results indicate that the ANN model can predict the surface roughness with good accuracy. It was showed that ANNs may be used as a good alternative in analyzing the effects of cutting parameters on the surface roughness.

Knowledge Mining from Clinical Datasets Using Rough Sets and Backpropagation Neural Network

Directory of Open Access Journals (Sweden)

Kindie Biredagn Nahato

2015-01-01

Full Text Available The availability of clinical datasets and knowledge mining methodologies encourages the researchers to pursue research in extracting knowledge from clinical datasets. Different data mining techniques have been used for mining rules, and mathematical models have been developed to assist the clinician in decision making. The objective of this research is to build a classifier that will predict the presence or absence of a disease by learning from the minimal set of attributes that has been extracted from the clinical dataset. In this work rough set indiscernibility relation method with backpropagation neural network (RS-BPNN is used. This work has two stages. The first stage is handling of missing values to obtain a smooth data set and selection of appropriate attributes from the clinical dataset by indiscernibility relation method. The second stage is classification using backpropagation neural network on the selected reducts of the dataset. The classifier has been tested with hepatitis, Wisconsin breast cancer, and Statlog heart disease datasets obtained from the University of California at Irvine (UCI machine learning repository. The accuracy obtained from the proposed method is 97.3%, 98.6%, and 90.4% for hepatitis, breast cancer, and heart disease, respectively. The proposed system provides an effective classification model for clinical datasets.

Modeling and Simulated Annealing Optimization of Surface Roughness in CO2 Laser Nitrogen Cutting of Stainless Steel

OpenAIRE

M. Madić; M. Radovanović; B. Nedić

2013-01-01

This paper presents a systematic methodology for empirical modeling and optimization of surface roughness in nitrogen, CO2 laser cutting of stainless steel . The surface roughness prediction model was developed in terms of laser power , cutting speed , assist gas pressure and focus position by using The artificial neural network ( ANN ) . To cover a wider range of laser cutting parameters and obtain an experimental database for the ANN model development, Taguchi 's L27 orthogonal array was im...

Grinding and polishing articles in bulk: Burnishing

Science.gov (United States)

Schmotz, K.

1980-01-01

Various processes and equipment used for burnishing different materials are discussed. Drum and vibration installations are considered, as are processing chemicals and additive materials used in the burnishing process.

Burnishing Systems: a Short Survey of the State-of-the-art

Science.gov (United States)

Bobrovskij, I. N.

2018-01-01

The modern technological solutions allowing to implement a new technology of surface plastic deformation are considered. The technological device allowing to implement the technology of hyper productive surface plastic deformation or wide burnishing (machining time is up to 2-3 revolutions of workpiece) is presented. The device provides the constant force of instruments regardless the beating, non-roundness and other surface shape defects; usable and easily controlled force adjustment; precise installation of instruments and holders toward the along the worpieces axis; automation of the supply and retraction of instruments. Also the device allowing to implement the technology of nanostructuring burnishing is presented. The design of the device allows to eliminate the effect of auto-oscillations.

Optimization of burnishing parameters and determination of select ...

Indian Academy of Sciences (India)

very much essential because the fatigue life, bearing properties and ... the film of lubricating oil; but, cannot as low surface finish leads to high wear and fatigue ..... that the pre-burnishing operations such as lathe turning too leaves behind sur-.

Study on high-speed cutting parameters optimization of AlMn1Cu based on neural network and genetic algorithm

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.

Identifying apple surface defects using principal components analysis and artifical neural networks

Science.gov (United States)

Artificial neural networks and principal components were used to detect surface defects on apples in near-infrared images. Neural networks were trained and tested on sets of principal components derived from columns of pixels from images of apples acquired at two wavelengths (740 nm and 950 nm). I...

Soil surface roughness: comparing old and new measuring methods and application in a soil erosion model

Science.gov (United States)

Thomsen, L. M.; Baartman, J. E. M.; Barneveld, R. J.; Starkloff, T.; Stolte, J.

2015-04-01

Quantification of soil roughness, i.e. the irregularities of the soil surface due to soil texture, aggregates, rock fragments and land management, is important as it affects surface storage, infiltration, overland flow, and ultimately sediment detachment and erosion. Roughness has been measured in the field using both contact methods (such as roller chain and pinboard) and sensor methods (such as stereophotogrammetry and terrestrial laser scanning (TLS)). A novel depth-sensing technique, originating in the gaming industry, has recently become available for earth sciences: the Xtion Pro method. Roughness data obtained using various methods are assumed to be similar; this assumption is tested in this study by comparing five different methods to measure roughness in the field on 1 m2 agricultural plots with different management (ploughing, harrowing, forest and direct seeding on stubble) in southern Norway. Subsequently, the values were used as input for the LISEM soil erosion model to test their effect on the simulated hydrograph at catchment scale. Results show that statistically significant differences between the methods were obtained only for the fields with direct seeding on stubble; for the other land management types the methods were in agreement. The spatial resolution of the contact methods was much lower than for the sensor methods (10 000 versus at least 57 000 points per square metre). In terms of costs and ease of use in the field, the Xtion Pro method is promising. Results from the LISEM model indicate that especially the roller chain overestimated the random roughness (RR) values and the model subsequently calculated less surface runoff than measured. In conclusion, the choice of measurement method for roughness data matters and depends on the required accuracy, resolution, mobility in the field and available budget. It is recommended to use only one method within one study.

A STUDY ON THE PROPERTIES OF SURFACE – ACTIVE FLUIDS USED IN BURNISHING AND SHOT PEENING PROCESSES

OpenAIRE

Kazmierz Zaleski

2016-01-01

A method is presented for the study of surface-active properties of a fluids, in burnishing and shot peening processes used, which consists in comparing mean plastic strains of thin metal foil subjected to tensile tests in the examined fluid and in air. As a surface-active additive to the fluid (mineral oil), methyl polymethacrylate solution was used. It was found that the surfactant activity coefficient depended on the type of examined fluid as well as on the thickness of the foil being stre...

Modeling and Simulated Annealing Optimization of Surface Roughness in CO2 Laser Nitrogen Cutting of Stainless Steel

Directory of Open Access Journals (Sweden)

M. Madić

2013-09-01

Full Text Available This paper presents a systematic methodology for empirical modeling and optimization of surface roughness in nitrogen, CO2 laser cutting of stainless steel . The surface roughness prediction model was developed in terms of laser power , cutting speed , assist gas pressure and focus position by using The artificial neural network ( ANN . To cover a wider range of laser cutting parameters and obtain an experimental database for the ANN model development, Taguchi 's L27 orthogonal array was implemented in the experimental plan. The developed ANN model was expressed as an explicit nonlinear function , while the influence of laser cutting parameters and their interactions on surface roughness were analyzed by generating 2D and 3D plots . The final goal of the experimental study Focuses on the determinationof the optimum laser cutting parameters for the minimization of surface roughness . Since the solution space of the developed ANN model is complex, and the possibility of many local solutions is great, simulated annealing (SA was selected as a method for the optimization of surface roughness.

Prediction of Surface Roughness in End Milling Process Using Intelligent Systems: A Comparative Study

Directory of Open Access Journals (Sweden)

Abdel Badie Sharkawy

2011-01-01

Full Text Available A study is presented to model surface roughness in end milling process. Three types of intelligent networks have been considered. They are (i radial basis function neural networks (RBFNs, (ii adaptive neurofuzzy inference systems (ANFISs, and (iii genetically evolved fuzzy inference systems (G-FISs. The machining parameters, namely, the spindle speed, feed rate, and depth of cut have been used as inputs to model the workpiece surface roughness. The goal is to get the best prediction accuracy. The procedure is illustrated using experimental data of end milling 6061 aluminum alloy. The three networks have been trained using experimental training data. After training, they have been examined using another set of data, that is, validation data. Results are compared with previously published results. It is concluded that ANFIS networks may suffer the local minima problem, and genetic tuning of fuzzy networks cannot insure perfect optimality unless suitable parameter setting (population size, number of generations etc. and tuning range for the FIS, parameters are used which can be hardly satisfied. It is shown that the RBFN model has the best performance (prediction accuracy in this particular case.

Neural network committees for finger joint angle estimation from surface EMG signals

Directory of Open Access Journals (Sweden)

Reddy Narender P

2009-01-01

Full Text Available Abstract Background In virtual reality (VR systems, the user's finger and hand positions are sensed and used to control the virtual environments. Direct biocontrol of VR environments using surface electromyography (SEMG signals may be more synergistic and unconstraining to the user. The purpose of the present investigation was to develop a technique to predict the finger joint angle from the surface EMG measurements of the extensor muscle using neural network models. Methodology SEMG together with the actual joint angle measurements were obtained while the subject was performing flexion-extension rotation of the index finger at three speeds. Several neural networks were trained to predict the joint angle from the parameters extracted from the SEMG signals. The best networks were selected to form six committees. The neural network committees were evaluated using data from new subjects. Results There was hysteresis in the measured SMEG signals during the flexion-extension cycle. However, neural network committees were able to predict the joint angle with reasonable accuracy. RMS errors ranged from 0.085 ± 0.036 for fast speed finger-extension to 0.147 ± 0.026 for slow speed finger extension, and from 0.098 ± 0.023 for the fast speed finger flexion to 0.163 ± 0.054 for slow speed finger flexion. Conclusion Although hysteresis was observed in the measured SEMG signals, the committees of neural networks were able to predict the finger joint angle from SEMG signals.

Communication: Fitting potential energy surfaces with fundamental invariant neural network

Energy Technology Data Exchange (ETDEWEB)

Shao, Kejie; Chen, Jun; Zhao, Zhiqiang; Zhang, Dong H., E-mail: zhangdh@dicp.ac.cn [State Key Laboratory of Molecular Reaction Dynamics and Center for Theoretical Computational Chemistry, Dalian Institute of Chemical Physics, Chinese Academy of Sciences, Dalian 116023, People’s Republic of China and University of Chinese Academy of Sciences, Beijing 100049, People’s Republic of China. (China)

2016-08-21

A more flexible neural network (NN) method using the fundamental invariants (FIs) as the input vector is proposed in the construction of potential energy surfaces for molecular systems involving identical atoms. Mathematically, FIs finitely generate the permutation invariant polynomial (PIP) ring. In combination with NN, fundamental invariant neural network (FI-NN) can approximate any function to arbitrary accuracy. Because FI-NN minimizes the size of input permutation invariant polynomials, it can efficiently reduce the evaluation time of potential energy, in particular for polyatomic systems. In this work, we provide the FIs for all possible molecular systems up to five atoms. Potential energy surfaces for OH{sub 3} and CH{sub 4} were constructed with FI-NN, with the accuracy confirmed by full-dimensional quantum dynamic scattering and bound state calculations.

Quantitative surface topography assessment of directly compressed and roller compacted tablet cores using photometric stereo image analysis

DEFF Research Database (Denmark)

Allesø, Morten; Carstensen, Jens Michael; Holm, Per

2016-01-01

Surface topography, in the context of surface smoothness/roughness, was investigated by the use of an image analysis technique, MultiRay™, related to photometric stereo, on different tablet batches manufactured either by direct compression or roller compaction. In the present study, oblique...... illumination of the tablet (darkfield) was considered and the area of cracks and pores in the surface was used as a measure of tablet surface topography; the higher a value, the rougher the surface. The investigations demonstrated a high precision of the proposed technique, which was able to rapidly (within...... milliseconds) and quantitatively measure the obtained surface topography of the produced tablets. Compaction history, in the form of applied roll force and tablet punch pressure, was also reflected in the measured smoothness of the tablet surfaces. Generally it was found that a higher degree of plastic...

Influence of Surface-profile and Movement-path of Roller on Thickness Thinning during Multi-pass Deep Drawing Spinning

Directory of Open Access Journals (Sweden)

Xia Qinxiang

2016-01-01

Full Text Available Over thinning is a serious defect influencing the forming quality of spun workpiece during multi-pass deep drawing spinning. Surface-profile and movement-path of roller are the key factors influencing the thinning ratio of wall thickness of spun workpiece. The influence of surface-profile and movement-path of roller on thickness thinning were studied based on numerical simulation and experimental research, four groups of forming experiments were carried out under the combination of the different surface-profile of roller (R12 and R25-12 and movement-path of roller (spinning from the bottom of the blank and spinning from the middle of the blank. The results show that both the surface-profile and movement-path of roller have great influence on wall thickness thinning during multi-pass deep drawing spinning; and compared with the movement-path of roller, the influence of surface-profile of roller is more significant. The experimental results conform well to the simulation ones. It indicates that the FEA model established is reasonable and reliable.

Surface excitation parameter for rough surfaces

International Nuclear Information System (INIS)

Da, Bo; Salma, Khanam; Ji, Hui; Mao, Shifeng; Zhang, Guanghui; Wang, Xiaoping; Ding, Zejun

2015-01-01

Graphical abstract: - Highlights: • Instead of providing a general mathematical model of roughness, we directly use a finite element triangle mesh method to build a fully 3D rough surface from the practical sample. • The surface plasmon excitation can be introduced to the realistic sample surface by dielectric response theory and finite element method. • We found that SEP calculated based on ideal plane surface model are still reliable for real sample surface with common roughness. - Abstract: In order to assess quantitatively the importance of surface excitation effect in surface electron spectroscopy measurement, surface excitation parameter (SEP) has been introduced to describe the surface excitation probability as an average number of surface excitations that electrons can undergo when they move through solid surface either in incoming or outgoing directions. Meanwhile, surface roughness is an inevitable issue in experiments particularly when the sample surface is cleaned with ion beam bombardment. Surface roughness alters not only the electron elastic peak intensity but also the surface excitation intensity. However, almost all of the popular theoretical models for determining SEP are based on ideal plane surface approximation. In order to figure out whether this approximation is efficient or not for SEP calculation and the scope of this assumption, we proposed a new way to determine the SEP for a rough surface by a Monte Carlo simulation of electron scattering process near to a realistic rough surface, which is modeled by a finite element analysis method according to AFM image. The elastic peak intensity is calculated for different electron incident and emission angles. Assuming surface excitations obey the Poisson distribution the SEPs corrected for surface roughness are then obtained by analyzing the elastic peak intensity for several materials and for different incident and emission angles. It is found that the surface roughness only plays an

Cooling-load prediction by the combination of rough set theory and an artificial neural-network based on data-fusion technique

International Nuclear Information System (INIS)

Hou Zhijian; Lian Zhiwei; Yao Ye; Yuan Xinjian

2006-01-01

A novel method integrating rough sets (RS) theory and an artificial neural network (ANN) based on data-fusion technique is presented to forecast an air-conditioning load. Data-fusion technique is the process of combining multiple sensors data or related information to estimate or predict entity states. In this paper, RS theory is applied to find relevant factors to the load, which are used as inputs of an artificial neural-network to predict the cooling load. To improve the accuracy and enhance the robustness of load forecasting results, a general load-prediction model, by synthesizing multi-RSAN (MRAN), is presented so as to make full use of redundant information. The optimum principle is employed to deduce the weights of each RSAN model. Actual prediction results from a real air-conditioning system show that, the MRAN forecasting model is better than the individual RSAN and moving average (AMIMA) ones, whose relative error is within 4%. In addition, individual RSAN forecasting results are better than that of ARIMA

Optimization and control of a small angle ion source using an adaptive neural network controller

Energy Technology Data Exchange (ETDEWEB)

Brown, S.K.; Mead, W.C.; Bowling, P.S.; Jones, R.D.; Barnes, C.W.

1993-09-01

This project developed an automated controller based on an artificial neural network and evaluated its applicability in a real-time environment. This capability was developed within the context of a small angle negative ion source on the Discharge Test Stand at Los Alamos. The controller processes information obtained from the beam current waveform, developing a figure of merit (fom) to determine the ion source operating conditions. The fom is composed of the magnitude of the beam current, the stability of operation, and the quietness of the beam. Using no knowledge of operating conditions, the controller begins by making of rough scan of the four-dimensional operating surface. This surface uses as independent variables the anode and cathode temperatures, the hydrogen flow rate, and the arc voltage. `Me dependent variable is the fom described above. Once the rough approximation of the surface has been determined, the network formulates a model from which it determines the best operating point. The controller takes the ion source to that operating point for a reality check. As real data is fed in, the model of the operating surface is updated until the neural network`s model agrees with reality. The controller then uses a gradient ascent method to optimize the operation of the ion source. Initial tests of the controller indicate that it is remarkably capable. It has optimized the operation of the ion source on six different occasions bringing the beam to excellent quality and stability.

Deep convolutional neural networks for detection of rail surface defects

NARCIS (Netherlands)

Faghih Roohi, S.; Hajizadeh, S.; Nunez Vicencio, Alfredo; Babuska, R.; De Schutter, B.H.K.; Estevez, Pablo A.; Angelov, Plamen P.; Del Moral Hernandez, Emilio

2016-01-01

In this paper, we propose a deep convolutional neural network solution to the analysis of image data for the detection of rail surface defects. The images are obtained from many hours of automated video recordings. This huge amount of data makes it impossible to manually inspect the images and

Granular neural networks, pattern recognition and bioinformatics

CERN Document Server

Pal, Sankar K; Ganivada, Avatharam

2017-01-01

This book provides a uniform framework describing how fuzzy rough granular neural network technologies can be formulated and used in building efficient pattern recognition and mining models. It also discusses the formation of granules in the notion of both fuzzy and rough sets. Judicious integration in forming fuzzy-rough information granules based on lower approximate regions enables the network to determine the exactness in class shape as well as to handle the uncertainties arising from overlapping regions, resulting in efficient and speedy learning with enhanced performance. Layered network and self-organizing analysis maps, which have a strong potential in big data, are considered as basic modules,. The book is structured according to the major phases of a pattern recognition system (e.g., classification, clustering, and feature selection) with a balanced mixture of theory, algorithm, and application. It covers the latest findings as well as directions for future research, particularly highlighting bioinf...

Surface Casting Defects Inspection Using Vision System and Neural Network Techniques

Directory of Open Access Journals (Sweden)

Świłło S.J.

2013-12-01

Full Text Available The paper presents a vision based approach and neural network techniques in surface defects inspection and categorization. Depending on part design and processing techniques, castings may develop surface discontinuities such as cracks and pores that greatly influence the material’s properties Since the human visual inspection for the surface is slow and expensive, a computer vision system is an alternative solution for the online inspection. The authors present the developed vision system uses an advanced image processing algorithm based on modified Laplacian of Gaussian edge detection method and advanced lighting system. The defect inspection algorithm consists of several parameters that allow the user to specify the sensitivity level at which he can accept the defects in the casting. In addition to the developed image processing algorithm and vision system apparatus, an advanced learning process has been developed, based on neural network techniques. Finally, as an example three groups of defects were investigated demonstrates automatic selection and categorization of the measured defects, such as blowholes, shrinkage porosity and shrinkage cavity.

Modeling of Throughput in Production Lines Using Response Surface Methodology and Artificial Neural Networks

Directory of Open Access Journals (Sweden)

Federico Nuñez-Piña

2018-01-01

Full Text Available The problem of assigning buffers in a production line to obtain an optimum production rate is a combinatorial problem of type NP-Hard and it is known as Buffer Allocation Problem. It is of great importance for designers of production systems due to the costs involved in terms of space requirements. In this work, the relationship among the number of buffer slots, the number of work stations, and the production rate is studied. Response surface methodology and artificial neural network were used to develop predictive models to find optimal throughput values. 360 production rate values for different number of buffer slots and workstations were used to obtain a fourth-order mathematical model and four hidden layers’ artificial neural network. Both models have a good performance in predicting the throughput, although the artificial neural network model shows a better fit (R=1.0000 against the response surface methodology (R=0.9996. Moreover, the artificial neural network produces better predictions for data not utilized in the models construction. Finally, this study can be used as a guide to forecast the maximum or near maximum throughput of production lines taking into account the buffer size and the number of machines in the line.

Predicting wettability behavior of fluorosilica coated metal surface using optimum neural network

Science.gov (United States)

Taghipour-Gorjikolaie, Mehran; Valipour Motlagh, Naser

2018-02-01

The interaction between variables, which are effective on the surface wettability, is very complex to predict the contact angles and sliding angles of liquid drops. In this paper, in order to solve this complexity, artificial neural network was used to develop reliable models for predicting the angles of liquid drops. Experimental data are divided into training data and testing data. By using training data and feed forward structure for the neural network and using particle swarm optimization for training the neural network based models, the optimum models were developed. The obtained results showed that regression index for the proposed models for the contact angles and sliding angles are 0.9874 and 0.9920, respectively. As it can be seen, these values are close to unit and it means the reliable performance of the models. Also, it can be inferred from the results that the proposed model have more reliable performance than multi-layer perceptron and radial basis function based models.

[Segmentation of whole body bone SPECT image based on BP neural network].

Science.gov (United States)

Zhu, Chunmei; Tian, Lianfang; Chen, Ping; He, Yuanlie; Wang, Lifei; Ye, Guangchun; Mao, Zongyuan

2007-10-01

In this paper, BP neural network is used to segment whole body bone SPECT image so that the lesion area can be recognized automatically. For the uncertain characteristics of SPECT images, it is hard to achieve good segmentation result if only the BP neural network is employed. Therefore, the segmentation process is divided into three steps: first, the optimal gray threshold segmentation method is employed for preprocessing, then BP neural network is used to roughly identify the lesions, and finally template match method and symmetry-removing program are adopted to delete the wrongly recognized areas.

Antenna analysis using neural networks

Science.gov (United States)

Smith, William T.

1992-01-01

Conventional computing schemes have long been used to analyze problems in electromagnetics (EM). The vast majority of EM applications require computationally intensive algorithms involving numerical integration and solutions to large systems of equations. The feasibility of using neural network computing algorithms for antenna analysis is investigated. The ultimate goal is to use a trained neural network algorithm to reduce the computational demands of existing reflector surface error compensation techniques. Neural networks are computational algorithms based on neurobiological systems. Neural nets consist of massively parallel interconnected nonlinear computational elements. They are often employed in pattern recognition and image processing problems. Recently, neural network analysis has been applied in the electromagnetics area for the design of frequency selective surfaces and beam forming networks. The backpropagation training algorithm was employed to simulate classical antenna array synthesis techniques. The Woodward-Lawson (W-L) and Dolph-Chebyshev (D-C) array pattern synthesis techniques were used to train the neural network. The inputs to the network were samples of the desired synthesis pattern. The outputs are the array element excitations required to synthesize the desired pattern. Once trained, the network is used to simulate the W-L or D-C techniques. Various sector patterns and cosecant-type patterns (27 total) generated using W-L synthesis were used to train the network. Desired pattern samples were then fed to the neural network. The outputs of the network were the simulated W-L excitations. A 20 element linear array was used. There were 41 input pattern samples with 40 output excitations (20 real parts, 20 imaginary). A comparison between the simulated and actual W-L techniques is shown for a triangular-shaped pattern. Dolph-Chebyshev is a different class of synthesis technique in that D-C is used for side lobe control as opposed to pattern

Estimating surface longwave radiative fluxes from satellites utilizing artificial neural networks

Science.gov (United States)

Nussbaumer, Eric A.; Pinker, Rachel T.

2012-04-01

A novel approach for calculating downwelling surface longwave (DSLW) radiation under all sky conditions is presented. The DSLW model (hereafter, DSLW/UMD v2) similarly to its predecessor, DSLW/UMD v1, is driven with a combination of Moderate Resolution Imaging Spectroradiometer (MODIS) level-3 cloud parameters and information from the European Centre for Medium-Range Weather Forecasts (ECMWF) ERA-Interim model. To compute the clear sky component of DSLW a two layer feed-forward artificial neural network with sigmoid hidden neurons and linear output neurons is implemented; it is trained with simulations derived from runs of the Rapid Radiative Transfer Model (RRTM). When computing the cloud contribution to DSLW, the cloud base temperature is estimated by using an independent artificial neural network approach of similar architecture as previously mentioned, and parameterizations. The cloud base temperature neural network is trained using spatially and temporally co-located MODIS and CloudSat Cloud Profiling Radar (CPR) and the Cloud-Aerosol Lidar and Infrared Pathfinder Satellite Observation (CALIPSO) Cloud-Aerosol Lidar with Orthogonal Polarization (CALIOP) observations. Daily average estimates of DSLW from 2003 to 2009 are compared against ground measurements from the Baseline Surface Radiation Network (BSRN) giving an overall correlation coefficient of 0.98, root mean square error (rmse) of 15.84 W m-2, and a bias of -0.39 W m-2. This is an improvement over an earlier version of the model (DSLW/UMD v1) which for the same time period has an overall correlation coefficient 0.97 rmse of 17.27 W m-2, and bias of 0.73 W m-2.

Modélisation de la rugosité et de la dureté de surface par la ...

African Journals Online (AJOL)

The turning surface roughness about 2.5 μm was decreased to 0.15 μm after burnishing, while the hardness about 176 HV was increased to 226 HV. Statistically based on experimental design (response surface methodology) using central composite second-order rotatable design was used to establish a mathematical ...

Prediction of surface roughness in turning of Ti-6Al-4V using cutting parameters, forces and tool vibration

Science.gov (United States)

Sahu, Neelesh Kumar; Andhare, Atul B.; Andhale, Sandip; Raju Abraham, Roja

2018-04-01

Present work deals with prediction of surface roughness using cutting parameters along with in-process measured cutting force and tool vibration (acceleration) during turning of Ti-6Al-4V with cubic boron nitride (CBN) inserts. Full factorial design is used for design of experiments using cutting speed, feed rate and depth of cut as design variables. Prediction model for surface roughness is developed using response surface methodology with cutting speed, feed rate, depth of cut, resultant cutting force and acceleration as control variables. Analysis of variance (ANOVA) is performed to find out significant terms in the model. Insignificant terms are removed after performing statistical test using backward elimination approach. Effect of each control variables on surface roughness is also studied. Correlation coefficient (R2 pred) of 99.4% shows that model correctly explains the experiment results and it behaves well even when adjustment is made in factors or new factors are added or eliminated. Validation of model is done with five fresh experiments and measured forces and acceleration values. Average absolute error between RSM model and experimental measured surface roughness is found to be 10.2%. Additionally, an artificial neural network model is also developed for prediction of surface roughness. The prediction results of modified regression model are compared with ANN. It is found that RSM model and ANN (average absolute error 7.5%) are predicting roughness with more than 90% accuracy. From the results obtained it is found that including cutting force and vibration for prediction of surface roughness gives better prediction than considering only cutting parameters. Also, ANN gives better prediction over RSM models.

Neural network approach to time-dependent dividing surfaces in classical reaction dynamics

Science.gov (United States)

Schraft, Philippe; Junginger, Andrej; Feldmaier, Matthias; Bardakcioglu, Robin; Main, Jörg; Wunner, Günter; Hernandez, Rigoberto

2018-04-01

In a dynamical system, the transition between reactants and products is typically mediated by an energy barrier whose properties determine the corresponding pathways and rates. The latter is the flux through a dividing surface (DS) between the two corresponding regions, and it is exact only if it is free of recrossings. For time-independent barriers, the DS can be attached to the top of the corresponding saddle point of the potential energy surface, and in time-dependent systems, the DS is a moving object. The precise determination of these direct reaction rates, e.g., using transition state theory, requires the actual construction of a DS for a given saddle geometry, which is in general a demanding methodical and computational task, especially in high-dimensional systems. In this paper, we demonstrate how such time-dependent, global, and recrossing-free DSs can be constructed using neural networks. In our approach, the neural network uses the bath coordinates and time as input, and it is trained in a way that its output provides the position of the DS along the reaction coordinate. An advantage of this procedure is that, once the neural network is trained, the complete information about the dynamical phase space separation is stored in the network's parameters, and a precise distinction between reactants and products can be made for all possible system configurations, all times, and with little computational effort. We demonstrate this general method for two- and three-dimensional systems and explain its straightforward extension to even more degrees of freedom.

Reducing the stair step effect of layer manufactured surfaces by ball burnishing

Science.gov (United States)

Hiegemann, Lars; Agarwal, Chiranshu; Weddeling, Christian; Tekkaya, A. Erman

2016-10-01

The layer technology enables fast and flexible additive manufacturing of forming tools. The disadvantages of this system is the formation of stair steps in the range of tool radii. Within this work a new method to smooth this stair steps by ball burnishing is introduced. This includes studies on the general feasibility of the process and the determination of the influence of the rolling parameters. The investigations are carried out experimentally and numerically. Ultimately, the gained knowledge is applied to finish a deep drawing tool which is manufactured by layer technology.

Analysis of surface ozone using a recurrent neural network.

Science.gov (United States)

Biancofiore, Fabio; Verdecchia, Marco; Di Carlo, Piero; Tomassetti, Barbara; Aruffo, Eleonora; Busilacchio, Marcella; Bianco, Sebastiano; Di Tommaso, Sinibaldo; Colangeli, Carlo

2015-05-01

Hourly concentrations of ozone (O₃) and nitrogen dioxide (NO₂) have been measured for 16 years, from 1998 to 2013, in a seaside town in central Italy. The seasonal trends of O₃ and NO₂ recorded in this period have been studied. Furthermore, we used the data collected during one year (2005), to define the characteristics of a multiple linear regression model and a neural network model. Both models are used to model the hourly O₃ concentration, using, two scenarios: 1) in the first as inputs, only meteorological parameters and 2) in the second adding photochemical parameters at those of the first scenario. In order to evaluate the performance of the model four statistical criteria are used: correlation coefficient, fractional bias, normalized mean squared error and a factor of two. All the criteria show that the neural network gives better results, compared to the regression model, in all the model scenarios. Predictions of O₃ have been carried out by many authors using a feed forward neural architecture. In this paper we show that a recurrent architecture significantly improves the performances of neural predictors. Using only the meteorological parameters as input, the recurrent architecture shows performance better than the multiple linear regression model that uses meteorological and photochemical data as input, making the neural network model with recurrent architecture a more useful tool in areas where only weather measurements are available. Finally, we used the neural network model to forecast the O₃ hourly concentrations 1, 3, 6, 12, 24 and 48 h ahead. The performances of the model in predicting O₃ levels are discussed. Emphasis is given to the possibility of using the neural network model in operational ways in areas where only meteorological data are available, in order to predict O₃ also in sites where it has not been measured yet. Copyright © 2015 Elsevier B.V. All rights reserved.

Notions of Rough Neutrosophic Digraphs

Directory of Open Access Journals (Sweden)

Nabeela Ishfaq

2018-01-01

Full Text Available [-3]Graph theory has numerous applications in various disciplines, including computer networks, neural networks, expert systems, cluster analysis, and image capturing. Rough neutrosophic set (NS theory is a hybrid tool for handling uncertain information that exists in real life. In this research paper, we apply the concept of rough NS theory to graphs and present a new kind of graph structure, rough neutrosophic digraphs. We present certain operations, including lexicographic products, strong products, rejection and tensor products on rough neutrosophic digraphs. We investigate some of their properties. We also present an application of a rough neutrosophic digraph in decision-making.

A fast button surface defects detection method based on convolutional neural network

Science.gov (United States)

Liu, Lizhe; Cao, Danhua; Wu, Songlin; Wu, Yubin; Wei, Taoran

2018-01-01

Considering the complexity of the button surface texture and the variety of buttons and defects, we propose a fast visual method for button surface defect detection, based on convolutional neural network (CNN). CNN has the ability to extract the essential features by training, avoiding designing complex feature operators adapted to different kinds of buttons, textures and defects. Firstly, we obtain the normalized button region and then use HOG-SVM method to identify the front and back side of the button. Finally, a convolutional neural network is developed to recognize the defects. Aiming at detecting the subtle defects, we propose a network structure with multiple feature channels input. To deal with the defects of different scales, we take a strategy of multi-scale image block detection. The experimental results show that our method is valid for a variety of buttons and able to recognize all kinds of defects that have occurred, including dent, crack, stain, hole, wrong paint and uneven. The detection rate exceeds 96%, which is much better than traditional methods based on SVM and methods based on template match. Our method can reach the speed of 5 fps on DSP based smart camera with 600 MHz frequency.

Using Artificial Neural Networks to Model the Surface Roughness of Massive Wooden Edge-Glued Panels Made of Scotch Pine (Pinus sylvestris L. in a Machining Process with Computer Numerical Control

Directory of Open Access Journals (Sweden)

Sait Dundar Sofuoglu

2015-08-01

Full Text Available An artificial neural network (ANN approach was employed for the prediction and control of surface roughness (Ra and Rz in a computer numerical control (CNC machine. Experiments were performed on a CNC machine to obtain data used for the training and testing of an ANN. Experimental studies were conducted, and a model based on the experimental results was set up. Five machining parameters (cutter type, tool clearance strategy, spindle speed, feed rate, and depth of cut were used. One hidden layer was used for all models, while there were five neurons in the hidden layer of the Ra and Rz models. The RMSE values were calculated as 1.05 and 3.70. The mean absolute percentage error (MAPE values were calculated as 20.18 and 15.14, which can be considered as a good prediction. The results of the ANN approach were compared with the measured values. It was shown that the ANN prediction model obtained is a useful and effective tool for modeling the Ra and Rz of wood. The results of the present research can be applied in the wood machining industry to reduce energy, time, and cost.

Applications of Artificial Neural Network for the Prediction of Pool Boiling Curves

International Nuclear Information System (INIS)

Su, Guanghui; Fukuda, K.; Morita, K.

2002-01-01

Artificial neural network (ANN) has the advantage that the best-fit correlations of experimental data will no longer be necessary for predicting unknowns from the known parameters. The ANN was applied to predict the pool boiling curves in this paper. The database of experimental data presented by Berenson, Dhuga et al., and Bui and Dhir etc. were used in the analysis. The database is subdivided in two subsets. The first subset is used to train the network and the second one is used to test the network after the training process. The input parameters of the ANN are: wall superheat ΔT w , surface roughness, steady/transient heating/transient cooling, subcooling, Surface inclination and pressure. The output parameter is heat flux q. The proposed methodology allows us to achieve the accuracy that satisfies the user's convergence criterion and it is suitable for pool boiling curve data processing. (authors)

A simple mechanical system for studying adaptive oscillatory neural networks

DEFF Research Database (Denmark)

Jouffroy, Guillaume; Jouffroy, Jerome

Central Pattern Generators (CPG) are oscillatory systems that are responsible for generating rhythmic patterns at the origin of many biological activities such as for example locomotion or digestion. These systems are generally modelled as recurrent neural networks whose parameters are tuned so...... that the network oscillates in a suitable way, this tuning being a non trivial task. It also appears that the link with the physical body that these oscillatory entities control has a fundamental importance, and it seems that most bodies used for experimental validation in the literature (walking robots, lamprey...... a brief description of the Roller-Racer, we present as a preliminary study an RNN-based feed-forward controller whose parameters are obtained through the well-known teacher forcing learning algorithm, extended to learn signals with a continuous component....

Quantitative surface topography assessment of directly compressed and roller compacted tablet cores using photometric stereo image analysis.

Science.gov (United States)

Allesø, Morten; Holm, Per; Carstensen, Jens Michael; Holm, René

2016-05-25

Surface topography, in the context of surface smoothness/roughness, was investigated by the use of an image analysis technique, MultiRay™, related to photometric stereo, on different tablet batches manufactured either by direct compression or roller compaction. In the present study, oblique illumination of the tablet (darkfield) was considered and the area of cracks and pores in the surface was used as a measure of tablet surface topography; the higher a value, the rougher the surface. The investigations demonstrated a high precision of the proposed technique, which was able to rapidly (within milliseconds) and quantitatively measure the obtained surface topography of the produced tablets. Compaction history, in the form of applied roll force and tablet punch pressure, was also reflected in the measured smoothness of the tablet surfaces. Generally it was found that a higher degree of plastic deformation of the microcrystalline cellulose resulted in a smoother tablet surface. This altogether demonstrated that the technique provides the pharmaceutical developer with a reliable, quantitative response parameter for visual appearance of solid dosage forms, which may be used for process and ultimately product optimization. Copyright © 2015 Elsevier B.V. All rights reserved.

Morphological neural networks

Energy Technology Data Exchange (ETDEWEB)

Ritter, G.X.; Sussner, P. [Univ. of Florida, Gainesville, FL (United States)

1996-12-31

The theory of artificial neural networks has been successfully applied to a wide variety of pattern recognition problems. In this theory, the first step in computing the next state of a neuron or in performing the next layer neural network computation involves the linear operation of multiplying neural values by their synaptic strengths and adding the results. Thresholding usually follows the linear operation in order to provide for nonlinearity of the network. In this paper we introduce a novel class of neural networks, called morphological neural networks, in which the operations of multiplication and addition are replaced by addition and maximum (or minimum), respectively. By taking the maximum (or minimum) of sums instead of the sum of products, morphological network computation is nonlinear before thresholding. As a consequence, the properties of morphological neural networks are drastically different than those of traditional neural network models. In this paper we consider some of these differences and provide some particular examples of morphological neural network.

Application of artificial neural networks for response surface modelling in HPLC method development

Directory of Open Access Journals (Sweden)

Mohamed A. Korany

2012-01-01

Full Text Available This paper discusses the usefulness of artificial neural networks (ANNs for response surface modelling in HPLC method development. In this study, the combined effect of pH and mobile phase composition on the reversed-phase liquid chromatographic behaviour of a mixture of salbutamol (SAL and guaiphenesin (GUA, combination I, and a mixture of ascorbic acid (ASC, paracetamol (PAR and guaiphenesin (GUA, combination II, was investigated. The results were compared with those produced using multiple regression (REG analysis. To examine the respective predictive power of the regression model and the neural network model, experimental and predicted response factor values, mean of squares error (MSE, average error percentage (Er%, and coefficients of correlation (r were compared. It was clear that the best networks were able to predict the experimental responses more accurately than the multiple regression analysis.

Surface correlations of hydrodynamic drag for transitionally rough engineering surfaces

Science.gov (United States)

Thakkar, Manan; Busse, Angela; Sandham, Neil

2017-02-01

Rough surfaces are usually characterised by a single equivalent sand-grain roughness height scale that typically needs to be determined from laboratory experiments. Recently, this method has been complemented by a direct numerical simulation approach, whereby representative surfaces can be scanned and the roughness effects computed over a range of Reynolds number. This development raises the prospect over the coming years of having enough data for different types of rough surfaces to be able to relate surface characteristics to roughness effects, such as the roughness function that quantifies the downward displacement of the logarithmic law of the wall. In the present contribution, we use simulation data for 17 irregular surfaces at the same friction Reynolds number, for which they are in the transitionally rough regime. All surfaces are scaled to the same physical roughness height. Mean streamwise velocity profiles show a wide range of roughness function values, while the velocity defect profiles show a good collapse. Profile peaks of the turbulent kinetic energy also vary depending on the surface. We then consider which surface properties are important and how new properties can be incorporated into an empirical model, the accuracy of which can then be tested. Optimised models with several roughness parameters are systematically developed for the roughness function and profile peak turbulent kinetic energy. In determining the roughness function, besides the known parameters of solidity (or frontal area ratio) and skewness, it is shown that the streamwise correlation length and the root-mean-square roughness height are also significant. The peak turbulent kinetic energy is determined by the skewness and root-mean-square roughness height, along with the mean forward-facing surface angle and spanwise effective slope. The results suggest feasibility of relating rough-wall flow properties (throughout the range from hydrodynamically smooth to fully rough) to surface

Artificial neural network analysis of RBS data with roughness: Application to Ti{sub 0.4}Al{sub 0.6}N/Mo multilayers

Energy Technology Data Exchange (ETDEWEB)

Oehl, G.; Matias, V.; Vieira, A.; Barradas, N.P. E-mail: nunoni@itn.mces.pt

2003-10-01

In multilayered Ti{sub 0.4}Al{sub 0.6}N/Mo coatings, a strengthening effect can be obtained by using alternate layers of materials with high and low elastic constants. This behaviour requires a multilayer periodicity below a certain value in order to reduce dislocation motion across layer interface. Below this critical period, in most cases the hardness decreases as the period decreases. The multiple interfaces have an important role on this behaviour, working as stress relaxation areas and preventing crack propagation, influencing the mechanical properties of the system. Understanding the origin of these effects requires knowledge of the interface structure, where the interfacial roughness is of prime importance. We used Rutherford backscattering to study roughness in a quantitative way, and developed an artificial neural network algorithm dedicated to the analysis of the data. The results compare very well with previous TEM and AFM data.

Neural network-based adaptive dynamic surface control for permanent magnet synchronous motors.

Science.gov (United States)

Yu, Jinpeng; Shi, Peng; Dong, Wenjie; Chen, Bing; Lin, Chong

2015-03-01

This brief considers the problem of neural networks (NNs)-based adaptive dynamic surface control (DSC) for permanent magnet synchronous motors (PMSMs) with parameter uncertainties and load torque disturbance. First, NNs are used to approximate the unknown and nonlinear functions of PMSM drive system and a novel adaptive DSC is constructed to avoid the explosion of complexity in the backstepping design. Next, under the proposed adaptive neural DSC, the number of adaptive parameters required is reduced to only one, and the designed neural controllers structure is much simpler than some existing results in literature, which can guarantee that the tracking error converges to a small neighborhood of the origin. Then, simulations are given to illustrate the effectiveness and potential of the new design technique.

Assessing artificial neural networks and statistical methods for infilling missing soil moisture records

Science.gov (United States)

Dumedah, Gift; Walker, Jeffrey P.; Chik, Li

2014-07-01

Soil moisture information is critically important for water management operations including flood forecasting, drought monitoring, and groundwater recharge estimation. While an accurate and continuous record of soil moisture is required for these applications, the available soil moisture data, in practice, is typically fraught with missing values. There are a wide range of methods available to infilling hydrologic variables, but a thorough inter-comparison between statistical methods and artificial neural networks has not been made. This study examines 5 statistical methods including monthly averages, weighted Pearson correlation coefficient, a method based on temporal stability of soil moisture, and a weighted merging of the three methods, together with a method based on the concept of rough sets. Additionally, 9 artificial neural networks are examined, broadly categorized into feedforward, dynamic, and radial basis networks. These 14 infilling methods were used to estimate missing soil moisture records and subsequently validated against known values for 13 soil moisture monitoring stations for three different soil layer depths in the Yanco region in southeast Australia. The evaluation results show that the top three highest performing methods are the nonlinear autoregressive neural network, rough sets method, and monthly replacement. A high estimation accuracy (root mean square error (RMSE) of about 0.03 m/m) was found in the nonlinear autoregressive network, due to its regression based dynamic network which allows feedback connections through discrete-time estimation. An equally high accuracy (0.05 m/m RMSE) in the rough sets procedure illustrates the important role of temporal persistence of soil moisture, with the capability to account for different soil moisture conditions.

Modeling polyvinyl chloride Plasma Modification by Neural Networks

Science.gov (United States)

Wang, Changquan

2018-03-01

Neural networks model were constructed to analyze the connection between dielectric barrier discharge parameters and surface properties of material. The experiment data were generated from polyvinyl chloride plasma modification by using uniform design. Discharge voltage, discharge gas gap and treatment time were as neural network input layer parameters. The measured values of contact angle were as the output layer parameters. A nonlinear mathematical model of the surface modification for polyvinyl chloride was developed based upon the neural networks. The optimum model parameters were obtained by the simulation evaluation and error analysis. The results of the optimal model show that the predicted value is very close to the actual test value. The prediction model obtained here are useful for discharge plasma surface modification analysis.

Neural Networks

International Nuclear Information System (INIS)

Smith, Patrick I.

2003-01-01

Physicists use large detectors to measure particles created in high-energy collisions at particle accelerators. These detectors typically produce signals indicating either where ionization occurs along the path of the particle, or where energy is deposited by the particle. The data produced by these signals is fed into pattern recognition programs to try to identify what particles were produced, and to measure the energy and direction of these particles. Ideally, there are many techniques used in this pattern recognition software. One technique, neural networks, is particularly suitable for identifying what type of particle caused by a set of energy deposits. Neural networks can derive meaning from complicated or imprecise data, extract patterns, and detect trends that are too complex to be noticed by either humans or other computer related processes. To assist in the advancement of this technology, Physicists use a tool kit to experiment with several neural network techniques. The goal of this research is interface a neural network tool kit into Java Analysis Studio (JAS3), an application that allows data to be analyzed from any experiment. As the final result, a physicist will have the ability to train, test, and implement a neural network with the desired output while using JAS3 to analyze the results or output. Before an implementation of a neural network can take place, a firm understanding of what a neural network is and how it works is beneficial. A neural network is an artificial representation of the human brain that tries to simulate the learning process [5]. It is also important to think of the word artificial in that definition as computer programs that use calculations during the learning process. In short, a neural network learns by representative examples. Perhaps the easiest way to describe the way neural networks learn is to explain how the human brain functions. The human brain contains billions of neural cells that are responsible for processing

Improving Dry Powder Inhaler Performance by Surface Roughening of Lactose Carrier Particles.

Science.gov (United States)

Tan, Bernice Mei Jin; Chan, Lai Wah; Heng, Paul Wan Sia

2016-08-01

This study investigated the impact of macro-scale carrier surface roughness on the performance of dry powder inhaler (DPI) formulations. Fluid-bed processing and roller compaction were explored as processing methods to increase the surface roughness (Ra) of lactose carrier particles. DPI formulations containing either (a) different concentrations of fine lactose at a fixed concentration of micronized drug (isoniazid) or (b) various concentrations of drug in the absence of fine lactose were prepared. The fine particle fraction (FPF) and aerodynamic particle size of micronized drug of all formulations were determined using the Next Generation Impactor. Fluid-bed processing resulted in a modest increase in the Ra from 562 to 907 nm while roller compaction led to significant increases in Ra > 1300 nm. The roller compacted carriers exhibited FPF > 35%, which were twice that of the smoothest carriers. The addition of up to 5%, w/w of fine lactose improved the FPF of smoother carriers by 60-200% whereas only lactose carrier particles by roller compaction was immensely beneficial to improving DPI performance, primarily due to increased surface roughness at the macro-scale.

Neural network based method for conversion of solar radiation data

International Nuclear Information System (INIS)

Celik, Ali N.; Muneer, Tariq

2013-01-01

Highlights: ► Generalized regression neural network is used to predict the solar radiation on tilted surfaces. ► The above network, amongst many such as multilayer perceptron, is the most successful one. ► The present neural network returns a relative mean absolute error value of 9.1%. ► The present model leads to a mean absolute error value of estimate of 14.9 Wh/m 2 . - Abstract: The receiving ends of the solar energy conversion systems that generate heat or electricity from radiation is usually tilted at an optimum angle to increase the solar incident on the surface. Solar irradiation data measured on horizontal surfaces is readily available for many locations where such solar energy conversion systems are installed. Various equations have been developed to convert solar irradiation data measured on horizontal surface to that on tilted one. These equations constitute the conventional approach. In this article, an alternative approach, generalized regression type of neural network, is used to predict the solar irradiation on tilted surfaces, using the minimum number of variables involved in the physical process, namely the global solar irradiation on horizontal surface, declination and hour angles. Artificial neural networks have been successfully used in recent years for optimization, prediction and modeling in energy systems as alternative to conventional modeling approaches. To show the merit of the presently developed neural network, the solar irradiation data predicted from the novel model was compared to that from the conventional approach (isotropic and anisotropic models), with strict reference to the irradiation data measured in the same location. The present neural network model was found to provide closer solar irradiation values to the measured than the conventional approach, with a mean absolute error value of 14.9 Wh/m 2 . The other statistical values of coefficient of determination and relative mean absolute error also indicate the

A comparison RSM and ANN surface roughness models in thin-wall machining of Ti6Al4V using vegetable oils under MQL-condition

Science.gov (United States)

Mohruni, Amrifan Saladin; Yanis, Muhammad; Sharif, Safian; Yani, Irsyadi; Yuliwati, Erna; Ismail, Ahmad Fauzi; Shayfull, Zamree

2017-09-01

Thin-wall components as usually applied in the structural parts of aeronautical industry require significant challenges in machining. Unacceptable surface roughness can occur during machining of thin-wall. Titanium product such Ti6Al4V is mostly applied to get the appropriate surface texture in thin wall designed requirements. In this study, the comparison of the accuracy between Response Surface Methodology (RSM) and Artificial Neural Networks (ANN) in the prediction of surface roughness was conducted. Furthermore, the machining tests were carried out under Minimum Quantity Lubrication (MQL) using AlCrN-coated carbide tools. The use of Coconut oil as cutting fluids was also chosen in order to evaluate its performance when involved in end milling. This selection of cutting fluids is based on the better performance of oxidative stability than that of other vegetable based cutting fluids. The cutting speed, feed rate, radial and axial depth of cut were used as independent variables, while surface roughness is evaluated as the dependent variable or output. The results showed that the feed rate is the most significant factors in increasing the surface roughness value followed by the radial depth of cut and lastly the axial depth of cut. In contrary, the surface becomes smoother with increasing the cutting speed. From a comparison of both methods, the ANN model delivered a better accuracy than the RSM model.

Rock discontinuity surface roughness variation with scale

Science.gov (United States)

Bitenc, Maja; Kieffer, D. Scott; Khoshelham, Kourosh

2017-04-01

ABSTRACT: Rock discontinuity surface roughness refers to local departures of the discontinuity surface from planarity and is an important factor influencing the shear resistance. In practice, the Joint Roughness Coefficient (JRC) roughness parameter is commonly relied upon and input to a shear strength criterion such as developed by Barton and Choubey [1977]. The estimation of roughness by JRC is hindered firstly by the subjective nature of visually comparing the joint profile to the ten standard profiles. Secondly, when correlating the standard JRC values and other objective measures of roughness, the roughness idealization is limited to a 2D profile of 10 cm length. With the advance of measuring technologies that provide accurate and high resolution 3D data of surface topography on different scales, new 3D roughness parameters have been developed. A desirable parameter is one that describes rock surface geometry as well as the direction and scale dependency of roughness. In this research a 3D roughness parameter developed by Grasselli [2001] and adapted by Tatone and Grasselli [2009] is adopted. It characterizes surface topography as the cumulative distribution of local apparent inclination of asperities with respect to the shear strength (analysis) direction. Thus, the 3D roughness parameter describes the roughness amplitude and anisotropy (direction dependency), but does not capture the scale properties. In different studies the roughness scale-dependency has been attributed to data resolution or size of the surface joint (see a summary of researches in [Tatone and Grasselli, 2012]). Clearly, the lower resolution results in lower roughness. On the other hand, have the investigations of surface size effect produced conflicting results. While some studies have shown a decrease in roughness with increasing discontinuity size (negative scale effect), others have shown the existence of positive scale effects, or both positive and negative scale effects. We

Shadow analysis of soil surface roughness compared to the chain set method and direct measurement of micro-relief

Directory of Open Access Journals (Sweden)

R. García Moreno

2010-08-01

Full Text Available Soil surface roughness (SSR expresses soil susceptibility to wind and water erosion and plays an important role in the development and the maintenance of soil biota. Several methods have been developed to characterise SSR based on different methods of acquiring data. Because the main problems related to these methods involve the use and handling of equipment in the field, the present study aims to fill the need for a method for measuring SSR that is more reliable, low-cost and convenient in the field than traditional field methods. Shadow analysis, which interprets micro-topographic shadows, is based on the principle that there is a direct relationship between the soil surface roughness and the shadows cast by soil structures under fixed sunlight conditions. SSR was calculated with shadows analysis in the laboratory using hemispheres of different diameter with a diverse distribution of known altitudes and a surface area of 1 m².

Data obtained from the shadow analysis were compared to data obtained with the chain method and simulation of the micro-relief. The results show a relationship among the SSR calculated using the different methods. To further improve the method, shadow analysis was used to measure the SSR in a sandy clay loam field using different tillage tools (chisel, tiller and roller and in a control of 4 m² surface plots divided into subplots of 1 m². The measurements were compared to the data obtained using the chain set and pin meter methods. The SSR measured was the highest when the chisel was used, followed by the tiller and the roller, and finally the control, for each of the three methods. Shadow analysis is shown to be a reliable method that does not disturb the measured surface, is easy to handle and analyse, and shortens the time involved in field operations by a factor ranging from 4 to 20 compared to well known techniques such as the chain set and pin meter methods.

Three-tier rough superhydrophobic surfaces

International Nuclear Information System (INIS)

Cao, Yuanzhi; Yuan, Longyan; Hu, Bin; Zhou, Jun

2015-01-01

A three-tier rough superhydrophobic surface was fabricated by growing hydrophobic modified (fluorinated silane) zinc oxide (ZnO)/copper oxide (CuO) hetero-hierarchical structures on silicon (Si) micro-pillar arrays. Compared with the other three control samples with a less rough tier, the three-tier surface exhibits the best water repellency with the largest contact angle 161° and the lowest sliding angle 0.5°. It also shows a robust Cassie state which enables the water to flow with a speed over 2 m s"−"1. In addition, it could prevent itself from being wetted by the droplet with low surface tension (mixed water and ethanol 1:1 in volume) which reveals a flow speed of 0.6 m s"−"1 (dropped from the height of 2 cm). All these features prove that adding another rough tier on a two-tier rough surface could futher improve its water-repellent properties. (paper)

Inverting radiometric measurements with a neural network

Science.gov (United States)

Measure, Edward M.; Yee, Young P.; Balding, Jeff M.; Watkins, Wendell R.

1992-02-01

A neural network scheme for retrieving remotely sensed vertical temperature profiles was applied to observed ground based radiometer measurements. The neural network used microwave radiance measurements and surface measurements of temperature and pressure as inputs. Because the microwave radiometer is capable of measuring 4 oxygen channels at 5 different elevation angles (9, 15, 25, 40, and 90 degs), 20 microwave measurements are potentially available. Because these measurements have considerable redundancy, a neural network was experimented with, accepting as inputs microwave measurements taken at 53.88 GHz, 40 deg; 57.45 GHz, 40 deg; and 57.45, 90 deg. The primary test site was located at White Sands Missile Range (WSMR), NM. Results are compared with measurements made simultaneously with balloon borne radiosonde instruments and with radiometric temperature retrievals made using more conventional retrieval algorithms. The neural network was trained using a Widrow-Hoff delta rule procedure. Functions of date to include season dependence in the retrieval process and functions of time to include diurnal effects were used as inputs to the neural network.

Design of cognitive engine for cognitive radio based on the rough sets and radial basis function neural network

Science.gov (United States)

Yang, Yanchao; Jiang, Hong; Liu, Congbin; Lan, Zhongli

2013-03-01

Cognitive radio (CR) is an intelligent wireless communication system which can dynamically adjust the parameters to improve system performance depending on the environmental change and quality of service. The core technology for CR is the design of cognitive engine, which introduces reasoning and learning methods in the field of artificial intelligence, to achieve the perception, adaptation and learning capability. Considering the dynamical wireless environment and demands, this paper proposes a design of cognitive engine based on the rough sets (RS) and radial basis function neural network (RBF_NN). The method uses experienced knowledge and environment information processed by RS module to train the RBF_NN, and then the learning model is used to reconfigure communication parameters to allocate resources rationally and improve system performance. After training learning model, the performance is evaluated according to two benchmark functions. The simulation results demonstrate the effectiveness of the model and the proposed cognitive engine can effectively achieve the goal of learning and reconfiguration in cognitive radio.

Bayesian inversion of surface wave data for discontinuities and velocity structure in the upper mantle using Neural Networks. Geologica Ultraiectina (287)

NARCIS (Netherlands)

Meier, U.

2008-01-01

We present a neural network approach to invert surface wave data for discontinuities and velocity structure in the upper mantle. We show how such a neural network can be trained on a set of random samples to give a continuous approximation to the inverse relation in a compact and computationally

Chaotic diagonal recurrent neural network

International Nuclear Information System (INIS)

Wang Xing-Yuan; Zhang Yi

2012-01-01

We propose a novel neural network based on a diagonal recurrent neural network and chaos, and its structure and learning algorithm are designed. The multilayer feedforward neural network, diagonal recurrent neural network, and chaotic diagonal recurrent neural network are used to approach the cubic symmetry map. The simulation results show that the approximation capability of the chaotic diagonal recurrent neural network is better than the other two neural networks. (interdisciplinary physics and related areas of science and technology)

Dissolution of minerals with rough surfaces

Science.gov (United States)

de Assis, Thiago A.; Aarão Reis, Fábio D. A.

2018-05-01

We study dissolution of minerals with initial rough surfaces using kinetic Monte Carlo simulations and a scaling approach. We consider a simple cubic lattice structure, a thermally activated rate of detachment of a molecule (site), and rough surface configurations produced by fractional Brownian motion algorithm. First we revisit the problem of dissolution of initial flat surfaces, in which the dissolution rate rF reaches an approximately constant value at short times and is controlled by detachment of step edge sites. For initial rough surfaces, the dissolution rate r at short times is much larger than rF ; after dissolution of some hundreds of molecular layers, r decreases by some orders of magnitude across several time decades. Meanwhile, the surface evolves through configurations of decreasing energy, beginning with dissolution of isolated sites, then formation of terraces with disordered boundaries, their growth, and final smoothing. A crossover time to a smooth configuration is defined when r = 1.5rF ; the surface retreat at the crossover is approximately 3 times the initial roughness and is temperature-independent, while the crossover time is proportional to the initial roughness and is controlled by step-edge site detachment. The initial dissolution process is described by the so-called rough rates, which are measured for fixed ratios between the surface retreat and the initial roughness. The temperature dependence of the rough rates indicates control by kink site detachment; in general, it suggests that rough rates are controlled by the weakest microscopic bonds during the nucleation and formation of the lowest energy configurations of the crystalline surface. Our results are related to recent laboratory studies which show enhanced dissolution in polished calcite surfaces. In the application to calcite dissolution in alkaline environment, the minimal values of recently measured dissolution rate spectra give rF ∼10-9 mol/(m2 s), and the calculated rate

Neural networks

International Nuclear Information System (INIS)

Denby, Bruce; Lindsey, Clark; Lyons, Louis

1992-01-01

The 1980s saw a tremendous renewal of interest in 'neural' information processing systems, or 'artificial neural networks', among computer scientists and computational biologists studying cognition. Since then, the growth of interest in neural networks in high energy physics, fueled by the need for new information processing technologies for the next generation of high energy proton colliders, can only be described as explosive

Nano-topography Enhances Communication in Neural Cells Networks

KAUST Repository

Onesto, V.; Cancedda, L.; Coluccio, M. L.; Nanni, M.; Pesce, M.; Malara, N.; Cesarelli, M.; Di Fabrizio, Enzo M.; Amato, F.; Gentile, F.

2017-01-01

Neural cells are the smallest building blocks of the central and peripheral nervous systems. Information in neural networks and cell-substrate interactions have been heretofore studied separately. Understanding whether surface nano-topography can

Towards predictive models for transitionally rough surfaces

Science.gov (United States)

Abderrahaman-Elena, Nabil; Garcia-Mayoral, Ricardo

2017-11-01

We analyze and model the previously presented decomposition for flow variables in DNS of turbulence over transitionally rough surfaces. The flow is decomposed into two contributions: one produced by the overlying turbulence, which has no footprint of the surface texture, and one induced by the roughness, which is essentially the time-averaged flow around the surface obstacles, but modulated in amplitude by the first component. The roughness-induced component closely resembles the laminar steady flow around the roughness elements at the same non-dimensional roughness size. For small - yet transitionally rough - textures, the roughness-free component is essentially the same as over a smooth wall. Based on these findings, we propose predictive models for the onset of the transitionally rough regime. Project supported by the Engineering and Physical Sciences Research Council (EPSRC).

Permutation invariant potential energy surfaces for polyatomic reactions using atomistic neural networks

International Nuclear Information System (INIS)

Kolb, Brian; Zhao, Bin; Guo, Hua; Li, Jun; Jiang, Bin

2016-01-01

The applicability and accuracy of the Behler-Parrinello atomistic neural network method for fitting reactive potential energy surfaces is critically examined in three systems, H + H 2 → H 2 + H, H + H 2 O → H 2 + OH, and H + CH 4 → H 2 + CH 3 . A pragmatic Monte Carlo method is proposed to make efficient choice of the atom-centered mapping functions. The accuracy of the potential energy surfaces is not only tested by fitting errors but also validated by direct comparison in dynamically important regions and by quantum scattering calculations. Our results suggest this method is both accurate and efficient in representing multidimensional potential energy surfaces even when dissociation continua are involved.

An optimum design on rollers containing the groove with changeable inner diameter based on response surface methodology

Directory of Open Access Journals (Sweden)

Xi Zhao

2016-05-01

Full Text Available In order to realize the precision plastic forming of the revolving body component with changeable wall thickness, a kind of roller containing grooves with changeable inner diameter is put forward, as the forming mould of the technology of rolling-extrusion. Specifically, first, the arc length of the groove in the roller is designed according to the prediction on the forward slip value during the process of forming, to make accurate control of the actual length of the forming segments; then, to obtain better parameters of the roller structure, a second-order response surface model combining finite element numerical simulation and response surface methodology was put forward, taking the factor of forming uniformity as evaluation index. The result of the experiment shows that, for the formed component, not only the size can meet the needs but also each mechanical property index can be greatly improved, which verify the rationality of the forward slip model and the structural parameter of the optimum model based on the response surface methodology.

Loss surface of XOR artificial neural networks

Science.gov (United States)

Mehta, Dhagash; Zhao, Xiaojun; Bernal, Edgar A.; Wales, David J.

2018-05-01

Training an artificial neural network involves an optimization process over the landscape defined by the cost (loss) as a function of the network parameters. We explore these landscapes using optimization tools developed for potential energy landscapes in molecular science. The number of local minima and transition states (saddle points of index one), as well as the ratio of transition states to minima, grow rapidly with the number of nodes in the network. There is also a strong dependence on the regularization parameter, with the landscape becoming more convex (fewer minima) as the regularization term increases. We demonstrate that in our formulation, stationary points for networks with Nh hidden nodes, including the minimal network required to fit the XOR data, are also stationary points for networks with Nh+1 hidden nodes when all the weights involving the additional node are zero. Hence, smaller networks trained on XOR data are embedded in the landscapes of larger networks. Our results clarify certain aspects of the classification and sensitivity (to perturbations in the input data) of minima and saddle points for this system, and may provide insight into dropout and network compression.

Characterisation of surface roughness for ultra-precision freeform surfaces

International Nuclear Information System (INIS)

Li Huifen; Cheung, C F; Lee, W B; To, S; Jiang, X Q

2005-01-01

Ultra-precision freeform surfaces are widely used in many advanced optics applications which demand for having surface roughness down to nanometer range. Although a lot of research work has been reported on the study of surface generation, reconstruction and surface characterization such as MOTIF and fractal analysis, most of them are focused on axial symmetric surfaces such as aspheric surfaces. Relative little research work has been found in the characterization of surface roughness in ultra-precision freeform surfaces. In this paper, a novel Robust Gaussian Filtering (RGF) method is proposed for the characterisation of surface roughness for ultra-precision freeform surfaces with known mathematic model or a cloud of discrete points. A series of computer simulation and measurement experiments were conducted to verify the capability of the proposed method. The experimental results were found to agree well with the theoretical results

Neural networks for aircraft control

Science.gov (United States)

Linse, Dennis

1990-01-01

Current research in Artificial Neural Networks indicates that networks offer some potential advantages in adaptation and fault tolerance. This research is directed at determining the possible applicability of neural networks to aircraft control. The first application will be to aircraft trim. Neural network node characteristics, network topology and operation, neural network learning and example histories using neighboring optimal control with a neural net are discussed.

Periodicity and stability for variable-time impulsive neural networks.

Science.gov (United States)

Li, Hongfei; Li, Chuandong; Huang, Tingwen

2017-10-01

The paper considers a general neural networks model with variable-time impulses. It is shown that each solution of the system intersects with every discontinuous surface exactly once via several new well-proposed assumptions. Moreover, based on the comparison principle, this paper shows that neural networks with variable-time impulse can be reduced to the corresponding neural network with fixed-time impulses under well-selected conditions. Meanwhile, the fixed-time impulsive systems can be regarded as the comparison system of the variable-time impulsive neural networks. Furthermore, a series of sufficient criteria are derived to ensure the existence and global exponential stability of periodic solution of variable-time impulsive neural networks, and to illustrate the same stability properties between variable-time impulsive neural networks and the fixed-time ones. The new criteria are established by applying Schaefer's fixed point theorem combined with the use of inequality technique. Finally, a numerical example is presented to show the effectiveness of the proposed results. Copyright © 2017 Elsevier Ltd. All rights reserved.

Chaos control of the brushless direct current motor using adaptive dynamic surface control based on neural network with the minimum weights

International Nuclear Information System (INIS)

Luo, Shaohua; Wu, Songli; Gao, Ruizhen

2015-01-01

This paper investigates chaos control for the brushless DC motor (BLDCM) system by adaptive dynamic surface approach based on neural network with the minimum weights. The BLDCM system contains parameter perturbation, chaotic behavior, and uncertainty. With the help of radial basis function (RBF) neural network to approximate the unknown nonlinear functions, the adaptive law is established to overcome uncertainty of the control gain. By introducing the RBF neural network and adaptive technology into the dynamic surface control design, a robust chaos control scheme is developed. It is proved that the proposed control approach can guarantee that all signals in the closed-loop system are globally uniformly bounded, and the tracking error converges to a small neighborhood of the origin. Simulation results are provided to show that the proposed approach works well in suppressing chaos and parameter perturbation

Chaos control of the brushless direct current motor using adaptive dynamic surface control based on neural network with the minimum weights.

Science.gov (United States)

Luo, Shaohua; Wu, Songli; Gao, Ruizhen

2015-07-01

This paper investigates chaos control for the brushless DC motor (BLDCM) system by adaptive dynamic surface approach based on neural network with the minimum weights. The BLDCM system contains parameter perturbation, chaotic behavior, and uncertainty. With the help of radial basis function (RBF) neural network to approximate the unknown nonlinear functions, the adaptive law is established to overcome uncertainty of the control gain. By introducing the RBF neural network and adaptive technology into the dynamic surface control design, a robust chaos control scheme is developed. It is proved that the proposed control approach can guarantee that all signals in the closed-loop system are globally uniformly bounded, and the tracking error converges to a small neighborhood of the origin. Simulation results are provided to show that the proposed approach works well in suppressing chaos and parameter perturbation.

Permutation invariant potential energy surfaces for polyatomic reactions using atomistic neural networks

Energy Technology Data Exchange (ETDEWEB)

Kolb, Brian [Department of Chemistry and Chemical Biology, University of New Mexico, Albuquerque, New Mexico 87131 (United States); Department of Mechanical Engineering, Massachusetts Institute of Technology, Cambridge, Massachusetts 02139 (United States); Zhao, Bin; Guo, Hua, E-mail: hguo@unm.edu [Department of Chemistry and Chemical Biology, University of New Mexico, Albuquerque, New Mexico 87131 (United States); Li, Jun [School of Chemistry and Chemical Engineering, Chongqing University, Chongqing 401331 (China); Jiang, Bin [Department of Chemical Physics, University of Science and Technology of China, Hefei, Anhui 230026 (China)

2016-06-14

The applicability and accuracy of the Behler-Parrinello atomistic neural network method for fitting reactive potential energy surfaces is critically examined in three systems, H + H{sub 2} → H{sub 2} + H, H + H{sub 2}O → H{sub 2} + OH, and H + CH{sub 4} → H{sub 2} + CH{sub 3}. A pragmatic Monte Carlo method is proposed to make efficient choice of the atom-centered mapping functions. The accuracy of the potential energy surfaces is not only tested by fitting errors but also validated by direct comparison in dynamically important regions and by quantum scattering calculations. Our results suggest this method is both accurate and efficient in representing multidimensional potential energy surfaces even when dissociation continua are involved.

Prediction Of Tensile And Shear Strength Of Friction Surfaced Tool Steel Deposit By Using Artificial Neural Networks

Science.gov (United States)

Manzoor Hussain, M.; Pitchi Raju, V.; Kandasamy, J.; Govardhan, D.

2018-04-01

Friction surface treatment is well-established solid technology and is used for deposition, abrasion and corrosion protection coatings on rigid materials. This novel process has wide range of industrial applications, particularly in the field of reclamation and repair of damaged and worn engineering components. In this paper, we present the prediction of tensile and shear strength of friction surface treated tool steel using ANN for simulated results of friction surface treatment. This experiment was carried out to obtain tool steel coatings of low carbon steel parts by changing contribution process parameters essentially friction pressure, rotational speed and welding speed. The simulation is performed by a 33-factor design that takes into account the maximum and least limits of the experimental work performed with the 23-factor design. Neural network structures, such as the Feed Forward Neural Network (FFNN), were used to predict tensile and shear strength of tool steel sediments caused by friction.

Within-footprint roughness measurements using ICESat/GLAS waveform and LVIS elevation

International Nuclear Information System (INIS)

Li, Xiaolu; Xu, Kai; Xu, Lijun

2016-01-01

The surface roughness is an important characteristic over an ice sheet or glacier, since it is an identification of boundary-layer meteorology and is an important limiter on the accuracy of surface-height measurements. In this paper, we propose a simulation method to derive the within-footprint roughness (called simulation-derived roughness) using ICESat/GLAS echo waveform, laser vegetation imaging sensor (LVIS) elevations, and laser profile array (LPA) images of ICESat/GLAS. By dividing the within-footprint surface into several elements, a simulation echo waveform can be obtained as the sum of the elementary pulses reflected from each surface element. The elevation of the surface elements, which is utilized to get the return time of the elementary pulses, is implemented based on an LVIS interpolated elevation using a radial basis function (RBF) neural network. The intensity of the elementary pulses can be obtained from the thresholded LPA images. Based on the return time and the intensity of the elementary pulses, we used the particle swarm optimization (PSO) method to approximate the simulation waveform to the ICESat/GLAS echo waveform. The full width at half maximum) (FWHM) of the elementary pulse was extracted from the simulation waveform for estimating the simulation-derived roughness. By comparing with the elevation-derived roughness (derived from the elevation) and the waveform-derived roughness (derived from the ICESat/GLAS waveform), the proposed algorithm can exclude the slope effect from waveform width broadening for describing the roughness of the surface elements. (paper)

Hidden neural networks

DEFF Research Database (Denmark)

Krogh, Anders Stærmose; Riis, Søren Kamaric

1999-01-01

A general framework for hybrids of hidden Markov models (HMMs) and neural networks (NNs) called hidden neural networks (HNNs) is described. The article begins by reviewing standard HMMs and estimation by conditional maximum likelihood, which is used by the HNN. In the HNN, the usual HMM probability...... parameters are replaced by the outputs of state-specific neural networks. As opposed to many other hybrids, the HNN is normalized globally and therefore has a valid probabilistic interpretation. All parameters in the HNN are estimated simultaneously according to the discriminative conditional maximum...... likelihood criterion. The HNN can be viewed as an undirected probabilistic independence network (a graphical model), where the neural networks provide a compact representation of the clique functions. An evaluation of the HNN on the task of recognizing broad phoneme classes in the TIMIT database shows clear...

Direct fabrication of rigid microstructures on a metallic roller using a dry film resist

International Nuclear Information System (INIS)

Jiang, Liang-Ting; Huang, Tzu-Chien; Chang, Chih-Yuan; Ciou, Jian-Ren; Yang, Sen-Yeu; Huang, Po-Hsun

2008-01-01

This paper presents a novel method to fabricate a metallic roller mold with microstructures on its surface using a dry film resist (DFR). The DFR is laminated uniformly onto the curvy surface of a copper roller. After that, the micro-scale photoresist on the surface of the roller can be patterned by non-planar lithography using a flexible film photomask, followed by ferric chloride wet etching to obtain the desired microstructures. This method overcomes the uniformity issue of photoresist coating on rollers, and solves the molds sliding problem during the embossing process because the microstructures are fabricated directly on the roller surface. Furthermore, the rigid metallic roller mold has excellent strength durability and temperature endurance, which can be used in roller hot embossing with a high embossing pressure. The fabricated microstructure roller mold is used as a mold in the hybrid extrusion roller embossing process and successfully fabricates uniform micro-scale prominent line arrays on PC films. This result proves that the roller fabricated by this method can be successfully used in roller embossing for microstructure mass production. The excellent flatness of dry film resist laminating is the key in this fabrication process. The flexible film photomask can be easily designed using CAD software; this roller fabrication method enhances the design flexibility and reduces the cost and time

Permutation invariant polynomial neural network approach to fitting potential energy surfaces. II. Four-atom systems

Energy Technology Data Exchange (ETDEWEB)

Li, Jun; Jiang, Bin; Guo, Hua, E-mail: hguo@unm.edu [Department of Chemistry and Chemical Biology, University of New Mexico, Albuquerque, New Mexico 87131 (United States)

2013-11-28

A rigorous, general, and simple method to fit global and permutation invariant potential energy surfaces (PESs) using neural networks (NNs) is discussed. This so-called permutation invariant polynomial neural network (PIP-NN) method imposes permutation symmetry by using in its input a set of symmetry functions based on PIPs. For systems with more than three atoms, it is shown that the number of symmetry functions in the input vector needs to be larger than the number of internal coordinates in order to include both the primary and secondary invariant polynomials. This PIP-NN method is successfully demonstrated in three atom-triatomic reactive systems, resulting in full-dimensional global PESs with average errors on the order of meV. These PESs are used in full-dimensional quantum dynamical calculations.

Application of artificial neural networks to segmentation and classification of topographic profiles of ridge-flank seafloor

Digital Repository Service at National Institute of Oceanography (India)

Chakraborty, B.; Lourenco, E.; Kodagali, V.N.; Baracho, J.

In this paper, we have utilized Artificial Neural Networks (ANN) for seafloor topographic data segmentation and roughness classification using the multibeam- Hydrosweep system (installed onboard ocean research vessel Sagar Kanya) data. Bathymetric...

Evaluation of Surface Fatigue Strength Based on Surface Temperature

Science.gov (United States)

Deng, Gang; Nakanishi, Tsutomu

Surface temperature is considered to be an integrated index that is dependent on not only the load and the dimensions at the contact point but also the sliding velocity, rolling velocity, surface roughness, and lubrication conditions. Therefore, the surface durability of rollers and gears can be evaluated more exactly and simply by the use of surface temperature rather than Hertzian stress. In this research, surface temperatures of rollers under different rolling and sliding conditions are measured using a thermocouple. The effects of load P, mean velocity Vm and sliding velocity Vs on surface temperature are clarified. An experimental formula, which expresses the linear relationship between surface temperature and the P0.86Vs1.31Vm-0.83 value, is used to determine surface temperature. By comparing calculated and measured temperature on the tooth surface of a gear, this formula is confirmed to be applicable for gear tooth surface temperature calculation.

Investigation on Surface Roughness in Cylindrical Grinding

Science.gov (United States)

Rudrapati, Ramesh; Bandyopadhyay, Asish; Pal, Pradip Kumar

2011-01-01

Cylindrical grinding is a complex machining process. And surface roughness is often a key factor in any machining process while considering the machine tool or machining performance. Further, surface roughness is one of the measures of the technological quality of the product and is a factor that greatly influences cost and quality. The present work is related to some aspects of surface finish in the context of traverse-cut cylindrical grinding. The parameters considered have been: infeed, longitudinal feed and work speed. Taguchi quality design is used to design the experiments and to identify the significantly import parameter(s) affecting the surface roughness. By utilization of Response Surface Methodology (RSM), second order differential equation has been developed and attempts have also been made for optimization of the process in the context of surface roughness by using C- programming.

Deep Learning Neural Networks and Bayesian Neural Networks in Data Analysis

Directory of Open Access Journals (Sweden)

Chernoded Andrey

2017-01-01

Full Text Available Most of the modern analyses in high energy physics use signal-versus-background classification techniques of machine learning methods and neural networks in particular. Deep learning neural network is the most promising modern technique to separate signal and background and now days can be widely and successfully implemented as a part of physical analysis. In this article we compare Deep learning and Bayesian neural networks application as a classifiers in an instance of top quark analysis.

Influence of surface roughness on the friction property of textured surface

Directory of Open Access Journals (Sweden)

Yuankai Zhou

2015-02-01

Full Text Available In contrast with dimple textures, surface roughness is a texture at the micro-scale, essentially which will influence the load-bearing capacity of lubricant film. The numerical simulation was carried out to investigate the influence of surface roughness on friction property of textured surface. The lubricant film pressure was obtained using the method of computational fluid dynamics according to geometric model of round dimple, and the renormalization-group k–ε turbulent model was adopted in the computation. The numerical simulation results suggest that there is an optimum dimensionless surface roughness, and near this value, the maximum load-bearing capacity can be achieved. The load-bearing capacity is determined by the surface texture, the surface roughness, and the interaction between them. To get information of friction coefficient, the experiments were conducted. This experiment was used to evaluate the simulation. The experimental results show that for the frequency of 4 and 6 Hz, friction coefficient decreases at first and then increases with decreasing surface roughness, which indicates that there exists the optimum region of surface roughness leading to the best friction reduction effect, and it becomes larger when area fractions increase from 2% to 10%. The experimental results agree well with the simulation results.

An Improved Neural Network Training Algorithm for Wi-Fi Fingerprinting Positioning

Directory of Open Access Journals (Sweden)

Esmond Mok

2013-09-01

Full Text Available Ubiquitous positioning provides continuous positional information in both indoor and outdoor environments for a wide spectrum of location based service (LBS applications. With the rapid development of the low-cost and high speed data communication, Wi-Fi networks in many metropolitan cities, strength of signals propagated from the Wi-Fi access points (APs namely received signal strength (RSS have been cleverly adopted for indoor positioning. In this paper, a Wi-Fi positioning algorithm based on neural network modeling of Wi-Fi signal patterns is proposed. This algorithm is based on the correlation between the initial parameter setting for neural network training and output of the mean square error to obtain better modeling of the nonlinear highly complex Wi-Fi signal power propagation surface. The test results show that this neural network based data processing algorithm can significantly improve the neural network training surface to achieve the highest possible accuracy of the Wi-Fi fingerprinting positioning method.

High-throughput creation of micropatterned PDMS surfaces using microscale dual roller casting

International Nuclear Information System (INIS)

DiBartolomeo, Franklin J; Ge, Ning; Trinkle, Christine A

2012-01-01

This work introduces microscale dual roller casting (MDRC), a novel high-throughput fabrication method for creating continuous micropatterned surfaces using thermosetting polymers. MDRC utilizes a pair of rotating, heated cylindrical molds with microscale surface patterns to cure a continuous microstructured film. Using unmodified polydimethylsiloxane as the thermosetting polymer, we were able to create optically transparent, biocompatible surfaces with submicron patterning fidelity. Compared to other roll-to-roll fabrication processes, this method offers increased flexibility in the types of materials and topography that can be generated, including dual-sided patterning, embedded materials and tunable film thickness. (paper)

Modelling and Predicting the Breaking Strength and Mass Irregularity of Cotton Rotor-Spun Yarns Containing Cotton Fiber Recovered from Ginning Process by Using Artificial Neural Network Algorithm

Directory of Open Access Journals (Sweden)

Mohsen Shanbeh

2011-01-01

Full Text Available One of the main methods to reduce the production costs is waste recycling which is the most important challenge for the future. Cotton wastes collected from ginning process have desirable properties which could be used during spinning process. The purpose of this study was to develop predictive models of breaking strength and mass irregularity (CV% of cotton waste rotor-spun yarns containing cotton waste collected from ginning process by using the artificial neural network trained with backpropagation algorithm. Artificial neural network models have been developed based on rotor diameter, rotor speed, navel type, opener roller speed, ginning waste proportion and yarn linear density as input parameters. The parameters of artificial neural network model, namely, learning, and momentum rate, number of hidden layers and number of hidden processing elements (neurons were optimized to get the best predictive models. The findings showed that the breaking strength and mass irregularity of rotor spun yarns could be predicted satisfactorily by artificial neural network. The maximum error in predicting the breaking strength and mass irregularity of testing data was 8.34% and 6.65%, respectively.

Role of surface roughness in superlubricity

International Nuclear Information System (INIS)

Tartaglino, U; Samoilov, V N; Persson, B N J

2006-01-01

We study the sliding of elastic solids in adhesive contact with flat and rough interfaces. We consider the dependence of the sliding friction on the elastic modulus of the solids. For elastically hard solids with planar surfaces with incommensurate surface structures we observe extremely low friction (superlubricity), which very abruptly increases as the elastic modulus decreases. We show that even a relatively small surface roughness may completely kill the superlubricity state

Modeling surface roughness scattering in metallic nanowires

Energy Technology Data Exchange (ETDEWEB)

Moors, Kristof, E-mail: kristof@itf.fys.kuleuven.be [KU Leuven, Institute for Theoretical Physics, Celestijnenlaan 200D, B-3001 Leuven (Belgium); IMEC, Kapeldreef 75, B-3001 Leuven (Belgium); Sorée, Bart [IMEC, Kapeldreef 75, B-3001 Leuven (Belgium); Physics Department, University of Antwerp, Groenenborgerlaan 171, B-2020 Antwerpen (Belgium); KU Leuven, Electrical Engineering (ESAT) Department, Kasteelpark Arenberg 10, B-3001 Leuven (Belgium); Magnus, Wim [IMEC, Kapeldreef 75, B-3001 Leuven (Belgium); Physics Department, University of Antwerp, Groenenborgerlaan 171, B-2020 Antwerpen (Belgium)

2015-09-28

Ando's model provides a rigorous quantum-mechanical framework for electron-surface roughness scattering, based on the detailed roughness structure. We apply this method to metallic nanowires and improve the model introducing surface roughness distribution functions on a finite domain with analytical expressions for the average surface roughness matrix elements. This approach is valid for any roughness size and extends beyond the commonly used Prange-Nee approximation. The resistivity scaling is obtained from the self-consistent relaxation time solution of the Boltzmann transport equation and is compared to Prange-Nee's approach and other known methods. The results show that a substantial drop in resistivity can be obtained for certain diameters by achieving a large momentum gap between Fermi level states with positive and negative momentum in the transport direction.

Numerical Investigation of Effect of Surface Roughness in a Microchannel

Energy Technology Data Exchange (ETDEWEB)

Shin, Myung Seob; Byun, Sung Jun; Yoon, Joon Yong [Hanyang University, Seoul (Korea, Republic of)

2010-05-15

In this paper, lattice Boltzmann method(LBM) results for a laminar flow in a microchannel with rough surface are presented. The surface roughness is modeled as an array of rectangular modules placed on the top and bottom surface of a parallel-plate channel. The effects of relative surface roughness, roughness distribution, and roughness size are presented in terms of the Poiseuille number. The roughness distribution characterized by the ratio of the roughness height to the spacing between the modules has a negligible effect on the flow and friction factors. Finally, a significant increase in the Poiseuille number is observed when the surface roughness is considered, and the effects of roughness on the microflow field mainly depend on the surface roughness.

Surface roughness effects on heat transfer in Couette flow

International Nuclear Information System (INIS)

Elia, G.G.

1981-01-01

A cell theory for viscous flow with rough surfaces is applied to two basic illustrative heat transfer problems which occur in Couette flow. Couette flow between one adiabatic surface and one isothermal surface exhibits roughness effects on the adiabatic wall temperature. Two types of rough cell adiabatic surfaces are studied: (1) perfectly insulating (the temperature gradient vanishes at the boundary of each cell); (2) average insulating (each cell may gain or lose heat but the total heat flow at the wall is zero). The results for the roughness on a surface in motion are postulated to occur because of fluid entrainment in the asperities on the moving surface. The symmetry of the roughness effects on thermal-viscous dissipation is discussed in detail. Explicit effects of the roughness on each surface, including combinations of roughness values, are presented to enable the case where the two surfaces may be from different materials to be studied. The fluid bulk temperature rise is also calculated for Couette flow with two ideal adiabatic surfaces. The effect of roughness on thermal-viscous dissipation concurs with the viscous hydrodynamic effect. The results are illustrated by an application to lubrication. (Auth.)

Adaptive neural networks control for camera stabilization with active suspension system

Directory of Open Access Journals (Sweden)

Feng Zhao

2015-08-01

Full Text Available The camera always suffers from image instability on the moving vehicle due to unintentional vibrations caused by road roughness. This article presents an adaptive neural network approach mixed with linear quadratic regulator control for a quarter-car active suspension system to stabilize the image captured area of the camera. An active suspension system provides extra force through the actuator which allows it to suppress vertical vibration of sprung mass. First, to deal with the road disturbance and the system uncertainties, radial basis function neural network is proposed to construct the map between the state error and the compensation component, which can correct the optimal state-feedback control law. The weights matrix of radial basis function neural network is adaptively tuned online. Then, the closed-loop stability and asymptotic convergence performance is guaranteed by Lyapunov analysis. Finally, the simulation results demonstrate that the proposed controller effectively suppresses the vibration of the camera and enhances the stabilization of the entire camera, where different excitations are considered to validate the system performance.

Parallel consensual neural networks.

Science.gov (United States)

Benediktsson, J A; Sveinsson, J R; Ersoy, O K; Swain, P H

1997-01-01

A new type of a neural-network architecture, the parallel consensual neural network (PCNN), is introduced and applied in classification/data fusion of multisource remote sensing and geographic data. The PCNN architecture is based on statistical consensus theory and involves using stage neural networks with transformed input data. The input data are transformed several times and the different transformed data are used as if they were independent inputs. The independent inputs are first classified using the stage neural networks. The output responses from the stage networks are then weighted and combined to make a consensual decision. In this paper, optimization methods are used in order to weight the outputs from the stage networks. Two approaches are proposed to compute the data transforms for the PCNN, one for binary data and another for analog data. The analog approach uses wavelet packets. The experimental results obtained with the proposed approach show that the PCNN outperforms both a conjugate-gradient backpropagation neural network and conventional statistical methods in terms of overall classification accuracy of test data.

A FILTRATION METHOD AND APPARATUS INCLUDING A ROLLER WITH PORES

DEFF Research Database (Denmark)

2008-01-01

The present invention offers a method for separating dry matter from a medium. A separation chamber is at least partly defined by a plurality of rollers (2,7) and is capable of being pressure regulated. At least one of the rollers is a pore roller (7) having a surface with pores allowing permeabi...

Modelling of surface evolution of rough surface on divertor target in fusion devices

International Nuclear Information System (INIS)

Dai, Shuyu; Liu, Shengguang; Sun, Jizhong; Kirschner, A.; Kawamura, G.; Tskhakaya, D.; Ding, Rui; Luo, Guangnan; Wang, Dezhen

2015-01-01

Highlights: • We study the surface evolution of rough surface on divertor target in fusion devices. • The effects of gyration motion and E × B drift affect 3D angular distribution. • A larger magnetic field angle leads to a reduced net eroded areal density. • The rough surface evolution affects the physical sputtering yield. - Abstract: The 3D Monte-Carlo code SURO has been used to study the surface evolution of rough surface on the divertor target in fusion devices. The edge plasma at divertor region is modelled by the SDPIC code and used as input data for SURO. Coupled with SDPIC, SURO can perform more sophisticated simulations to calculate the local angle and surface evolution of rough surface. The simulation results show that the incident direction of magnetic field, gyration and E × B force has a significant impact on 3D angular distribution of background plasma and accordingly on the erosion of rough surface. The net eroded areal density of rough surface is studied by varying the magnetic field angle with surface normal. The evolution of the microscopic morphology of rough surface can lead to a significant change in the physical sputtering yield

Nonlinear Dynamic Surface Control of Chaos in Permanent Magnet Synchronous Motor Based on the Minimum Weights of RBF Neural Network

Directory of Open Access Journals (Sweden)

Shaohua Luo

2014-01-01

Full Text Available This paper is concerned with the problem of the nonlinear dynamic surface control (DSC of chaos based on the minimum weights of RBF neural network for the permanent magnet synchronous motor system (PMSM wherein the unknown parameters, disturbances, and chaos are presented. RBF neural network is used to approximate the nonlinearities and an adaptive law is employed to estimate unknown parameters. Then, a simple and effective controller is designed by introducing dynamic surface control technique on the basis of first-order filters. Asymptotically tracking stability in the sense of uniformly ultimate boundedness is achieved in a short time. Finally, the performance of the proposed controller is testified through simulation results.

Neural Networks for protein Structure Prediction

DEFF Research Database (Denmark)

Bohr, Henrik

1998-01-01

This is a review about neural network applications in bioinformatics. Especially the applications to protein structure prediction, e.g. prediction of secondary structures, prediction of surface structure, fold class recognition and prediction of the 3-dimensional structure of protein backbones...

Incorporating Skew into RMS Surface Roughness Probability Distribution

Science.gov (United States)

Stahl, Mark T.; Stahl, H. Philip.

2013-01-01

The standard treatment of RMS surface roughness data is the application of a Gaussian probability distribution. This handling of surface roughness ignores the skew present in the surface and overestimates the most probable RMS of the surface, the mode. Using experimental data we confirm the Gaussian distribution overestimates the mode and application of an asymmetric distribution provides a better fit. Implementing the proposed asymmetric distribution into the optical manufacturing process would reduce the polishing time required to meet surface roughness specifications.

Neural Networks in R Using the Stuttgart Neural Network Simulator: RSNNS

Directory of Open Access Journals (Sweden)

Christopher Bergmeir

2012-01-01

Full Text Available Neural networks are important standard machine learning procedures for classification and regression. We describe the R package RSNNS that provides a convenient interface to the popular Stuttgart Neural Network Simulator SNNS. The main features are (a encapsulation of the relevant SNNS parts in a C++ class, for sequential and parallel usage of different networks, (b accessibility of all of the SNNSalgorithmic functionality from R using a low-level interface, and (c a high-level interface for convenient, R-style usage of many standard neural network procedures. The package also includes functions for visualization and analysis of the models and the training procedures, as well as functions for data input/output from/to the original SNNSfile formats.

Neural Networks: Implementations and Applications

OpenAIRE

Vonk, E.; Veelenturf, L.P.J.; Jain, L.C.

1996-01-01

Artificial neural networks, also called neural networks, have been used successfully in many fields including engineering, science and business. This paper presents the implementation of several neural network simulators and their applications in character recognition and other engineering areas

Neural electrical activity and neural network growth.

Science.gov (United States)

Gafarov, F M

2018-05-01

The development of central and peripheral neural system depends in part on the emergence of the correct functional connectivity in its input and output pathways. Now it is generally accepted that molecular factors guide neurons to establish a primary scaffold that undergoes activity-dependent refinement for building a fully functional circuit. However, a number of experimental results obtained recently shows that the neuronal electrical activity plays an important role in the establishing of initial interneuronal connections. Nevertheless, these processes are rather difficult to study experimentally, due to the absence of theoretical description and quantitative parameters for estimation of the neuronal activity influence on growth in neural networks. In this work we propose a general framework for a theoretical description of the activity-dependent neural network growth. The theoretical description incorporates a closed-loop growth model in which the neural activity can affect neurite outgrowth, which in turn can affect neural activity. We carried out the detailed quantitative analysis of spatiotemporal activity patterns and studied the relationship between individual cells and the network as a whole to explore the relationship between developing connectivity and activity patterns. The model, developed in this work will allow us to develop new experimental techniques for studying and quantifying the influence of the neuronal activity on growth processes in neural networks and may lead to a novel techniques for constructing large-scale neural networks by self-organization. Copyright © 2018 Elsevier Ltd. All rights reserved.

Factors influencing surface roughness of polyimide film

International Nuclear Information System (INIS)

Yao Hong; Zhang Zhanwen; Huang Yong; Li Bo; Li Sai

2011-01-01

The polyimide (PI) films of pyromellitic dianhydride-oxydiamiline (PMDA-ODA) were fabricated using vapor deposition polymerization (VDP) method under high vacuum pressure of 10-4 Pa level. The influence of equipment, substrate temperature, the process of heating and deposition ratio of monomers on the surface roughness of the PI films was investigated. The surface topography of films was measured by interferometer microscopy and scanning electron microscopy(SEM), and the surface roughness was probed with atomic force microscopy(AFM). The results show that consecutive films can be formed when the distance from steering flow pipe to substrate is 74 cm. The surface roughnesses are 291.2 nm and 61.9 nm respectively for one-step heating process and multi-step heating process, and using fine mesh can effectively avoid the splash of materials. The surface roughness can be 3.3 nm when the deposition rate ratio of PMDA to ODA is 0.9:1, and keeping the temperature of substrate around 30 degree C is advantageous to form a film with planar micro-surface topography. (authors)

Foot Plantar Pressure Estimation Using Artificial Neural Networks

OpenAIRE

Xidias , Elias; Koutkalaki , Zoi; Papagiannis , Panagiotis; Papanikos , Paraskevas; Azariadis , Philip

2015-01-01

Part 1: Smart Products; International audience; In this paper, we present a novel approach to estimate the maximum pressure over the foot plantar surface exerted by a two-layer shoe sole for three distinct phases of the gait cycle. The proposed method is based on Artificial Neural Networks and can be utilized for the determination of the comfort that is related to the sole construction. Input parameters to the proposed neural network are the material properties and the thicknesses of the sole...

Fractional Hopfield Neural Networks: Fractional Dynamic Associative Recurrent Neural Networks.

Science.gov (United States)

Pu, Yi-Fei; Yi, Zhang; Zhou, Ji-Liu

2017-10-01

This paper mainly discusses a novel conceptual framework: fractional Hopfield neural networks (FHNN). As is commonly known, fractional calculus has been incorporated into artificial neural networks, mainly because of its long-term memory and nonlocality. Some researchers have made interesting attempts at fractional neural networks and gained competitive advantages over integer-order neural networks. Therefore, it is naturally makes one ponder how to generalize the first-order Hopfield neural networks to the fractional-order ones, and how to implement FHNN by means of fractional calculus. We propose to introduce a novel mathematical method: fractional calculus to implement FHNN. First, we implement fractor in the form of an analog circuit. Second, we implement FHNN by utilizing fractor and the fractional steepest descent approach, construct its Lyapunov function, and further analyze its attractors. Third, we perform experiments to analyze the stability and convergence of FHNN, and further discuss its applications to the defense against chip cloning attacks for anticounterfeiting. The main contribution of our work is to propose FHNN in the form of an analog circuit by utilizing a fractor and the fractional steepest descent approach, construct its Lyapunov function, prove its Lyapunov stability, analyze its attractors, and apply FHNN to the defense against chip cloning attacks for anticounterfeiting. A significant advantage of FHNN is that its attractors essentially relate to the neuron's fractional order. FHNN possesses the fractional-order-stability and fractional-order-sensitivity characteristics.

Artificial neural networks in NDT

International Nuclear Information System (INIS)

Abdul Aziz Mohamed

2001-01-01

Artificial neural networks, simply known as neural networks, have attracted considerable interest in recent years largely because of a growing recognition of the potential of these computational paradigms as powerful alternative models to conventional pattern recognition or function approximation techniques. The neural networks approach is having a profound effect on almost all fields, and has been utilised in fields Where experimental inter-disciplinary work is being carried out. Being a multidisciplinary subject with a broad knowledge base, Nondestructive Testing (NDT) or Nondestructive Evaluation (NDE) is no exception. This paper explains typical applications of neural networks in NDT/NDE. Three promising types of neural networks are highlighted, namely, back-propagation, binary Hopfield and Kohonen's self-organising maps. (Author)

Optimization of extraction of linarin from Flos chrysanthemi indici by response surface methodology and artificial neural network.

Science.gov (United States)

Pan, Hongye; Zhang, Qing; Cui, Keke; Chen, Guoquan; Liu, Xuesong; Wang, Longhu

2017-05-01

The extraction of linarin from Flos chrysanthemi indici by ethanol was investigated. Two modeling techniques, response surface methodology and artificial neural network, were adopted to optimize the process parameters, such as, ethanol concentration, extraction period, extraction frequency, and solvent to material ratio. We showed that both methods provided good predictions, but artificial neural network provided a better and more accurate result. The optimum process parameters include, ethanol concentration of 74%, extraction period of 2 h, extraction three times, solvent to material ratio of 12 mL/g. The experiment yield of linarin was 90.5% that deviated less than 1.6% from that obtained by predicted result. © 2017 WILEY-VCH Verlag GmbH & Co. KGaA, Weinheim.

Prediction of the Tensile Load of Drilled CFRP by Artificial Neural Network

Directory of Open Access Journals (Sweden)

Burak Yenigun

2018-04-01

Full Text Available The application areas of carbon fiber reinforced plastics (CFRP have been increasing day by day. The machining of CFRP with incorrect machining parameters leads in huge loss cost and time. Therefore, it is very important that the composite materials are machined with correct machining parameters. The aim of this paper is to examine the influence of drilling parameters on tensile load after drilling of CFRP. The drilling operations were carried out on Computer Numerical Control (CNC by Tungsten Carbide (WC, High Speed Steel (HSS and Brad Spur type drill bits with spindle speeds of 1000, 3000 and 5000 rpm and feed rates of 0.05, 0.10 and 0.15 mm/rev. The results indicate that the surface roughness, delamination and thrust force, were affected by drilling parameters therefore tensile load was also affected by the same parameters. It was observed that increase in surface roughness, delamination and thrust force all lead to the decrease of tensile load of CFRP. If the correct drilling parameters are selected; the decrease in tensile load of CFRP can be saved up to 25%. Furthermore, an artificial neural network (ANN model has been used to predict of tensile load. The results of the ANN model are in close agreement with the experimental results.

ANN Surface Roughness Optimization of AZ61 Magnesium Alloy Finish Turning: Minimum Machining Times at Prime Machining Costs

Directory of Open Access Journals (Sweden)

Adel Taha Abbas

2018-05-01

Full Text Available Magnesium alloys are widely used in aerospace vehicles and modern cars, due to their rapid machinability at high cutting speeds. A novel Edgeworth–Pareto optimization of an artificial neural network (ANN is presented in this paper for surface roughness (Ra prediction of one component in computer numerical control (CNC turning over minimal machining time (Tm and at prime machining costs (C. An ANN is built in the Matlab programming environment, based on a 4-12-3 multi-layer perceptron (MLP, to predict Ra, Tm, and C, in relation to cutting speed, vc, depth of cut, ap, and feed per revolution, fr. For the first time, a profile of an AZ61 alloy workpiece after finish turning is constructed using an ANN for the range of experimental values vc, ap, and fr. The global minimum length of a three-dimensional estimation vector was defined with the following coordinates: Ra = 0.087 μm, Tm = 0.358 min/cm3, C = $8.2973. Likewise, the corresponding finish-turning parameters were also estimated: cutting speed vc = 250 m/min, cutting depth ap = 1.0 mm, and feed per revolution fr = 0.08 mm/rev. The ANN model achieved a reliable prediction accuracy of ±1.35% for surface roughness.

Modeling of surface dust concentrations using neural networks and kriging

Science.gov (United States)

Buevich, Alexander G.; Medvedev, Alexander N.; Sergeev, Alexander P.; Tarasov, Dmitry A.; Shichkin, Andrey V.; Sergeeva, Marina V.; Atanasova, T. B.

2016-12-01

Creating models which are able to accurately predict the distribution of pollutants based on a limited set of input data is an important task in environmental studies. In the paper two neural approaches: (multilayer perceptron (MLP)) and generalized regression neural network (GRNN)), and two geostatistical approaches: (kriging and cokriging), are using for modeling and forecasting of dust concentrations in snow cover. The area of study is under the influence of dust emissions from a copper quarry and a several industrial companies. The comparison of two mentioned approaches is conducted. Three indices are used as the indicators of the models accuracy: the mean absolute error (MAE), root mean square error (RMSE) and relative root mean square error (RRMSE). Models based on artificial neural networks (ANN) have shown better accuracy. When considering all indices, the most precision model was the GRNN, which uses as input parameters for modeling the coordinates of sampling points and the distance to the probable emissions source. The results of work confirm that trained ANN may be more suitable tool for modeling of dust concentrations in snow cover.

Roller bearing geometry design

Science.gov (United States)

Savage, M.; Pinkston, B. H. W.

1976-01-01

A theory of kinematic stabilization of rolling cylinders is extended and applied to the design of cylindrical roller bearings. The kinematic stabilization mechanism puts a reverse skew into the rolling elements by changing the roller taper. Twelve basic bearing modification designs are identified amd modeled. Four have single transverse convex curvature in their rollers while eight have rollers which have compound transverse curvature made up of a central cylindrical band surrounded by symmetric bands with slope and transverse curvature. The bearing designs are modeled for restoring torque per unit axial displacement, contact stress capacity, and contact area including dynamic loading, misalignment sensitivity and roller proportion. Design programs are available which size the single transverse curvature roller designs for a series of roller slopes and load separations and which design the compound roller bearings for a series of slopes and transverse radii of curvature. The compound rollers are proportioned to have equal contact stresses and minimum size. Design examples are also given.

Rough Surface Contact

Directory of Open Access Journals (Sweden)

T Nguyen

2017-06-01

Full Text Available This paper studies the contact of general rough curved surfaces having nearly identical geometries, assuming the contact at each differential area obeys the model proposed by Greenwood and Williamson. In order to account for the most general gross geometry, principles of differential geometry of surface are applied. This method while requires more rigorous mathematical manipulations, the fact that it preserves the original surface geometries thus makes the modeling procedure much more intuitive. For subsequent use, differential geometry of axis-symmetric surface is considered instead of general surface (although this “general case” can be done as well in Chapter 3.1. The final formulas for contact area, load, and frictional torque are derived in Chapter 3.2.

Introduction to neural networks

International Nuclear Information System (INIS)

Pavlopoulos, P.

1996-01-01

This lecture is a presentation of today's research in neural computation. Neural computation is inspired by knowledge from neuro-science. It draws its methods in large degree from statistical physics and its potential applications lie mainly in computer science and engineering. Neural networks models are algorithms for cognitive tasks, such as learning and optimization, which are based on concepts derived from research into the nature of the brain. The lecture first gives an historical presentation of neural networks development and interest in performing complex tasks. Then, an exhaustive overview of data management and networks computation methods is given: the supervised learning and the associative memory problem, the capacity of networks, the Perceptron networks, the functional link networks, the Madaline (Multiple Adalines) networks, the back-propagation networks, the reduced coulomb energy (RCE) networks, the unsupervised learning and the competitive learning and vector quantization. An example of application in high energy physics is given with the trigger systems and track recognition system (track parametrization, event selection and particle identification) developed for the CPLEAR experiment detectors from the LEAR at CERN. (J.S.). 56 refs., 20 figs., 1 tab., 1 appendix

Nanocrystalline, superhard, ductile ceramic coatings for roller-cone bit bearings

Energy Technology Data Exchange (ETDEWEB)

Namavar, F.; Colter, P.; Karimy, H. [Spire Corp., Bedford, MA (United States)] [and others

1997-12-31

The established method for construction of roller bits utilizes carburized steel, frequently with inserted metal bearing surfaces. This construction provides the necessary surface hardness while maintaining other desirable properties in the core. Protective coatings are a logical development where enhanced hardness, wear resistance, corrosion resistance, and surface properties are required. The wear properties of geothermal roller-cone bit bearings could be further improved by application of protective ceramic hard coatings consisting of nanometer-sized crystallites. Nanocrystalline protective coatings provide the required combination of hardness and toughness which has not been available thus far using traditional ceramics having larger grains. Increased durability of roller-cone bit bearings will ultimately reduce the cost of drilling geothermal wells through increased durability.

Prediction of paddy drying kinetics: A comparative study between mathematical and artificial neural network modelling

Directory of Open Access Journals (Sweden)

Beigi Mohsen

2017-01-01

Full Text Available The present study aimed at investigation of deep bed drying of rough rice kernels at various thin layers at different drying air temperatures and flow rates. A comparative study was performed between mathematical thin layer models and artificial neural networks to estimate the drying curves of rough rice. The suitability of nine mathematical models in simulating the drying kinetics was examined and the Midilli model was determined as the best approach for describing drying curves. Different feed forward-back propagation artificial neural networks were examined to predict the moisture content variations of the grains. The ANN with 4-18-18-1 topology, transfer function of hyperbolic tangent sigmoid and a Levenberg-Marquardt back propagation training algorithm provided the best results with the maximum correlation coefficient and the minimum mean square error values. Furthermore, it was revealed that ANN modeling had better performance in prediction of drying curves with lower root mean square error values.

Surface inspection of flat products by means of texture analysis: on-line implementation using neural networks

Science.gov (United States)

Fernandez, Carlos; Platero, Carlos; Campoy, Pascual; Aracil, Rafael

1994-11-01

This paper describes some texture-based techniques that can be applied to quality assessment of flat products continuously produced (metal strips, wooden surfaces, cork, textile products, ...). Since the most difficult task is that of inspecting for product appearance, human-like inspection ability is required. A common feature to all these products is the presence of non- deterministic texture on their surfaces. Two main subjects are discussed: statistical techniques for both surface finishing determination and surface defect analysis as well as real-time implementation for on-line inspection in high-speed applications. For surface finishing determination a Gray Level Difference technique is presented to perform over low resolution images, that is, no-zoomed images. Defect analysis is performed by means of statistical texture analysis over defective portions of the surface. On-line implementation is accomplished by means of neural networks. When a defect arises, textural analysis is applied which result in a data-vector, acting as input of a neural net, previously trained in a supervised way. This approach tries to reach on-line performance in automated visual inspection applications when texture is presented in flat product surfaces.

Precision Interval Estimation of the Response Surface by Means of an Integrated Algorithm of Neural Network and Linear Regression

Science.gov (United States)

Lo, Ching F.

1999-01-01

The integration of Radial Basis Function Networks and Back Propagation Neural Networks with the Multiple Linear Regression has been accomplished to map nonlinear response surfaces over a wide range of independent variables in the process of the Modem Design of Experiments. The integrated method is capable to estimate the precision intervals including confidence and predicted intervals. The power of the innovative method has been demonstrated by applying to a set of wind tunnel test data in construction of response surface and estimation of precision interval.

Surface roughness effects on turbulent Couette flow

Science.gov (United States)

Lee, Young Mo; Lee, Jae Hwa

2017-11-01

Direct numerical simulation of a turbulent Couette flow with two-dimensional (2-D) rod roughness is performed to examine the effects of the surface roughness. The Reynolds number based on the channel centerline laminar velocity (Uco) and channel half height (h) is Re =7200. The 2-D rods are periodically arranged with a streamwise pitch of λ = 8 k on the bottom wall, and the roughness height is k = 0.12 h. It is shown that the wall-normal extent for the logarithmic layer is significantly shortened in the rough-wall turbulent Couette flow, compared to a turbulent Couette flow with smooth wall. Although the Reynolds stresses are increased in a turbulent channel flow with surface roughness in the outer layer due to large-scale ejection motions produced by the 2-D rods, those of the rough-wall Couette flow are decreased. Isosurfaces of the u-structures averaged in time suggest that the decrease of the turbulent activity near the centerline is associated with weakened large-scale counter-rotating roll modes by the surface roughness. This research was supported by the National Research Foundation of Korea (NRF) funded by the Ministry of Education (NRF-2017R1D1A1A09000537) and the Ministry of Science, ICT & Future Planning (NRF-2017R1A5A1015311).

The Laplacian spectrum of neural networks

Science.gov (United States)

de Lange, Siemon C.; de Reus, Marcel A.; van den Heuvel, Martijn P.

2014-01-01

The brain is a complex network of neural interactions, both at the microscopic and macroscopic level. Graph theory is well suited to examine the global network architecture of these neural networks. Many popular graph metrics, however, encode average properties of individual network elements. Complementing these “conventional” graph metrics, the eigenvalue spectrum of the normalized Laplacian describes a network's structure directly at a systems level, without referring to individual nodes or connections. In this paper, the Laplacian spectra of the macroscopic anatomical neuronal networks of the macaque and cat, and the microscopic network of the Caenorhabditis elegans were examined. Consistent with conventional graph metrics, analysis of the Laplacian spectra revealed an integrative community structure in neural brain networks. Extending previous findings of overlap of network attributes across species, similarity of the Laplacian spectra across the cat, macaque and C. elegans neural networks suggests a certain level of consistency in the overall architecture of the anatomical neural networks of these species. Our results further suggest a specific network class for neural networks, distinct from conceptual small-world and scale-free models as well as several empirical networks. PMID:24454286

Construction of diabatic energy surfaces for LiFH with artificial neural networks

Science.gov (United States)

Guan, Yafu; Fu, Bina; Zhang, Dong H.

2017-12-01

A new set of diabatic potential energy surfaces (PESs) for LiFH is constructed with artificial neural networks (NNs). The adiabatic PESs of the ground state and the first excited state are directly fitted with NNs. Meanwhile, the adiabatic-to-diabatic transformation (ADT) angles (mixing angles) are obtained by simultaneously fitting energy difference and interstate coupling gradients. No prior assumptions of the functional form of ADT angles are used before fitting, and the ab initio data including energy difference and interstate coupling gradients are well reproduced. Converged dynamical results show remarkable differences between adiabatic and diabatic PESs, which suggests the significance of non-adiabatic processes.

Program Helps Simulate Neural Networks

Science.gov (United States)

Villarreal, James; Mcintire, Gary

1993-01-01

Neural Network Environment on Transputer System (NNETS) computer program provides users high degree of flexibility in creating and manipulating wide variety of neural-network topologies at processing speeds not found in conventional computing environments. Supports back-propagation and back-propagation-related algorithms. Back-propagation algorithm used is implementation of Rumelhart's generalized delta rule. NNETS developed on INMOS Transputer(R). Predefines back-propagation network, Jordan network, and reinforcement network to assist users in learning and defining own networks. Also enables users to configure other neural-network paradigms from NNETS basic architecture. Small portion of software written in OCCAM(R) language.

Construction of an interatomic potential for zinc oxide surfaces by high-dimensional neural networks

Energy Technology Data Exchange (ETDEWEB)

Artrith, Nongnuch; Morawietz, Tobias; Behler, Joerg [Lehrstuhl fuer Theoretische Chemie, Ruhr-Universitaet Bochum, D-44780 Bochum (Germany)

2011-07-01

Zinc oxide (ZnO) is a technologically important material with many applications, e.g. in heterogeneous catalysis. For theoretical studies of the structural properties of ZnO surfaces, defects, and crystal structures it is necessary to simulate large systems over long time-scales with sufficient accuracy. Often, the required system size is not accessible by computationally rather demanding density-functional theory (DFT) calculations. Recently, artificial Neural Networks (NN) trained to first principles data have shown to provide accurate potential-energy surfaces (PESs) for condensed systems. We present the construction and analysis of a NN PES for ZnO. The structural and energetic properties of bulk ZnO and ZnO surfaces are investigated using this potential and compared to DFT calculations.

Modeling Surface Roughness to Estimate Surface Moisture Using Radarsat-2 Quad Polarimetric SAR Data

Science.gov (United States)

Nurtyawan, R.; Saepuloh, A.; Budiharto, A.; Wikantika, K.

2016-08-01

Microwave backscattering from the earth's surface depends on several parameters such as surface roughness and dielectric constant of surface materials. The two parameters related to water content and porosity are crucial for estimating soil moisture. The soil moisture is an important parameter for ecological study and also a factor to maintain energy balance of land surface and atmosphere. Direct roughness measurements to a large area require extra time and cost. Heterogeneity roughness scale for some applications such as hydrology, climate, and ecology is a problem which could lead to inaccuracies of modeling. In this study, we modeled surface roughness using Radasat-2 quad Polarimetric Synthetic Aperture Radar (PolSAR) data. The statistical approaches to field roughness measurements were used to generate an appropriate roughness model. This modeling uses a physical SAR approach to predicts radar backscattering coefficient in the parameter of radar configuration (wavelength, polarization, and incidence angle) and soil parameters (surface roughness and dielectric constant). Surface roughness value is calculated using a modified Campbell and Shepard model in 1996. The modification was applied by incorporating the backscattering coefficient (σ°) of quad polarization HH, HV and VV. To obtain empirical surface roughness model from SAR backscattering intensity, we used forty-five sample points from field roughness measurements. We selected paddy field in Indramayu district, West Java, Indonesia as the study area. This area was selected due to intensive decreasing of rice productivity in the Northern Coast region of West Java. Third degree polynomial is the most suitable data fitting with coefficient of determination R2 and RMSE are about 0.82 and 1.18 cm, respectively. Therefore, this model is used as basis to generate the map of surface roughness.

Aeroelasticity of morphing wings using neural networks

Science.gov (United States)

Natarajan, Anand

In this dissertation, neural networks are designed to effectively model static non-linear aeroelastic problems in adaptive structures and linear dynamic aeroelastic systems with time varying stiffness. The use of adaptive materials in aircraft wings allows for the change of the contour or the configuration of a wing (morphing) in flight. The use of smart materials, to accomplish these deformations, can imply that the stiffness of the wing with a morphing contour changes as the contour changes. For a rapidly oscillating body in a fluid field, continuously adapting structural parameters may render the wing to behave as a time variant system. Even the internal spars/ribs of the aircraft wing which define the wing stiffness can be made adaptive, that is, their stiffness can be made to vary with time. The immediate effect on the structural dynamics of the wing, is that, the wing motion is governed by a differential equation with time varying coefficients. The study of this concept of a time varying torsional stiffness, made possible by the use of active materials and adaptive spars, in the dynamic aeroelastic behavior of an adaptable airfoil is performed here. Another type of aeroelastic problem of an adaptive structure that is investigated here, is the shape control of an adaptive bump situated on the leading edge of an airfoil. Such a bump is useful in achieving flow separation control for lateral directional maneuverability of the aircraft. Since actuators are being used to create this bump on the wing surface, the energy required to do so needs to be minimized. The adverse pressure drag as a result of this bump needs to be controlled so that the loss in lift over the wing is made minimal. The design of such a "spoiler bump" on the surface of the airfoil is an optimization problem of maximizing pressure drag due to flow separation while minimizing the loss in lift and energy required to deform the bump. One neural network is trained using the CFD code FLUENT to

Spin Hall effect by surface roughness

KAUST Repository

Zhou, Lingjun

2015-01-08

The spin Hall and its inverse effects, driven by the spin orbit interaction, provide an interconversion mechanism between spin and charge currents. Since the spin Hall effect generates and manipulates spin current electrically, to achieve a large effect is becoming an important topic in both academia and industries. So far, materials with heavy elements carrying a strong spin orbit interaction, provide the only option. We propose here a new mechanism, using the surface roughness in ultrathin films, to enhance the spin Hall effect without heavy elements. Our analysis based on Cu and Al thin films suggests that surface roughness is capable of driving a spin Hall angle that is comparable to that in bulk Au. We also demonstrate that the spin Hall effect induced by surface roughness subscribes only to the side-jump contribution but not the skew scattering. The paradigm proposed in this paper provides the second, not if only, alternative to generate a sizable spin Hall effect.

AIRBORNE ASBESTOS CONCENTRATIONS DURING BUFFING, BURNISHING, AND STRIPPING OF RESILIENT FLOOR TILE

Science.gov (United States)

The study was conducted to evaluate airborne asbestos concentrations during low-speed spray-buffing, ultra high-speed burnishing, and wet-stripping of asbestos-containing resilient floor tile under pre-existing and prepared levels of floor care maintenance. Low-speed spray-buffin...

Neural network to diagnose lining condition

Science.gov (United States)

Yemelyanov, V. A.; Yemelyanova, N. Y.; Nedelkin, A. A.; Zarudnaya, M. V.

2018-03-01

The paper presents data on the problem of diagnosing the lining condition at the iron and steel works. The authors describe the neural network structure and software that are designed and developed to determine the lining burnout zones. The simulation results of the proposed neural networks are presented. The authors note the low learning and classification errors of the proposed neural networks. To realize the proposed neural network, the specialized software has been developed.

Integrated control of the cooling system and surface openings using the artificial neural networks

International Nuclear Information System (INIS)

Moon, Jin Woo

2015-01-01

This study aimed at suggesting an indoor temperature control method that can provide a comfortable thermal environment through the integrated control of the cooling system and the surface openings. Four control logic were developed, employing different application levels of rules and artificial neural network models. Rule-based control methods represented the conventional approach while ANN-based methods were applied for the predictive and adaptive controls. Comparative performance tests for the conventional- and ANN-based methods were numerically conducted for the double-skin-facade building, using the MATLAB (Matrix Laboratory) and TRNSYS (Transient Systems Simulation) software, after proving the validity by comparing the simulation and field measurement results. Analysis revealed that the ANN-based controls of the cooling system and surface openings improved the indoor temperature conditions with increased comfortable temperature periods and decreased standard deviation of the indoor temperature from the center of the comfortable range. In addition, the proposed ANN-based logic effectively reduced the number of operating condition changes of the cooling system and surface openings, which can prevent system failure. The ANN-based logic, however, did not show superiority in energy efficiency over the conventional logic. Instead, they have increased the amount of heat removal by the cooling system. From the analysis, it can be concluded that the ANN-based temperature control logic was able to keep the indoor temperature more comfortably and stably within the comfortable range due to its predictive and adaptive features. - Highlights: • Integrated rule-based and artificial neural network based logics were developed. • A cooling device and surface openings were controlled in an integrated manner. • Computer simulation method was employed for comparative performance tests. • ANN-based logics showed the advanced features of thermal environment. • Rule

Memristor-based neural networks

International Nuclear Information System (INIS)

Thomas, Andy

2013-01-01

The synapse is a crucial element in biological neural networks, but a simple electronic equivalent has been absent. This complicates the development of hardware that imitates biological architectures in the nervous system. Now, the recent progress in the experimental realization of memristive devices has renewed interest in artificial neural networks. The resistance of a memristive system depends on its past states and exactly this functionality can be used to mimic the synaptic connections in a (human) brain. After a short introduction to memristors, we present and explain the relevant mechanisms in a biological neural network, such as long-term potentiation and spike time-dependent plasticity, and determine the minimal requirements for an artificial neural network. We review the implementations of these processes using basic electric circuits and more complex mechanisms that either imitate biological systems or could act as a model system for them. (topical review)

Roughness analysis of graphite surfaces of casting elements

Directory of Open Access Journals (Sweden)

M. Wieczorowski

2010-01-01

Full Text Available In the paper profilometric measurements of graphite casting elements were described. Basic topics necessary to assess roughness of their surfaces and influence of asperities on various properties related to manufacturing and use were discussed. Stylus profilometer technique of surface irregularities measurements including its limits resulting from pickup geometry and its contact with measured object were ana-lyzed. Working principle of tactile profilometer and phenomena taking place during movement of a probe on a measured surface were shown. One of the important aspects is a flight phenomenon, which means movement of a pickup without contact with a surface during inspection resulting from too high scanning speed. results of comparison research for graphite elements of new and used mould and pin composing a set were presented. Using some surface roughness, waviness and primary profile parameters (arithmetical mean of roughness profile heights Ra, biggest roughness profile height Rz, maximum primary profile height Pt as well as maximum waviness profile height Wt a possibility of using surface asperities parameters as a measure of wear of chill graphite elements was proved. The most often applied parameter is Ra, but with a help of parameters from W and P family it was shown, that big changes occur not only for roughness but also for other components of surface irregularities.

Suitability assessment of artificial neural network to approximate surface subsidence due to rock mass drainage

Directory of Open Access Journals (Sweden)

Ryszard Hejmanowski

2015-01-01

Full Text Available Based on the previous studies conducted by the authors, a new approach was proposed, namely the tools of artificial intelligence. One of neural networks is a multilayer perceptron network (MLP, which has already found applications in many fields of science. Sequentially, a series of calculations was made for different MLP neural network configuration and the best of them was selected. Mean square error (MSE and the correlation coefficient R were adopted as the selection criterion for the optimal network. The obtained results were characterized with a considerable dispersion. With an increase in the amount of hidden neurons, the MSE of the network increased while the correlation coefficient R decreased. Similar conclusions were drawn for the network with a small number of hidden neurons. The analysis allowed to select a network composed of 24 neurons as the best one for the issue under question. The obtained final answers of artificial neural network were presented in a histogram as differences between the calculated and expected value.

Surface Forces Apparatus measurements of interactions between rough and reactive calcite surfaces.

Science.gov (United States)

Dziadkowiec, Joanna; Javadi, Shaghayegh; Bratvold, Jon Einar; Nilsen, Ola; Røyne, Anja

2018-05-28

Nm-range forces acting between calcite surfaces in water affect macroscopic properties of carbonate rocks and calcite-based granular materials, and are significantly influenced by calcite surface recrystallization. We suggest that the repulsive mechanical effects related to nm-scale surface recrystallization of calcite in water could be partially responsible for the observed decrease of cohesion in calcitic rocks saturated with water. Using the Surface Forces Apparatus (SFA), we simultaneously followed the calcite reactivity and measured the forces in water in two surface configurations: between two rough calcite surfaces (CC), or between rough calcite and a smooth mica surface (CM). We used nm-scale rough, polycrystalline calcite films prepared by Atomic Layer Deposition (ALD). We measured only repulsive forces in CC in CaCO 3 -saturated water, which was related to roughness and possibly to repulsive hydration effects. Adhesive or repulsive forces were measured in CM in CaCO 3 -saturated water depending on calcite roughness, and the adhesion was likely enhanced by electrostatic effects. The pull-off adhesive force in CM became stronger with time and this increase was correlated with a decrease of roughness at contacts, which parameter could be estimated from the measured force-distance curves. That suggested a progressive increase of real contact areas between the surfaces, caused by gradual pressure-driven deformation of calcite surface asperities during repeated loading-unloading cycles. Reactivity of calcite was affected by mass transport across nm to µm-thick gaps between the surfaces. Major roughening was observed only for the smoothest calcite films, where gaps between two opposing surfaces were nm-thick over µm-sized areas, and led to force of crystallization that could overcome confining pressures of the order of MPa. Any substantial roughening of calcite caused a significant increase of the repulsive mechanical force contribution.

Neural Networks in Control Applications

DEFF Research Database (Denmark)

Sørensen, O.

The intention of this report is to make a systematic examination of the possibilities of applying neural networks in those technical areas, which are familiar to a control engineer. In other words, the potential of neural networks in control applications is given higher priority than a detailed...... study of the networks themselves. With this end in view the following restrictions have been made: - Amongst numerous neural network structures, only the Multi Layer Perceptron (a feed-forward network) is applied. - Amongst numerous training algorithms, only four algorithms are examined, all...... in a recursive form (sample updating). The simplest is the Back Probagation Error Algorithm, and the most complex is the recursive Prediction Error Method using a Gauss-Newton search direction. - Over-fitting is often considered to be a serious problem when training neural networks. This problem is specifically...

Salmonella transfer during pilot plant scale washing and roller conveying of tomatoes.

Science.gov (United States)

Wang, Haiqiang; Ryser, Elliot T

2014-03-01

Salmonella transfer during washing and roller conveying of inoculated tomatoes was quantified using a pilot scale tomato packing line equipped with plastic, foam, or brush rollers. Red round tomatoes (2.3 kg) were dip inoculated with Salmonella enterica serovar Typhimurium LT2 (avirulent) (4 log CFU/g), air dried for 2 h, and then washed in sanitizer-free water for 2 min. Inoculated tomatoes were then passed single file over a 1.5-m conveyor equipped with plastic, foam, or brush rollers followed by 25 previously washed uninoculated tomatoes. Tomato samples were collected after 2 min of both washing and roller conveying, with all 25 uninoculated tomatoes collected individually after conveying. Roller surface samples were collected before and after conveying the uninoculated tomatoes. Both tomato and surface samples were quantitatively examined for Salmonella by direct plating or membrane filtration using xylose lysine Tergitol 4 agar. Regardless of the roller type, Salmonella populations on inoculated tomatoes did not significantly (P conveyors. After conveying uninoculated tomatoes over contaminated foam rollers, 96% of the 25 tomatoes were cross-contaminated with Salmonella at >100 CFU per tomato. With plastic rollers, 24 and 76% of tomatoes were cross-contaminated with Salmonella at 10 to 100 and 1 to 10 CFU per tomato, respectively. In contrast, only 8% of 25 tomatoes were cross-contaminated with brush rollers with Salmonella populations of 1 to 10 CFU per tomato. Overall, cross-contamination was greatest with foam, followed by plastic and brush rollers (P < 0.05). Adding peroxyacetic acid or chlorine to the wash water significantly decreased cross-contamination during tomato conveying, with chlorine less effective in controlling Salmonella on foam compared with plastic and brush rollers.

Practical neural network recipies in C++

CERN Document Server

Masters

2014-01-01

This text serves as a cookbook for neural network solutions to practical problems using C++. It will enable those with moderate programming experience to select a neural network model appropriate to solving a particular problem, and to produce a working program implementing that network. The book provides guidance along the entire problem-solving path, including designing the training set, preprocessing variables, training and validating the network, and evaluating its performance. Though the book is not intended as a general course in neural networks, no background in neural works is assum

Why do rough surfaces appear glossy?

Science.gov (United States)

Qi, Lin; Chantler, Mike J; Siebert, J Paul; Dong, Junyu

2014-05-01

The majority of work on the perception of gloss has been performed using smooth surfaces (e.g., spheres). Previous studies that have employed more complex surfaces reported that increasing mesoscale roughness increases perceived gloss [Psychol. Sci.19, 196 (2008), J. Vis.10(9), 13 (2010), Curr. Biol.22, 1909 (2012)]. We show that the use of realistic rendering conditions is important and that, in contrast to [Psychol. Sci.19, 196 (2008), J. Vis.10(9), 13 (2010)], after a certain point increasing roughness further actually reduces glossiness. We investigate five image statistics of estimated highlights and show that for our stimuli, one in particular, which we term "percentage of highlight area," is highly correlated with perceived gloss. We investigate a simple model that explains the unimodal, nonmonotonic relationship between mesoscale roughness and percentage highlight area.

Signal Processing and Neural Network Simulator

Science.gov (United States)

Tebbe, Dennis L.; Billhartz, Thomas J.; Doner, John R.; Kraft, Timothy T.

1995-04-01

The signal processing and neural network simulator (SPANNS) is a digital signal processing simulator with the capability to invoke neural networks into signal processing chains. This is a generic tool which will greatly facilitate the design and simulation of systems with embedded neural networks. The SPANNS is based on the Signal Processing WorkSystemTM (SPWTM), a commercial-off-the-shelf signal processing simulator. SPW provides a block diagram approach to constructing signal processing simulations. Neural network paradigms implemented in the SPANNS include Backpropagation, Kohonen Feature Map, Outstar, Fully Recurrent, Adaptive Resonance Theory 1, 2, & 3, and Brain State in a Box. The SPANNS was developed by integrating SAIC's Industrial Strength Neural Networks (ISNN) Software into SPW.

Surface Roughness of the Moon Derived from Multi-frequency Radar Data

Science.gov (United States)

Fa, W.

2011-12-01

Surface roughness of the Moon provides important information concerning both significant questions about lunar surface processes and engineering constrains for human outposts and rover trafficabillity. Impact-related phenomena change the morphology and roughness of lunar surface, and therefore surface roughness provides clues to the formation and modification mechanisms of impact craters. Since the Apollo era, lunar surface roughness has been studied using different approaches, such as direct estimation from lunar surface digital topographic relief, and indirect analysis of Earth-based radar echo strengths. Submillimeter scale roughness at Apollo landing sites has been studied by computer stereophotogrammetry analysis of Apollo Lunar Surface Closeup Camera (ALSCC) pictures, whereas roughness at meter to kilometer scale has been studied using laser altimeter data from recent missions. Though these studies shown lunar surface roughness is scale dependent that can be described by fractal statistics, roughness at centimeter scale has not been studied yet. In this study, lunar surface roughnesses at centimeter scale are investigated using Earth-based 70 cm Arecibo radar data and miniature synthetic aperture radar (Mini-SAR) data at S- and X-band (with wavelengths 12.6 cm and 4.12 cm). Both observations and theoretical modeling show that radar echo strengths are mostly dominated by scattering from the surface and shallow buried rocks. Given the different penetration depths of radar waves at these frequencies (< 30 m for 70 cm wavelength, < 3 m at S-band, and < 1 m at X-band), radar echo strengths at S- and X-band will yield surface roughness directly, whereas radar echo at 70-cm will give an upper limit of lunar surface roughness. The integral equation method is used to model radar scattering from the rough lunar surface, and dielectric constant of regolith and surface roughness are two dominate factors. The complex dielectric constant of regolith is first estimated

ANN Surface Roughness Optimization of AZ61 Magnesium Alloy Finish Turning: Minimum Machining Times at Prime Machining Costs.

Science.gov (United States)

Abbas, Adel Taha; Pimenov, Danil Yurievich; Erdakov, Ivan Nikolaevich; Taha, Mohamed Adel; Soliman, Mahmoud Sayed; El Rayes, Magdy Mostafa

2018-05-16

Magnesium alloys are widely used in aerospace vehicles and modern cars, due to their rapid machinability at high cutting speeds. A novel Edgeworth⁻Pareto optimization of an artificial neural network (ANN) is presented in this paper for surface roughness ( Ra ) prediction of one component in computer numerical control (CNC) turning over minimal machining time ( T m ) and at prime machining costs ( C ). An ANN is built in the Matlab programming environment, based on a 4-12-3 multi-layer perceptron (MLP), to predict Ra , T m , and C , in relation to cutting speed, v c , depth of cut, a p , and feed per revolution, f r . For the first time, a profile of an AZ61 alloy workpiece after finish turning is constructed using an ANN for the range of experimental values v c , a p , and f r . The global minimum length of a three-dimensional estimation vector was defined with the following coordinates: Ra = 0.087 μm, T m = 0.358 min/cm³, C = $8.2973. Likewise, the corresponding finish-turning parameters were also estimated: cutting speed v c = 250 m/min, cutting depth a p = 1.0 mm, and feed per revolution f r = 0.08 mm/rev. The ANN model achieved a reliable prediction accuracy of ±1.35% for surface roughness.

An artifical neural network for detection of simulated dental caries

Energy Technology Data Exchange (ETDEWEB)

Kositbowornchai, S. [Khon Kaen Univ. (Thailand). Dept. of Oral Diagnosis; Siriteptawee, S.; Plermkamon, S.; Bureerat, S. [Khon Kaen Univ. (Thailand). Dept. of Mechanical Engineering; Chetchotsak, D. [Khon Kaen Univ. (Thailand). Dept. of Industrial Engineering

2006-08-15

Objects: A neural network was developed to diagnose artificial dental caries using images from a charged-coupled device (CCD)camera and intra-oral digital radiography. The diagnostic performance of this neural network was evaluated against a gold standard. Materials and methods: The neural network design was the Learning Vector Quantization (LVQ) used to classify a tooth surface as sound or as having dental caries. The depth of the dental caries was indicated on a graphic user interface (GUI) screen developed by Matlab programming. Forty-nine images of both sound and simulated dental caries, derived from a CCD camera and by digital radiography, were used to 'train' an artificial neural network. After the 'training' process, a separate test-set comprising 322 unseen images was evaluated. Tooth sections and microscopic examinations were used to confirm the actual dental caries status.The performance of neural network was evaluated using diagnostic test. Results: The sensitivity (95%CI)/specificity (95%CI) of dental caries detection by the CCD camera and digital radiography were 0.77(0.68-0.85)/0.85(0.75-0.92) and 0.81(0.72-0.88)/0.93(0.84-0.97), respectively. The accuracy of caries depth-detection by the CCD camera and digital radiography was 58 and 40%, respectively. Conclusions: The model neural network used in this study could be a prototype for caries detection but should be improved for classifying caries depth. Our study suggests an artificial neural network can be trained to make the correct interpretations of dental caries. (orig.)

An artifical neural network for detection of simulated dental caries

International Nuclear Information System (INIS)

Kositbowornchai, S.; Siriteptawee, S.; Plermkamon, S.; Bureerat, S.; Chetchotsak, D.

2006-01-01

Objects: A neural network was developed to diagnose artificial dental caries using images from a charged-coupled device (CCD)camera and intra-oral digital radiography. The diagnostic performance of this neural network was evaluated against a gold standard. Materials and methods: The neural network design was the Learning Vector Quantization (LVQ) used to classify a tooth surface as sound or as having dental caries. The depth of the dental caries was indicated on a graphic user interface (GUI) screen developed by Matlab programming. Forty-nine images of both sound and simulated dental caries, derived from a CCD camera and by digital radiography, were used to 'train' an artificial neural network. After the 'training' process, a separate test-set comprising 322 unseen images was evaluated. Tooth sections and microscopic examinations were used to confirm the actual dental caries status.The performance of neural network was evaluated using diagnostic test. Results: The sensitivity (95%CI)/specificity (95%CI) of dental caries detection by the CCD camera and digital radiography were 0.77(0.68-0.85)/0.85(0.75-0.92) and 0.81(0.72-0.88)/0.93(0.84-0.97), respectively. The accuracy of caries depth-detection by the CCD camera and digital radiography was 58 and 40%, respectively. Conclusions: The model neural network used in this study could be a prototype for caries detection but should be improved for classifying caries depth. Our study suggests an artificial neural network can be trained to make the correct interpretations of dental caries. (orig.)

A new fiber optic sensor for inner surface roughness measurement

Science.gov (United States)

Xu, Xiaomei; Liu, Shoubin; Hu, Hong

2009-11-01

In order to measure inner surface roughness of small holes nondestructively, a new fiber optic sensor is researched and developed. Firstly, a new model for surface roughness measurement is proposed, which is based on intensity-modulated fiber optic sensors and scattering modeling of rough surfaces. Secondly, a fiber optical measurement system is designed and set up. Under the help of new techniques, the fiber optic sensor can be miniaturized. Furthermore, the use of micro prism makes the light turn 90 degree, so the inner side surface roughness of small holes can be measured. Thirdly, the fiber optic sensor is gauged by standard surface roughness specimens, and a series of measurement experiments have been done. The measurement results are compared with those obtained by TR220 Surface Roughness Instrument and Form Talysurf Laser 635, and validity of the developed fiber optic sensor is verified. Finally, precision and influence factors of the fiber optic sensor are analyzed.

Trimaran Resistance Artificial Neural Network

Science.gov (United States)

2011-01-01

11th International Conference on Fast Sea Transportation FAST 2011, Honolulu, Hawaii, USA, September 2011 Trimaran Resistance Artificial Neural Network Richard...Trimaran Resistance Artificial Neural Network 5a. CONTRACT NUMBER 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR(S) 5d. PROJECT NUMBER 5e... Artificial Neural Network and is restricted to the center and side-hull configurations tested. The value in the parametric model is that it is able to

Influence of surface roughness on the corrosion behaviour of magnesium alloy

International Nuclear Information System (INIS)

Walter, R.; Kannan, M. Bobby

2011-01-01

Research highlights: → Surface roughness of AZ91 magnesium alloy plays a critical role in the passivation behaviour of the alloy. → The passivation behaviour of the alloy influences the pitting tendency. → Increase in surface roughness of AZ91 magnesium alloy increases the pitting tendency of the alloy. -- Abstract: In this study, the influence of surface roughness on the passivation and pitting corrosion behaviour of AZ91 magnesium alloy in chloride-containing environment was examined using electrochemical techniques. Potentiodynamic polarisation and electrochemical impedance spectroscopy tests suggested that the passivation behaviour of the alloy was affected by increasing the surface roughness. Consequently, the corrosion current and the pitting tendency of the alloy also increased with increase in the surface roughness. Scanning electron micrographs of 24 h immersion test samples clearly revealed pitting corrosion in the highest surface roughness (Sa 430) alloy, whereas in the lowest surface roughness (Sa 80) alloy no evidence of pitting corrosion was observed. Interestingly, when the passivity of the alloy was disturbed by galvanostatically holding the sample at anodic current for 1 h, the alloy underwent high pitting corrosion irrespective of their surface roughness. Thus the study suggests that the surface roughness plays a critical role in the passivation behaviour of the alloy and hence the pitting tendency.

Neural network regulation driven by autonomous neural firings

Science.gov (United States)

Cho, Myoung Won

2016-07-01

Biological neurons naturally fire spontaneously due to the existence of a noisy current. Such autonomous firings may provide a driving force for network formation because synaptic connections can be modified due to neural firings. Here, we study the effect of autonomous firings on network formation. For the temporally asymmetric Hebbian learning, bidirectional connections lose their balance easily and become unidirectional ones. Defining the difference between reciprocal connections as new variables, we could express the learning dynamics as if Ising model spins interact with each other in magnetism. We present a theoretical method to estimate the interaction between the new variables in a neural system. We apply the method to some network systems and find some tendencies of autonomous neural network regulation.

Use of roughness maps in visualisation of surfaces

DEFF Research Database (Denmark)

Seitavuopio, Paulus; Rantanen, Jukka; Yliruusi, Jouko

2005-01-01

monohydrate, theophylline anhydrate, sodium chloride and potassium chloride. The roughness determinations were made by a laser profilometer. The new matrix method gives detailed roughness maps, which are able to show local variations in surface roughness values and provide an illustrative picture...

Parameter estimation of breast tumour using dynamic neural network from thermal pattern

Directory of Open Access Journals (Sweden)

Elham Saniei

2016-11-01

Full Text Available This article presents a new approach for estimating the depth, size, and metabolic heat generation rate of a tumour. For this purpose, the surface temperature distribution of a breast thermal image and the dynamic neural network was used. The research consisted of two steps: forward and inverse. For the forward section, a finite element model was created. The Pennes bio-heat equation was solved to find surface and depth temperature distributions. Data from the analysis, then, were used to train the dynamic neural network model (DNN. Results from the DNN training/testing confirmed those of the finite element model. For the inverse section, the trained neural network was applied to estimate the depth temperature distribution (tumour position from the surface temperature profile, extracted from the thermal image. Finally, tumour parameters were obtained from the depth temperature distribution. Experimental findings (20 patients were promising in terms of the model’s potential for retrieving tumour parameters.

ROUGHNESS ANALYSIS OF VARIOUSLY POLISHED NIOBIUM SURFACES

Energy Technology Data Exchange (ETDEWEB)

Ribeill, G.; Reece, C.

2008-01-01

Niobium superconducting radio frequency (SRF) cavities have gained widespread use in accelerator systems. It has been shown that surface roughness is a determining factor in the cavities’ effi ciency and maximum accelerating potential achievable through this technology. Irregularities in the surface can lead to spot heating, undesirable local electrical fi eld enhancement and electron multipacting. Surface quality is typically ensured through the use of acid etching in a Buffered Chemical Polish (BCP) bath and electropolishing (EP). In this study, the effects of these techniques on surface morphology have been investigated in depth. The surface of niobium samples polished using different combinations of these techniques has been characterized through atomic force microscopy (AFM) and stylus profi lometry across a range of length scales. The surface morphology was analyzed using spectral techniques to determine roughness and characteristic dimensions. Experimentation has shown that this method is a valuable tool that provides quantitative information about surface roughness at different length scales. It has demonstrated that light BCP pretreatment and lower electrolyte temperature favors a smoother electropolish. These results will allow for the design of a superior polishing process for niobium SRF cavities and therefore increased accelerator operating effi ciency and power.

Influence of surface roughness on the friction property of textured surface

OpenAIRE

Yuankai Zhou; Hua Zhu; Wenqian Zhang; Xue Zuo; Yan Li; Jianhua Yang

2015-01-01

In contrast with dimple textures, surface roughness is a texture at the micro-scale, essentially which will influence the load-bearing capacity of lubricant film. The numerical simulation was carried out to investigate the influence of surface roughness on friction property of textured surface. The lubricant film pressure was obtained using the method of computational fluid dynamics according to geometric model of round dimple, and the renormalization-group k–ε turbulent model was adopted in ...

Neural networks with discontinuous/impact activations

CERN Document Server

Akhmet, Marat

2014-01-01

This book presents as its main subject new models in mathematical neuroscience. A wide range of neural networks models with discontinuities are discussed, including impulsive differential equations, differential equations with piecewise constant arguments, and models of mixed type. These models involve discontinuities, which are natural because huge velocities and short distances are usually observed in devices modeling the networks. A discussion of the models, appropriate for the proposed applications, is also provided. This book also: Explores questions related to the biological underpinning for models of neural networks\\ Considers neural networks modeling using differential equations with impulsive and piecewise constant argument discontinuities Provides all necessary mathematical basics for application to the theory of neural networks Neural Networks with Discontinuous/Impact Activations is an ideal book for researchers and professionals in the field of engineering mathematics that have an interest in app...

Simplified LQG Control with Neural Networks

DEFF Research Database (Denmark)

Sørensen, O.

1997-01-01

A new neural network application for non-linear state control is described. One neural network is modelled to form a Kalmann predictor and trained to act as an optimal state observer for a non-linear process. Another neural network is modelled to form a state controller and trained to produce...

Roller Testing to Mimic Damage of the ISS SARJ Ring and Durability Test to Simulate Fifteen Years of SARJ Operation Using the Damaged Surface

Science.gov (United States)

Krantz, Timothy L.; Elchert, Justin P.; DellaCorte, Christopher; Dube, Michael J.

2016-01-01

The International Space Station's starboard Solar Alpha Rotary Joint (SARJ) experienced a breakdown of the joint's race ring surface. The starboard SARJ mechanism was cleaned and lubricated with grease. To provide some guidance on the expected behavior of the damaged SARJ ring with continued operations, experiments were conducted using rollers and a vacuum roller test rig. The approach of the experimental work involved three main steps: (1) initiate damage using conditions representative of the SARJ with inadequate lubrication; (2) propagate the damage by operating the test rollers without lubrication; and (3) assess the durability of the roller by testing to simulate the equivalent of 15 years of SARJ operation on the damaged surface assuming adequate grease lubrication. During the rig testing, additional and/or replacement grease was introduced at regular intervals to maintain good lubrication in the rig. The damage to the nitride layer continued even after application of grease. The grease lubrication proved to be effective for limiting the value of the axial force that can be developed. Limiting the axial force on the SARJ mechanism is important since the larger the axial force the more concentrated the load pressure becomes on the blend-radius location on the SARJ roller. After the testing simulating 15 years of SARJ operations, the wear depths were the order of 0.2 mm for the nitrided 15-5 roller and the order of 0.06 mm for the mating 440C roller. Metallographic inspections were done to search for indications of impending fatigue or other fracture indications that might eventually propagate and cause structural failure. There were no indications or features found that could eventually compromise structural integrity.

Fuzzy neural network theory and application

CERN Document Server

Liu, Puyin

2004-01-01

This book systematically synthesizes research achievements in the field of fuzzy neural networks in recent years. It also provides a comprehensive presentation of the developments in fuzzy neural networks, with regard to theory as well as their application to system modeling and image restoration. Special emphasis is placed on the fundamental concepts and architecture analysis of fuzzy neural networks. The book is unique in treating all kinds of fuzzy neural networks and their learning algorithms and universal approximations, and employing simulation examples which are carefully designed to he

Modular representation of layered neural networks.

Science.gov (United States)

Watanabe, Chihiro; Hiramatsu, Kaoru; Kashino, Kunio

2018-01-01

Layered neural networks have greatly improved the performance of various applications including image processing, speech recognition, natural language processing, and bioinformatics. However, it is still difficult to discover or interpret knowledge from the inference provided by a layered neural network, since its internal representation has many nonlinear and complex parameters embedded in hierarchical layers. Therefore, it becomes important to establish a new methodology by which layered neural networks can be understood. In this paper, we propose a new method for extracting a global and simplified structure from a layered neural network. Based on network analysis, the proposed method detects communities or clusters of units with similar connection patterns. We show its effectiveness by applying it to three use cases. (1) Network decomposition: it can decompose a trained neural network into multiple small independent networks thus dividing the problem and reducing the computation time. (2) Training assessment: the appropriateness of a trained result with a given hyperparameter or randomly chosen initial parameters can be evaluated by using a modularity index. And (3) data analysis: in practical data it reveals the community structure in the input, hidden, and output layers, which serves as a clue for discovering knowledge from a trained neural network. Copyright © 2017 Elsevier Ltd. All rights reserved.

Armor Plate Surface Roughness Measurements

National Research Council Canada - National Science Library

Stanton, Brian; Coburn, William; Pizzillo, Thomas J

2005-01-01

...., surface texture and coatings) that could become important at high frequency. We measure waviness and roughness of various plates to know the parameter range for smooth aluminum and rolled homogenous armor (RHA...

Introduction to Artificial Neural Networks

DEFF Research Database (Denmark)

Larsen, Jan

1999-01-01

The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks.......The note addresses introduction to signal analysis and classification based on artificial feed-forward neural networks....

Numerical analysis of the bucket surface roughness effects in Pelton turbine

International Nuclear Information System (INIS)

Xiao, Y X; Zeng, C J; Zhang, J; Yan, Z G; Wang, Z W

2013-01-01

The internal flow of a Pelton turbine is quite complex. It is difficult to analyse the unsteady free water sheet flow in the rotating bucket owing to the lack of a sound theory. Affected by manufacturing technique and silt abrasion during the operation, the bucket surface roughness of Pelton turbine may be too great, and thereby influence unit performance. To investigate the effect of bucket roughness on Pelton turbine performance, this paper presents the numerical simulation of the interaction between the jet and the bucket in a Pelton turbine. The unsteady three-dimensional numerical simulations were performed with CFX code by using the SST turbulence model coupling the two-phase flow volume of fluid method. Different magnitude orders of bucket surface roughness were analysed and compared. Unsteady numerical results of the free water sheet flow patterns on bucket surface, torque and unit performance for each bucket surface roughness were generated. The total pressure distribution on bucket surface is used to show the free water sheet flow pattern on bucket surface. By comparing the variation of water sheet flow patterns on bucket surface with different roughness, this paper qualitatively analyses how the bucket surface roughness magnitude influences the impeding effect on free water sheet flow. Comparison of the torque variation of different bucket surface roughness highlighted the effect of the bucket surface roughness on the Pelton turbine output capacity. To further investigate the effect of bucket surface roughness on Pelton turbine performance, the relation between the relative efficiency loss rate and bucket surface roughness magnitude is quantitatively analysed. The result can be used to predict and evaluate the Pelton turbine performance

Numerical analysis of the bucket surface roughness effects in Pelton turbine

Science.gov (United States)

Xiao, Y. X.; Zeng, C. J.; Zhang, J.; Yan, Z. G.; Wang, Z. W.

2013-12-01

The internal flow of a Pelton turbine is quite complex. It is difficult to analyse the unsteady free water sheet flow in the rotating bucket owing to the lack of a sound theory. Affected by manufacturing technique and silt abrasion during the operation, the bucket surface roughness of Pelton turbine may be too great, and thereby influence unit performance. To investigate the effect of bucket roughness on Pelton turbine performance, this paper presents the numerical simulation of the interaction between the jet and the bucket in a Pelton turbine. The unsteady three-dimensional numerical simulations were performed with CFX code by using the SST turbulence model coupling the two-phase flow volume of fluid method. Different magnitude orders of bucket surface roughness were analysed and compared. Unsteady numerical results of the free water sheet flow patterns on bucket surface, torque and unit performance for each bucket surface roughness were generated. The total pressure distribution on bucket surface is used to show the free water sheet flow pattern on bucket surface. By comparing the variation of water sheet flow patterns on bucket surface with different roughness, this paper qualitatively analyses how the bucket surface roughness magnitude influences the impeding effect on free water sheet flow. Comparison of the torque variation of different bucket surface roughness highlighted the effect of the bucket surface roughness on the Pelton turbine output capacity. To further investigate the effect of bucket surface roughness on Pelton turbine performance, the relation between the relative efficiency loss rate and bucket surface roughness magnitude is quantitatively analysed. The result can be used to predict and evaluate the Pelton turbine performance.

THE EFFECT OF OPACIFIERS ON SURFACE ROUGHNESS OFCERAMIC GLAZES

Directory of Open Access Journals (Sweden)

R. Sarjahani

2016-03-01

Full Text Available Surface smoothness of ceramic glazes is always an important characteristic of ceramic glazes as a point of surface engineering studies. Surface roughness affects chemical resistivity, glossiness and stainabiliy of glazes. In fact, less surface roughness improves cleanability of the surface by the least usage amount of detergents. In this investigation, surface topography of two common opaque glazes, zirconia and titania-based, has been investigated. Crystallinity of the surface has been studied from SEM images, and comparison of EDS elemental results with phase analysis results of XRD. Surface roughness profile measured by Marsurf M300, shows that titania-based glaze is almost 24% percentage more smooth than zirconia based glaze. Surface smoothness is in relation with crystallinity of glaze surface, crystal type and crystal distribution in amorphous matrix phase

Comparison of optical methods for surface roughness characterization

DEFF Research Database (Denmark)

Feidenhans'l, Nikolaj Agentoft; Hansen, Poul Erik; Pilny, Lukas

2015-01-01

We report a study of the correlation between three optical methods for characterizing surface roughness: a laboratory scatterometer measuring the bi-directional reflection distribution function (BRDF instrument), a simple commercial scatterometer (rBRDF instrument), and a confocal optical profiler....... For each instrument, the effective range of spatial surface wavelengths is determined, and the common bandwidth used when comparing the evaluated roughness parameters. The compared roughness parameters are: the root-mean-square (RMS) profile deviation (Rq), the RMS profile slope (Rdq), and the variance...... of the scattering angle distribution (Aq). The twenty-two investigated samples were manufactured with several methods in order to obtain a suitable diversity of roughness patterns.Our study shows a one-to-one correlation of both the Rq and the Rdq roughness values when obtained with the BRDF and the confocal...

Single-layer model for surface roughness.

Science.gov (United States)

Carniglia, C K; Jensen, D G

2002-06-01

Random roughness of an optical surface reduces its specular reflectance and transmittance by the scattering of light. The reduction in reflectance can be modeled by a homogeneous layer on the surface if the refractive index of the layer is intermediate to the indices of the media on either side of the surface. Such a layer predicts an increase in the transmittance of the surface and therefore does not provide a valid model for the effects of scatter on the transmittance. Adding a small amount of absorption to the layer provides a model that predicts a reduction in both reflectance and transmittance. The absorbing layer model agrees with the predictions of a scalar scattering theory for a layer with a thickness that is twice the rms roughness of the surface. The extinction coefficient k for the layer is proportional to the thickness of the layer.

Artificial Neural Network Analysis System

Science.gov (United States)

2001-02-27

Contract No. DASG60-00-M-0201 Purchase request no.: Foot in the Door-01 Title Name: Artificial Neural Network Analysis System Company: Atlantic... Artificial Neural Network Analysis System 5b. GRANT NUMBER 5c. PROGRAM ELEMENT NUMBER 6. AUTHOR(S) Powell, Bruce C 5d. PROJECT NUMBER 5e. TASK NUMBER...34) 27-02-2001 Report Type N/A Dates Covered (from... to) ("DD MON YYYY") 28-10-2000 27-02-2001 Title and Subtitle Artificial Neural Network Analysis

Application of neural network technique to determine a corrector surface for global geopotential model using GPS/levelling measurements in Egypt

Science.gov (United States)

Elshambaky, Hossam Talaat

2018-01-01

Owing to the appearance of many global geopotential models, it is necessary to determine the most appropriate model for use in Egyptian territory. In this study, we aim to investigate three global models, namely EGM2008, EIGEN-6c4, and GECO. We use five mathematical transformation techniques, i.e., polynomial expression, exponential regression, least-squares collocation, multilayer feed forward neural network, and radial basis neural networks to make the conversion from regional geometrical geoid to global geoid models and vice versa. From a statistical comparison study based on quality indexes between previous transformation techniques, we confirm that the multilayer feed forward neural network with two neurons is the most accurate of the examined transformation technique, and based on the mean tide condition, EGM2008 represents the most suitable global geopotential model for use in Egyptian territory to date. The final product gained from this study was the corrector surface that was used to facilitate the transformation process between regional geometrical geoid model and the global geoid model.

Analysis of the experimental positron lifetime spectra by neural networks

International Nuclear Information System (INIS)

Avdic, S.; Chakarova, R.; Pazsit, I.

2003-01-01

This paper deals with the analysis of experimental positron lifetime spectra in polymer materials by using various algorithms of neural networks. A method based on the use of artificial neural networks for unfolding the mean lifetime and intensity of the spectral components of simulated positron lifetime spectra was previously suggested and tested on simulated data [Pazsit et al., Applied Surface Science, 149 (1998), 97]. In this work, the applicability of the method to the analysis of experimental positron spectra has been verified in the case of spectra from polymer materials with three components. It has been demonstrated that the backpropagation neural network can determine the spectral parameters with a high accuracy and perform the decomposition of lifetimes which differ by 10% or more. The backpropagation network has not been suitable for the identification of both the parameters and the number of spectral components. Therefore, a separate artificial neural network module has been designed to solve the classification problem. Module types based on self-organizing map and learning vector quantization algorithms have been tested. The learning vector quantization algorithm was found to have better performance and reliability. A complete artificial neural network analysis tool of positron lifetime spectra has been constructed to include a spectra classification module and parameter evaluation modules for spectra with a different number of components. In this way, both flexibility and high resolution can be achieved. (author)

Neural Network Ensembles

DEFF Research Database (Denmark)

Hansen, Lars Kai; Salamon, Peter

1990-01-01

We propose several means for improving the performance an training of neural networks for classification. We use crossvalidation as a tool for optimizing network parameters and architecture. We show further that the remaining generalization error can be reduced by invoking ensembles of similar...... networks....

Complex-Valued Neural Networks

CERN Document Server

Hirose, Akira

2012-01-01

This book is the second enlarged and revised edition of the first successful monograph on complex-valued neural networks (CVNNs) published in 2006, which lends itself to graduate and undergraduate courses in electrical engineering, informatics, control engineering, mechanics, robotics, bioengineering, and other relevant fields. In the second edition the recent trends in CVNNs research are included, resulting in e.g. almost a doubled number of references. The parametron invented in 1954 is also referred to with discussion on analogy and disparity. Also various additional arguments on the advantages of the complex-valued neural networks enhancing the difference to real-valued neural networks are given in various sections. The book is useful for those beginning their studies, for instance, in adaptive signal processing for highly functional sensing and imaging, control in unknown and changing environment, robotics inspired by human neural systems, and brain-like information processing, as well as interdisciplina...

Hybrid response surface methodology-artificial neural network optimization of drying process of banana slices in a forced convective dryer.

Science.gov (United States)

Taheri-Garavand, Amin; Karimi, Fatemeh; Karimi, Mahmoud; Lotfi, Valiullah; Khoobbakht, Golmohammad

2018-06-01

The aim of the study is to fit models for predicting surfaces using the response surface methodology and the artificial neural network to optimize for obtaining the maximum acceptability using desirability functions methodology in a hot air drying process of banana slices. The drying air temperature, air velocity, and drying time were chosen as independent factors and moisture content, drying rate, energy efficiency, and exergy efficiency were dependent variables or responses in the mentioned drying process. A rotatable central composite design as an adequate method was used to develop models for the responses in the response surface methodology. Moreover, isoresponse contour plots were useful to predict the results by performing only a limited set of experiments. The optimum operating conditions obtained from the artificial neural network models were moisture content 0.14 g/g, drying rate 1.03 g water/g h, energy efficiency 0.61, and exergy efficiency 0.91, when the air temperature, air velocity, and drying time values were equal to -0.42 (74.2 ℃), 1.00 (1.50 m/s), and -0.17 (2.50 h) in the coded units, respectively.

Prototype-Incorporated Emotional Neural Network.

Science.gov (United States)

Oyedotun, Oyebade K; Khashman, Adnan

2017-08-15

Artificial neural networks (ANNs) aim to simulate the biological neural activities. Interestingly, many ''engineering'' prospects in ANN have relied on motivations from cognition and psychology studies. So far, two important learning theories that have been subject of active research are the prototype and adaptive learning theories. The learning rules employed for ANNs can be related to adaptive learning theory, where several examples of the different classes in a task are supplied to the network for adjusting internal parameters. Conversely, the prototype-learning theory uses prototypes (representative examples); usually, one prototype per class of the different classes contained in the task. These prototypes are supplied for systematic matching with new examples so that class association can be achieved. In this paper, we propose and implement a novel neural network algorithm based on modifying the emotional neural network (EmNN) model to unify the prototype- and adaptive-learning theories. We refer to our new model as ``prototype-incorporated EmNN''. Furthermore, we apply the proposed model to two real-life challenging tasks, namely, static hand-gesture recognition and face recognition, and compare the result to those obtained using the popular back-propagation neural network (BPNN), emotional BPNN (EmNN), deep networks, an exemplar classification model, and k-nearest neighbor.

The contact sport of rough surfaces

Science.gov (United States)

Carpick, Robert W.

2018-01-01

Describing the way two surfaces touch and make contact may seem simple, but it is not. Fully describing the elastic deformation of ideally smooth contacting bodies, under even low applied pressure, involves second-order partial differential equations and fourth-rank elastic constant tensors. For more realistic rough surfaces, the problem becomes a multiscale exercise in surface-height statistics, even before including complex phenomena such as adhesion, plasticity, and fracture. A recent research competition, the “Contact Mechanics Challenge” (1), was designed to test various approximate methods for solving this problem. A hypothetical rough surface was generated, and the community was invited to model contact with this surface with competing theories for the calculation of properties, including contact area and pressure. A supercomputer-generated numerical solution was kept secret until competition entries were received. The comparison of results (2) provides insights into the relative merits of competing models and even experimental approaches to the problem.

Pattern classification and recognition of invertebrate functional groups using self-organizing neural networks.

Science.gov (United States)

Zhang, WenJun

2007-07-01

Self-organizing neural networks can be used to mimic non-linear systems. The main objective of this study is to make pattern classification and recognition on sampling information using two self-organizing neural network models. Invertebrate functional groups sampled in the irrigated rice field were classified and recognized using one-dimensional self-organizing map and self-organizing competitive learning neural networks. Comparisons between neural network models, distance (similarity) measures, and number of neurons were conducted. The results showed that self-organizing map and self-organizing competitive learning neural network models were effective in pattern classification and recognition of sampling information. Overall the performance of one-dimensional self-organizing map neural network was better than self-organizing competitive learning neural network. The number of neurons could determine the number of classes in the classification. Different neural network models with various distance (similarity) measures yielded similar classifications. Some differences, dependent upon the specific network structure, would be found. The pattern of an unrecognized functional group was recognized with the self-organizing neural network. A relative consistent classification indicated that the following invertebrate functional groups, terrestrial blood sucker; terrestrial flyer; tourist (nonpredatory species with no known functional role other than as prey in ecosystem); gall former; collector (gather, deposit feeder); predator and parasitoid; leaf miner; idiobiont (acarine ectoparasitoid), were classified into the same group, and the following invertebrate functional groups, external plant feeder; terrestrial crawler, walker, jumper or hunter; neustonic (water surface) swimmer (semi-aquatic), were classified into another group. It was concluded that reliable conclusions could be drawn from comparisons of different neural network models that use different distance

Adaptive Neural Network Sliding Mode Control for Quad Tilt Rotor Aircraft

Directory of Open Access Journals (Sweden)

Yanchao Yin

2017-01-01

Full Text Available A novel neural network sliding mode control based on multicommunity bidirectional drive collaborative search algorithm (M-CBDCS is proposed to design a flight controller for performing the attitude tracking control of a quad tilt rotors aircraft (QTRA. Firstly, the attitude dynamic model of the QTRA concerning propeller tension, channel arm, and moment of inertia is formulated, and the equivalent sliding mode control law is stated. Secondly, an adaptive control algorithm is presented to eliminate the approximation error, where a radial basis function (RBF neural network is used to online regulate the equivalent sliding mode control law, and the novel M-CBDCS algorithm is developed to uniformly update the unknown neural network weights and essential model parameters adaptively. The nonlinear approximation error is obtained and serves as a novel leakage term in the adaptations to guarantee the sliding surface convergence and eliminate the chattering phenomenon, which benefit the overall attitude control performance for QTRA. Finally, the appropriate comparisons among the novel adaptive neural network sliding mode control, the classical neural network sliding mode control, and the dynamic inverse PID control are examined, and comparative simulations are included to verify the efficacy of the proposed control method.

Influence of surface roughness on streptococcal adhesion forces to composite resins

NARCIS (Netherlands)

Mei, Li; Busscher, Henk J; van der Mei, Henny C; Ren, Yijin

OBJECTIVE: To determine streptococcal adhesion forces with composite resins with different surface roughness. METHODS: Polishing and grinding were applied to obtain smooth (roughness 20 nm), moderately rough (150 nm) and rough (350 nm) surfaces of two orthodontic, light-cured composites. Adhesion

Deconvolution using a neural network

Energy Technology Data Exchange (ETDEWEB)

Lehman, S.K.

1990-11-15

Viewing one dimensional deconvolution as a matrix inversion problem, we compare a neural network backpropagation matrix inverse with LMS, and pseudo-inverse. This is a largely an exercise in understanding how our neural network code works. 1 ref.

A Neural Network Approach to Fluid Quantity Measurement in Dynamic Environments

CERN Document Server

Terzic, Edin; Nagarajah, Romesh; Alamgir, Muhammad

2012-01-01

Sloshing causes liquid to fluctuate, making accurate level readings difficult to obtain in dynamic environments. The measurement system described uses a single-tube capacitive sensor to obtain an instantaneous level reading of the fluid surface, thereby accurately determining the fluid quantity in the presence of slosh. A neural network based classification technique has been applied to predict the actual quantity of the fluid contained in a tank under sloshing conditions.   In A neural network approach to fluid quantity measurement in dynamic environments, effects of temperature variations and contamination on the capacitive sensor are discussed, and the authors propose that these effects can also be eliminated with the proposed neural network based classification system. To examine the performance of the classification system, many field trials were carried out on a running vehicle at various tank volume levels that range from 5 L to 50 L. The effectiveness of signal enhancement on the neural network base...

Connectivity effects in the dynamic model of neural networks

International Nuclear Information System (INIS)

Choi, J; Choi, M Y; Yoon, B-G

2009-01-01

We study, via extensive Monte Carlo calculations, the effects of connectivity in the dynamic model of neural networks, to observe that the Mattis-state order parameter increases with the number of coupled neurons. Such effects appear more pronounced when the average number of connections is increased by introducing shortcuts in the network. In particular, the power spectra of the order parameter at stationarity are found to exhibit power-law behavior, depending on how the average number of connections is increased. The cluster size distribution of the 'memory-unmatched' sites also follows a power law and possesses strong correlations with the power spectra. It is further observed that the distribution of waiting times for neuron firing fits roughly to a power law, again depending on how neuronal connections are increased

Fuzzy Linguistic Optimization on Surface Roughness for CNC Turning

Directory of Open Access Journals (Sweden)

Tian-Syung Lan

2010-01-01

Full Text Available Surface roughness is often considered the main purpose in contemporary computer numerical controlled (CNC machining industry. Most existing optimization researches for CNC finish turning were either accomplished within certain manufacturing circumstances or achieved through numerous equipment operations. Therefore, a general deduction optimization scheme is deemed to be necessary for the industry. In this paper, the cutting depth, feed rate, speed, and tool nose runoff with low, medium, and high level are considered to optimize the surface roughness for finish turning based on L9(34 orthogonal array. Additionally, nine fuzzy control rules using triangle membership function with respective to five linguistic grades for surface roughness are constructed. Considering four input and twenty output intervals, the defuzzification using center of gravity is then completed. Thus, the optimum general fuzzy linguistic parameters can then be received. The confirmation experiment result showed that the surface roughness from the fuzzy linguistic optimization parameters is significantly advanced compared to that from the benchmark. This paper certainly proposes a general optimization scheme using orthogonal array fuzzy linguistic approach to the surface roughness for CNC turning with profound insight.

Modeling superhydrophobic surfaces comprised of random roughness

Science.gov (United States)

Samaha, M. A.; Tafreshi, H. Vahedi; Gad-El-Hak, M.

2011-11-01

We model the performance of superhydrophobic surfaces comprised of randomly distributed roughness that resembles natural surfaces, or those produced via random deposition of hydrophobic particles. Such a fabrication method is far less expensive than ordered-microstructured fabrication. The present numerical simulations are aimed at improving our understanding of the drag reduction effect and the stability of the air-water interface in terms of the microstructure parameters. For comparison and validation, we have also simulated the flow over superhydrophobic surfaces made up of aligned or staggered microposts for channel flows as well as streamwise or spanwise ridge configurations for pipe flows. The present results are compared with other theoretical and experimental studies. The numerical simulations indicate that the random distribution of surface roughness has a favorable effect on drag reduction, as long as the gas fraction is kept the same. The stability of the meniscus, however, is strongly influenced by the average spacing between the roughness peaks, which needs to be carefully examined before a surface can be recommended for fabrication. Financial support from DARPA, contract number W91CRB-10-1-0003, is acknowledged.

Effects of capillary condensation in adhesion between rough surfaces.

Science.gov (United States)

Wang, Jizeng; Qian, Jin; Gao, Huajian

2009-10-06

Experiments on the effects of humidity in adhesion between rough surfaces have shown that the adhesion energy remains constant below a critical relative humidity (RHcr) and then abruptly jumps to a higher value at RHcr before approaching its upper limit at 100% relative humidity. A model based on a hierarchical rough surface topography is proposed, which quantitatively explains the experimental observations and predicts two threshold RH values, RHcr and RHdry, which define three adhesion regimes: (1) RHRHcr, water menisci freely form and spread along the interface between the rough surfaces.

The Black Burnished Type 18 Bowl and the Fifth Century

Directory of Open Access Journals (Sweden)

James Gerrard

2016-03-01

Full Text Available This article discusses a late Roman Black Burnished form known as the Type 18 bowl. The lateness of this form was first discussed in 2004 but new discoveries have continued to reinforce the probably late fourth to early fifth century date assigned to this vessel. Imitations in other fabrics are also beginning to be identified with one such vessel found in association with early Anglo-Saxon pottery.

Containment control of networked autonomous underwater vehicles: A predictor-based neural DSC design.

Science.gov (United States)

Peng, Zhouhua; Wang, Dan; Wang, Wei; Liu, Lu

2015-11-01

This paper investigates the containment control problem of networked autonomous underwater vehicles in the presence of model uncertainty and unknown ocean disturbances. A predictor-based neural dynamic surface control design method is presented to develop the distributed adaptive containment controllers, under which the trajectories of follower vehicles nearly converge to the dynamic convex hull spanned by multiple reference trajectories over a directed network. Prediction errors, rather than tracking errors, are used to update the neural adaptation laws, which are independent of the tracking error dynamics, resulting in two time-scales to govern the entire system. The stability property of the closed-loop network is established via Lyapunov analysis, and transient property is quantified in terms of L2 norms of the derivatives of neural weights, which are shown to be smaller than the classical neural dynamic surface control approach. Comparative studies are given to show the substantial improvements of the proposed new method. Copyright © 2015 ISA. Published by Elsevier Ltd. All rights reserved.

Neural networks and statistical learning

CERN Document Server

Du, Ke-Lin

2014-01-01

Providing a broad but in-depth introduction to neural network and machine learning in a statistical framework, this book provides a single, comprehensive resource for study and further research. All the major popular neural network models and statistical learning approaches are covered with examples and exercises in every chapter to develop a practical working understanding of the content. Each of the twenty-five chapters includes state-of-the-art descriptions and important research results on the respective topics. The broad coverage includes the multilayer perceptron, the Hopfield network, associative memory models, clustering models and algorithms, the radial basis function network, recurrent neural networks, principal component analysis, nonnegative matrix factorization, independent component analysis, discriminant analysis, support vector machines, kernel methods, reinforcement learning, probabilistic and Bayesian networks, data fusion and ensemble learning, fuzzy sets and logic, neurofuzzy models, hardw...

Effect of surface roughness on the aerodynamic characteristics of a symmetrical airfoil

Energy Technology Data Exchange (ETDEWEB)

Chakroun, W.; Al-Mesri, I.; Al-Fahad, S.

2005-07-01

The objective of this study is to investigate the effect of surface roughness by varying the roughness size and location on the aerodynamic characteristics of the airfoil. Test were conducted on the symmetrical airfoil models NACA 0012 in which the nature of the surface was varied from smooth to very rough and at a chord Reynolds number of 1.5*10{sup 5}. Different airfoil models with various roughness sizes and roughness locations were tested for different angles of attack. Lift, drag and pressure coefficients were measured and velocity profiles were determined for the smooth and grit 36 roughened models. It is shown that as the surface roughness increases, the minimum drag also increases due to the increase of the skin friction and the lift decreases. Surface roughness is seen to delay the stall angle and also increase the lift in the stall region. The airfoil model with the roughness located at the trailing edge shows minimum drag and maximum lift up to the stall angle compared to the other cases of different roughness locations. It is confirmed that, for the rough surface, a turbulent boundary layer exists where the laminar boundary layer is encountered for the smooth surface at the same Reynolds number. The measured skin friction for the rough surface is larger than that for the smooth surface. (author)

Neural network recognition of mammographic lesions

International Nuclear Information System (INIS)

Oldham, W.J.B.; Downes, P.T.; Hunter, V.

1987-01-01

A method for recognition of mammographic lesions through the use of neural networks is presented. Neural networks have exhibited the ability to learn the shape andinternal structure of patterns. Digitized mammograms containing circumscribed and stelate lesions were used to train a feedfoward synchronous neural network that self-organizes to stable attractor states. Encoding of data for submission to the network was accomplished by performing a fractal analysis of the digitized image. This results in scale invariant representation of the lesions. Results are discussed

Neural Networks and Micromechanics

Science.gov (United States)

Kussul, Ernst; Baidyk, Tatiana; Wunsch, Donald C.

The title of the book, "Neural Networks and Micromechanics," seems artificial. However, the scientific and technological developments in recent decades demonstrate a very close connection between the two different areas of neural networks and micromechanics. The purpose of this book is to demonstrate this connection. Some artificial intelligence (AI) methods, including neural networks, could be used to improve automation system performance in manufacturing processes. However, the implementation of these AI methods within industry is rather slow because of the high cost of conducting experiments using conventional manufacturing and AI systems. To lower the cost, we have developed special micromechanical equipment that is similar to conventional mechanical equipment but of much smaller size and therefore of lower cost. This equipment could be used to evaluate different AI methods in an easy and inexpensive way. The proved methods could be transferred to industry through appropriate scaling. In this book, we describe the prototypes of low cost microequipment for manufacturing processes and the implementation of some AI methods to increase precision, such as computer vision systems based on neural networks for microdevice assembly and genetic algorithms for microequipment characterization and the increase of microequipment precision.

Crystal surface analysis using matrix textural features classified by a Probabilistic Neural Network

International Nuclear Information System (INIS)

Sawyer, C.R.; Quach, V.T.; Nason, D.; van den Berg, L.

1991-01-01

A system is under development in which surface quality of a growing bulk mercuric iodide crystal is monitored by video camera at regular intervals for early detection of growth irregularities. Mercuric iodide single crystals are employed in radiation detectors. A microcomputer system is used for image capture and processing. The digitized image is divided into multiple overlappings subimage and features are extracted from each subimage based on statistical measures of the gray tone distribution, according to the method of Haralick [1]. Twenty parameters are derived from each subimage and presented to a Probabilistic Neural Network (PNN) [2] for classification. This number of parameters was found to be optimal for the system. The PNN is a hierarchical, feed-forward network that can be rapidly reconfigured as additional training data become available. Training data is gathered by reviewing digital images of many crystals during their growth cycle and compiling two sets of images, those with and without irregularities. 6 refs., 4 figs

Cassie state robustness of plasma generated randomly nano-rough surfaces

Energy Technology Data Exchange (ETDEWEB)

Di Mundo, Rosa, E-mail: rosa.dimundo@poliba.it; Bottiglione, Francesco; Carbone, Giuseppe

2014-10-15

Graphical abstract: - Highlights: • Superhydrophobic randomly rough surfaces are generated by plasma etching. • Statistical analysis of roughness allows calculation of theWenzel roughness factor, r{sub W.} • A r{sub W} threshold is theoretically determined, above which superhydrophobicity is “robust”. • Dynamic wetting, e.g. with high speed impacting drops, confirms this prediction. - Abstract: Superhydrophobic surfaces are effective in practical applications provided they are “robust superhydrophobic”, i.e. able to retain the Cassie state, i.e. with water suspended onto the surface protrusions, even under severe conditions (high pressure, vibrations, high speed impact, etc.). We show that for randomly rough surfaces, given the Young angle, Cassie states are robust when a threshold value of the Wenzel roughness factor, r{sub W}, is exceeded. In particular, superhydrophobic nano-textured surfaces have been generated by self-masked plasma etching. In view of their random roughness, topography features, acquired by Atomic Force Microscopy, have been statistically analyzed in order to gain information on statistical parameters such as power spectral density, fractal dimension and Wenzel roughness factor (r{sub W}), which has been used to assess Cassie state robustness. Results indicate that randomly rough surfaces produced by plasma at high power or long treatment duration, which are also fractal self-affine, have a r{sub W} higher than the theoretical threshold, thus for them a robust superhydrophobicity is predicted. In agreement with this, under dynamic wetting conditionson these surfaces the most pronounced superhydrophobic character has been appreciated: they show the lowest contact angle hysteresis and result in the sharpest bouncing when hit by drops at high impact velocity.

Parameterization Of Solar Radiation Using Neural Network

International Nuclear Information System (INIS)

Jiya, J. D.; Alfa, B.

2002-01-01

This paper presents a neural network technique for parameterization of global solar radiation. The available data from twenty-one stations is used for training the neural network and the data from other ten stations is used to validate the neural model. The neural network utilizes latitude, longitude, altitude, sunshine duration and period number to parameterize solar radiation values. The testing data was not used in the training to demonstrate the performance of the neural network in unknown stations to parameterize solar radiation. The results indicate a good agreement between the parameterized solar radiation values and actual measured values

Comparison of optical methods for surface roughness characterization

International Nuclear Information System (INIS)

Feidenhans’l, Nikolaj A; Hansen, Poul-Erik; Madsen, Morten H; Petersen, Jan C; Pilný, Lukáš; Bissacco, Giuliano; Taboryski, Rafael

2015-01-01

We report a study of the correlation between three optical methods for characterizing surface roughness: a laboratory scatterometer measuring the bi-directional reflection distribution function (BRDF instrument), a simple commercial scatterometer (rBRDF instrument), and a confocal optical profiler. For each instrument, the effective range of spatial surface wavelengths is determined, and the common bandwidth used when comparing the evaluated roughness parameters. The compared roughness parameters are: the root-mean-square (RMS) profile deviation (Rq), the RMS profile slope (Rdq), and the variance of the scattering angle distribution (Aq). The twenty-two investigated samples were manufactured with several methods in order to obtain a suitable diversity of roughness patterns.Our study shows a one-to-one correlation of both the Rq and the Rdq roughness values when obtained with the BRDF and the confocal instruments, if the common bandwidth is applied. Likewise, a correlation is observed when determining the Aq value with the BRDF and the rBRDF instruments.Furthermore, we show that it is possible to determine the Rq value from the Aq value, by applying a simple transfer function derived from the instrument comparisons. The presented method is validated for surfaces with predominantly 1D roughness, i.e. consisting of parallel grooves of various periods, and a reflectance similar to stainless steel. The Rq values are predicted with an accuracy of 38% at the 95% confidence interval. (paper)

Surface roughness control by extreme ultraviolet (EUV) radiation

Science.gov (United States)

Ahad, Inam Ul; Obeidi, Muhannad Ahmed; Budner, Bogusław; Bartnik, Andrzej; Fiedorowicz, Henryk; Brabazon, Dermot

2017-10-01

Surface roughness control of polymeric materials is often desirable in various biomedical engineering applications related to biocompatibility control, separation science and surface wettability control. In this study, Polyethylene terephthalate (PET) polymer films were irradiated with Extreme ultraviolet (EUV) photons in nitrogen environment and investigations were performed on surface roughness modification via EUV exposure. The samples were irradiated at 3 mm and 4 mm distance from the focal spot to investigate the effect of EUV fluence on topography. The topography of the EUV treated PET samples were studied by AFM. The detailed scanning was also performed on the sample irradiated at 3 mm. It was observed that the average surface roughness of PET samples was increased from 9 nm (pristine sample) to 280 nm and 253 nm for EUV irradiated samples. Detailed AFM studies confirmed the presence of 1.8 mm wide period U-shaped channels in EUV exposed PET samples. The walls of the channels were having FWHM of about 0.4 mm. The channels were created due to translatory movements of the sample in horizontal and transverse directions during the EUV exposure. The increased surface roughness is useful for many applications. The nanoscale channels fabricated by EUV exposure could be interesting for microfluidic applications based on lab-on-a-chip (LOC) devices.

Analysis of neural networks through base functions

NARCIS (Netherlands)

van der Zwaag, B.J.; Slump, Cornelis H.; Spaanenburg, L.

Problem statement. Despite their success-story, neural networks have one major disadvantage compared to other techniques: the inability to explain comprehensively how a trained neural network reaches its output; neural networks are not only (incorrectly) seen as a "magic tool" but possibly even more

The surface roughness and planetary boundary layer

Science.gov (United States)

Telford, James W.

1980-03-01

Applications of the entrainment process to layers at the boundary, which meet the self similarity requirements of the logarithmic profile, have been studied. By accepting that turbulence has dominating scales related in scale length to the height above the surface, a layer structure is postulated wherein exchange is rapid enough to keep the layers internally uniform. The diffusion rate is then controlled by entrainment between layers. It has been shown that theoretical relationships derived on the basis of using a single layer of this type give quantitatively correct factors relating the turbulence, wind and shear stress for very rough surface conditions. For less rough surfaces, the surface boundary layer can be divided into several layers interacting by entrainment across each interface. This analysis leads to the following quantitatively correct formula compared to published measurements. 1 24_2004_Article_BF00877766_TeX2GIFE1.gif {σ _w }/{u^* } = ( {2/{9Aa}} )^{{1/4}} ( {1 - 3^{{1/2}{ a/k{d_n }/z{σ _w }/{u^* }z/L} )^{{1/4}} = 1.28(1 - 0.945({{σ _w }/{u^* }}}) {{z/L}})^{{1/4 where u^* = ( {{tau/ρ}}^{{1/2}}, σ w is the standard deviation of the vertical velocity, z is the height and L is the Obukhov scale lenght. The constants a, A, k and d n are the entrainment constant, the turbulence decay constant, Von Karman's constant, and the layer depth derived from the theory. Of these, a and A, are universal constants and not empirically determined for the boundary layer. Thus the turbulence needed for the plume model of convection, which resides above these layers and reaches to the inversion, is determined by the shear stress and the heat flux in the surface layers. This model applies to convection in cool air over a warm sea. The whole field is now determined except for the temperature of the air relative to the water, and the wind, which need a further parameter describing sea surface roughness. As a first stop to describing a surface where roughness elements

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....

Boolean Factor Analysis by Attractor Neural Network

Czech Academy of Sciences Publication Activity Database

Frolov, A. A.; Húsek, Dušan; Muraviev, I. P.; Polyakov, P.Y.

2007-01-01

Roč. 18, č. 3 (2007), s. 698-707 ISSN 1045-9227 R&D Projects: GA AV ČR 1ET100300419; GA ČR GA201/05/0079 Institutional research plan: CEZ:AV0Z10300504 Keywords : recurrent neural network * Hopfield-like neural network * associative memory * unsupervised learning * neural network architecture * neural network application * statistics * Boolean factor analysis * dimensionality reduction * features clustering * concepts search * information retrieval Subject RIV: BB - Applied Statistics, Operational Research Impact factor: 2.769, year: 2007

Effect of nanometer scale surface roughness of titanium for osteoblast function

Directory of Open Access Journals (Sweden)

Satoshi Migita

2017-02-01

Full Text Available Surface roughness is an important property for metallic materials used in medical implants or other devices. The present study investigated the effects of surface roughness on cellular function, namely cell attachment, proliferation, and differentiation potential. Titanium (Ti discs, with a hundred nanometer- or nanometer-scale surface roughness (rough and smooth Ti surface, respectively were prepared by polishing with silicon carbide paper. MC3T3-E1 mouse osteoblast-like cells were cultured on the discs, and their attachment, spreading area, proliferation, and calcification were analyzed. Cells cultured on rough Ti discs showed reduced attachment, proliferation, and calcification ability suggesting that the surface inhibited osteoblast function. The findings can provide a basis for improving the biocompatibility of medical devices.

Friction and adhesion of gecko-inspired PDMS flaps on rough surfaces.

Science.gov (United States)

Yu, Jing; Chary, Sathya; Das, Saurabh; Tamelier, John; Turner, Kimberly L; Israelachvili, Jacob N

2012-08-07

Geckos have developed a unique hierarchical structure to maintain climbing ability on surfaces with different roughness, one of the extremely important parameters that affect the friction and adhesion forces between two surfaces. Although much attention has been paid on fabricating various structures that mimic the hierarchical structure of a gecko foot, yet no systematic effort, in experiment or theory, has been made to quantify the effect of surface roughness on the performance of the fabricated structures that mimic the hierarchical structure of geckos. Using a modified surface forces apparatus (SFA), we measured the adhesion and friction forces between microfabricated tilted PDMS flaps and optically smooth SiO(2) and rough SiO(2) surfaces created by plasma etching. Anisotropic adhesion and friction forces were measured when sliding the top glass surface along (+y) and against (-y) the tilted direction of the flaps. Increasing the surface roughness first increased the adhesion and friction forces measured between the flaps and the rough surface due to topological matching of the two surfaces but then led to a rapid decrease in both of these forces. Our results demonstrate that the surface roughness significantly affects the performance of gecko mimetic adhesives and that different surface textures can either increase or decrease the adhesion and friction forces of the fabricated adhesives.

Response Ant Colony Optimization of End Milling Surface Roughness

Directory of Open Access Journals (Sweden)

Ahmed N. Abd Alla

2010-03-01

Full Text Available Metal cutting processes are important due to increased consumer demands for quality metal cutting related products (more precise tolerances and better product surface roughness that has driven the metal cutting industry to continuously improve quality control of metal cutting processes. This paper presents optimum surface roughness by using milling mould aluminium alloys (AA6061-T6 with Response Ant Colony Optimization (RACO. The approach is based on Response Surface Method (RSM and Ant Colony Optimization (ACO. The main objectives to find the optimized parameters and the most dominant variables (cutting speed, feedrate, axial depth and radial depth. The first order model indicates that the feedrate is the most significant factor affecting surface roughness.

Neural networks at the Tevatron

International Nuclear Information System (INIS)

Badgett, W.; Burkett, K.; Campbell, M.K.; Wu, D.Y.; Bianchin, S.; DeNardi, M.; Pauletta, G.; Santi, L.; Caner, A.; Denby, B.; Haggerty, H.; Lindsey, C.S.; Wainer, N.; Dall'Agata, M.; Johns, K.; Dickson, M.; Stanco, L.; Wyss, J.L.

1992-10-01

This paper summarizes neural network applications at the Fermilab Tevatron, including the first online hardware application in high energy physics (muon tracking): the CDF and DO neural network triggers; offline quark/gluon discrimination at CDF; ND a new tool for top to multijets recognition at CDF

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.

Simple model of surface roughness for binary collision sputtering simulations

Energy Technology Data Exchange (ETDEWEB)

Lindsey, Sloan J. [Institute of Solid-State Electronics, TU Wien, Floragasse 7, A-1040 Wien (Austria); Hobler, Gerhard, E-mail: gerhard.hobler@tuwien.ac.at [Institute of Solid-State Electronics, TU Wien, Floragasse 7, A-1040 Wien (Austria); Maciążek, Dawid; Postawa, Zbigniew [Institute of Physics, Jagiellonian University, ul. Lojasiewicza 11, 30348 Kraków (Poland)

2017-02-15

Highlights: • A simple model of surface roughness is proposed. • Its key feature is a linearly varying target density at the surface. • The model can be used in 1D/2D/3D Monte Carlo binary collision simulations. • The model fits well experimental glancing incidence sputtering yield data. - Abstract: It has been shown that surface roughness can strongly influence the sputtering yield – especially at glancing incidence angles where the inclusion of surface roughness leads to an increase in sputtering yields. In this work, we propose a simple one-parameter model (the “density gradient model”) which imitates surface roughness effects. In the model, the target’s atomic density is assumed to vary linearly between the actual material density and zero. The layer width is the sole model parameter. The model has been implemented in the binary collision simulator IMSIL and has been evaluated against various geometric surface models for 5 keV Ga ions impinging an amorphous Si target. To aid the construction of a realistic rough surface topography, we have performed MD simulations of sequential 5 keV Ga impacts on an initially crystalline Si target. We show that our new model effectively reproduces the sputtering yield, with only minor variations in the energy and angular distributions of sputtered particles. The success of the density gradient model is attributed to a reduction of the reflection coefficient – leading to increased sputtering yields, similar in effect to surface roughness.

Simple model of surface roughness for binary collision sputtering simulations

International Nuclear Information System (INIS)

Lindsey, Sloan J.; Hobler, Gerhard; Maciążek, Dawid; Postawa, Zbigniew

2017-01-01

Highlights: • A simple model of surface roughness is proposed. • Its key feature is a linearly varying target density at the surface. • The model can be used in 1D/2D/3D Monte Carlo binary collision simulations. • The model fits well experimental glancing incidence sputtering yield data. - Abstract: It has been shown that surface roughness can strongly influence the sputtering yield – especially at glancing incidence angles where the inclusion of surface roughness leads to an increase in sputtering yields. In this work, we propose a simple one-parameter model (the “density gradient model”) which imitates surface roughness effects. In the model, the target’s atomic density is assumed to vary linearly between the actual material density and zero. The layer width is the sole model parameter. The model has been implemented in the binary collision simulator IMSIL and has been evaluated against various geometric surface models for 5 keV Ga ions impinging an amorphous Si target. To aid the construction of a realistic rough surface topography, we have performed MD simulations of sequential 5 keV Ga impacts on an initially crystalline Si target. We show that our new model effectively reproduces the sputtering yield, with only minor variations in the energy and angular distributions of sputtered particles. The success of the density gradient model is attributed to a reduction of the reflection coefficient – leading to increased sputtering yields, similar in effect to surface roughness.

Effects of surface roughness on plastic strain localization in polycrystalline aggregates

Directory of Open Access Journals (Sweden)

Guilhem Yoann

2014-06-01

Full Text Available The surface state of mechanical components differs according to applied loadings. Industrial processes may produce specific features at the surface, such as roughness, local hardening, residual stresses or recrystallization. Under fatigue loading, all these parameters will affect the component lifetime, but in different manner. A better understanding of each surface state parameter, separately first and then all combined, will provide a better prediction of fatigue life. The study focuses on the effect of surface roughness. Crystal plasticity finite element computations have been carried out on three-dimensional polycrystalline aggregates with different roughness levels. Local mechanical fields have been analyzed both at the surface and inside the bulk to highlight the competition between crystallography and roughness to impose localization patterns. As soon as surface roughness is strong enough, classical localization bands driven by grains orientation are replaced by localizations patterns driven by the local roughness topology. Nevertheless, this effect tends to decrease gradually under the surface, and it becomes usually negligible after the first layer of grains. The discussion allows us to characterize the influence of the surface state on the local mechanical fields.

Elastic–plastic adhesive contact of non-Gaussian rough surfaces

Indian Academy of Sciences (India)

Grinding, milling, honing and abrasion processes produce grooved surfaces with negative ... This may be defined as λ = π2RH4σ/(18K2γ2) where H is the hardness ... The effect of surface roughness on adhesion at the contact of rough solids ...

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.)

Kinematic correction for roller skewing

Science.gov (United States)

Savage, M.; Loewenthal, S. H.

1980-01-01

A theory of kinematic stabilization of rolling cylinders is developed for high-speed cylindrical roller bearings. This stabilization requires race and roller crowning to product changes in the rolling geometry as the roller shifts axially. These changes put a reverse skew in the rolling elements by changing the rolling taper. Twelve basic possible bearing modifications are identified in this paper. Four have single transverse convex curvature in the rollers while eight have rollers with compound transverse curvature composed of a central cylindrical band of constant radius surrounded by symmetric bands with both slope and transverse curvature.

Fuzzy logic and neural networks basic concepts & application

CERN Document Server

Alavala, Chennakesava R

2008-01-01

About the Book: The primary purpose of this book is to provide the student with a comprehensive knowledge of basic concepts of fuzzy logic and neural networks. The hybridization of fuzzy logic and neural networks is also included. No previous knowledge of fuzzy logic and neural networks is required. Fuzzy logic and neural networks have been discussed in detail through illustrative examples, methods and generic applications. Extensive and carefully selected references is an invaluable resource for further study of fuzzy logic and neural networks. Each chapter is followed by a question bank

Numerically Analysed Thermal Condition of Hearth Rollers with the Water-Cooled Shaft

Directory of Open Access Journals (Sweden)

A. V. Ivanov

2016-01-01

Full Text Available Continuous furnaces with roller hearth have wide application in the steel industry. Typically, furnaces with roller hearth belong to the class of medium-temperature heat treatment furnaces, but can be used to heat the billets for rolling. In this case, the furnaces belong to the class of high temperature heating furnaces, and their efficiency depends significantly on the reliability of the roller hearth furnace. In the high temperature heating furnaces are used three types of watercooled shaft rollers, namely rollers without insulation, rollers with insulating screens placed between the barrel and the shaft, and rollers with bulk insulation. The definition of the operating conditions of rollers with water-cooled shaft greatly facilitates the choice of their design parameters when designing. In this regard, at the design stage of the furnace with roller hearth, it is important to have information about the temperature distribution in the body of the rollers at various operating conditions. The article presents the research results of the temperature field of the hearth rollers of metallurgical heating furnaces. Modeling of stationary heat exchange between the oven atmosphere and a surface of rollers, and between the cooling water and shaft was executed by finite elements method. Temperature fields in the water-cooled shaft rollers of various designs are explored. The water-cooled shaft rollers without isolation, rollers with screen and rollers with bulk insulation, placed between the barrel and the water-cooled shaft were investigated. Determined the change of the thermo-physic parameters of the coolant, the temperature change of water when flowing in a pipe and shaft, as well as the desired pressure to supply water with a specified flow rate. Heat transfer coefficients between the cooling water and the shaft were determined directly during the solution based on the specified boundary conditions. Found that the greatest heat losses occur in the

Investigation of surface roughness influence on hyperbolic metamaterial performance

Directory of Open Access Journals (Sweden)

S. Kozik

2014-12-01

Full Text Available The main goal of this work was to introduce simple model of surface roughness which does not involve objects with complicated shapes and could help to reduce computational costs. We described and proved numerically that the influence of surface roughness at the interfaces in metal-dielectric composite materials could be described by proper selection of refractive index of dielectric layers. Our calculations show that this model works for roughness with RMS value about 1 nm and below.

Kinematics of Planetary Roller Screw Mechanism considering Helical Directions of Screw and Roller Threads

Directory of Open Access Journals (Sweden)

Shangjun Ma

2015-01-01

Full Text Available Based on the differential principle of thread transmission, an analytical model considering helical directions between screw and roller threads in planetary roller screw mechanism (PRSM is presented in this work. The model is critical for the design of PRSM with a smaller lead and a bigger pitch to realize a higher transmission accuracy. The kinematic principle of planetary transmission is employed to analyze the PRSM with different screw thread and roller thread directions. In order to investigate the differences with different screw thread and roller thread directions, the numerical model is developed by using the software Adams to validate the analytical solutions calculated by the presented model. The results indicate, when the helical direction of screw thread is identical with the direction of roller thread, that the lead of PRSM is unaffected regardless of whether sliding between screw and rollers occurs or not. Only when the direction of screw thread is reverse to the direction of roller thread, the design of PRSM with a smaller lead can be realized under a bigger pitch. The presented models and numerical simulation method can be used to research the transmission accuracy of PRSM.

Simple model of surface roughness for binary collision sputtering simulations

Science.gov (United States)

Lindsey, Sloan J.; Hobler, Gerhard; Maciążek, Dawid; Postawa, Zbigniew

2017-02-01

It has been shown that surface roughness can strongly influence the sputtering yield - especially at glancing incidence angles where the inclusion of surface roughness leads to an increase in sputtering yields. In this work, we propose a simple one-parameter model (the "density gradient model") which imitates surface roughness effects. In the model, the target's atomic density is assumed to vary linearly between the actual material density and zero. The layer width is the sole model parameter. The model has been implemented in the binary collision simulator IMSIL and has been evaluated against various geometric surface models for 5 keV Ga ions impinging an amorphous Si target. To aid the construction of a realistic rough surface topography, we have performed MD simulations of sequential 5 keV Ga impacts on an initially crystalline Si target. We show that our new model effectively reproduces the sputtering yield, with only minor variations in the energy and angular distributions of sputtered particles. The success of the density gradient model is attributed to a reduction of the reflection coefficient - leading to increased sputtering yields, similar in effect to surface roughness.

A Methodology of Designing the Teeth Conjugation in a Planetary Roller Screw

Directory of Open Access Journals (Sweden)

Lisowski Filip

2016-12-01

Full Text Available The paper presents the methodology for designing the teeth conjunction of planetary gears in the planetary roller screw mechanism. A function of the planetary gears is to synchronize an operation of rollers in order to avoid axial displacements. A condition of the correct operation is no axial movement of rollers in relation to the nut. The planetary gears are integral parts of rollers and therefore an operation of the gear transmissions has a direct impact on cooperation of the screw, rollers and the nut. The proper design of gear engagements is essential for reducing slippage on surfaces of the cooperating threaded elements. For this purpose, in a designing method, both the limitations of operation and kinematic conditions of rollers’ operation have to be taken into account.

The effect of the neural activity on topological properties of growing neural networks.

Science.gov (United States)

Gafarov, F M; Gafarova, V R

2016-09-01

The connectivity structure in cortical networks defines how information is transmitted and processed, and it is a source of the complex spatiotemporal patterns of network's development, and the process of creation and deletion of connections is continuous in the whole life of the organism. In this paper, we study how neural activity influences the growth process in neural networks. By using a two-dimensional activity-dependent growth model we demonstrated the neural network growth process from disconnected neurons to fully connected networks. For making quantitative investigation of the network's activity influence on its topological properties we compared it with the random growth network not depending on network's activity. By using the random graphs theory methods for the analysis of the network's connections structure it is shown that the growth in neural networks results in the formation of a well-known "small-world" network.

Calibration of surface roughness standards

DEFF Research Database (Denmark)

Thalmann, R.; Nicolet, A.; Meli, F.

2016-01-01

organisations. Five surface texture standards of different type were circulated and on each of the standards several roughness parameters according to the standard ISO 4287 had to be determined. 32 out of 395 individual results were not consistent with the reference value. After some corrective actions...

Soil surface roughness decay in contrasting climates, tillage types and management systems

Science.gov (United States)

Vidal Vázquez, Eva; Bertol, Ildegardis; Tondello Barbosa, Fabricio; Paz-Ferreiro, Jorge

2014-05-01

Soil surface roughness describes the variations in the elevation of the soil surface. Such variations define the soil surface microrelief, which is characterized by a high spatial variability. Soil surface roughness is a property affecting many processes such as depression storage, infiltration, sediment generation, storage and transport and runoff routing. Therefore the soil surface microrelief is a key element in hydrology and soil erosion processes at different spatial scales as for example at the plot, field or catchment scale. In agricultural land soil surface roughness is mainly created by tillage operations, which promote to different extent the formation of microdepressions and microelevations and increase infiltration and temporal retention of water. The decay of soil surface roughness has been demonstrated to be mainly driven by rain height and rain intensity, and to depend also on runoff, aggregate stability, soil reface porosity and soil surface density. Soil roughness formation and decay may be also influenced by antecedent soil moisture (either before tillage or rain), quantity and type of plant residues over the soil surface and soil composition. Characterization of the rate and intensity of soil surface roughness decay provides valuable information about the degradation of the upper most soil surface layer before soil erosion has been initiated or at the very beginning of soil runoff and erosion processes. We analyzed the rate of decay of soil surface roughness from several experiments conducted in two regions under temperate and subtropical climate and with contrasting land use systems. The data sets studied were obtained both under natural and simulated rainfall for various soil tillage and management types. Soil surface roughness decay was characterized bay several parameters, including classic and single parameters such as the random roughness or the tortuosity and parameters based on advanced geostatistical methods or on the fractal theory. Our

Enhancing neural-network performance via assortativity

International Nuclear Information System (INIS)

Franciscis, Sebastiano de; Johnson, Samuel; Torres, Joaquin J.

2011-01-01

The performance of attractor neural networks has been shown to depend crucially on the heterogeneity of the underlying topology. We take this analysis a step further by examining the effect of degree-degree correlations - assortativity - on neural-network behavior. We make use of a method recently put forward for studying correlated networks and dynamics thereon, both analytically and computationally, which is independent of how the topology may have evolved. We show how the robustness to noise is greatly enhanced in assortative (positively correlated) neural networks, especially if it is the hub neurons that store the information.

Effect of surfaces similarity on contact resistance of fractal rough surfaces under cyclic loading

Science.gov (United States)

Gao, Yuanwen; Liu, Limei; Ta, Wurui; Song, Jihua

2018-03-01

Although numerous studies have shown that contact resistance depends significantly on roughness and fractal dimension, it remains elusive how they affect contact resistance between rough surfaces. The interface similarity index is first proposed to describe the similarity of the contact surfaces, which gives a good indication of the actual contact area between surfaces. We reveal that the surfaces' similarity be an origin of contact resistance variation. The cyclic loading can increase the contact stiffness, and the contact stiffness increases with the increase of the interface similarity index. These findings explain the mechanism of surface roughness and fractal dimension on contact resistance, and also provide reference for the reliability design of the electrical connection.

Genetic algorithm for neural networks optimization

Science.gov (United States)

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«.

Neural Network Based Load Frequency Control for Restructuring ...

African Journals Online (AJOL)

Neural Network Based Load Frequency Control for Restructuring Power Industry. ... an artificial neural network (ANN) application of load frequency control (LFC) of a Multi-Area power system by using a neural network controller is presented.

Application of Entropy Ensemble Filter in Neural Network Forecasts of Tropical Pacific Sea Surface Temperatures

Directory of Open Access Journals (Sweden)

Hossein Foroozand

2018-03-01

Full Text Available Recently, the Entropy Ensemble Filter (EEF method was proposed to mitigate the computational cost of the Bootstrap AGGregatING (bagging method. This method uses the most informative training data sets in the model ensemble rather than all ensemble members created by the conventional bagging. In this study, we evaluate, for the first time, the application of the EEF method in Neural Network (NN modeling of El Nino-southern oscillation. Specifically, we forecast the first five principal components (PCs of sea surface temperature monthly anomaly fields over tropical Pacific, at different lead times (from 3 to 15 months, with a three-month increment for the period 1979–2017. We apply the EEF method in a multiple-linear regression (MLR model and two NN models, one using Bayesian regularization and one Levenberg-Marquardt algorithm for training, and evaluate their performance and computational efficiency relative to the same models with conventional bagging. All models perform equally well at the lead time of 3 and 6 months, while at higher lead times, the MLR model’s skill deteriorates faster than the nonlinear models. The neural network models with both bagging methods produce equally successful forecasts with the same computational efficiency. It remains to be shown whether this finding is sensitive to the dataset size.

Simplified Approach to Predicting Rough Surface Transition

Science.gov (United States)

Boyle, Robert J.; Stripf, Matthias

2009-01-01

Turbine vane heat transfer predictions are given for smooth and rough vanes where the experimental data show transition moving forward on the vane as the surface roughness physical height increases. Consiste nt with smooth vane heat transfer, the transition moves forward for a fixed roughness height as the Reynolds number increases. Comparison s are presented with published experimental data. Some of the data ar e for a regular roughness geometry with a range of roughness heights, Reynolds numbers, and inlet turbulence intensities. The approach ta ken in this analysis is to treat the roughness in a statistical sense , consistent with what would be obtained from blades measured after e xposure to actual engine environments. An approach is given to determ ine the equivalent sand grain roughness from the statistics of the re gular geometry. This approach is guided by the experimental data. A roughness transition criterion is developed, and comparisons are made with experimental data over the entire range of experimental test co nditions. Additional comparisons are made with experimental heat tran sfer data, where the roughness geometries are both regular as well a s statistical. Using the developed analysis, heat transfer calculatio ns are presented for the second stage vane of a high pressure turbine at hypothetical engine conditions.

PREDIKSI FOREX MENGGUNAKAN MODEL NEURAL NETWORK

Directory of Open Access Journals (Sweden)

R. Hadapiningradja Kusumodestoni

2015-11-01

Full Text Available ABSTRAK Prediksi adalah salah satu teknik yang paling penting dalam menjalankan bisnis forex. Keputusan dalam memprediksi adalah sangatlah penting, karena dengan prediksi dapat membantu mengetahui nilai forex di waktu tertentu kedepan sehingga dapat mengurangi resiko kerugian. Tujuan dari penelitian ini dimaksudkan memprediksi bisnis fores menggunakan model neural network dengan data time series per 1 menit untuk mengetahui nilai akurasi prediksi sehingga dapat mengurangi resiko dalam menjalankan bisnis forex. Metode penelitian pada penelitian ini meliputi metode pengumpulan data kemudian dilanjutkan ke metode training, learning, testing menggunakan neural network. Setelah di evaluasi hasil penelitian ini menunjukan bahwa penerapan algoritma Neural Network mampu untuk memprediksi forex dengan tingkat akurasi prediksi 0.431 +/- 0.096 sehingga dengan prediksi ini dapat membantu mengurangi resiko dalam menjalankan bisnis forex. Kata kunci: prediksi, forex, neural network.

Artificial neural networks a practical course

CERN Document Server

da Silva, Ivan Nunes; Andrade Flauzino, Rogerio; Liboni, Luisa Helena Bartocci; dos Reis Alves, Silas Franco

2017-01-01

This book provides comprehensive coverage of neural networks, their evolution, their structure, the problems they can solve, and their applications. The first half of the book looks at theoretical investigations on artificial neural networks and addresses the key architectures that are capable of implementation in various application scenarios. The second half is designed specifically for the production of solutions using artificial neural networks to solve practical problems arising from different areas of knowledge. It also describes the various implementation details that were taken into account to achieve the reported results. These aspects contribute to the maturation and improvement of experimental techniques to specify the neural network architecture that is most appropriate for a particular application scope. The book is appropriate for students in graduate and upper undergraduate courses in addition to researchers and professionals.

Optical-Correlator Neural Network Based On Neocognitron

Science.gov (United States)

Chao, Tien-Hsin; Stoner, William W.

1994-01-01

Multichannel optical correlator implements shift-invariant, high-discrimination pattern-recognizing neural network based on paradigm of neocognitron. Selected as basic building block of this neural network because invariance under shifts is inherent advantage of Fourier optics included in optical correlators in general. Neocognitron is conceptual electronic neural-network model for recognition of visual patterns. Multilayer processing achieved by iteratively feeding back output of feature correlator to input spatial light modulator and updating Fourier filters. Neural network trained by use of characteristic features extracted from target images. Multichannel implementation enables parallel processing of large number of selected features.

Nonequilibrium landscape theory of neural networks

Science.gov (United States)

Yan, Han; Zhao, Lei; Hu, Liang; Wang, Xidi; Wang, Erkang; Wang, Jin

2013-01-01

The brain map project aims to map out the neuron connections of the human brain. Even with all of the wirings mapped out, the global and physical understandings of the function and behavior are still challenging. Hopfield quantified the learning and memory process of symmetrically connected neural networks globally through equilibrium energy. The energy basins of attractions represent memories, and the memory retrieval dynamics is determined by the energy gradient. However, the realistic neural networks are asymmetrically connected, and oscillations cannot emerge from symmetric neural networks. Here, we developed a nonequilibrium landscape–flux theory for realistic asymmetrically connected neural networks. We uncovered the underlying potential landscape and the associated Lyapunov function for quantifying the global stability and function. We found the dynamics and oscillations in human brains responsible for cognitive processes and physiological rhythm regulations are determined not only by the landscape gradient but also by the flux. We found that the flux is closely related to the degrees of the asymmetric connections in neural networks and is the origin of the neural oscillations. The neural oscillation landscape shows a closed-ring attractor topology. The landscape gradient attracts the network down to the ring. The flux is responsible for coherent oscillations on the ring. We suggest the flux may provide the driving force for associations among memories. We applied our theory to rapid-eye movement sleep cycle. We identified the key regulation factors for function through global sensitivity analysis of landscape topography against wirings, which are in good agreements with experiments. PMID:24145451

Nonequilibrium landscape theory of neural networks.

Science.gov (United States)

Yan, Han; Zhao, Lei; Hu, Liang; Wang, Xidi; Wang, Erkang; Wang, Jin

2013-11-05

The brain map project aims to map out the neuron connections of the human brain. Even with all of the wirings mapped out, the global and physical understandings of the function and behavior are still challenging. Hopfield quantified the learning and memory process of symmetrically connected neural networks globally through equilibrium energy. The energy basins of attractions represent memories, and the memory retrieval dynamics is determined by the energy gradient. However, the realistic neural networks are asymmetrically connected, and oscillations cannot emerge from symmetric neural networks. Here, we developed a nonequilibrium landscape-flux theory for realistic asymmetrically connected neural networks. We uncovered the underlying potential landscape and the associated Lyapunov function for quantifying the global stability and function. We found the dynamics and oscillations in human brains responsible for cognitive processes and physiological rhythm regulations are determined not only by the landscape gradient but also by the flux. We found that the flux is closely related to the degrees of the asymmetric connections in neural networks and is the origin of the neural oscillations. The neural oscillation landscape shows a closed-ring attractor topology. The landscape gradient attracts the network down to the ring. The flux is responsible for coherent oscillations on the ring. We suggest the flux may provide the driving force for associations among memories. We applied our theory to rapid-eye movement sleep cycle. We identified the key regulation factors for function through global sensitivity analysis of landscape topography against wirings, which are in good agreements with experiments.

Modeling of surface roughness effects on Stokes flow in circular pipes

Science.gov (United States)

Song, Siyuan; Yang, Xiaohu; Xin, Fengxian; Lu, Tian Jian

2018-02-01

Fluid flow and pressure drop across a channel are significantly influenced by surface roughness on a channel wall. The present study investigates the effects of periodically structured surface roughness upon flow field and pressure drop in a circular pipe at low Reynolds numbers. The periodic roughness considered exhibits sinusoidal, triangular, and rectangular morphologies, with the relative roughness (i.e., ratio of the amplitude of surface roughness to hydraulic diameter of the pipe) no more than 0.2. Based upon a revised perturbation theory, a theoretical model is developed to quantify the effect of roughness on fully developed Stokes flow in the pipe. The ratio of static flow resistivity and the ratio of the Darcy friction factor between rough and smooth pipes are expressed in four-order approximate formulations, which are validated against numerical simulation results. The relative roughness and the wave number are identified as the two key parameters affecting the static flow resistivity and the Darcy friction factor.

Multifractal scaling analysis of autopoisoning reactions over a rough surface

International Nuclear Information System (INIS)

Chaudhari, Ajay; Yan, Ching-Cher Sanders; Lee, S.-L.

2003-01-01

Decay type diffusion-limited reactions (DLR) over a rough surface generated by a random deposition model were performed. To study the effect of the decay profile on the reaction probability distribution (RPD), multifractal scaling analysis has been carried out. The dynamics of these autopoisoning reactions are controlled by the two parameters in the decay function, namely, the initial sticking probability (P ini ) of every site and the decay rate (m). The smaller the decay rate, the narrower is the range of α values in the α-f(α) multifractal spectrum. The results are compared with the earlier work of DLR over a surface of diffusion-limited aggregation (DLA). We also considered here the autopoisoning reactions over a smooth surface for comparing our results, which show clearly how the roughness affects the chemical reactions. The q-τ(q) multifractal curves for the smooth surface are linear whereas those for the rough surface are nonlinear. The range of α values in the case of a rough surface is wider than that of the smooth surface

Grey relational and neural network approach for multi-objective optimization in small scale resistance spot welding of titanium alloy

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.

Neutron spectrometry and dosimetry by means of Bonner spheres system and artificial neural networks applying robust design of artificial neural networks

Energy Technology Data Exchange (ETDEWEB)

Martinez B, M.R.; Ortiz R, J.M.; Vega C, H.R. [UAZ, Av. Ramon Lopez Velarde No. 801, 98000 Zacatecas (Mexico)

2006-07-01

An Artificial Neural Network has been designed, trained and tested to unfold neutron spectra and simultaneously to calculate equivalent doses. A set of 187 neutron spectra compiled by the International Atomic Energy Agency and 13 equivalent doses were used in the artificial neural network designed, trained and tested. In order to design the neural network was used the robust design of artificial neural networks methodology, which assures that the quality of the neural networks takes into account from the design stage. Unless previous works, here, for first time a group of neural networks were designed and trained to unfold 187 neutron spectra and at the same time to calculate 13 equivalent doses, starting from the count rates coming from the Bonner spheres system by using a systematic and experimental strategy. (Author)

Neutron spectrometry and dosimetry by means of Bonner spheres system and artificial neural networks applying robust design of artificial neural networks

International Nuclear Information System (INIS)

Martinez B, M.R.; Ortiz R, J.M.; Vega C, H.R.

2006-01-01

An Artificial Neural Network has been designed, trained and tested to unfold neutron spectra and simultaneously to calculate equivalent doses. A set of 187 neutron spectra compiled by the International Atomic Energy Agency and 13 equivalent doses were used in the artificial neural network designed, trained and tested. In order to design the neural network was used the robust design of artificial neural networks methodology, which assures that the quality of the neural networks takes into account from the design stage. Unless previous works, here, for first time a group of neural networks were designed and trained to unfold 187 neutron spectra and at the same time to calculate 13 equivalent doses, starting from the count rates coming from the Bonner spheres system by using a systematic and experimental strategy. (Author)

Neural networks within multi-core optic fibers.

Science.gov (United States)

Cohen, Eyal; Malka, Dror; Shemer, Amir; Shahmoon, Asaf; Zalevsky, Zeev; London, Michael

2016-07-07

Hardware implementation of artificial neural networks facilitates real-time parallel processing of massive data sets. Optical neural networks offer low-volume 3D connectivity together with large bandwidth and minimal heat production in contrast to electronic implementation. Here, we present a conceptual design for in-fiber optical neural networks. Neurons and synapses are realized as individual silica cores in a multi-core fiber. Optical signals are transferred transversely between cores by means of optical coupling. Pump driven amplification in erbium-doped cores mimics synaptic interactions. We simulated three-layered feed-forward neural networks and explored their capabilities. Simulations suggest that networks can differentiate between given inputs depending on specific configurations of amplification; this implies classification and learning capabilities. Finally, we tested experimentally our basic neuronal elements using fibers, couplers, and amplifiers, and demonstrated that this configuration implements a neuron-like function. Therefore, devices similar to our proposed multi-core fiber could potentially serve as building blocks for future large-scale small-volume optical artificial neural networks.

Surface roughness of composite resins subjected to hydrochloric acid.

Science.gov (United States)

Roque, Ana Carolina Cabral; Bohner, Lauren Oliveira Lima; de Godoi, Ana Paula Terossi; Colucci, Vivian; Corona, Silmara Aparecida Milori; Catirse, Alma Blásida Concepción Elizaur Benitez

2015-01-01

The purpose of this study was to determine the influence of hydrochloric acid on surface roughness of composite resins subjected to brushing. Sixty samples measuring 2 mm thick x 6 mm diameter were prepared and used as experimental units. The study presented a 3x2 factorial design, in which the factors were composite resin (n=20), at 3 levels: microhybrid composite (Z100), nanofilled composite (FiltekTM Supreme), nanohybrid composite (Ice), and acid challenge (n=10) at 2 levels: absence and presence. Acid challenge was performed by immersion of specimens in hydrochloric acid (pH 1.2) for 1 min, 4 times per day for 7 days. The specimens not subjected to acid challenge were stored in 15 mL of artificial saliva at 37 oC. Afterwards, all specimens were submitted to abrasive challenge by a brushing cycle performed with a 200 g weight at a speed of 356 rpm, totaling 17.8 cycles. Surface roughness measurements (Ra) were performed and analyzed by ANOVA and Tukey test (p≤0.05). Surface roughness values were higher in the presence (1.07±0.24) as compared with the absence of hydrochloric acid (0.72±0.04). Surface roughness values were higher for microhybrid (1.01±0.27) compared with nanofilled (0.68 ±0.09) and nanohybrid (0.48±0.15) composites when the specimens were not subjects to acid challenge. In the presence of hydrochloric acid, microhybrid (1.26±0.28) and nanofilled (1.18±0,30) composites presents higher surface roughness values compared with nanohybrid (0.77±0.15). The hydrochloric acid affected the surface roughness of composite resin subjected to brushing.

Intelligent neural network diagnostic system

International Nuclear Information System (INIS)

Mohamed, A.H.

2010-01-01

Recently, artificial neural network (ANN) has made a significant mark in the domain of diagnostic applications. Neural networks are used to implement complex non-linear mappings (functions) using simple elementary units interrelated through connections with adaptive weights. The performance of the ANN is mainly depending on their topology structure and weights. Some systems have been developed using genetic algorithm (GA) to optimize the topology of the ANN. But, they suffer from some limitations. They are : (1) The computation time requires for training the ANN several time reaching for the average weight required, (2) Slowness of GA for optimization process and (3) Fitness noise appeared in the optimization of ANN. This research suggests new issues to overcome these limitations for finding optimal neural network architectures to learn particular problems. This proposed methodology is used to develop a diagnostic neural network system. It has been applied for a 600 MW turbo-generator as a case of real complex systems. The proposed system has proved its significant performance compared to two common methods used in the diagnostic applications.

Cheap and fast measuring roughness on big surfaces with an imprint method

Science.gov (United States)

Schopf, C.; Liebl, J.; Rascher, R.

2017-10-01

Roughness, shape and structure of a surface offer information on the state, shape and surface characteristics of a component. Particularly the roughness of the surface dictates the subsequent polishing of the optical surface. The roughness is usually measured by a white light interferometer, which is limited by the size of the components. Using a moulding method of surfaces that are difficult to reach, an imprint is taken and analysed regarding to roughness and structure. This moulding compound method is successfully used in dental technology. In optical production, the moulding compound method is advantageous in roughness determination in inaccessible spots or on large components (astrological optics). The "replica method" has been around in metal analysis and processing. Film is used in order to take an impression of a surface. Then, it is analysed for structures. In optical production, compound moulding seems advantageous in roughness determination in inaccessible spots or on large components (astrological optics). In preliminary trials, different glass samples with different roughness levels were manufactured. Imprints were taken from these samples (based on DIN 54150 "Abdruckverfahren für die Oberflächenprüfung"). The objective of these feasibility tests was to determine the limits of this method (smallest roughness determinable / highest roughness). The roughness of the imprint was compared with the roughness of the glass samples. By comparing the results, the uncertainty of the measuring method was determined. The spectrum for the trials ranged from rough grind (0.8 μm rms), over finishing grind (0.6 μm rms) to polishing (0.1 μm rms).

Surface roughness reduction using spray-coated hydrogen silsesquioxane reflow

DEFF Research Database (Denmark)

Cech, Jiri; Pranov, Henrik; Kofod, Guggi

2013-01-01

Surface roughness or texture is the most visible property of any object, including injection molded plastic parts. Roughness of the injection molding (IM) tool cavity directly affects not only appearance and perception of quality, but often also the function of all manufactured plastic parts. So...... called “optically smooth” plastic surfaces is one example, where low roughness of a tool cavity is desirable. Such tool surfaces can be very expensive to fabricate using conventional means, such as abrasive diamond polishing or diamond turning. We present a novel process to coat machined metal parts...... are reduced 10 and 3 times respectively. We completed more than 10,000 injection molding cycles without detectable degradation of the HSQ coating. This result opens new possibilities for molding of affordable plastic parts with perfect surface finish....

Neural networks and applications tutorial

Science.gov (United States)

Guyon, I.

1991-09-01

The importance of neural networks has grown dramatically during this decade. While only a few years ago they were primarily of academic interest, now dozens of companies and many universities are investigating the potential use of these systems and products are beginning to appear. The idea of building a machine whose architecture is inspired by that of the brain has roots which go far back in history. Nowadays, technological advances of computers and the availability of custom integrated circuits, permit simulations of hundreds or even thousands of neurons. In conjunction, the growing interest in learning machines, non-linear dynamics and parallel computation spurred renewed attention in artificial neural networks. Many tentative applications have been proposed, including decision systems (associative memories, classifiers, data compressors and optimizers), or parametric models for signal processing purposes (system identification, automatic control, noise canceling, etc.). While they do not always outperform standard methods, neural network approaches are already used in some real world applications for pattern recognition and signal processing tasks. The tutorial is divided into six lectures, that where presented at the Third Graduate Summer Course on Computational Physics (September 3-7, 1990) on Parallel Architectures and Applications, organized by the European Physical Society: (1) Introduction: machine learning and biological computation. (2) Adaptive artificial neurons (perceptron, ADALINE, sigmoid units, etc.): learning rules and implementations. (3) Neural network systems: architectures, learning algorithms. (4) Applications: pattern recognition, signal processing, etc. (5) Elements of learning theory: how to build networks which generalize. (6) A case study: a neural network for on-line recognition of handwritten alphanumeric characters.

Friction of hydrogels with controlled surface roughness on solid flat substrates.

Science.gov (United States)

Yashima, Shintaro; Takase, Natsuko; Kurokawa, Takayuki; Gong, Jian Ping

2014-05-14

This study investigated the effect of hydrogel surface roughness on its sliding friction against a solid substrate having modestly adhesive interaction with hydrogels under small normal pressure in water. The friction test was performed between bulk polyacrylamide hydrogels of varied surface roughness and a smooth glass substrate by using a strain-controlled rheometer with parallel-plates geometry. At small pressure (normal strain 1.4-3.6%), the flat surface gel showed a poor reproducibility in friction. In contrast, the gels with a surface roughness of 1-10 μm order showed well reproducible friction behaviors and their frictional stress was larger than that of the flat surface hydrogel. Furthermore, the flat gel showed an elasto-hydrodynamic transition while the rough gels showed a monotonous decrease of friction with velocity. The difference between the flat surface and the rough surface diminished with the increase of the normal pressure. These phenomena are associated with the different contact behaviors of these soft hydrogels in liquid, as revealed by the observation of the interface using a confocal laser microscope.

Distribution network fault section identification and fault location using artificial neural network

DEFF Research Database (Denmark)

Dashtdar, Masoud; Dashti, Rahman; Shaker, Hamid Reza

2018-01-01

In this paper, a method for fault location in power distribution network is presented. The proposed method uses artificial neural network. In order to train the neural network, a series of specific characteristic are extracted from the recorded fault signals in relay. These characteristics...... components of the sequences as well as three-phase signals could be obtained using statistics to extract the hidden features inside them and present them separately to train the neural network. Also, since the obtained inputs for the training of the neural network strongly depend on the fault angle, fault...... resistance, and fault location, the training data should be selected such that these differences are properly presented so that the neural network does not face any issues for identification. Therefore, selecting the signal processing function, data spectrum and subsequently, statistical parameters...

To Enhance the Fire Resistance Performance of High-Speed Steel Roller Door with Water Film System

Directory of Open Access Journals (Sweden)

De-Hua Chung

2015-01-01

Full Text Available The structure of high-speed roller door with water film has improved in this study. The flameproof water film system is equipped with a water circulating device to reduce the water consumption of water film system. The water film is generated at the roller box of the high-speed roller door in this study. The heating test is done with the full-scale heating furnace. Both cases of the water film on unexposed surface and water film on exposed surface passed the fire resistance test based on ISO 834, proving that the high-speed roller door with water film system has 120A fire resistance period. The main findings indicate that the water film on exposed surface shows that as the amount of water film evaporated by high temperature inside the furnace must be greater than the evaporation capacity of water film on unexposed surface, the required water supply is 660 L more than the water film on unexposed surface.

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.

Neural Networks

Directory of Open Access Journals (Sweden)

Schwindling Jerome

2010-04-01

Full Text Available This course presents an overview of the concepts of the neural networks and their aplication in the framework of High energy physics analyses. After a brief introduction on the concept of neural networks, the concept is explained in the frame of neuro-biology, introducing the concept of multi-layer perceptron, learning and their use as data classifer. The concept is then presented in a second part using in more details the mathematical approach focussing on typical use cases faced in particle physics. Finally, the last part presents the best way to use such statistical tools in view of event classifers, putting the emphasis on the setup of the multi-layer perceptron. The full article (15 p. corresponding to this lecture is written in french and is provided in the proceedings of the book SOS 2008.

Altered Synchronizations among Neural Networks in Geriatric Depression.

Science.gov (United States)

Wang, Lihong; Chou, Ying-Hui; Potter, Guy G; Steffens, David C

2015-01-01

Although major depression has been considered as a manifestation of discoordinated activity between affective and cognitive neural networks, only a few studies have examined the relationships among neural networks directly. Because of the known disconnection theory, geriatric depression could be a useful model in studying the interactions among different networks. In the present study, using independent component analysis to identify intrinsically connected neural networks, we investigated the alterations in synchronizations among neural networks in geriatric depression to better understand the underlying neural mechanisms. Resting-state fMRI data was collected from thirty-two patients with geriatric depression and thirty-two age-matched never-depressed controls. We compared the resting-state activities between the two groups in the default-mode, central executive, attention, salience, and affective networks as well as correlations among these networks. The depression group showed stronger activity than the controls in an affective network, specifically within the orbitofrontal region. However, unlike the never-depressed controls, geriatric depression group lacked synchronized/antisynchronized activity between the affective network and the other networks. Those depressed patients with lower executive function has greater synchronization between the salience network with the executive and affective networks. Our results demonstrate the effectiveness of the between-network analyses in examining neural models for geriatric depression.

Temporal code in the vibrissal system-Part II: Roughness surface discrimination

Energy Technology Data Exchange (ETDEWEB)

Farfan, F D [Departamento de BioingenierIa, FACET, Universidad Nacional de Tucuman, INSIBIO - CONICET, CC 327, Postal Code CP 4000 (Argentina); AlbarracIn, A L [Catedra de Neurociencias, Facultad de Medicina, Universidad Nacional de Tucuman (Argentina); Felice, C J [Departamento de BioingenierIa, FACET, Universidad Nacional de Tucuman, INSIBIO - CONICET, CC 327, Postal Code CP 4000 (Argentina)

2007-11-15

Previous works have purposed hypotheses about the neural code of the tactile system in the rat. One of them is based on the physical characteristics of vibrissae, such as frequency of resonance; another is based on discharge patterns on the trigeminal ganglion. In this work, the purpose is to find a temporal code analyzing the afferent signals of two vibrissal nerves while vibrissae sweep surfaces of different roughness. Two levels of pressure were used between the vibrissa and the contact surface. We analyzed the afferent discharge of DELTA and GAMMA vibrissal nerves. The vibrissae movements were produced using electrical stimulation of the facial nerve. The afferent signals were analyzed using an event detection algorithm based on Continuous Wavelet Transform (CWT). The algorithm was able to detect events of different duration. The inter-event times detected were calculated for each situation and represented in box plot. This work allowed establishing the existence of a temporal code at peripheral level.

Temporal code in the vibrissal system-Part II: Roughness surface discrimination

International Nuclear Information System (INIS)

Farfan, F D; AlbarracIn, A L; Felice, C J

2007-01-01

Previous works have purposed hypotheses about the neural code of the tactile system in the rat. One of them is based on the physical characteristics of vibrissae, such as frequency of resonance; another is based on discharge patterns on the trigeminal ganglion. In this work, the purpose is to find a temporal code analyzing the afferent signals of two vibrissal nerves while vibrissae sweep surfaces of different roughness. Two levels of pressure were used between the vibrissa and the contact surface. We analyzed the afferent discharge of DELTA and GAMMA vibrissal nerves. The vibrissae movements were produced using electrical stimulation of the facial nerve. The afferent signals were analyzed using an event detection algorithm based on Continuous Wavelet Transform (CWT). The algorithm was able to detect events of different duration. The inter-event times detected were calculated for each situation and represented in box plot. This work allowed establishing the existence of a temporal code at peripheral level

Neural Networks for the Beginner.

Science.gov (United States)

Snyder, Robin M.

Motivated by the brain, neural networks are a right-brained approach to artificial intelligence that is used to recognize patterns based on previous training. In practice, one would not program an expert system to recognize a pattern and one would not train a neural network to make decisions from rules; but one could combine the best features of…

An investigation into the impact of magnesium stearate on powder feeding during roller compaction.

Science.gov (United States)

Dawes, Jason; Gamble, John F; Greenwood, Richard; Robbins, Phil; Tobyn, Mike

2012-01-01

A systematic evaluation on the effect of magnesium stearate on the transmission of a placebo formulation from the hopper to the rolls during screw fed roller compaction has been carried out. It is demonstrated that, for a system with two 'knurled' rollers, addition of 0.5% w/w magnesium stearate can lead to a significant increase in ribbon mass throughput, with a consequential increase in roll gap, compared to an unlubricated formulation (manufactured at equivalent process conditions). However, this effect is reduced if one of the rollers is smooth. Roller compaction of a lubricated formulation using two smooth rollers was found to be ineffective due to a reduction in friction at the powder/roll interface, i.e. powder was not drawn through the rollers leading to a blockage in the feeding system. An increase in ribbon mass throughput could also be achieved if the equipment surfaces were pre-lubricated. However this increase was found to be temporary suggesting that the residual magnesium stearate layer was removed from the equipment surfaces. Powder sticking to the equipment surfaces, which is common during pharmaceutical manufacturing, was prevented if magnesium stearate was present either in the blend, or at the roll surface. It is further demonstrated that the influence of the hopper stirrer, which is primarily used to prevent bridge formation in the hopper and help draw powder more evenly into the auger chamber, can lead to further mixing of the formulation, and could therefore affect a change in the lubricity of the carefully blended input material.

Determination of forest road surface roughness by Kinect depth imaging

Directory of Open Access Journals (Sweden)

Francesco Marinello

2017-12-01

Full Text Available Roughness is a dynamic property of the gravel road surface that affects safety, ride comfort as well as vehicle tyre life and maintenance costs. A rapid survey of gravel road condition is fundamental for an effective maintenance planning and definition of the intervention priorities.Different non-contact techniques such as laser scanning, ultrasonic sensors and photogrammetry have recently been proposed to reconstruct three-dimensional topography of road surface and allow extraction of roughness metrics. The application of Microsoft Kinect™ depth camera is proposed and discussed here for collection of 3D data sets from gravel roads, to be implemented in order to allow quantification of surface roughness.The objectives are to: i verify the applicability of the Kinect sensor for characterization of different forest roads, ii identify the appropriateness and potential of different roughness parameters and iii analyse the correlation with vibrations recoded by 3-axis accelerometers installed on different vehicles. The test took advantage of the implementation of the Kinect depth camera for surface roughness determination of 4 different forest gravel roads and one well-maintained asphalt road as reference. Different vehicles (mountain bike, off-road motorcycle, ATV vehicle, 4WD car and compact crossover were included in the experiment in order to verify the vibration intensity when travelling on different road surface conditions. Correlations between the extracted roughness parameters and vibration levels of the tested vehicles were then verified. Coefficients of determination of between 0.76 and 0.97 were detected between average surface roughness and standard deviation of relative accelerations, with higher values in the case of lighter vehicles.

Neural network-based model reference adaptive control system.

Science.gov (United States)

Patino, H D; Liu, D

2000-01-01

In this paper, an approach to model reference adaptive control based on neural networks is proposed and analyzed for a class of first-order continuous-time nonlinear dynamical systems. The controller structure can employ either a radial basis function network or a feedforward neural network to compensate adaptively the nonlinearities in the plant. A stable controller-parameter adjustment mechanism, which is determined using the Lyapunov theory, is constructed using a sigma-modification-type updating law. The evaluation of control error in terms of the neural network learning error is performed. That is, the control error converges asymptotically to a neighborhood of zero, whose size is evaluated and depends on the approximation error of the neural network. In the design and analysis of neural network-based control systems, it is important to take into account the neural network learning error and its influence on the control error of the plant. Simulation results showing the feasibility and performance of the proposed approach are given.

Mass reconstruction with a neural network

International Nuclear Information System (INIS)

Loennblad, L.; Peterson, C.; Roegnvaldsson, T.

1992-01-01

A feed-forward neural network method is developed for reconstructing the invariant mass of hadronic jets appearing in a calorimeter. The approach is illustrated in W→qanti q, where W-bosons are produced in panti p reactions at SPS collider energies. The neural network method yields results that are superior to conventional methods. This neural network application differs from the classification ones in the sense that an analog number (the mass) is computed by the network, rather than a binary decision being made. As a by-product our application clearly demonstrates the need for using 'intelligent' variables in instances when the amount of training instances is limited. (orig.)

Inversion of a lateral log using neural networks

International Nuclear Information System (INIS)

Garcia, G.; Whitman, W.W.

1992-01-01

In this paper a technique using neural networks is demonstrated for the inversion of a lateral log. The lateral log is simulated by a finite difference method which in turn is used as an input to a backpropagation neural network. An initial guess earth model is generated from the neural network, which is then input to a Marquardt inversion. The neural network reacts to gross and subtle data features in actual logs and produces a response inferred from the knowledge stored in the network during a training process. The neural network inversion of lateral logs is tested on synthetic and field data. Tests using field data resulted in a final earth model whose simulated lateral is in good agreement with the actual log data

Surface roughness induced electron mobility degradation in InAs nanowires

International Nuclear Information System (INIS)

Wang Fengyun; Yip, Sen Po; Han, Ning; Fok, KitWa; Lin, Hao; Hou, Jared J; Dong, Guofa; Hung, Tak Fu; Chan, K S; Ho, Johnny C

2013-01-01

In this work, we present a study of the surface roughness dependent electron mobility in InAs nanowires grown by the nickel-catalyzed chemical vapor deposition method. These nanowires have good crystallinity, well-controlled surface morphology without any surface coating or tapering and an excellent peak field-effect mobility up to 15 000 cm 2 V −1 s −1 when configured into back-gated field-effect nanowire transistors. Detailed electrical characterizations reveal that the electron mobility degrades monotonically with increasing surface roughness and diameter scaling, while low-temperature measurements further decouple the effects of surface/interface traps and phonon scattering, highlighting the dominant impact of surface roughness scattering on the electron mobility for miniaturized and surface disordered nanowires. All these factors suggest that careful consideration of nanowire geometries and surface condition is required for designing devices with optimal performance. (paper)

Financial time series prediction using spiking neural networks.

Science.gov (United States)

Reid, David; Hussain, Abir Jaafar; Tawfik, Hissam

2014-01-01

In this paper a novel application of a particular type of spiking neural network, a Polychronous Spiking Network, was used for financial time series prediction. It is argued that the inherent temporal capabilities of this type of network are suited to non-stationary data such as this. The performance of the spiking neural network was benchmarked against three systems: two "traditional", rate-encoded, neural networks; a Multi-Layer Perceptron neural network and a Dynamic Ridge Polynomial neural network, and a standard Linear Predictor Coefficients model. For this comparison three non-stationary and noisy time series were used: IBM stock data; US/Euro exchange rate data, and the price of Brent crude oil. The experiments demonstrated favourable prediction results for the Spiking Neural Network in terms of Annualised Return and prediction error for 5-Step ahead predictions. These results were also supported by other relevant metrics such as Maximum Drawdown and Signal-To-Noise ratio. This work demonstrated the applicability of the Polychronous Spiking Network to financial data forecasting and this in turn indicates the potential of using such networks over traditional systems in difficult to manage non-stationary environments.

Neural Networks in Mobile Robot Motion

Directory of Open Access Journals (Sweden)

Danica Janglová

2004-03-01

Full Text Available This paper deals with a path planning and intelligent control of an autonomous robot which should move safely in partially structured environment. This environment may involve any number of obstacles of arbitrary shape and size; some of them are allowed to move. We describe our approach to solving the motion-planning problem in mobile robot control using neural networks-based technique. Our method of the construction of a collision-free path for moving robot among obstacles is based on two neural networks. The first neural network is used to determine the “free” space using ultrasound range finder data. The second neural network “finds” a safe direction for the next robot section of the path in the workspace while avoiding the nearest obstacles. Simulation examples of generated path with proposed techniques will be presented.

International Conference on Artificial Neural Networks (ICANN)

CERN Document Server

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...

The VHCF experimental investigation of FV520B-I with surface roughness Ry

Science.gov (United States)

Wang, J. L.; Zhang, Y. L.; Ding, M. C.; Zhao, Q. C.

2018-05-01

Different surface roughness type (Ra and Ry) has different effect on the VHCF failure and life. Ra is widely employed as the quantitative expression of the surface roughness, but there are few fatigue failure mechanism analysis and experimental study under surface roughness Ry. The VHCF experiment is conducted out using the specimen with different surface roughness values. The surface roughness Ry is employed as the major research object to investigate the relationship and distribution tendency between the Ry, fatigue life and the distance between internal inclusion and surface, and a new VHCF failure character is proposed.

Radiation properties modeling for plasma-sprayed-alumina-coated rough surfaces for spacecrafts

International Nuclear Information System (INIS)

Li, R.M.; Joshi, Sunil C.; Ng, H.W.

2006-01-01

Spacecraft thermal control materials (TCMs) play a vital role in the entire service life of a spacecraft . Most of the conventional TCMs degrade in the harmful space environment . In the previous study, plasma sprayed alumina (PSA) coating was established as a new and better TCM for spacecrafts, in view of its stability and reliability compared to the traditional TCMs . During the investigation, the surface roughness of PSA was found important, because the roughness affects the radiative heat exchange between the surface and its surroundings. Parameters such as root-mean-square roughness cannot properly evaluate surface roughness effects on radiative properties of opaque surfaces . Some models have been developed earlier to predict the effects, such as Davies' model , Tang and Buckius's statistical geometric optics model . However, they are valid only in their own specific situations. In this paper, an energy absorption geometry model was developed and applied to investigate the roughness effects with the help of 2D surface profile of PSA coated substrate scanned at micron level. This model predicts effective normal solar absorptance (α ne ) and effective hemispherical infrared emittance (ε he ) of a rough PSA surface. These values, if used in the heat transfer analysis of an equivalent, smooth and optically flat surface, lead to the prediction of the same rate of heat exchange and temperature as that of for the rough PSA surface. The model was validated through comparison between a smooth and a rough PSA coated surfaces. Even though not tested for other types of materials, the model formulation is generic and can be used to incorporate the rough surface effects for other types of thermal coatings, provided the baseline values of normal solar absorptance (α n ) and hemispherical infrared emittance (ε h ) are available for a generic surface of the same material

Computer simulation of RBS spectra from samples with surface roughness

Energy Technology Data Exchange (ETDEWEB)

Malinský, P., E-mail: malinsky@ujf.cas.cz [Nuclear Physics Institute of the Academy of Sciences of the Czech Republic, v. v. i., 250 68 Rez (Czech Republic); Department of Physics, Faculty of Science, J. E. Purkinje University, Ceske mladeze 8, 400 96 Usti nad Labem (Czech Republic); Hnatowicz, V., E-mail: hnatowicz@ujf.cas.cz [Nuclear Physics Institute of the Academy of Sciences of the Czech Republic, v. v. i., 250 68 Rez (Czech Republic); Macková, A., E-mail: mackova@ujf.cas.cz [Nuclear Physics Institute of the Academy of Sciences of the Czech Republic, v. v. i., 250 68 Rez (Czech Republic); Department of Physics, Faculty of Science, J. E. Purkinje University, Ceske mladeze 8, 400 96 Usti nad Labem (Czech Republic)

2016-03-15

A fast code for the simulation of common RBS spectra including surface roughness effects has been written and tested on virtual samples comprising either a rough layer deposited on a smooth substrate or smooth layer deposited on a rough substrate and simulated at different geometries. The sample surface or interface relief has been described by a polyline and the simulated RBS spectrum has been obtained as the sum of many particular spectra from randomly chosen particle trajectories. The code includes several procedures generating virtual samples with random and regular (periodical) roughness. The shape of the RBS spectra has been found to change strongly with increasing sample roughness and an increasing angle of the incoming ion beam.

Self-Mobilization Using a Foam Roller Versus a Roller Massager: Which Is More Effective for Increasing Hamstrings Flexibility?

Science.gov (United States)

DeBruyne, Danielle M; Dewhurst, Marina M; Fischer, Katelyn M; Wojtanowski, Michael S; Durall, Chris

2017-01-01

Clinical Scenario: Increasing the length of the muscle-tendon unit may prevent musculotendinous injury. Various methods have been proposed to increase muscle-tendon flexibility, including self-mobilization using foam rollers or roller massagers, although the effectiveness of these devices is uncertain. This review was conducted to determine if the use of foam rollers or roller massagers to improve hamstrings flexibility is supported by moderate- to high-quality evidence. Are foam rollers or roller massagers effective for increasing hamstrings flexibility in asymptomatic physically active adults? Summary of Key Findings: The literature was searched for studies on the effects of using foam rollers or roller massagers to increase hamstrings flexibility in asymptomatic physically active adults. Four randomized controlled trials were included; 2 studies provided level 2 or 3 evidence regarding foam rollers and 2 studies provided level 2 or 3 evidence regarding roller massagers. Both roller-massager studies reported increases in hamstrings flexibility after treatment. Data from the foam-roller studies did not demonstrate a statistically significant increase in hamstrings flexibility, but 1 study did demonstrate a strong effect size. Clinical Bottom Line: The reviewed moderate-quality studies support the use of roller massagers but provide limited evidence on the effectiveness of foam rolling to increase hamstrings flexibility in asymptomatic physically active adults. Flexibility gains may be improved by a longer duration of treatment and administration by a trained therapist. Gains appear to decline rapidly postrolling. Neither device has been shown to confer a therapeutic benefit superior to static stretching, and the effectiveness of these devices for preventing injury is unknown. Strength of Recommendation: Grade B evidence supports the use of roller massagers to increase hamstrings flexibility in asymptomatic physically active adults.

Turbulent lubrication theory considering the surface roughness effects, 2

International Nuclear Information System (INIS)

Hashimoto, Hiromu; Wada, Sanae; Kobayashi, Toshinobu.

1990-01-01

This second paper describes an application of the generalized turbulent lubrication theory considering the surface roughness effects, which is developed in the previous paper, to the finite-width journal bearings. In the numerical analysis, the nonlinear equations for the modified turbulence coefficients are simplified to save a computation time within a satisfactory accuracy under the assumption that the shear flow is superior to the pressure flow in the turbulent lubrication films. The numerical results of pressure distribution, Sommerfeld number, attitude angle, friction coefficient and flow rate for the Reynolds number of Re=2000, 5000 and 10000 are indicated in graphic form for various values of relative roughness, and the effects of surface roughness on these static performance characteristics are discussed. Moreover, the eccentricity ratio and attitude angle of the journal bearings with homogeneous rough surface are obtained experimentally for a wide range of Sommerfeld number, and the experimental results are compared with theoretical results. (author)

Interpretable neural networks with BP-SOM

NARCIS (Netherlands)

Weijters, A.J.M.M.; Bosch, van den A.P.J.; Pobil, del A.P.; Mira, J.; Ali, M.

1998-01-01

Artificial Neural Networks (ANNS) are used successfully in industry and commerce. This is not surprising since neural networks are especially competitive for complex tasks for which insufficient domain-specific knowledge is available. However, interpretation of models induced by ANNS is often

Adaptive nonlinear control using input normalized neural networks

International Nuclear Information System (INIS)

Leeghim, Henzeh; Seo, In Ho; Bang, Hyo Choong

2008-01-01

An adaptive feedback linearization technique combined with the neural network is addressed to control uncertain nonlinear systems. The neural network-based adaptive control theory has been widely studied. However, the stability analysis of the closed-loop system with the neural network is rather complicated and difficult to understand, and sometimes unnecessary assumptions are involved. As a result, unnecessary assumptions for stability analysis are avoided by using the neural network with input normalization technique. The ultimate boundedness of the tracking error is simply proved by the Lyapunov stability theory. A new simple update law as an adaptive nonlinear control is derived by the simplification of the input normalized neural network assuming the variation of the uncertain term is sufficiently small

Surface roughness retrieval by inversion of the Hapke model: A multiscale approach

Science.gov (United States)

Labarre, S.; Ferrari, C.; Jacquemoud, S.

2017-07-01

Surface roughness is a key property of soils that controls many surface processes and influences the scattering of incident electromagnetic waves at a wide range of scales. Hapke (2012b) designed a photometric model providing an approximate analytical solution of the Bidirectional Reflectance Distribution Function (BRDF) of a particulate medium: he introduced the effect of surface roughness as a correction factor of the BRDF of a smooth surface. This photometric roughness is defined as the mean slope angle of the facets composing the surface, integrated over all scales from the grain size to the local topography. Yet its physical meaning is still a question at issue, as the scale at which it occurs is not clearly defined. This work aims at better understanding the relative influence of roughness scales on soil BRDF and to test the ability of the Hapke model to retrieve a roughness that depicts effectively the ground truth. We apply a wavelet transform on millimeter digital terrain models (DTM) acquired over volcanic terrains. This method allows splitting the frequency band of a signal in several sub-bands, each corresponding to a spatial scale. We demonstrate that sub-centimeter surface features dominate both the integrated roughness and the BRDF shape. We investigate the suitability of the Hapke model for surface roughness retrieval by inversion on optical data. A global sensitivity analysis of the model shows that soil BRDF is very sensitive to surface roughness, nearly as much as the single scattering albedo according to the phase angle, but also that these two parameters are strongly correlated. Based on these results, a simplified two-parameter model depending on surface albedo and roughness is proposed. Inversion of this model on BRDF data simulated by a ray-tracing code over natural targets shows a good estimation of surface roughness when the assumptions of the model are verified, with a priori knowledge on surface albedo.

Qualitative internal surface roughness classification using acoustic emission

International Nuclear Information System (INIS)

Mohd Hafizi Zohari; Mohd Hanif Saad

2009-04-01

This paper describes a novel new nondestructive method of qualitative internal surface roughness classification for pipes utilizing Acoustic Emission (AE) signal. Two different flowrate are introduced in a pipe obstructed using normally available components (e.g.: valve). The AE signal at suitable location from the obstruction are obtained and the peak amplitudes, RMS amplitude and energy of the AE signal are obtained. A dimensionless number, the Bangi Number, AB, is then calculated as a ratio of the AE parameters (peak amplitude, RMS amplitude or energy) in low flowrate measurement compared to the AE parameters in high flowrate measurement. It was observed that the Bangi Number, AB obtained can then be used to successfully discriminate between rough and smooth internal surface roughness. (author)

Runoff Modelling in Urban Storm Drainage by Neural Networks

DEFF Research Database (Denmark)

Rasmussen, Michael R.; Brorsen, Michael; Schaarup-Jensen, Kjeld

1995-01-01

A neural network is used to simulate folw and water levels in a sewer system. The calibration of th neural network is based on a few measured events and the network is validated against measureed events as well as flow simulated with the MOUSE model (Lindberg and Joergensen, 1986). The neural...... network is used to compute flow or water level at selected points in the sewer system, and to forecast the flow from a small residential area. The main advantages of the neural network are the build-in self calibration procedure and high speed performance, but the neural network cannot be used to extract...... knowledge of the runoff process. The neural network was found to simulate 150 times faster than e.g. the MOUSE model....

Neural networks in economic modelling : An empirical study

NARCIS (Netherlands)

Verkooijen, W.J.H.

1996-01-01

This dissertation addresses the statistical aspects of neural networks and their usability for solving problems in economics and finance. Neural networks are discussed in a framework of modelling which is generally accepted in econometrics. Within this framework a neural network is regarded as a

Surface roughness characterization of cast components using 3D optical methods

DEFF Research Database (Denmark)

Nwaogu, Ugochukwu Chibuzoh; Tiedje, Niels Skat; Hansen, Hans Nørgaard

scanning probe image processor (SPIP) software and the results of the surface roughness parameters obtained were subjected to statistical analyses. The bearing area ratio was introduced and applied to the surface roughness analysis. From the results, the surface quality of the standard comparators...... is successfully characterised and it was established that the areal parameters are more informative for sand cast components. The roughness values of the standard visual comparators can serve as a control for the cast components and for order specifications in the foundry industry. A series of iron castings were...... made in green sand moulds and the surface roughness parameter (Sa) values were compared with those of the standards. Sa parameter suffices for the evaluation of casting surface texture. The S series comparators showed a better description of the surface of castings after shot blasting than the A series...

Spin Hall effect by surface roughness

KAUST Repository

Zhou, Lingjun; Grigoryan, Vahram L.; Maekawa, Sadamichi; Wang, Xuhui; Xiao, Jiang

2015-01-01

induced by surface roughness subscribes only to the side-jump contribution but not the skew scattering. The paradigm proposed in this paper provides the second, not if only, alternative to generate a sizable spin Hall effect.

Growth kinetics of borided layers: Artificial neural network and least square approaches

Science.gov (United States)

Campos, I.; Islas, M.; Ramírez, G.; VillaVelázquez, C.; Mota, C.

2007-05-01

The present study evaluates the growth kinetics of the boride layer Fe 2B in AISI 1045 steel, by means of neural networks and the least square techniques. The Fe 2B phase was formed at the material surface using the paste boriding process. The surface boron potential was modified considering different boron paste thicknesses, with exposure times of 2, 4 and 6 h, and treatment temperatures of 1193, 1223 and 1273 K. The neural network and the least square models were set by the layer thickness of Fe 2B phase, and assuming that the growth of the boride layer follows a parabolic law. The reliability of the techniques used is compared with a set of experiments at a temperature of 1223 K with 5 h of treatment time and boron potentials of 2, 3, 4 and 5 mm. The results of the Fe 2B layer thicknesses show a mean error of 5.31% for the neural network and 3.42% for the least square method.

Elastic–plastic adhesive contact of non-Gaussian rough surfaces

Indian Academy of Sciences (India)

Adhesion; asymmetric roughness; elastic–plastic contact; non-Gaussian rough surfaces. ... model of contact deformation that is based on accurate Finite Element Analysis (FEA) of an elastic–plastic single asperity contact. ... Sadhana | News.

Investigation of surface roughness on etched glass surfaces

International Nuclear Information System (INIS)

Papa, Z.; Budai, J.; Farkas, B.; Toth, Z.

2011-01-01

Roughening the surface of solar cells is a common practice within the photovoltaic industry as it reduces reflectance, and thus enhances the performance of devices. In this work the relationship between reflectance characterized by the haze parameter, surface roughness and optical properties was investigated. To achieve this goal, model samples were prepared by hydrofluoric acid etching of glass for various times and measured by optical microscopy, spectroscopic ellipsometry, scanning electron microscopy, and atomic force microscopy. Our investigation showed that the surface reflectance was decreased not only by the roughening of the surface but also by the modification of the depth profile and lowering of the refractive index of the surface domain of the samples.

Influence of neural adaptation on dynamics and equilibrium state of neural activities in a ring neural network

Science.gov (United States)

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.

Artificial neural network intelligent method for prediction

Science.gov (United States)

Trifonov, Roumen; Yoshinov, Radoslav; Pavlova, Galya; Tsochev, Georgi

2017-09-01

Accounting and financial classification and prediction problems are high challenge and researchers use different methods to solve them. Methods and instruments for short time prediction of financial operations using artificial neural network are considered. The methods, used for prediction of financial data as well as the developed forecasting system with neural network are described in the paper. The architecture of a neural network used four different technical indicators, which are based on the raw data and the current day of the week is presented. The network developed is used for forecasting movement of stock prices one day ahead and consists of an input layer, one hidden layer and an output layer. The training method is algorithm with back propagation of the error. The main advantage of the developed system is self-determination of the optimal topology of neural network, due to which it becomes flexible and more precise The proposed system with neural network is universal and can be applied to various financial instruments using only basic technical indicators as input data.

Surface roughness of orthodontic band cements with different compositions

Directory of Open Access Journals (Sweden)

Françoise Hélène van de Sande

2011-06-01

Full Text Available OBJECTIVES: The present study evaluated comparatively the surface roughness of four orthodontic band cements after storage in various solutions. MATERIAL AND METHODS: Eight standardized cylinders were made from 4 materials: zinc phosphate cement (ZP, compomer (C, resin-modified glass ionomer cement (RMGIC and resin cement (RC. Specimens were stored for 24 h in deionized water and immersed in saline (pH 7.0 or 0.1 M lactic acid solution (pH 4.0 for 15 days. Surface roughness readings were taken with a profilometer (Surfcorder SE1200 before and after the storage period. Data were analyzed by two-way ANOVA and Tukey's test (comparison among cements and storage solutions or paired t-test (comparison before and after the storage period at 5% significance level. RESULTS: The values for average surface roughness were statistically different (pRMGIC>C>R (p0.05. Compared to the current threshold (0.2 µm related to biofilm accumulation, both RC and C remained below the threshold, even after acidic challenge by immersion in lactic acid solution. CONCLUSIONS: Storage time and immersion in lactic acid solution increased the surface roughness of the majority of the tested cements. RC presented the smoothest surface and it was not influenced by storage conditions.

A fuzzy neural network for sensor signal estimation

International Nuclear Information System (INIS)

Na, Man Gyun

2000-01-01

In this work, a fuzzy neural network is used to estimate the relevant sensor signal using other sensor signals. Noise components in input signals into the fuzzy neural network are removed through the wavelet denoising technique. Principal component analysis (PCA) is used to reduce the dimension of an input space without losing a significant amount of information. A lower dimensional input space will also usually reduce the time necessary to train a fuzzy-neural network. Also, the principal component analysis makes easy the selection of the input signals into the fuzzy neural network. The fuzzy neural network parameters are optimized by two learning methods. A genetic algorithm is used to optimize the antecedent parameters of the fuzzy neural network and a least-squares algorithm is used to solve the consequent parameters. The proposed algorithm was verified through the application to the pressurizer water level and the hot-leg flowrate measurements in pressurized water reactors

Multistability in bidirectional associative memory neural networks

International Nuclear Information System (INIS)

Huang Gan; Cao Jinde

2008-01-01

In this Letter, the multistability issue is studied for Bidirectional Associative Memory (BAM) neural networks. Based on the existence and stability analysis of the neural networks with or without delay, it is found that the 2n-dimensional networks can have 3 n equilibria and 2 n equilibria of them are locally exponentially stable, where each layer of the BAM network has n neurons. Furthermore, the results has been extended to (n+m)-dimensional BAM neural networks, where there are n and m neurons on the two layers respectively. Finally, two numerical examples are presented to illustrate the validity of our results

Multistability in bidirectional associative memory neural networks

Science.gov (United States)

Huang, Gan; Cao, Jinde

2008-04-01

In this Letter, the multistability issue is studied for Bidirectional Associative Memory (BAM) neural networks. Based on the existence and stability analysis of the neural networks with or without delay, it is found that the 2 n-dimensional networks can have 3 equilibria and 2 equilibria of them are locally exponentially stable, where each layer of the BAM network has n neurons. Furthermore, the results has been extended to (n+m)-dimensional BAM neural networks, where there are n and m neurons on the two layers respectively. Finally, two numerical examples are presented to illustrate the validity of our results.

Machine Learning Topological Invariants with Neural Networks

Science.gov (United States)

Zhang, Pengfei; Shen, Huitao; Zhai, Hui

2018-02-01

In this Letter we supervisedly train neural networks to distinguish different topological phases in the context of topological band insulators. After training with Hamiltonians of one-dimensional insulators with chiral symmetry, the neural network can predict their topological winding numbers with nearly 100% accuracy, even for Hamiltonians with larger winding numbers that are not included in the training data. These results show a remarkable success that the neural network can capture the global and nonlinear topological features of quantum phases from local inputs. By opening up the neural network, we confirm that the network does learn the discrete version of the winding number formula. We also make a couple of remarks regarding the role of the symmetry and the opposite effect of regularization techniques when applying machine learning to physical systems.

Investigation and modelling of rubber stationary friction on rough surfaces

International Nuclear Information System (INIS)

Le Gal, A; Klueppel, M

2008-01-01

This paper presents novel aspects regarding the physically motivated modelling of rubber stationary sliding friction on rough surfaces. The description of dynamic contact is treated within the framework of a generalized Greenwood-Williamson theory for rigid/soft frictional pairings. Due to the self-affinity of rough surfaces, both hysteresis and adhesion friction components arise from a multi-scale excitation of surface roughness. Beside a complete analytical formulation of contact parameters, the morphology of macrotexture is considered via the introduction of a second scaling range at large length scales which mostly contribute to hysteresis friction. Moreover, adhesion friction is related to the real area of contact combined with the kinetics of interfacial peeling effects. Friction experiments carried out with different rubbers on rough granite and asphalt point out the relevance of hysteresis and adhesion friction concepts on rough surfaces. The two scaling ranges approach significantly improves the description of wet and dry friction behaviour within the range of low sliding velocity. In addition, material and surface effects are predicted and understood on a physical basis. The applicability of such modelling is of high interest for materials developers and road constructors regarding the prediction of wet grip performance of tyres on road tracks

Investigation and modelling of rubber stationary friction on rough surfaces

Energy Technology Data Exchange (ETDEWEB)

Le Gal, A; Klueppel, M [Deutsches Institut fuer Kautschuktechnologie, Eupener Strasse 33, D-30519 Hannover (Germany)

2008-01-09

This paper presents novel aspects regarding the physically motivated modelling of rubber stationary sliding friction on rough surfaces. The description of dynamic contact is treated within the framework of a generalized Greenwood-Williamson theory for rigid/soft frictional pairings. Due to the self-affinity of rough surfaces, both hysteresis and adhesion friction components arise from a multi-scale excitation of surface roughness. Beside a complete analytical formulation of contact parameters, the morphology of macrotexture is considered via the introduction of a second scaling range at large length scales which mostly contribute to hysteresis friction. Moreover, adhesion friction is related to the real area of contact combined with the kinetics of interfacial peeling effects. Friction experiments carried out with different rubbers on rough granite and asphalt point out the relevance of hysteresis and adhesion friction concepts on rough surfaces. The two scaling ranges approach significantly improves the description of wet and dry friction behaviour within the range of low sliding velocity. In addition, material and surface effects are predicted and understood on a physical basis. The applicability of such modelling is of high interest for materials developers and road constructors regarding the prediction of wet grip performance of tyres on road tracks.

Time series prediction with simple recurrent neural networks ...

African Journals Online (AJOL)

A hybrid of the two called Elman-Jordan (or Multi-recurrent) neural network is also being used. In this study, we evaluated the performance of these neural networks on three established bench mark time series prediction problems. Results from the experiments showed that Jordan neural network performed significantly ...

Quantum neural networks: Current status and prospects for development

Science.gov (United States)

Altaisky, M. V.; Kaputkina, N. E.; Krylov, V. A.

2014-11-01

The idea of quantum artificial neural networks, first formulated in [34], unites the artificial neural network concept with the quantum computation paradigm. Quantum artificial neural networks were first systematically considered in the PhD thesis by T. Menneer (1998). Based on the works of Menneer and Narayanan [42, 43], Kouda, Matsui, and Nishimura [35, 36], Altaisky [2, 68], Zhou [67], and others, quantum-inspired learning algorithms for neural networks were developed, and are now used in various training programs and computer games [29, 30]. The first practically realizable scaled hardware-implemented model of the quantum artificial neural network is obtained by D-Wave Systems, Inc. [33]. It is a quantum Hopfield network implemented on the basis of superconducting quantum interference devices (SQUIDs). In this work we analyze possibilities and underlying principles of an alternative way to implement quantum neural networks on the basis of quantum dots. A possibility of using quantum neural network algorithms in automated control systems, associative memory devices, and in modeling biological and social networks is examined.

Neural network modeling for near wall turbulent flow

International Nuclear Information System (INIS)

Milano, Michele; Koumoutsakos, Petros

2002-01-01

A neural network methodology is developed in order to reconstruct the near wall field in a turbulent flow by exploiting flow fields provided by direct numerical simulations. The results obtained from the neural network methodology are compared with the results obtained from prediction and reconstruction using proper orthogonal decomposition (POD). Using the property that the POD is equivalent to a specific linear neural network, a nonlinear neural network extension is presented. It is shown that for a relatively small additional computational cost nonlinear neural networks provide us with improved reconstruction and prediction capabilities for the near wall velocity fields. Based on these results advantages and drawbacks of both approaches are discussed with an outlook toward the development of near wall models for turbulence modeling and control

Symmetric and asymmetric capillary bridges between a rough surface and a parallel surface.

Science.gov (United States)

Wang, Yongxin; Michielsen, Stephen; Lee, Hoon Joo

2013-09-03

Although the formation of a capillary bridge between two parallel surfaces has been extensively studied, the majority of research has described only symmetric capillary bridges between two smooth surfaces. In this work, an instrument was built to form a capillary bridge by squeezing a liquid drop on one surface with another surface. An analytical solution that describes the shape of symmetric capillary bridges joining two smooth surfaces has been extended to bridges that are asymmetric about the midplane and to rough surfaces. The solution, given by elliptical integrals of the first and second kind, is consistent with a constant Laplace pressure over the entire surface and has been verified for water, Kaydol, and dodecane drops forming symmetric and asymmetric bridges between parallel smooth surfaces. This solution has been applied to asymmetric capillary bridges between a smooth surface and a rough fabric surface as well as symmetric bridges between two rough surfaces. These solutions have been experimentally verified, and good agreement has been found between predicted and experimental profiles for small drops where the effect of gravity is negligible. Finally, a protocol for determining the profile from the volume and height of the capillary bridge has been developed and experimentally verified.

Application of neural networks in CRM systems

Directory of Open Access Journals (Sweden)

Bojanowska Agnieszka

2017-01-01

Full Text Available The central aim of this study is to investigate how to apply artificial neural networks in Customer Relationship Management (CRM. The paper presents several business applications of neural networks in software systems designed to aid CRM, e.g. in deciding on the profitability of building a relationship with a given customer. Furthermore, a framework for a neural-network based CRM software tool is developed. Building beneficial relationships with customers is generating considerable interest among various businesses, and is often mentioned as one of the crucial objectives of enterprises, next to their key aim: to bring satisfactory profit. There is a growing tendency among businesses to invest in CRM systems, which together with an organisational culture of a company aid managing customer relationships. It is the sheer amount of gathered data as well as the need for constant updating and analysis of this breadth of information that may imply the suitability of neural networks for the application in question. Neural networks exhibit considerably higher computational capabilities than sequential calculations because the solution to a problem is obtained without the need for developing a special algorithm. In the majority of presented CRM applications neural networks constitute and are presented as a managerial decision-taking optimisation tool.

Effects of thickness and surface roughness on mechanical properties of aluminum sheets

International Nuclear Information System (INIS)

Suh, Chang Hee; Jung, Yun Chul; Kim, Young Suk

2010-01-01

The effect of thickness on the mechanical properties of Al 6K21-T4 sheet specimens under uniaxial tension was investigated. In order to reduce the thickness of the specimens without changing the microstructure and grain size, chemical etching was carried out, resulting in Al sheets ranging from 0.40 mm to 1.58 mm in thickness. Additionally, the effect of surface roughness was determined by finite element (FE) calculations performed using FE code MARC 2007. Tensile specimens of varying surface roughness were modeled and simulated. An analysis of the combined effects of the thickness and surface roughness revealed that the yield and tensile strengths decreased when the number of grains over the thickness was decreased. The ductility also decreased when reducing the thickness. An FE simulation showed that both the surface roughness and thickness affected the flow-curve shape. Moreover, the effect of the surface roughness tended to increase when decreasing the sheet thickness of specimens having the same roughness

Local Dynamics in Trained Recurrent Neural Networks.

Science.gov (United States)

Rivkind, Alexander; Barak, Omri

2017-06-23

Learning a task induces connectivity changes in neural circuits, thereby changing their dynamics. To elucidate task-related neural dynamics, we study trained recurrent neural networks. We develop a mean field theory for reservoir computing networks trained to have multiple fixed point attractors. Our main result is that the dynamics of the network's output in the vicinity of attractors is governed by a low-order linear ordinary differential equation. The stability of the resulting equation can be assessed, predicting training success or failure. As a consequence, networks of rectified linear units and of sigmoidal nonlinearities are shown to have diametrically different properties when it comes to learning attractors. Furthermore, a characteristic time constant, which remains finite at the edge of chaos, offers an explanation of the network's output robustness in the presence of variability of the internal neural dynamics. Finally, the proposed theory predicts state-dependent frequency selectivity in the network response.

Local Dynamics in Trained Recurrent Neural Networks

Science.gov (United States)

Rivkind, Alexander; Barak, Omri

2017-06-01

Learning a task induces connectivity changes in neural circuits, thereby changing their dynamics. To elucidate task-related neural dynamics, we study trained recurrent neural networks. We develop a mean field theory for reservoir computing networks trained to have multiple fixed point attractors. Our main result is that the dynamics of the network's output in the vicinity of attractors is governed by a low-order linear ordinary differential equation. The stability of the resulting equation can be assessed, predicting training success or failure. As a consequence, networks of rectified linear units and of sigmoidal nonlinearities are shown to have diametrically different properties when it comes to learning attractors. Furthermore, a characteristic time constant, which remains finite at the edge of chaos, offers an explanation of the network's output robustness in the presence of variability of the internal neural dynamics. Finally, the proposed theory predicts state-dependent frequency selectivity in the network response.

Mode Choice Modeling Using Artificial Neural Networks

OpenAIRE

Edara, Praveen Kumar

2003-01-01

Artificial intelligence techniques have produced excellent results in many diverse fields of engineering. Techniques such as neural networks and fuzzy systems have found their way into transportation engineering. In recent years, neural networks are being used instead of regression techniques for travel demand forecasting purposes. The basic reason lies in the fact that neural networks are able to capture complex relationships and learn from examples and also able to adapt when new data becom...

Problematics of Reliability of Road Rollers

Science.gov (United States)

Stawowiak, Michał; Kuczaj, Mariusz

2018-06-01

This article refers to the reliability of road rollers used in a selected roadworks company. Information on the method of road rollers service and how the service affects the reliability of these rollers is presented. Attention was paid to the process of the implemented maintenance plan with regard to the machine's operational time. The reliability of road rollers was analyzed by determining and interpreting readiness coefficients.

Neutron spectrometry with artificial neural networks

International Nuclear Information System (INIS)

Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E.; Rodriguez, J.M.; Mercado S, G.A.; Iniguez de la Torre Bayo, M.P.; Barquero, R.; Arteaga A, T.

2005-01-01

An artificial neural network has been designed to obtain the neutron spectra from the Bonner spheres spectrometer's count rates. The neural network was trained using 129 neutron spectra. These include isotopic neutron sources; reference and operational spectra from accelerators and nuclear reactors, spectra from mathematical functions as well as few energy groups and monoenergetic spectra. The spectra were transformed from lethargy to energy distribution and were re-bin ned to 31 energy groups using the MCNP 4C code. Re-binned spectra and UTA4 response matrix were used to calculate the expected count rates in Bonner spheres spectrometer. These count rates were used as input and the respective spectrum was used as output during neural network training. After training the network was tested with the Bonner spheres count rates produced by a set of neutron spectra. This set contains data used during network training as well as data not used. Training and testing was carried out in the Mat lab program. To verify the network unfolding performance the original and unfolded spectra were compared using the χ 2 -test and the total fluence ratios. The use of Artificial Neural Networks to unfold neutron spectra in neutron spectrometry is an alternative procedure that overcomes the drawbacks associated in this ill-conditioned problem. (Author)

Neural network and its application to CT imaging

Energy Technology Data Exchange (ETDEWEB)

Nikravesh, M.; Kovscek, A.R.; Patzek, T.W. [Lawrence Berkeley National Lab., CA (United States)] [and others

1997-02-01

We present an integrated approach to imaging the progress of air displacement by spontaneous imbibition of oil into sandstone. We combine Computerized Tomography (CT) scanning and neural network image processing. The main aspects of our approach are (I) visualization of the distribution of oil and air saturation by CT, (II) interpretation of CT scans using neural networks, and (III) reconstruction of 3-D images of oil saturation from the CT scans with a neural network model. Excellent agreement between the actual images and the neural network predictions is found.

Prediction of metal corrosion using feed-forward neural networks

International Nuclear Information System (INIS)

Mahjani, M.G.; Jalili, S.; Jafarian, M.; Jaberi, A.

2004-01-01

The reliable prediction of corrosion behavior for the effective control of corrosion is a fundamental requirement. Since real world corrosion never seems to involve quite the same conditions that have previously been tested, using corrosion literature does not provide the necessary answers. In order to provide a methodology for predicting corrosion in real and complex situations, artificial neural networks can be utilized. Feed-forward artificial neural network (FFANN) is an information-processing paradigm inspired by the way the densely interconnected, parallel structure of the human brain process information.The aim of the present work is to predict corrosion behavior in critical conditions, such as industrial applications, based on some laboratory experimental data. Electrochemical behavior of stainless steel in different conditions were studied, using polarization technique and Tafel curves. Back-propagation neural networks models were developed to predict the corrosion behavior. The trained networks result in predicted value in good comparison to the experimental data. They have generally been claimed to be successful in modeling the corrosion behavior. The results are presented in two tables. Table 1 gives corrosion behavior of stainless-steel as a function of pH and CuSO 4 concentration and table 2 gives corrosion behavior of stainless - steel as a function of electrode surface area and CuSO 4 concentration. (authors)

Artificial neural networks in neutron dosimetry

Energy Technology Data Exchange (ETDEWEB)

Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E.; Mercado, G.A.; Perales M, W.A.; Robles R, J.A. [Unidades Academicas de Estudios Nucleares, UAZ, A.P. 336, 98000 Zacatecas (Mexico); Gallego, E.; Lorente, A. [Depto. de Ingenieria Nuclear, Universidad Politecnica de Madrid, (Spain)

2005-07-01

An artificial neural network has been designed to obtain the neutron doses using only the Bonner spheres spectrometer's count rates. Ambient, personal and effective neutron doses were included. 187 neutron spectra were utilized to calculate the Bonner count rates and the neutron doses. The spectra were transformed from lethargy to energy distribution and were re-binned to 31 energy groups using the MCNP 4C code. Re-binned spectra, UTA4 response matrix and fluence-to-dose coefficients were used to calculate the count rates in Bonner spheres spectrometer and the doses. Count rates were used as input and the respective doses were used as output during neural network training. Training and testing was carried out in Mat lab environment. The artificial neural network performance was evaluated using the {chi}{sup 2}- test, where the original and calculated doses were compared. The use of Artificial Neural Networks in neutron dosimetry is an alternative procedure that overcomes the drawbacks associated in this ill-conditioned problem. (Author)

Artificial neural networks in neutron dosimetry

International Nuclear Information System (INIS)

Vega C, H.R.; Hernandez D, V.M.; Manzanares A, E.; Mercado, G.A.; Perales M, W.A.; Robles R, J.A.; Gallego, E.; Lorente, A.

2005-01-01

An artificial neural network has been designed to obtain the neutron doses using only the Bonner spheres spectrometer's count rates. Ambient, personal and effective neutron doses were included. 187 neutron spectra were utilized to calculate the Bonner count rates and the neutron doses. The spectra were transformed from lethargy to energy distribution and were re-binned to 31 energy groups using the MCNP 4C code. Re-binned spectra, UTA4 response matrix and fluence-to-dose coefficients were used to calculate the count rates in Bonner spheres spectrometer and the doses. Count rates were used as input and the respective doses were used as output during neural network training. Training and testing was carried out in Mat lab environment. The artificial neural network performance was evaluated using the χ 2 - test, where the original and calculated doses were compared. The use of Artificial Neural Networks in neutron dosimetry is an alternative procedure that overcomes the drawbacks associated in this ill-conditioned problem. (Author)

When the going gets rough – studying the effect of surface roughness on the adhesive abilities of tree frogs

Directory of Open Access Journals (Sweden)

Niall Crawford

2016-12-01

Full Text Available Tree frogs need to adhere to surfaces of various roughnesses in their natural habitats; these include bark, leaves and rocks. Rough surfaces can alter the effectiveness of their toe pads, due to factors such as a change of real contact area and abrasion of the pad epithelium. Here, we tested the effect of surface roughness on the attachment abilities of the tree frog Litoria caerulea. This was done by testing shear and adhesive forces on artificial surfaces with controlled roughness, both on single toe pads and whole animal scales. It was shown that frogs can stick 2–3 times better on small scale roughnesses (3–6 µm asperities, producing higher adhesive and frictional forces, but relatively poorly on the larger scale roughnesses tested (58.5–562.5 µm asperities. Our experiments suggested that, on such surfaces, the pads secrete insufficient fluid to fill the space under the pad, leaving air pockets that would significantly reduce the Laplace pressure component of capillarity. Therefore, we measured how well the adhesive toe pad would conform to spherical asperities of known sizes using interference reflection microscopy. Based on experiments where the conformation of the pad to individual asperities was examined microscopically, our calculations indicate that the pad epithelium has a low elastic modulus, making it highly deformable.

Estimation of gloss from rough surface parameters

Science.gov (United States)

Simonsen, Ingve; Larsen, Åge G.; Andreassen, Erik; Ommundsen, Espen; Nord-Varhaug, Katrin

2005-12-01

Gloss is a quantity used in the optical industry to quantify and categorize materials according to how well they scatter light specularly. With the aid of phase perturbation theory, we derive an approximate expression for this quantity for a one-dimensional randomly rough surface. It is demonstrated that gloss depends in an exponential way on two dimensionless quantities that are associated with the surface randomness: the root-mean-square roughness times the perpendicular momentum transfer for the specular direction, and a correlation function dependent factor times a lateral momentum variable associated with the collection angle. Rigorous Monte Carlo simulations are used to access the quality of this approximation, and good agreement is observed over large regions of parameter space.

Determining the surface roughness coefficient by 3D Scanner

Directory of Open Access Journals (Sweden)

Karmen Fifer Bizjak

2010-12-01

Full Text Available Currently, several test methods can be used in the laboratory to determine the roughness of rock joint surfaces.However, true roughness can be distorted and underestimated by the differences in the sampling interval of themeasurement methods. Thus, these measurement methods produce a dead zone and distorted roughness profiles.In this paper a new rock joint surface roughness measurement method is presented, with the use of a camera-typethree-dimensional (3D scanner as an alternative to current methods. For this study, the surfaces of ten samples oftuff were digitized by means of a 3D scanner, and the results were compared with the corresponding Rock JointCoefficient (JRC values. Up until now such 3D scanner have been mostly used in the automotive industry, whereastheir use for comparison with obtained JRC coefficient values in rock mechanics is presented here for the first time.The proposed new method is a faster, more precise and more accurate than other existing test methods, and is apromising technique for use in this area of study in the future.

Artificial neural networks for plasma spectroscopy analysis

International Nuclear Information System (INIS)

Morgan, W.L.; Larsen, J.T.; Goldstein, W.H.

1992-01-01

Artificial neural networks have been applied to a variety of signal processing and image recognition problems. Of the several common neural models the feed-forward, back-propagation network is well suited for the analysis of scientific laboratory data, which can be viewed as a pattern recognition problem. The authors present a discussion of the basic neural network concepts and illustrate its potential for analysis of experiments by applying it to the spectra of laser produced plasmas in order to obtain estimates of electron temperatures and densities. Although these are high temperature and density plasmas, the neural network technique may be of interest in the analysis of the low temperature and density plasmas characteristic of experiments and devices in gaseous electronics

Roughness modification of surfaces treated by a pulsed dielectric barrier discharge

CERN Document Server

Dumitrascu, N; Apetroaei, N; Popa, G

2002-01-01

Local modifications of surface roughness are very important in many applications, as this surface property is able to generate new mechano-physical characteristics of a large category of materials. Roughness is one of the most important parameters used to characterize and control the surface morphology, and techniques that allow modifying and controlling the surface roughness present increasing interest. In this respect we propose the dielectric barrier discharge (DBD) as a simple and low cost method that can be used to induce controlled roughness on various surfaces in the nanoscale range. DBD is produced in helium, at atmospheric pressure, by a pulsed high voltage, 28 kV peak to peak, 13.5 kHz frequency and 40 W power. This type of discharge is a source of energy capable of modifying the physico-chemical properties of the surfaces without affecting their bulk properties. The discharge is characterized by means of electrical probes and, in order to analyse the heat transfer rate from the discharge to the tre...

Scattering from a PEC Slightly Rough Surface in Chiral Media

Directory of Open Access Journals (Sweden)

Haroon Akhtar Qureshi

2018-01-01

Full Text Available The scattering of left circularly polarized wave from a perfectly electric conducting (PEC rough surface in isotropic chiral media is investigated. Since a slightly rough interface is assumed, the solution is obtained using perturbation method. Zeroth-order term corresponds to solution for a flat interface which helps in making a comparison with the results reported in the literature. First-order term gives the contribution from the surface perturbations, and it is used to define incoherent bistatic scattering coefficients for a Gaussian rough surface. Higher order solution is obtained in a recursive manner. Numerical results are reported for different values of chirality, correlation length, and rms height of the surface. Diffraction efficiency is defined for a sinusoidal grating.

Dynamic training algorithm for dynamic neural networks

International Nuclear Information System (INIS)

Tan, Y.; Van Cauwenberghe, A.; Liu, Z.

1996-01-01

The widely used backpropagation algorithm for training neural networks based on the gradient descent has a significant drawback of slow convergence. A Gauss-Newton method based recursive least squares (RLS) type algorithm with dynamic error backpropagation is presented to speed-up the learning procedure of neural networks with local recurrent terms. Finally, simulation examples concerning the applications of the RLS type algorithm to identification of nonlinear processes using a local recurrent neural network are also included in this paper

Finite element method analysis of surface roughness transfer in micro flexible rolling

Directory of Open Access Journals (Sweden)

Qu Feijun

2016-01-01

Full Text Available Micro flexible rolling aims to fabricate submillimeter thick strips with varying thickness profile, where the surface quality of products is mainly determined by initial workpiece surface roughness and subsequent surface asperity flattening process, which is affected by process parameters during rolling. This paper shows a 3D finite element model for flexible rolling of a 250 μm thick workpiece with reduction of 20 to 50%, and rolling phase with thinner thickness indicates a better ability to decrease the surface roughness. Four types of initial workpiece surface roughness are studied in the simulation, and the influences of process parameters, such as friction coefficient, rolling speed and roll gap adjusting speed, on surface asperity flattening of workpieces with different initial surface roughness have been numerically investigated and analysed.

Neural Networks for Non-linear Control

DEFF Research Database (Denmark)

Sørensen, O.

1994-01-01

This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process.......This paper describes how a neural network, structured as a Multi Layer Perceptron, is trained to predict, simulate and control a non-linear process....

Structure Crack Identification Based on Surface-mounted Active Sensor Network with Time-Domain Feature Extraction and Neural Network

Directory of Open Access Journals (Sweden)

Chunling DU

2012-03-01

Full Text Available In this work the condition of metallic structures are classified based on the acquired sensor data from a surface-mounted piezoelectric sensor/actuator network. The structures are aluminum plates with riveted holes and possible crack damage at these holes. A 400 kHz sine wave burst is used as diagnostic signals. The combination of time-domain S0 waves from received sensor signals is directly used as features and preprocessing is not needed for the dam age detection. Since the time sequence of the extracted S0 has a high dimension, principal component estimation is applied to reduce its dimension before entering NN (neural network training for classification. An LVQ (learning vector quantization NN is used to classify the conditions as healthy or damaged. A number of FEM (finite element modeling results are taken as inputs to the NN for training, since the simulated S0 waves agree well with the experimental results on real plates. The performance of the classification is then validated by using these testing results.

Multipoint contact modeling of nanoparticle manipulation on rough surface

Energy Technology Data Exchange (ETDEWEB)

Zakeri, M., E-mail: m.zakeri@tabrizu.ac.ir; Faraji, J.; Kharazmi, M. [University of Tabriz, School of Engineering Emerging Technologies (Iran, Islamic Republic of)

2016-12-15

In this paper, the atomic force microscopy (AFM)-based 2-D pushing of nano/microparticles investigated on rough substrate by assuming a multipoint contact model. First, a new contact model was extracted and presented based on the geometrical profiles of Rumpf, Rabinovich and George models and the contact mechanics theories of JKR and Schwartz, to model the adhesion forces and the deformations in the multipoint contact of rough surfaces. The geometry of a rough surface was defined by two main parameters of asperity height (size of roughness) and asperity wavelength (compactness of asperities distribution). Then, the dynamic behaviors of nano/microparticles with radiuses in range of 50–500 nm studied during their pushing on rough substrate with a hexagonal or square arrangement of asperities. Dynamic behavior of particles were simulated and compared by assuming multipoint and single-point contact schemes. The simulation results show that the assumption of multipoint contact has a considerable influence on determining the critical manipulation force. Additionally, the assumption of smooth surfaces or single-point contact leads to large error in the obtained results. According to the results of previous research, it anticipated that a particles with the radius less than about 550 nm start to slide on smooth substrate; but by using multipoint contact model, the predicted behavior changed, and particles with radii of smaller than 400 nm begin to slide on rough substrate for different height of asperities, at first.

Drift chamber tracking with neural networks

International Nuclear Information System (INIS)

Lindsey, C.S.; Denby, B.; Haggerty, H.

1992-10-01

We discuss drift chamber tracking with a commercial log VLSI neural network chip. Voltages proportional to the drift times in a 4-layer drift chamber were presented to the Intel ETANN chip. The network was trained to provide the intercept and slope of straight tracks traversing the chamber. The outputs were recorded and later compared off line to conventional track fits. Two types of network architectures were studied. Applications of neural network tracking to high energy physics detector triggers is discussed

Using neural networks to describe tracer correlations

Directory of Open Access Journals (Sweden)

D. J. Lary

2004-01-01

Full Text Available Neural networks are ideally suited to describe the spatial and temporal dependence of tracer-tracer correlations. The neural network performs well even in regions where the correlations are less compact and normally a family of correlation curves would be required. For example, the CH4-N2O correlation can be well described using a neural network trained with the latitude, pressure, time of year, and methane volume mixing ratio (v.m.r.. In this study a neural network using Quickprop learning and one hidden layer with eight nodes was able to reproduce the CH4-N2O correlation with a correlation coefficient between simulated and training values of 0.9995. Such an accurate representation of tracer-tracer correlations allows more use to be made of long-term datasets to constrain chemical models. Such as the dataset from the Halogen Occultation Experiment (HALOE which has continuously observed CH4  (but not N2O from 1991 till the present. The neural network Fortran code used is available for download.

Geometrical properties of rough metallic surfaces and their implication in electromagnetic problems

International Nuclear Information System (INIS)

Hernandez, A.; Chicon, R.; Ortuno, M.; Abellan, J.

1987-01-01

We analyze the geometrical properties and their implications in the effective surface resistance and wall losses of rough metallic surfaces. The power spectrum and the autocorrelation function are calculated for a simple model that adequately represent the rough surface. The roughness parameters are obtained through average values of the roughness and its derivative. We calculate the density profile, directly related to the depth-dependent effective conductivity. The data from the profilometer are corrected to take into account the finite size of the tip. (author)

A TLD dose algorithm using artificial neural networks

International Nuclear Information System (INIS)

Moscovitch, M.; Rotunda, J.E.; Tawil, R.A.; Rathbone, B.A.

1995-01-01

An artificial neural network was designed and used to develop a dose algorithm for a multi-element thermoluminescence dosimeter (TLD). The neural network architecture is based on the concept of functional links network (FLN). Neural network is an information processing method inspired by the biological nervous system. A dose algorithm based on neural networks is fundamentally different as compared to conventional algorithms, as it has the capability to learn from its own experience. The neural network algorithm is shown the expected dose values (output) associated with given responses of a multi-element dosimeter (input) many times. The algorithm, being trained that way, eventually is capable to produce its own unique solution to similar (but not exactly the same) dose calculation problems. For personal dosimetry, the output consists of the desired dose components: deep dose, shallow dose and eye dose. The input consists of the TL data obtained from the readout of a multi-element dosimeter. The neural network approach was applied to the Harshaw Type 8825 TLD, and was shown to significantly improve the performance of this dosimeter, well within the U.S. accreditation requirements for personnel dosimeters

Artificial Astrocytes Improve Neural Network Performance

Science.gov (United States)

Porto-Pazos, Ana B.; Veiguela, Noha; Mesejo, Pablo; Navarrete, Marta; Alvarellos, Alberto; Ibáñez, Oscar; Pazos, Alejandro; Araque, Alfonso

2011-01-01

Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN) and artificial neuron-glia networks (NGN) to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function. PMID:21526157

Artificial astrocytes improve neural network performance.

Directory of Open Access Journals (Sweden)

Ana B Porto-Pazos

Full Text Available Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN and artificial neuron-glia networks (NGN to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function.

Artificial astrocytes improve neural network performance.

Science.gov (United States)

Porto-Pazos, Ana B; Veiguela, Noha; Mesejo, Pablo; Navarrete, Marta; Alvarellos, Alberto; Ibáñez, Oscar; Pazos, Alejandro; Araque, Alfonso

2011-04-19

Compelling evidence indicates the existence of bidirectional communication between astrocytes and neurons. Astrocytes, a type of glial cells classically considered to be passive supportive cells, have been recently demonstrated to be actively involved in the processing and regulation of synaptic information, suggesting that brain function arises from the activity of neuron-glia networks. However, the actual impact of astrocytes in neural network function is largely unknown and its application in artificial intelligence remains untested. We have investigated the consequences of including artificial astrocytes, which present the biologically defined properties involved in astrocyte-neuron communication, on artificial neural network performance. Using connectionist systems and evolutionary algorithms, we have compared the performance of artificial neural networks (NN) and artificial neuron-glia networks (NGN) to solve classification problems. We show that the degree of success of NGN is superior to NN. Analysis of performances of NN with different number of neurons or different architectures indicate that the effects of NGN cannot be accounted for an increased number of network elements, but rather they are specifically due to astrocytes. Furthermore, the relative efficacy of NGN vs. NN increases as the complexity of the network increases. These results indicate that artificial astrocytes improve neural network performance, and established the concept of Artificial Neuron-Glia Networks, which represents a novel concept in Artificial Intelligence with implications in computational science as well as in the understanding of brain function.

Electromagnetic Scattering from Rough Sea Surface with PM Spectrum Covered by an Organic Film

International Nuclear Information System (INIS)

Wang Rui; Guo Li-Xin; Wang An-Qi; Wu Zhen-Sen

2011-01-01

The rough sea surface covered by an organic film will cause attenuation of capillarity waves, which implies that the organic films play an important role in rough sea surface processes. We focus on a one-dimensional (1D) rough sea surface with the Pierson—Moskowitz (PM) spectrum distributed to the homogeneous insoluble organic slicks. First, the impact of the organic film on the PM surface spectrum is presented, as well as that of the correlation length, the rms height and slope of the rough sea surface. The damping effect of the organic film changes the physical parameters of the rough sea surface. For example, the organic film will reduce the rms height and slopee of the rough sea surface, which results in the attenuation of the high-frequency components of the PM spectrum leading to modification of the surface PM spectrum. Then, the influence of the organic film on the electromagnetic (EM) scattering coefficients from PM rough sea surface covered by the organic film is investigated and discussed in detail, compared with the clean PM rough sea surface through the method of moments. (fundamental areas of phenomenology(including applications))

Convolutional Neural Network for Image Recognition

CERN Document Server

Seifnashri, Sahand

2015-01-01

The aim of this project is to use machine learning techniques especially Convolutional Neural Networks for image processing. These techniques can be used for Quark-Gluon discrimination using calorimeters data, but unfortunately I didn’t manage to get the calorimeters data and I just used the Jet data fromminiaodsim(ak4 chs). The Jet data was not good enough for Convolutional Neural Network which is designed for ’image’ recognition. This report is made of twomain part, part one is mainly about implementing Convolutional Neural Network on unphysical data such as MNIST digits and CIFAR-10 dataset and part 2 is about the Jet data.

A neural network model for non invasive subsurface stratigraphic identification

International Nuclear Information System (INIS)

Sullivan, John M. Jr.; Ludwig, Reinhold; Lai Qiang

2000-01-01

Ground-Penetrating Radar (GRP) is a powerful tool to examine the stratigraphy below ground surface for remote sensing. Increasingly GPR has also found applications in microwave NDE as an interrogation tool to assess dielectric layers. Unfortunately, GPR data is characterized by a high degree of uncertainty and natural physical ambiguity. Robust decomposition routines are sparse for this application. We have developed a hierarchical set of neural network modules which split the task of layer profiling into consecutive stages. Successful GPR profiling of the subsurface stratigraphy is of key importance for many remote sensing applications including microwave NDE. Neural network modules were designed to accomplish the two main processing goals of recognizing the 'subsurface pattern' followed by the identification of the depths of the subsurface layers like permafrost, groundwater table, and bedrock. We used an adaptive transform technique to transform raw GPR data into a small feature vector containing the most representative and discriminative features of the signal. This information formed the input for the neural network processing units. This strategy reduced the number of required training samples for the neural network by orders of magnitude. The entire processing system was trained using the adaptive transformed feature vector inputs and tested with real measured GPR data. The successful results of this system establishes the feasibility the feasibility of delineating subsurface layering nondestructively

Abrasion Resistance of Nano Silica Modified Roller Compacted Rubbercrete: Cantabro Loss Method and Response Surface Methodology Approach

Science.gov (United States)

Adamu, Musa; Mohammed, Bashar S.; Shafiq, Nasir

2018-04-01

Roller compacted concrete (RCC) when used for pavement is subjected to skidding/rubbing by wheels of moving vehicles, this causes pavement surface to wear out and abrade. Therefore, abrasion resistance is one of the most important properties of concern for RCC pavement. In this study, response surface methodology was used to design, evaluate and analyze the effect of partial replacement of fine aggregate with crumb rubber, and addition of nano silica on the abrasion resistance of roller compacted rubbercrete (RCR). RCR is the terminology used for RCC pavement where crumb rubber was used as partial replacement to fine aggregate. The Box-Behnken design method was used to develop the mixtures combinations using 10%, 20%, and 30% crumb rubber with 0%, 1%, and 2% nano silica. The Cantabro loss method was used to measure the abrasion resistance. The results showed that the abrasion resistance of RCR decreases with increase in crumb rubber content, and increases with increase in addition of nano silica. The analysis of variance shows that the model developed using response surface methodology (RSM) has a very good degree of correlation, and can be used to predict the abrasion resistance of RCR with a percentage error of 5.44%. The combination of 10.76% crumb rubber and 1.59% nano silica yielded the best combinations of RCR in terms of abrasion resistance of RCR.

Dynamic modeling of manipulation of micro/nanoparticles on rough surfaces

International Nuclear Information System (INIS)

Korayem, M.H.; Zakeri, M.

2011-01-01

In this paper, the dynamic behavior of spherical micro/nanoparticles, while being pushed on rough substrates, is studied by means of an Atomic Force Microscope (AFM). For this purpose, first, the contact adhesion force, and the areas and penetration depths of rough surfaces are derived based on the Johnson-Kendall-Roberts (JKR) theory, the Schwarz method, and the Rumpf/Rabinovich models. Then, the dynamic model of particle manipulation on rough substrates is revised using the specified contact theory for rough surfaces. And finally, the pushing of spherical particles with 50, 100, 200, 500, and 10000 nm radii is simulated. The results show that the critical force and the critical time of manipulation decrease when the particles are pushed on the rough surfaces as compared to the smooth ones. It is also observed that the critical force for a rough substrate containing asperities of low height and large radius approaches a comparable critical force magnitude to the smooth substrate, as is expected. Also, when the asperity radius in the substrate is within the range of 0.5 < r < 5 nm, the critical force of pushing decreases; however, as the asperity radius becomes larger than 5 nm, the critical force begins to increase again. Furthermore, the critical values are generally more sensitive to the changes of the asperity radius than the height. It is also found that the difference between the critical values based on the Rumpf and Rabinovich models is negligible. However, the estimation of particles' dynamic behavior using the Rumpf model could be wrong for the rough substrates with small radius asperities, which is considerable in the manipulation and assembly practices. Moreover, the dynamic behavior of particles of small radius (r < 500 nm) change during the pushing process on rough surfaces, and the rolling behavior could be possible on the surfaces that have small radius asperities. The probability of this occurrence is increased in the pushing of larger particles on

A neural network approach to burst detection.

Science.gov (United States)

Mounce, S R; Day, A J; Wood, A S; Khan, A; Widdop, P D; Machell, J

2002-01-01

This paper describes how hydraulic and water quality data from a distribution network may be used to provide a more efficient leakage management capability for the water industry. The research presented concerns the application of artificial neural networks to the issue of detection and location of leakage in treated water distribution systems. An architecture for an Artificial Neural Network (ANN) based system is outlined. The neural network uses time series data produced by sensors to directly construct an empirical model for predication and classification of leaks. Results are presented using data from an experimental site in Yorkshire Water's Keighley distribution system.

QSAR modelling using combined simple competitive learning networks and RBF neural networks.

Science.gov (United States)

Sheikhpour, R; Sarram, M A; Rezaeian, M; Sheikhpour, E

2018-04-01

The aim of this study was to propose a QSAR modelling approach based on the combination of simple competitive learning (SCL) networks with radial basis function (RBF) neural networks for predicting the biological activity of chemical compounds. The proposed QSAR method consisted of two phases. In the first phase, an SCL network was applied to determine the centres of an RBF neural network. In the second phase, the RBF neural network was used to predict the biological activity of various phenols and Rho kinase (ROCK) inhibitors. The predictive ability of the proposed QSAR models was evaluated and compared with other QSAR models using external validation. The results of this study showed that the proposed QSAR modelling approach leads to better performances than other models in predicting the biological activity of chemical compounds. This indicated the efficiency of simple competitive learning networks in determining the centres of RBF neural networks.

Neural network classifier of attacks in IP telephony

Science.gov (United States)

Safarik, Jakub; Voznak, Miroslav; Mehic, Miralem; Partila, Pavol; Mikulec, Martin

2014-05-01

Various types of monitoring mechanism allow us to detect and monitor behavior of attackers in VoIP networks. Analysis of detected malicious traffic is crucial for further investigation and hardening the network. This analysis is typically based on statistical methods and the article brings a solution based on neural network. The proposed algorithm is used as a classifier of attacks in a distributed monitoring network of independent honeypot probes. Information about attacks on these honeypots is collected on a centralized server and then classified. This classification is based on different mechanisms. One of them is based on the multilayer perceptron neural network. The article describes inner structure of used neural network and also information about implementation of this network. The learning set for this neural network is based on real attack data collected from IP telephony honeypot called Dionaea. We prepare the learning set from real attack data after collecting, cleaning and aggregation of this information. After proper learning is the neural network capable to classify 6 types of most commonly used VoIP attacks. Using neural network classifier brings more accurate attack classification in a distributed system of honeypots. With this approach is possible to detect malicious behavior in a different part of networks, which are logically or geographically divided and use the information from one network to harden security in other networks. Centralized server for distributed set of nodes serves not only as a collector and classifier of attack data, but also as a mechanism for generating a precaution steps against attacks.

Evaluation of surface roughness of the bracket slot floor—a 3D perspective study

Directory of Open Access Journals (Sweden)

Chetankumar O. Agarwal

2016-01-01

Full Text Available Abstract Background An important constituent of an orthodontic appliance is orthodontic brackets. It is either the bracket or the archwire that slides through the bracket slot, during sliding mechanics. Overcoming the friction between the two surfaces demands an important consideration in an appliance design. The present study investigated the surface roughness of four different commercially available stainless steel brackets. Methods All tests were carried out to analyse quantitatively the morphological surface of the bracket slot floor with the help of scanning electron microscope (SEM machine and to qualitatively analyse the average surface roughness (Sa of the bracket slot floor with the help of a three-dimensional (3D non-contact optical surface profilometer machine. Results The SEM microphotographs were evaluated with the help of visual analogue scale, the surface roughness for group A = 0—very rough surface, group C = 1—rough surface, group B = 2—smooth surface, and group D = 3—very smooth surface. Surface roughness evaluation with the 3D non-contact optical surface profilometer machine was highest for group A, followed by group C, group B and group D. Groups B and D provided smooth surface roughness; however, group D had the very smooth surface with values 0.74 and 0.75 for mesial and distal slots, respectively. Conclusions Evaluation of surface roughness of the bracket slot floor with both SEM and profilometer machine led to the conclusion that the average surface roughness was highest for group A, followed by group C, group B and group D.

A Neural Network-Based Interval Pattern Matcher

Directory of Open Access Journals (Sweden)

Jing Lu

2015-07-01

Full Text Available One of the most important roles in the machine learning area is to classify, and neural networks are very important classifiers. However, traditional neural networks cannot identify intervals, let alone classify them. To improve their identification ability, we propose a neural network-based interval matcher in our paper. After summarizing the theoretical construction of the model, we take a simple and a practical weather forecasting experiment, which show that the recognizer accuracy reaches 100% and that is promising.

Artificial Neural Networks and the Mass Appraisal of Real Estate