Study on Fault Diagnostics of a Turboprop Engine Using Inverse Performance Model and Artificial Intelligent Methods

Science.gov (United States)

Kong, Changduk; Lim, Semyeong

2011-12-01

Recently, the health monitoring system of major gas path components of gas turbine uses mostly the model based method like the Gas Path Analysis (GPA). This method is to find quantity changes of component performance characteristic parameters such as isentropic efficiency and mass flow parameter by comparing between measured engine performance parameters such as temperatures, pressures, rotational speeds, fuel consumption, etc. and clean engine performance parameters without any engine faults which are calculated by the base engine performance model. Currently, the expert engine diagnostic systems using the artificial intelligent methods such as Neural Networks (NNs), Fuzzy Logic and Genetic Algorithms (GAs) have been studied to improve the model based method. Among them the NNs are mostly used to the engine fault diagnostic system due to its good learning performance, but it has a drawback due to low accuracy and long learning time to build learning data base if there are large amount of learning data. In addition, it has a very complex structure for finding effectively single type faults or multiple type faults of gas path components. This work builds inversely a base performance model of a turboprop engine to be used for a high altitude operation UAV using measured performance data, and proposes a fault diagnostic system using the base engine performance model and the artificial intelligent methods such as Fuzzy logic and Neural Network. The proposed diagnostic system isolates firstly the faulted components using Fuzzy Logic, then quantifies faults of the identified components using the NN leaned by fault learning data base, which are obtained from the developed base performance model. In leaning the NN, the Feed Forward Back Propagation (FFBP) method is used. Finally, it is verified through several test examples that the component faults implanted arbitrarily in the engine are well isolated and quantified by the proposed diagnostic system.

evelopment of a boiling water reactor fault diagnostic system with a signed directed graph method

International Nuclear Information System (INIS)

Chen, M.; Yu, C.C.; Liou, C.T.; Liao, L.Y.

1990-01-01

The fault diagnostic system for a nuclear power reactor is expected to be a useful decision support system for the operators during transients and accident conditions. A considerable research effort has been devoted to the development of automated fault diagnostic systems. One major approach, which has been widely used in chemical engineering, is to identify the possible causes of process disturbance using a logic-oriented method called signed directed graph (SDG). A knowledge based system was developed with the rules derived from the SDG representation. The SDG for the Chinshan nuclear power plant, which is a typical boiling water reactor, is established. The personal consultant system is used as the expert system development tool in this paper

Fault-tolerant and Diagnostic Methods for Navigation

DEFF Research Database (Denmark)

Blanke, Mogens

2003-01-01

to diagnose faults and autonomously provide valid navigation data, disregarding any faulty sensor data and use sensor fusion to obtain a best estimate for users. This paper discusses how diagnostic and fault-tolerant methods are applicable in marine systems. An example chosen is sensor fusion for navigation......Precise and reliable navigation is crucial, and for reasons of safety, essential navigation instruments are often duplicated. Hardware redundancy is mostly used to manually switch between instruments should faults occur. In contrast, diagnostic methods are available that can use analytic redundancy...

A fault diagnosis and operation advising cooperative expert system based on multi-agent technology

Energy Technology Data Exchange (ETDEWEB)

Zhao, W.; Bai, X.; Ding, J.; Fang, Z.; Li, Z. [China Electric Power Research Inst., Haidian District, Beijing (China)

2006-07-01

Power systems are becoming more and more complex. In addition, the amount of real-time alarm messages from the supervisory control and data acquisition, energy management systems and wide area measurement systems about switchgear and protection are also increasing to a point far beyond the operator's capacity to digest the information. Research and development of a fault diagnosis system is necessary for the timely identification of fault or malfunctioning devices and for realizing the automation functions of dynamic supervisory control system. The prevailing fault diagnosis approaches in power systems include the expert system, artificial neural network, and fault diagnosis based on optimal theory. This paper discussed the advantages and disadvantages of each of these approaches for diagnosing faults. The paper also proposed a new fault diagnosis and operational processing approach based on a cooperative expert system combined with a multi-agent architecture. For solving complex and correlative faults, the cooperative expert system can overcome the deficiency of a single expert system. It can be used not only for diagnosing complex faults in real time but also in providing timely operational advice. The proposed system has been used successfully in a district power grid in China's Shangdong province for a year. 9 refs., 4 figs.

Design of a real-time fault diagnosis expert system for the EAST cryoplant

International Nuclear Information System (INIS)

Zhou Zhiwei; Zhuang Ming; Lu Xiaofei; Hu Liangbing; Xia Genhai

2012-01-01

Highlights: ► An expert system of real-time fault diagnosis for EAST cryoplant is designed. ► Knowledge base is built via fault tree analysis based on our fault experience. ► It can make up the deficiency of safety monitoring in cryogenic DCS. ► It can help operators to find the fault causes and give operation suggestion. ► It plays a role of operators training in certain degree. - Abstract: The EAST cryoplant consists of a 2 kW/4 K helium refrigerator and a helium distribution system. It is a complex process system which involves many process variables and cryogenic equipments. Each potential fault or abnormal event may influence stability and safety of the cryogenic system, thereby disturbing the fusion experiment. The cryogenic control system can monitor the process data and detect process alarms, but it is difficult to effectively diagnose the fault causes and provide operation suggestions to operators when anomalies occur. Therefore, a real-time fault diagnosis expert system is essential for a safe and steady operation of EAST cryogenic system. After a brief description of the EAST cryoplant and its control system, the structure design of the cryogenic fault diagnosis expert system is proposed. Based on the empirical knowledge, the fault diagnosis model is built adopting fault tree analysis method which considers the uncertainty. The knowledge base and the inference machine are presented in detail. A cross-platform integrated development environment Qt Creator and MySQL database have been used to develop the system. The proposed expert system has a fine graphic user interface for monitoring and operation. Preliminary test was conducted and the results found to be satisfactory.

Development of expert system for fault diagnosis and restoration at substations

Energy Technology Data Exchange (ETDEWEB)

Choo, Jin Boo; Kwon, Tae Won; Yoon, Yong Beum; Park, Sung Taek [Korea Electric Power Corp. (KEPCO), Taejon (Korea, Republic of). Research Center; Park, Young Moon; Lee, Heung Jae [Electrical Engineering and Science Research Institute (Korea, Republic of)

1996-12-31

When a fault occurs in power systems, the operators have to make precise judgements on the situation and take appropriate actions rapidly to protect the system and minimize the black-out area. However, the larger and the more complex the power systems become, the more difficult it becomes to expect the effective actions of human operators. Therefore, it is a very important issue to support the operators of the local power systems in the case of various faults. We develop an expert system for fault diagnosis and reconfiguration of local power system. The expert system has a capability of identifying the location and the type of faults, the black-out area, and an appropriate reconfiguration procedure for re-energizing or minimizing the service interruption (author). 35 refs., 45 figs.

Development of expert system for fault diagnosis and restoration at substations

Energy Technology Data Exchange (ETDEWEB)

Choo, Jin Boo; Kwon, Tae Won; Yoon, Yong Beum; Park, Sung Taek [Korea Electric Power Corp. (KEPCO), Taejon (Korea, Republic of). Research Center; Park, Young Moon; Lee, Heung Jae [Electrical Engineering and Science Research Institute (Korea, Republic of)

1995-12-31

When a fault occurs in power systems, the operators have to make precise judgements on the situation and take appropriate actions rapidly to protect the system and minimize the black-out area. However, the larger and the more complex the power systems become, the more difficult it becomes to expect the effective actions of human operators. Therefore, it is a very important issue to support the operators of the local power systems in the case of various faults. We develop an expert system for fault diagnosis and reconfiguration of local power system. The expert system has a capability of identifying the location and the type of faults, the black-out area, and an appropriate reconfiguration procedure for re-energizing or minimizing the service interruption (author). 35 refs., 45 figs.

BWR recirculation pump diagnostic expert system

International Nuclear Information System (INIS)

Chiang, S.C.; Morimoto, C.N.; Torres, M.R.

2004-01-01

At General Electric (GE), an on-line expert system to support maintenance decisions for BWR recirculation pumps for nuclear power plants has been developed. This diagnostic expert system is an interactive on-line system that furnishes diagnostic information concerning BWR recirculation pump operational problems. It effectively provides the recirculation pump diagnostic expertise in the plant control room continuously 24 hours a day. The expert system is interfaced to an on-line monitoring system, which uses existing plant sensors to acquire non-safety related data in real time. The expert system correlates and evaluates process data and vibration data by applying expert rules to determine the condition of a BWR recirculation pump system by applying knowledge based rules. Any diagnosis will be automatically displayed, indicating which pump may have a problem, the category of the problem, and the degree of concern expressed by the validity index and color hierarchy. The rules incorporate the expert knowledge from various technical sources such as plant experience, engineering principles, and published reports. These rules are installed in IF-THEN formats and the resulting truth values are also expressed in fuzzy terms and a certainty factor called a validity index. This GE Recirculation Pump Expert System uses industry-standard software, hardware, and network access to provide flexible interfaces with other possible data acquisition systems. Gensym G2 Real-Time Expert System is used for the expert shell and provides the graphical user interface, knowledge base, and inference engine capabilities. (author)

Design of a real-time fault diagnosis expert system for the EAST cryoplant

Energy Technology Data Exchange (ETDEWEB)

Zhou Zhiwei, E-mail: zzw@ipp.ac.cn [Institute of Plasma Physics, Chinese Academy of Sciences, Hefei, Anhui (China); Zhuang Ming, E-mail: zhm@ipp.ac.cn [Institute of Plasma Physics, Chinese Academy of Sciences, Hefei, Anhui (China); Lu Xiaofei, E-mail: luxf1212@mail.ustc.edu.cn [Institute of Plasma Physics, Chinese Academy of Sciences, Hefei, Anhui (China); Hu Liangbing, E-mail: huliangbing@ipp.ac.cn [Institute of Plasma Physics, Chinese Academy of Sciences, Hefei, Anhui (China); Xia Genhai, E-mail: xgh@ipp.ac.cn [Institute of Plasma Physics, Chinese Academy of Sciences, Hefei, Anhui (China)

2012-12-15

Highlights: Black-Right-Pointing-Pointer An expert system of real-time fault diagnosis for EAST cryoplant is designed. Black-Right-Pointing-Pointer Knowledge base is built via fault tree analysis based on our fault experience. Black-Right-Pointing-Pointer It can make up the deficiency of safety monitoring in cryogenic DCS. Black-Right-Pointing-Pointer It can help operators to find the fault causes and give operation suggestion. Black-Right-Pointing-Pointer It plays a role of operators training in certain degree. - Abstract: The EAST cryoplant consists of a 2 kW/4 K helium refrigerator and a helium distribution system. It is a complex process system which involves many process variables and cryogenic equipments. Each potential fault or abnormal event may influence stability and safety of the cryogenic system, thereby disturbing the fusion experiment. The cryogenic control system can monitor the process data and detect process alarms, but it is difficult to effectively diagnose the fault causes and provide operation suggestions to operators when anomalies occur. Therefore, a real-time fault diagnosis expert system is essential for a safe and steady operation of EAST cryogenic system. After a brief description of the EAST cryoplant and its control system, the structure design of the cryogenic fault diagnosis expert system is proposed. Based on the empirical knowledge, the fault diagnosis model is built adopting fault tree analysis method which considers the uncertainty. The knowledge base and the inference machine are presented in detail. A cross-platform integrated development environment Qt Creator and MySQL database have been used to develop the system. The proposed expert system has a fine graphic user interface for monitoring and operation. Preliminary test was conducted and the results found to be satisfactory.

Study of expert system of fault diagnosis for nuclear power plant

International Nuclear Information System (INIS)

Chen Zhihui; Xia Hong; Liu Miao

2005-01-01

Based on the fault features of Nuclear Power Plant, the ES (expert system) of fault diagnosis has been programmed. The knowledge in the ES adopts the production systems, which can express the certain and uncertain knowledge. For certain knowledge, the simple reasoning mechanism of prepositional logic is adopted. For the uncertain knowledge, CF (certain factor) is used to express the uncertain, thus to set up the reasoning mechanism. In order to solve the 'bottleneck' problem for knowledge acquisition, rough set theory is incorporated into the fault diagnose system and the reduction algorithm based on the discernibility matrix is improved. In the improved algorithm, the measure of attribute importance first calculate the attribute which have the same value in the same decision-sort, then calculate the degrees of attribute in the discernibility matrix. Several different faults have been diagnosed on some emulator with this expert system. (authors)

Neural network based expert system for fault diagnosis of particle accelerators

International Nuclear Information System (INIS)

Dewidar, M.M.

1997-01-01

Particle accelerators are generators that produce beams of charged particles, acquiring different energies, depending on the accelerator type. The MGC-20 cyclotron is a cyclic particle accelerator used for accelerating protons, deuterons, alpha particles, and helium-3 to different energies. Its applications include isotope production, nuclear reaction, and mass spectroscopy studies. It is a complicated machine, it consists of five main parts, the ion source, the deflector, the beam transport system, the concentric and harmonic coils, and the radio frequency system. The diagnosis of this device is a very complex task. it depends on the conditions of 27 indicators of the control panel of the device. The accurate diagnosis can lead to a high system reliability and save maintenance costs. so an expert system for the cyclotron fault diagnosis is necessary to be built. In this thesis , a hybrid expert system was developed for the fault diagnosis of the MGC-20 cyclotron. Two intelligent techniques, multilayer feed forward back propagation neural network and the rule based expert system, are integrated as a pre-processor loosely coupled model to build the proposed hybrid expert system. The architecture of the developed hybrid expert system consists of two levels. The first level is two feed forward back propagation neural networks, used for isolating the faulty part of the cyclotron. The second level is the rule based expert system, used for troubleshooting the faults inside the isolated faulty part. 4-6 tabs., 4-5 figs., 36 refs

Model of critical diagnostic reasoning: achieving expert clinician performance.

Science.gov (United States)

Harjai, Prashant Kumar; Tiwari, Ruby

2009-01-01

Diagnostic reasoning refers to the analytical processes used to determine patient health problems. While the education curriculum and health care system focus on training nurse clinicians to accurately recognize and rescue clinical situations, assessments of non-expert nurses have yielded less than satisfactory data on diagnostic competency. The contrast between the expert and non-expert nurse clinician raises the important question of how differences in thinking may contribute to a large divergence in accurate diagnostic reasoning. This article recognizes superior organization of one's knowledge base, using prototypes, and quick retrieval of pertinent information, using similarity recognition as two reasons for the expert's superior diagnostic performance. A model of critical diagnostic reasoning, using prototypes and similarity recognition, is proposed and elucidated using case studies. This model serves as a starting point toward bridging the gap between clinical data and accurate problem identification, verification, and management while providing a structure for a knowledge exchange between expert and non-expert clinicians.

The Impact of Gas Turbine Component Leakage Fault on GPA Performance Diagnostics

Directory of Open Access Journals (Sweden)

E. L. Ntantis

2016-01-01

Full Text Available The leakage analysis is a key factor in determining energy loss from a gas turbine. Once the components assembly fails, air leakage through the opening increases resulting in a performance loss. Therefore, the performance efficiency of the engine cannot be reliably determined, without good estimates and analysis of leakage faults. Consequently, the implementation of a leakage fault within a gas turbine engine model is necessary for any performance diagnostic technique that can expand its diagnostics capabilities for more accurate predictions. This paper explores the impact of gas turbine component leakage fault on GPA (Gas Path Analysis Performance Diagnostics. The analysis is demonstrated with a test case where gas turbine performance simulation and diagnostics code TURBOMATCH is used to build a performance model of a model engine similar to Rolls-Royce Trent 500 turbofan engine, and carry out the diagnostic analysis with the presence of different component fault cases. Conclusively, to improve the reliability of the diagnostic results, a leakage fault analysis of the implemented faults is made. The diagnostic tool used to deal with the analysis of the gas turbine component implemented faults is a model-based method utilizing a non-linear GPA.

Research on alarm triggered fault-diagnosis expert system for U-shaped tube breaking accident of steam generators

International Nuclear Information System (INIS)

Qian Hong; Luo Jianbo; Jin Weixiao; Zhou Jinming; Wang Du

2015-01-01

According to the U-shaped tube breaking accident of steam generator (SGTR), this paper designs a fault-diagnosis expert system based on the alarm triggering. By analyzing the fault mechanism of SGTR accidents, the fault symptom is obtained. The parameters of the belief rule are set up based on the simulation experiment. The information fusion is conducted on the fault-diagnosis results from multiple expert systems to obtain the final diagnose result. The test result shows that the expert system can diagnose the SGTR accident accurately and rapidly, and provide with the operation guidance. (authors)

ISHM-oriented adaptive fault diagnostics for avionics based on a distributed intelligent agent system

Science.gov (United States)

Xu, Jiuping; Zhong, Zhengqiang; Xu, Lei

2015-10-01

In this paper, an integrated system health management-oriented adaptive fault diagnostics and model for avionics is proposed. With avionics becoming increasingly complicated, precise and comprehensive avionics fault diagnostics has become an extremely complicated task. For the proposed fault diagnostic system, specific approaches, such as the artificial immune system, the intelligent agents system and the Dempster-Shafer evidence theory, are used to conduct deep fault avionics diagnostics. Through this proposed fault diagnostic system, efficient and accurate diagnostics can be achieved. A numerical example is conducted to apply the proposed hybrid diagnostics to a set of radar transmitters on an avionics system and to illustrate that the proposed system and model have the ability to achieve efficient and accurate fault diagnostics. By analyzing the diagnostic system's feasibility and pragmatics, the advantages of this system are demonstrated.

Prodiag--a hybrid artificial intelligence based reactor diagnostic system for process faults

International Nuclear Information System (INIS)

Reifman, J.; Wei, T.Y.C.; Vitela, J.E.; Applequist, C. A.; Chasensky, T.M.

1996-01-01

Commonwealth Research Corporation (CRC) and Argonne National Laboratory (ANL) are collaborating on a DOE-sponsored Cooperative Research and Development Agreement (CRADA), project to perform feasibility studies on a novel approach to Artificial Intelligence (Al) based diagnostics for component faults in nuclear power plants. Investigations are being performed in the construction of a first-principles physics-based plant level process diagnostic expert system (ES) and the identification of component-level fault patterns through operating component characteristics using artificial neural networks (ANNs). The purpose of the proof-of-concept project is to develop a computer-based system using this Al approach to assist process plant operators during off-normal plant conditions. The proposed computer-based system will use thermal hydraulic (T-H) signals complemented by other non-T-H signals available in the data stream to provide the process operator with the component which most likely caused the observed process disturbance.To demonstrate the scale-up feasibility of the proposed diagnostic system it is being developed for use with the Chemical Volume Control System (CVCS) of a nuclear power plant. A full-scope operator training simulator representing the Commonwealth Edison Braidwood nuclear power plant is being used both as the source of development data and as the means to evaluate the advantages of the proposed diagnostic system. This is an ongoing multi-year project and this paper presents the results to date of the CRADA phase

Expert system for fault diagnostic in electronic devices

Energy Technology Data Exchange (ETDEWEB)

Benedetti, G

1984-03-01

Troubleshooting of electronic devices and highly complex PCBS (printed circuit boards) is an area where expert systems can be used. In addition to the difficulties intrinsic to this area it is also impossible to integrate the amount of knowledge based on experience in a traditional model. 8 references.

The Absolute Deviation Rank Diagnostic Approach to Gear Tooth Composite Fault

Directory of Open Access Journals (Sweden)

Guangbin Wang

2017-01-01

Full Text Available Aiming at nonlinear and nonstationary characteristics of the different degree with single fault gear tooth broken, pitting, and composite fault gear tooth broken-pitting, a method for the diagnosis of absolute deviation of gear faults is presented. The method uses ADAMS, respectively, set-up dynamics model of single fault gear tooth broken, pitting, and composite fault gear tooth broken-pitting, to obtain the result of different degree of broken teeth, pitting the single fault and compound faults in the meshing frequency, and the amplitude frequency doubling through simulating analysis. Through the comparison with the normal state to obtain the sensitive characteristic of the fault, the absolute value deviation diagnostic approach is used to identify the fault and validate it through experiments. The results show that absolute deviation rank diagnostic approach can realize the recognition of gear single faults and compound faults with different degrees and provide quick reference to determine the degree of gear fault.

Simulation-based expert system for nuclear reactor control and diagnostics. Progress report

International Nuclear Information System (INIS)

Lee, J.C.; Martin, W.R.

1986-01-01

This research concerns the development of artificial intelligence (AI) techniques suitable for application to the diagnostics and control of nuclear power plant systems. The overall objective of the current effort is to build a prototype simulation-based expert system for diagnosing accidents in nuclear reactors. The system is being designed to analyze plant data heuristically using fuzzy logic to form a set of hypotheses about a particular transient. Hypothesis testing, fault magnitude estimation and transient analysis is performed using simulation programs to model plant behavior. An adaptive learning technique has been developed for achieving accurate simulations of plant dynamics using low-order physical models of plant components. The results of the diagnostics and simulation analysis of the plant transient are to be analyzed by an expert system for final diagnoses and control guidance. To date, significant progress has been made toward achieving the primary goals of this project. Based on a critical safety functions approach, an overall design for the nuclear plant expert system has been developed. The methodology for performing diagnostic reasoning on plant signals has been developed and the algorithms implemented and tested. A methodology for utilizing the information contained in the physical models of plant components has also been developed. This work included the derivation of a unique Kalman filtering algorithm for using power plant data to systematically improve on-line simulations through the judicious adjustment of key model parameters. A few simulation models of key plant components have been developed and implemented to demonstrate the method on a realistic accident scenario. The chosen transient is a loss of feed flow exasperated by a stuck open relief valve, similar to the initiating event of the Three Mile Island Unit 2 accident in 1979

Advance in study of intelligent diagnostic method for nuclear power plant

International Nuclear Information System (INIS)

Zhou Gang; Yang Li

2008-01-01

The advance of research on the application of three types of intelligent diagnostic approach based on neural network (ANN), fuzzy logic and expert system to the operation status monitoring and fault diagnosis of nuclear power plant (NPP) was reviewed. The research status and characters on status monitoring and fault diagnosis approaches based on neural network, fuzzy logic and expert system for nuclear power plant were analyzed. The development trend of applied research on intelligent diagnostic approaches for nuclear power plant was explored. The analysis results show that the research achievements on intelligent diagnostic approaches based on fuzzy logic and expert system for nuclear power plant are not much relatively. The research of intelligent diagnostic approaches for nuclear power plant concentrate on the aspect of operation status monitoring and fault diagnosis based on neural networks for nuclear power plant. The advancing tendency of intelligent diagnostic approaches for nuclear power plant is the combination of various intelligent diagnostic approaches, the combination of neural network diagnostic approaches and other diagnostic approaches as well as multiple neural network diagnostic approaches. (authors)

A study on the fault diagnostic techniques for reactor internal structures using neutron noise analysis

International Nuclear Information System (INIS)

Kim, Tae Ryong; Jeong, Seong Ho; Park, Jin Ho; Park, Jin Suk

1994-08-01

The unfavorable phenomena, such as flow induced vibration and aging process in reactor internals, cause degradation of structural integrity and may result in loosing some mechanical binding components which might impact other equipments and components or cause flow blockage. Since these malfunctions and potential failures change reactor noise signal, it is necessary to analyze reactor noise signal for early fault diagnosis in the point of few of safety and plant economics. The objectives of this study are to establish fault diagnostic and TS(thermal shield), and to develop a data acquisition and signal processing software system. In the first year of this study, an analysis technique for the reactor internal vibration using the reactor noise was proposed. With the technique proposed and the reactor noise signals (ex-core neutron and acceleration), the dynamic characteristics of Ulchin-1 reactor internals were obtained, and compared with those of Tricastin-1 which is the prototype of Ulchin-1. In the second year, a PC-based expert system for reactor internals fault diagnosis is developed, which included data acquisition, signal processing, feature extraction function, and represented diagnostic knowledge by the IF-THEN rule. To know the effect of the faults, the reactor internals of Ulchin-1 is modeled using FEM and simulated with an artificial defect given in the hold-down spring. Trend in the dynamic characteristics of reactor internals is also observed during one fuel cycle to know the effect of boron concentration. 100 figs, 7 tabs, 18 refs. (Author)

An Embedded Rule-Based Diagnostic Expert System in Ada

Science.gov (United States)

Jones, Robert E.; Liberman, Eugene M.

1992-01-01

Ada is becoming an increasingly popular programming language for large Government-funded software projects. Ada with it portability, transportability, and maintainability lends itself well to today's complex programming environment. In addition, expert systems have also assumed a growing role in providing human-like reasoning capability expertise for computer systems. The integration is discussed of expert system technology with Ada programming language, especially a rule-based expert system using an ART-Ada (Automated Reasoning Tool for Ada) system shell. NASA Lewis was chosen as a beta test site for ART-Ada. The test was conducted by implementing the existing Autonomous Power EXpert System (APEX), a Lisp-based power expert system, in ART-Ada. Three components, the rule-based expert systems, a graphics user interface, and communications software make up SMART-Ada (Systems fault Management with ART-Ada). The rules were written in the ART-Ada development environment and converted to Ada source code. The graphics interface was developed with the Transportable Application Environment (TAE) Plus, which generates Ada source code to control graphics images. SMART-Ada communicates with a remote host to obtain either simulated or real data. The Ada source code generated with ART-Ada, TAE Plus, and communications code was incorporated into an Ada expert system that reads the data from a power distribution test bed, applies the rule to determine a fault, if one exists, and graphically displays it on the screen. The main objective, to conduct a beta test on the ART-Ada rule-based expert system shell, was achieved. The system is operational. New Ada tools will assist in future successful projects. ART-Ada is one such tool and is a viable alternative to the straight Ada code when an application requires a rule-based or knowledge-based approach.

A Diagnostic System for Speed-Varying Motor Rotary Faults

Directory of Open Access Journals (Sweden)

Chwan-Lu Tseng

2014-01-01

Full Text Available This study proposed an intelligent rotary fault diagnostic system for motors. A sensorless rotational speed detection method and an improved dynamic structural neural network are used. Moreover, to increase the convergence speed of training, a terminal attractor method and a hybrid discriminant analysis are also adopted. The proposed method can be employed to detect the rotary frequencies of motors with varying speeds and can enhance the discrimination of motor faults. To conduct the experiments, this study used wireless sensor nodes to transmit vibration data and employed MATLAB to write codes for functional modules, including the signal processing, sensorless rotational speed estimation, neural network, and stochastic process control chart. Additionally, Visual Basic software was used to create an integrated human-machine interface. The experimental results regarding the test of equipment faults indicated that the proposed novel diagnostic system can effectively estimate rotational speeds and provide superior ability of motor fault discrimination with fast training convergence.

Sensor Selection for Aircraft Engine Performance Estimation and Gas Path Fault Diagnostics

Science.gov (United States)

Simon, Donald L.; Rinehart, Aidan W.

2016-01-01

This paper presents analytical techniques for aiding system designers in making aircraft engine health management sensor selection decisions. The presented techniques, which are based on linear estimation and probability theory, are tailored for gas turbine engine performance estimation and gas path fault diagnostics applications. They enable quantification of the performance estimation and diagnostic accuracy offered by different candidate sensor suites. For performance estimation, sensor selection metrics are presented for two types of estimators including a Kalman filter and a maximum a posteriori estimator. For each type of performance estimator, sensor selection is based on minimizing the theoretical sum of squared estimation errors in health parameters representing performance deterioration in the major rotating modules of the engine. For gas path fault diagnostics, the sensor selection metric is set up to maximize correct classification rate for a diagnostic strategy that performs fault classification by identifying the fault type that most closely matches the observed measurement signature in a weighted least squares sense. Results from the application of the sensor selection metrics to a linear engine model are presented and discussed. Given a baseline sensor suite and a candidate list of optional sensors, an exhaustive search is performed to determine the optimal sensor suites for performance estimation and fault diagnostics. For any given sensor suite, Monte Carlo simulation results are found to exhibit good agreement with theoretical predictions of estimation and diagnostic accuracies.

Integrated system fault diagnostics utilising digraph and fault tree-based approaches

International Nuclear Information System (INIS)

Bartlett, L.M.; Hurdle, E.E.; Kelly, E.M.

2009-01-01

With the growing intolerance to failures within systems, the issue of fault diagnosis has become ever prevalent. Information concerning these possible failures can help to minimise the disruption to the functionality of the system by allowing quick rectification. Traditional approaches to fault diagnosis within engineering systems have focused on sequential testing procedures and real-time mechanisms. Both methods have been predominantly limited to single fault causes. Latest approaches also consider the issue of multiple faults in reflection to the characteristics of modern day systems designed for high reliability. In addition, a diagnostic capability is required in real time and for changeable system functionality. This paper focuses on two approaches which have been developed to cater for the demands of diagnosis within current engineering systems, namely application of the fault tree analysis technique and the method of digraphs. Both use a comparative approach to consider differences between actual system behaviour and that expected. The procedural guidelines are discussed for each method, with an experimental aircraft fuel system used to test and demonstrate the features of the techniques. The effectiveness of the approaches is compared and their future potential highlighted

Atom and the fault: experts, earthquakes, and nuclear power

International Nuclear Information System (INIS)

Meehan, R.L.

1984-01-01

A narrative account of the geology expert's role in an environmental controversy focuses on the problem of siting nuclear power plants near geologic faults and the conflicting testimony delivered by equally sincere consultants. The author examines the problem of faults and their significance to reactor safety, and concludes that part of the controversy and regulatory indecision are due to the lack of an accepted scientific standard for risk. He explores the historical and social role of the principal professional groups (geologists and engineers) in the debate, and concludes that concerns at some sites were warranted. Scientific advocacy, he feels, serves a useful function in the hearing process, and that the representation for intervenors has been generally good. 18 references, 10 figures

Diagnostic probability function for acute coronary heart disease garnered from experts' tacit knowledge.

Science.gov (United States)

Steurer, Johann; Held, Ulrike; Miettinen, Olli S

2013-11-01

Knowing about a diagnostic probability requires general knowledge about the way in which the probability depends on the diagnostic indicators involved in the specification of the case at issue. Diagnostic probability functions (DPFs) are generally unavailable at present. Our objective was to illustrate how diagnostic experts' case-specific tacit knowledge about diagnostic probabilities could be garnered in the form of DPFs. Focusing on diagnosis of acute coronary heart disease (ACHD), we presented doctors with extensive experience in hospitals' emergency departments a set of hypothetical cases specified in terms of an inclusive set of diagnostic indicators. We translated the medians of these experts' case-specific probabilities into a logistic DPF for ACHD. The principal result was the experts' typical diagnostic probability for ACHD as a joint function of the set of diagnostic indicators. A related result of note was the finding that the experts' probabilities in any given case had a surprising degree of variability. Garnering diagnostic experts' case-specific tacit knowledge about diagnostic probabilities in the form of DPFs is feasible to accomplish. Thus, once the methodology of this type of work has been "perfected," practice-guiding diagnostic expert systems can be developed. Copyright © 2013 Elsevier Inc. All rights reserved.

Strategies for adding adaptive learning mechanisms to rule-based diagnostic expert systems

Science.gov (United States)

Stclair, D. C.; Sabharwal, C. L.; Bond, W. E.; Hacke, Keith

1988-01-01

Rule-based diagnostic expert systems can be used to perform many of the diagnostic chores necessary in today's complex space systems. These expert systems typically take a set of symptoms as input and produce diagnostic advice as output. The primary objective of such expert systems is to provide accurate and comprehensive advice which can be used to help return the space system in question to nominal operation. The development and maintenance of diagnostic expert systems is time and labor intensive since the services of both knowledge engineer(s) and domain expert(s) are required. The use of adaptive learning mechanisms to increment evaluate and refine rules promises to reduce both time and labor costs associated with such systems. This paper describes the basic adaptive learning mechanisms of strengthening, weakening, generalization, discrimination, and discovery. Next basic strategies are discussed for adding these learning mechanisms to rule-based diagnostic expert systems. These strategies support the incremental evaluation and refinement of rules in the knowledge base by comparing the set of advice given by the expert system (A) with the correct diagnosis (C). Techniques are described for selecting those rules in the in the knowledge base which should participate in adaptive learning. The strategies presented may be used with a wide variety of learning algorithms. Further, these strategies are applicable to a large number of rule-based diagnostic expert systems. They may be used to provide either immediate or deferred updating of the knowledge base.

The integration of expert-defined importance factors to enrich Bayesian Fault Tree Analysis

International Nuclear Information System (INIS)

Darwish, Molham; Almouahed, Shaban; Lamotte, Florent de

2017-01-01

This paper proposes an analysis of a hybrid Bayesian-Importance model for system designers to improve the quality of services related to Active Assisted Living Systems. The proposed model is based on two factors: failure probability measure of different service components and, an expert defined degree of importance that each component holds for the success of the corresponding service. The proposed approach advocates the integration of expert-defined importance factors to enrich the Bayesian Fault Tree Analysis (FTA) approach. The evaluation of the proposed approach is conducted using the Fault Tree Analysis formalism where the undesired state of a system is analyzed using Boolean logic mechanisms to combine a series of lower-level events.

Non deterministic finite automata for power systems fault diagnostics

Directory of Open Access Journals (Sweden)

LINDEN, R.

2009-06-01

Full Text Available This paper introduces an application based on finite non-deterministic automata for power systems diagnosis. Automata for the simpler faults are presented and the proposed system is compared with an established expert system.

An expert fault diagnosis system for vehicle air conditioning product development

NARCIS (Netherlands)

Tan, C.F.; Tee, B.T.; Khalil, S.N.; Chen, W.; Rauterberg, G.W.M.

2015-01-01

The paper describes the development of the vehicle air-conditioning fault diagnosis system in automotive industries with expert system shell. The main aim of the research is to diagnose the problem of new vehicle air-conditioning system development process and select the most suitable solution to

A Fault Diagnostic Method for Position Sensor of Switched Reluctance Wind Generator

DEFF Research Database (Denmark)

Wang, Chao; Liu, Xiao; Liu, Hui

2016-01-01

Fast and accurate fault diagnosis of the position sensor is of great significance to ensure the reliability as well as sensor fault tolerant operation of the Switched Reluctance Wind Generator (SRWG). This paper presents a fault diagnostic scheme for a SRWG based on the residual between the estim...

An investigation into the use of ''expert systems'' for system-wide diagnostics

International Nuclear Information System (INIS)

Booth, A.W.; Carroll, J.T.

1987-01-01

This paper has explained how expert systems function and how they might be used to provide a FASTBUS system-wide diagnostic program. The authors propose that the system be used to diagnose the FASTBUS system at FERMILAB's CDF experiment. There are many important areas which have not been addressed in great detail in this paper (such as the roles of the knowledge engineer and the expert during the knowledge acquisition phase), but the central idea of the embodiment of an expert skill in a computer is clear. Development of a system-wide diagnostic program requires building knowledge from all our system experts, into the system. To expand the expert system beyond its network diagnostic ability, to include finding faulty modules would be worthwhile. Having an ''intelligent'' assistant who is on shift 24 hours each day would relieve the ''real'' experts from laborious, time-consuming and sometimes repetitive tasks undertaken during the debugging process. The system could also provide a testbed for evaluation and comparison when considering future expert-system applications such as ''run-control'' and ''data analysis''. In the context of a system-wide diagnostic program, an ''expert system'' is not intended to replace human experts but simply to help them. It is envisaged that there will always be important interaction between the human expert and the ''expert system''. The incremental development of the ''expert system'' should ensure that it is useful in the short term (by debugging to the S.I./segment level for example), and even more useful in the medium to longer term as it acquires more and more knowledge and the ability to debug to the module level. Expert systems exist and are working successfully in many problem domains. See the bibliography for examples of ''expert systems'' built in the high energy physics environment

REXS : A financial risk diagnostic expert system

Directory of Open Access Journals (Sweden)

W. Richter

2012-01-01

Full Text Available

ENGLISH ABSTRACT: Artificial intelligence techniques are rapidly emerging as important contributors to more effective management. One of the greatest growth areas probably lies in the use of Expert System methodology for supporting managerial decision processes.
Existing Decision Support Systems often attempt to apply analytical techniques in combination with traditional data access and retrieval functions. One of the problems usually encountered while developing such decision support systems is the need to transform an unstructured problem environment into a structured analytical model. Using an expert system approach to strategic decision making in such unstructured problem environments may provide significant advantages.
The financial Risk diagnostic EXpert System (REXS concentrates on Financial Risk Analysis. Based on a Forecasting Model the system will, with the support of several expert system knowledge bases, attempt to evaluate the financial risk of a business and provide guidelines for improvement.

AFRIKAANSE OPSOMMING: Tegnieke gebaseer op Kunsmatige Intelligensie toon tans die belofte om belangrike bydraes te maak tot meerBestaande Besluitsteunstelsels poog dikwels om analitiese tegnieke en lradisionele datatoegang- en onttrekkingsfunksies te kombineer. Een van die probleme wat gewoonlik ondervind word gedurende die ontwikkeling van '0 besluitsteunstelsel bestaan uit die behoefte om 'n ongestruktueerde probleemomgewing te transformeer na 'n gestruktueerde analitiese model. 'n Ekspertstelselbenadering lot strategiese besluitneming in 'n ongeSlruktureerde probleemomgewing mag betekenisvolle voordele inhou.
Die "financial Risk diagnostic EXpert System (REXS" konsentreer op fmansiele risiko-analise. Uitgaande vanaf 'n Vooruitskattingsmode~ en deur gebruik te maak van verskeie ekspertstelselkennisbasisse, poog die stelsel om die fmansiele risiko van 'n onderneming te evalueer en riglyne vir moontlike verbetering

Adaptive neural network/expert system that learns fault diagnosis for different structures

Science.gov (United States)

Simon, Solomon H.

1992-08-01

Corporations need better real-time monitoring and control systems to improve productivity by watching quality and increasing production flexibility. The innovative technology to achieve this goal is evolving in the form artificial intelligence and neural networks applied to sensor processing, fusion, and interpretation. By using these advanced Al techniques, we can leverage existing systems and add value to conventional techniques. Neural networks and knowledge-based expert systems can be combined into intelligent sensor systems which provide real-time monitoring, control, evaluation, and fault diagnosis for production systems. Neural network-based intelligent sensor systems are more reliable because they can provide continuous, non-destructive monitoring and inspection. Use of neural networks can result in sensor fusion and the ability to model highly, non-linear systems. Improved models can provide a foundation for more accurate performance parameters and predictions. We discuss a research software/hardware prototype which integrates neural networks, expert systems, and sensor technologies and which can adapt across a variety of structures to perform fault diagnosis. The flexibility and adaptability of the prototype in learning two structures is presented. Potential applications are discussed.

Problem-solving strategies in psychiatry: differences between experts and novices in diagnostic accuracy and reasoning.

Science.gov (United States)

Gabriel, Adel; Violato, Claudio

2013-01-01

The purpose of this study was to examine and compare diagnostic success and its relationship with the diagnostic reasoning process between novices and experts in psychiatry. Nine volunteers, comprising five expert psychiatrists and four clinical clerks, completed a think-aloud protocol while attempting to make a DSM-IV (Diagnostic and Statistical Manual of Mental Disorders, Fourth Edition) diagnosis of a selected case with both Axis I and Axis III diagnoses. Expert psychiatrists made significantly more successful diagnoses for both the primary psychiatric and medical diagnoses than clinical clerks. Expert psychiatrists also gave fewer differential options. Analyzing the think-aloud protocols, expert psychiatrists were much more organized, made fewer mistakes, and utilized significantly less time to access their knowledge than clinical clerks. Both novices and experts seemed to use the hypothetic-deductive and scheme-inductive approaches to diagnosis. However, experts utilized hypothetic-deductive approaches significantly more often than novices. The hypothetic-deductive diagnostic strategy was utilized more than the scheme-inductive approach by both expert psychiatrists and clinical clerks. However, a specific relationship between diagnostic reasoning and diagnostic success could not be identified in this small pilot study. The author recommends a larger study that would include a detailed analysis of the think-aloud protocols.

Mechanical fault diagnostics for induction motor with variable speed drives using Adaptive Neuro-fuzzy Inference System

Energy Technology Data Exchange (ETDEWEB)

Ye, Z. [Department of Electrical & amp; Computer Engineering, Queen' s University, Kingston, Ont. (Canada K7L 3N6); Sadeghian, A. [Department of Computer Science, Ryerson University, Toronto, Ont. (Canada M5B 2K3); Wu, B. [Department of Electrical & amp; Computer Engineering, Ryerson University, Toronto, Ont. (Canada M5B 2K3)

2006-06-15

A novel online diagnostic algorithm for mechanical faults of electrical machines with variable speed drive systems is presented in this paper. Using Wavelet Packet Decomposition (WPD), a set of feature coefficients, represented with different frequency resolutions, related to the mechanical faults is extracted from the stator current of the induction motors operating over a wide range of speeds. A new integrated diagnostic system for electrical machine mechanical faults is then proposed using multiple Adaptive Neuro-fuzzy Inference Systems (ANFIS). This paper shows that using multiple ANFIS units significantly reduces the scale and complexity of the system and speeds up the training of the network. The diagnostic algorithm is validated on a three-phase induction motor drive system, and it is proven to be capable of detecting rotor bar breakage and air gap eccentricity faults with high accuracy. The algorithm is applicable to a variety of industrial applications where either continuous on-line monitoring or off-line fault diagnostics is required. (author)

A phase angle based diagnostic scheme to planetary gear faults diagnostics under non-stationary operational conditions

Science.gov (United States)

Feng, Ke; Wang, Kesheng; Ni, Qing; Zuo, Ming J.; Wei, Dongdong

2017-11-01

Planetary gearbox is a critical component for rotating machinery. It is widely used in wind turbines, aerospace and transmission systems in heavy industry. Thus, it is important to monitor planetary gearboxes, especially for fault diagnostics, during its operational conditions. However, in practice, operational conditions of planetary gearbox are often characterized by variations of rotational speeds and loads, which may bring difficulties for fault diagnosis through the measured vibrations. In this paper, phase angle data extracted from measured planetary gearbox vibrations is used for fault detection under non-stationary operational conditions. Together with sample entropy, fault diagnosis on planetary gearbox is implemented. The proposed scheme is explained and demonstrated in both simulation and experimental studies. The scheme proves to be effective and features advantages on fault diagnosis of planetary gearboxes under non-stationary operational conditions.

A proof-of-concept transient diagnostic expert system for BWRs [Boiling Water Reactors

International Nuclear Information System (INIS)

Yoshida, K.; Naser, J.A.

1988-05-01

A proof-of-concept transient diagnostic expert system has been developed to identify the cause and the type of an abnormal transient in a boiling water nuclear power plant. For this expert system development, the calculational results of the simulation code RETRAN were used as the knowledge source. The knowledge extracted from the RETRAN analyses was transformed into IF-THEN rules in the knowledge base for the expert system. An important feature of this expert system is the introduction of certainty factors to allow diagnosis even in the cases where data may be either missing or marked as invalid. To increase the capability of this diagnostic system to distinguish between similiar transients, backward chaining reasoning is used to support the forward chaining reasoning with certainty factors. Through this effort, it has been demonstrated that an expert system can be successfully used to create a transient diagnostic system. It has also successfully demonstrated that RETRAN can be used as the knowledge source for developing the knowledge base of the diagnostic system

Development of Fault Models for Hybrid Fault Detection and Diagnostics Algorithm: October 1, 2014 -- May 5, 2015

Energy Technology Data Exchange (ETDEWEB)

Cheung, Howard [Purdue Univ., West Lafayette, IN (United States); Braun, James E. [Purdue Univ., West Lafayette, IN (United States)

2015-12-31

This report describes models of building faults created for OpenStudio to support the ongoing development of fault detection and diagnostic (FDD) algorithms at the National Renewable Energy Laboratory. Building faults are operating abnormalities that degrade building performance, such as using more energy than normal operation, failing to maintain building temperatures according to the thermostat set points, etc. Models of building faults in OpenStudio can be used to estimate fault impacts on building performance and to develop and evaluate FDD algorithms. The aim of the project is to develop fault models of typical heating, ventilating and air conditioning (HVAC) equipment in the United States, and the fault models in this report are grouped as control faults, sensor faults, packaged and split air conditioner faults, water-cooled chiller faults, and other uncategorized faults. The control fault models simulate impacts of inappropriate thermostat control schemes such as an incorrect thermostat set point in unoccupied hours and manual changes of thermostat set point due to extreme outside temperature. Sensor fault models focus on the modeling of sensor biases including economizer relative humidity sensor bias, supply air temperature sensor bias, and water circuit temperature sensor bias. Packaged and split air conditioner fault models simulate refrigerant undercharging, condenser fouling, condenser fan motor efficiency degradation, non-condensable entrainment in refrigerant, and liquid line restriction. Other fault models that are uncategorized include duct fouling, excessive infiltration into the building, and blower and pump motor degradation.

Torsional vibration signal analysis as a diagnostic tool for planetary gear fault detection

Science.gov (United States)

Xue, Song; Howard, Ian

2018-02-01

This paper aims to investigate the effectiveness of using the torsional vibration signal as a diagnostic tool for planetary gearbox faults detection. The traditional approach for condition monitoring of the planetary gear uses a stationary transducer mounted on the ring gear casing to measure all the vibration data when the planet gears pass by with the rotation of the carrier arm. However, the time variant vibration transfer paths between the stationary transducer and the rotating planet gear modulate the resultant vibration spectra and make it complex. Torsional vibration signals are theoretically free from this modulation effect and therefore, it is expected to be much easier and more effective to diagnose planetary gear faults using the fault diagnostic information extracted from the torsional vibration. In this paper, a 20 degree of freedom planetary gear lumped-parameter model was developed to obtain the gear dynamic response. In the model, the gear mesh stiffness variations are the main internal vibration generation mechanism and the finite element models were developed for calculation of the sun-planet and ring-planet gear mesh stiffnesses. Gear faults on different components were created in the finite element models to calculate the resultant gear mesh stiffnesses, which were incorporated into the planetary gear model later on to obtain the faulted vibration signal. Some advanced signal processing techniques were utilized to analyses the fault diagnostic results from the torsional vibration. It was found that the planetary gear torsional vibration not only successfully detected the gear fault, but also had the potential to indicate the location of the gear fault. As a result, the planetary gear torsional vibration can be considered an effective alternative approach for planetary gear condition monitoring.

Fault diagnostics for turbo-shaft engine sensors based on a simplified on-board model.

Science.gov (United States)

Lu, Feng; Huang, Jinquan; Xing, Yaodong

2012-01-01

Combining a simplified on-board turbo-shaft model with sensor fault diagnostic logic, a model-based sensor fault diagnosis method is proposed. The existing fault diagnosis method for turbo-shaft engine key sensors is mainly based on a double redundancies technique, and this can't be satisfied in some occasions as lack of judgment. The simplified on-board model provides the analytical third channel against which the dual channel measurements are compared, while the hardware redundancy will increase the structure complexity and weight. The simplified turbo-shaft model contains the gas generator model and the power turbine model with loads, this is built up via dynamic parameters method. Sensor fault detection, diagnosis (FDD) logic is designed, and two types of sensor failures, such as the step faults and the drift faults, are simulated. When the discrepancy among the triplex channels exceeds a tolerance level, the fault diagnosis logic determines the cause of the difference. Through this approach, the sensor fault diagnosis system achieves the objectives of anomaly detection, sensor fault diagnosis and redundancy recovery. Finally, experiments on this method are carried out on a turbo-shaft engine, and two types of faults under different channel combinations are presented. The experimental results show that the proposed method for sensor fault diagnostics is efficient.

Fault Diagnostics for Turbo-Shaft Engine Sensors Based on a Simplified On-Board Model

Directory of Open Access Journals (Sweden)

Yaodong Xing

2012-08-01

Full Text Available Combining a simplified on-board turbo-shaft model with sensor fault diagnostic logic, a model-based sensor fault diagnosis method is proposed. The existing fault diagnosis method for turbo-shaft engine key sensors is mainly based on a double redundancies technique, and this can’t be satisfied in some occasions as lack of judgment. The simplified on-board model provides the analytical third channel against which the dual channel measurements are compared, while the hardware redundancy will increase the structure complexity and weight. The simplified turbo-shaft model contains the gas generator model and the power turbine model with loads, this is built up via dynamic parameters method. Sensor fault detection, diagnosis (FDD logic is designed, and two types of sensor failures, such as the step faults and the drift faults, are simulated. When the discrepancy among the triplex channels exceeds a tolerance level, the fault diagnosis logic determines the cause of the difference. Through this approach, the sensor fault diagnosis system achieves the objectives of anomaly detection, sensor fault diagnosis and redundancy recovery. Finally, experiments on this method are carried out on a turbo-shaft engine, and two types of faults under different channel combinations are presented. The experimental results show that the proposed method for sensor fault diagnostics is efficient.

Confirmation of Thermal Images and Vibration Signals for Intelligent Machine Fault Diagnostics

Directory of Open Access Journals (Sweden)

Achmad Widodo

2012-01-01

Full Text Available This paper deals with the maintenance technique for industrial machinery using the artificial neural network so-called self-organizing map (SOM. The aim of this work is to develop intelligent maintenance system for machinery based on an alternative way, namely, thermal images instead of vibration signals. SOM is selected due to its simplicity and is categorized as an unsupervised algorithm. Following the SOM training, machine fault diagnostics is performed by using the pattern recognition technique of machine conditions. The data used in this work are thermal images and vibration signals, which were acquired from machine fault simulator (MFS. It is a reliable tool and is able to simulate several conditions of faulty machine such as unbalance, misalignment, looseness, and rolling element bearing faults (outer race, inner race, ball, and cage defects. Data acquisition were conducted simultaneously by infrared thermography camera and vibration sensors installed in the MFS. The experimental data are presented as thermal image and vibration signal in the time domain. Feature extraction was carried out to obtain salient features sensitive to machine conditions from thermal images and vibration signals. These features are then used to train the SOM for intelligent machine diagnostics process. The results show that SOM can perform intelligent fault diagnostics with plausible accuracies.

Advanced monitoring, fault diagnostics, and maintenance of cryogenic systems

CERN Document Server

Girone, Mario; Pezzetti, Marco

In this Thesis, advanced methods and techniques of monitoring, fault diagnostics, and predictive maintenance for cryogenic processes and systems are described. In particular, in Chapter 1, mainstreams in research on measurement systems for cryogenic processes are reviewed with the aim of dening key current trends and possible future evolutions. Then, in Chapter 2, several innovative methods are proposed. A transducer based on a virtual ow meter is presented for monitoring helium distribution and consumption in cryogenic systems for particle accelerators [1]. Furthermore, a comprehensive metrological analysis of the proposed transducer for verifying the metrological performance and pointing out most critical uncertainty sources is described [2]. A model-based method for fault detection and early-stage isolation, able to work with few records of Frequency Response Function (FRF) on an unfaulty compressor, is then proposed [3]. To enrich the proposal, a distributed diagnostic procedure, based on a micro-genetic...

Eight meeting of the ITER diagnostic expert group

International Nuclear Information System (INIS)

Costley, A.E.; Young, K.M.

1998-01-01

The 8. Meeting of the ITER Diagnostics Expert Group which was held in San Diego, February 1998 had two main technical goals: to discuss the status and plans for developing kinetic control, and to review the current status of the design of the magnetic system

Telecontrol - Expert systems. Real-time monitoring and remote diagnostic

Energy Technology Data Exchange (ETDEWEB)

Lam, A.

1996-09-01

The role of expert systems in programming simple and complex tasks in utilities companies was discussed with examples from B.C. Hydro, where expert systems have been used in such diverse applications as an in-house programmable logic controller (PLC) training course, and a machine audit on a 150 MW steam turbine generating unit at their Burrard Thermal Generating Plant. The PLC tutoring program uses expert system technology for the air blast circuit breakers` air drier system, for individualized on-site training. The steam turbine audits (an eight-month long project) were performed remotely by dialing an on-site computer configured with customized expert software. Details of these, and other potential applications, such as transformer monitoring and diagnostics, circuit breaker performance analysis, and information management, were described.

[Development of expert diagnostic system for common respiratory diseases].

Science.gov (United States)

Xu, Wei-hua; Chen, You-ling; Yan, Zheng

2014-03-01

To develop an internet-based expert diagnostic system for common respiratory diseases. SaaS system was used to build architecture; pattern of forward reasoning was applied for inference engine design; ASP.NET with C# from the tool pack of Microsoft Visual Studio 2005 was used for website-interview medical expert system.The database of the system was constructed with Microsoft SQL Server 2005. The developed expert system contained large data memory and high efficient function of data interview and data analysis for diagnosis of various diseases.The users were able to perform this system to obtain diagnosis for common respiratory diseases via internet. The developed expert system may be used for internet-based diagnosis of various respiratory diseases,particularly in telemedicine setting.

Modeling and Measurement Constraints in Fault Diagnostics for HVAC Systems

Energy Technology Data Exchange (ETDEWEB)

Najafi, Massieh; Auslander, David M.; Bartlett, Peter L.; Haves, Philip; Sohn, Michael D.

2010-05-30

Many studies have shown that energy savings of five to fifteen percent are achievable in commercial buildings by detecting and correcting building faults, and optimizing building control systems. However, in spite of good progress in developing tools for determining HVAC diagnostics, methods to detect faults in HVAC systems are still generally undeveloped. Most approaches use numerical filtering or parameter estimation methods to compare data from energy meters and building sensors to predictions from mathematical or statistical models. They are effective when models are relatively accurate and data contain few errors. In this paper, we address the case where models are imperfect and data are variable, uncertain, and can contain error. We apply a Bayesian updating approach that is systematic in managing and accounting for most forms of model and data errors. The proposed method uses both knowledge of first principle modeling and empirical results to analyze the system performance within the boundaries defined by practical constraints. We demonstrate the approach by detecting faults in commercial building air handling units. We find that the limitations that exist in air handling unit diagnostics due to practical constraints can generally be effectively addressed through the proposed approach.

An Integrated Architecture for On-Board Aircraft Engine Performance Trend Monitoring and Gas Path Fault Diagnostics

Science.gov (United States)

Simon, Donald L.

2010-01-01

Aircraft engine performance trend monitoring and gas path fault diagnostics are closely related technologies that assist operators in managing the health of their gas turbine engine assets. Trend monitoring is the process of monitoring the gradual performance change that an aircraft engine will naturally incur over time due to turbomachinery deterioration, while gas path diagnostics is the process of detecting and isolating the occurrence of any faults impacting engine flow-path performance. Today, performance trend monitoring and gas path fault diagnostic functions are performed by a combination of on-board and off-board strategies. On-board engine control computers contain logic that monitors for anomalous engine operation in real-time. Off-board ground stations are used to conduct fleet-wide engine trend monitoring and fault diagnostics based on data collected from each engine each flight. Continuing advances in avionics are enabling the migration of portions of the ground-based functionality on-board, giving rise to more sophisticated on-board engine health management capabilities. This paper reviews the conventional engine performance trend monitoring and gas path fault diagnostic architecture commonly applied today, and presents a proposed enhanced on-board architecture for future applications. The enhanced architecture gains real-time access to an expanded quantity of engine parameters, and provides advanced on-board model-based estimation capabilities. The benefits of the enhanced architecture include the real-time continuous monitoring of engine health, the early diagnosis of fault conditions, and the estimation of unmeasured engine performance parameters. A future vision to advance the enhanced architecture is also presented and discussed

Study on Practical Application of Turboprop Engine Condition Monitoring and Fault Diagnostic System Using Fuzzy-Neuro Algorithms

Science.gov (United States)

Kong, Changduk; Lim, Semyeong; Kim, Keunwoo

2013-03-01

The Neural Networks is mostly used to engine fault diagnostic system due to its good learning performance, but it has a drawback due to low accuracy and long learning time to build learning data base. This work builds inversely a base performance model of a turboprop engine to be used for a high altitude operation UAV using measuring performance data, and proposes a fault diagnostic system using the base performance model and artificial intelligent methods such as Fuzzy and Neural Networks. Each real engine performance model, which is named as the base performance model that can simulate a new engine performance, is inversely made using its performance test data. Therefore the condition monitoring of each engine can be more precisely carried out through comparison with measuring performance data. The proposed diagnostic system identifies firstly the faulted components using Fuzzy Logic, and then quantifies faults of the identified components using Neural Networks leaned by fault learning data base obtained from the developed base performance model. In leaning the measuring performance data of the faulted components, the FFBP (Feed Forward Back Propagation) is used. In order to user's friendly purpose, the proposed diagnostic program is coded by the GUI type using MATLAB.

Pilot study of dynamic Bayesian networks approach for fault diagnostics and accident progression prediction in HTR-PM

Energy Technology Data Exchange (ETDEWEB)

Zhao, Yunfei; Tong, Jiejuan; Zhang, Liguo, E-mail: lgzhang@tsinghua.edu.cn; Zhang, Qin

2015-09-15

Highlights: • Dynamic Bayesian network is used to diagnose and predict accident progress in HTR-PM. • Dynamic Bayesian network model of HTR-PM is built based on detailed system analysis. • LOCA Simulations validate the above model even if part monitors are lost or false. - Abstract: The first high-temperature-reactor pebble-bed demonstration module (HTR-PM) is under construction currently in China. At the same time, development of a system that is used to support nuclear emergency response is in progress. The supporting system is expected to complete two tasks. The first one is diagnostics of the fault in the reactor based on abnormal sensor measurements obtained. The second one is prognostic of the accident progression based on sensor measurements obtained and operator actions. Both tasks will provide valuable guidance for emergency staff to take appropriate protective actions. Traditional method for the two tasks relies heavily on expert judgment, and has been proven to be inappropriate in some cases, such as Three Mile Island accident. To better perform the two tasks, dynamic Bayesian networks (DBN) is introduced in this paper and a pilot study based on the approach is carried out. DBN is advantageous in representing complex dynamic systems and taking full consideration of evidences obtained to perform diagnostics and prognostics. Pearl's loopy belief propagation (LBP) algorithm is recommended for diagnostics and prognostics in DBN. The DBN model of HTR-PM is created based on detailed system analysis and accident progression analysis. A small break loss of coolant accident (SBLOCA) is selected to illustrate the application of the DBN model of HTR-PM in fault diagnostics (FD) and accident progression prognostics (APP). Several advantages of DBN approach compared with other techniques are discussed. The pilot study lays the foundation for developing the nuclear emergency response supporting system (NERSS) for HTR-PM.

An efficient diagnostic technique for distribution systems based on under fault voltages and currents

Energy Technology Data Exchange (ETDEWEB)

Campoccia, A.; Di Silvestre, M.L.; Incontrera, I.; Riva Sanseverino, E. [Dipartimento di Ingegneria Elettrica elettronica e delle Telecomunicazioni, Universita degli Studi di Palermo, viale delle Scienze, 90128 Palermo (Italy); Spoto, G. [Centro per la Ricerca Elettronica in Sicilia, Monreale, Via Regione Siciliana 49, 90046 Palermo (Italy)

2010-10-15

Service continuity is one of the major aspects in the definition of the quality of the electrical energy, for this reason the research in the field of faults diagnostic for distribution systems is spreading ever more. Moreover the increasing interest around modern distribution systems automation for management purposes gives faults diagnostics more tools to detect outages precisely and in short times. In this paper, the applicability of an efficient fault location and characterization methodology within a centralized monitoring system is discussed. The methodology, appropriate for any kind of fault, is based on the use of the analytical model of the network lines and uses the fundamental components rms values taken from the transient measures of line currents and voltages at the MV/LV substations. The fault location and identification algorithm, proposed by the authors and suitably restated, has been implemented on a microprocessor-based device that can be installed at each MV/LV substation. The speed and precision of the algorithm have been tested against the errors deriving from the fundamental extraction within the prescribed fault clearing times and against the inherent precision of the electronic device used for computation. The tests have been carried out using Matlab Simulink for simulating the faulted system. (author)

Reasoning process characteristics in the diagnostic skills of beginner, competent, and expert dentists.

Science.gov (United States)

Crespo, Kathleen E; Torres, José E; Recio, María E

2004-12-01

The purpose of this study was to evaluate qualitative differences in the diagnostic reasoning process at different developmental stages of expertise. A qualitative design was used to study cognitive processes that characterize the diagnosis of oral disease at the stages of beginner (five junior students who had passed the NBDE I), competent (five GPR first-year residents), and expert dentists (five general dentists with ten or more years of experience). Individually, each participant was asked to determine the diagnosis of an oral condition based on a written clinical case, using the think aloud technique and retrospective reports. A subsequent interview was conducted to obtain the participants' diagnostic process model and pathophysiology of the case. The analysis of the verbal protocols indicated that experts referred to the patient's sociomedical context more frequently, demonstrated better organization of ideas, could determine key clinical findings, and had an ability to plan for the search of pertinent information. Fewer diagnostic hypotheses were formulated by participants who used forward reasoning, independent of the stage of development. Beginners requested additional diagnostic aids (radiographs, laboratory tests) more frequently than the competent/expert dentists. Experts recalled typical experiences with patients, while competent/beginner dentists recalled information from didactic courses. Experts evidenced cognitive diagnostic schemas that integrate pathophysiology of disease, while competent and beginner participants had not achieved this integration. We conclude that expert performance is a combination of a knowledge base, reasoning skills, and an accumulation of experiences with patients that is qualitatively different from that of competent and beginner dentists. It is important for dental education to emphasize the teaching of cognitive processes and to incorporate a wide variety of clinical experiences in addition to the teaching of

Hierarchical mixture of experts and diagnostic modeling approach to reduce hydrologic model structural uncertainty: STRUCTURAL UNCERTAINTY DIAGNOSTICS

Energy Technology Data Exchange (ETDEWEB)

Moges, Edom [Civil and Environmental Engineering Department, Washington State University, Richland Washington USA; Demissie, Yonas [Civil and Environmental Engineering Department, Washington State University, Richland Washington USA; Li, Hong-Yi [Hydrology Group, Pacific Northwest National Laboratory, Richland Washington USA

2016-04-01

In most water resources applications, a single model structure might be inadequate to capture the dynamic multi-scale interactions among different hydrological processes. Calibrating single models for dynamic catchments, where multiple dominant processes exist, can result in displacement of errors from structure to parameters, which in turn leads to over-correction and biased predictions. An alternative to a single model structure is to develop local expert structures that are effective in representing the dominant components of the hydrologic process and adaptively integrate them based on an indicator variable. In this study, the Hierarchical Mixture of Experts (HME) framework is applied to integrate expert model structures representing the different components of the hydrologic process. Various signature diagnostic analyses are used to assess the presence of multiple dominant processes and the adequacy of a single model, as well as to identify the structures of the expert models. The approaches are applied for two distinct catchments, the Guadalupe River (Texas) and the French Broad River (North Carolina) from the Model Parameter Estimation Experiment (MOPEX), using different structures of the HBV model. The results show that the HME approach has a better performance over the single model for the Guadalupe catchment, where multiple dominant processes are witnessed through diagnostic measures. Whereas, the diagnostics and aggregated performance measures prove that French Broad has a homogeneous catchment response, making the single model adequate to capture the response.

Vibration monitoring and fault diagnostics of a thermal power plant

International Nuclear Information System (INIS)

Hafeez, T.; Ghani, R.; Chohan, G.Y.; Amir, M.

2003-01-01

A thermal power plant was monitored from HP-turbine to the generator end. The vibration data at different plant locations was obtained with the help of a data collector/analyzer. The spectra of-all locations generate the symptoms for different problems of moderate and high vibration levels like bent shaft, misalignment in the exciter rotor and three couplings, mechanical looseness on generator and exciter sides. The possible causes of these faults are discussed on the basis of presented vibration spectra in this paper. The faults were later on rectified on the basis of this diagnostics. (author)

Diagnostic expert system in the PF LINAC

International Nuclear Information System (INIS)

Abe, Isamu; Nakahara, Kazuo; Kitamura, Masaharu.

1992-01-01

A prototype diagnostic expert system (ES) was developed for the Photon Factory 2.5-GeV electron/positron LINAC injector system. The ES has been on-lined with the conventional linac computer network for receiving real data. This project was undertaken in an attempt to reduce the linac operator's mental workload, diagnosis duties, and to explore Artificial Intelligence (AI) technologies. The outlook for ES and its problems, and what has been achieved are outlined in this presentation. (author)

Risk perception of diagnostic and therapeutic radiological applications. Comparison of experts and the public

International Nuclear Information System (INIS)

Arranz, L.; Macias, M.T.; Prades, A.; Sola, R.; Martinez-Arias, R.

2000-01-01

Recent research has found many differences between experts and lay people in judgements of radiological risks. However, most of these studies were carried out on experts from nuclear power plants, regulatory bodies etc. This paper analyses the differences among several groups of 'experts' coming from the Health area and the lay people. A survey was designed to assess the perceived seriousness of seven diagnostic and therapeutic applications: conventional diagnostic radiology, computed tomography, chemotherapy, ecography examinations, radiotherapy, and diagnostic and therapeutic nuclear medicine. The questionnaire was distributed to samples of experts (professionals exposed to ionizing radiations, and other health professionals), and outpatients. All samples were selected from ten countries: Argentine, Brazil, Colombia, Cuba, Ecuador, Mexico, Panama, Peru, Uruguay, and Spain, thanks to the collaboration of the different National Radioprotection Societies of the above mentioned countries, and of other concerned professionals (in case they didn't have any association at the time). The following comparisons will be presented: 1) Differences between experts' and the public; 2) differences among several groups of 'experts'; 3) within the 'expert' sample, differences between perceived seriousness as a patient and as a professional at risk; 4) within the public sample, individual differences related to some socio-demographic variables. A cross-cultural analysis of the above mentioned comparisons will also be carried out. (author)

Risk perception of diagnostic and therapeutic radiological applications. Comparison of experts and the public

Energy Technology Data Exchange (ETDEWEB)

Arranz, L. [Hospital Ramon y Cajal, Madrid (Spain); Macias, M.T. [CSIC, Madrid (Spain); Prades, A.; Sola, R. [Ciemat, Madrid (Spain); Martinez-Arias, R. [Universidad Complutense, Madrid (Spain)

2000-05-01

Recent research has found many differences between experts and lay people in judgements of radiological risks. However, most of these studies were carried out on experts from nuclear power plants, regulatory bodies etc. This paper analyses the differences among several groups of 'experts' coming from the Health area and the lay people. A survey was designed to assess the perceived seriousness of seven diagnostic and therapeutic applications: conventional diagnostic radiology, computed tomography, chemotherapy, ecography examinations, radiotherapy, and diagnostic and therapeutic nuclear medicine. The questionnaire was distributed to samples of experts (professionals exposed to ionizing radiations, and other health professionals), and outpatients. All samples were selected from ten countries: Argentine, Brazil, Colombia, Cuba, Ecuador, Mexico, Panama, Peru, Uruguay, and Spain, thanks to the collaboration of the different National Radioprotection Societies of the above mentioned countries, and of other concerned professionals (in case they didn't have any association at the time). The following comparisons will be presented: 1) Differences between experts' and the public; 2) differences among several groups of 'experts'; 3) within the 'expert' sample, differences between perceived seriousness as a patient and as a professional at risk; 4) within the public sample, individual differences related to some socio-demographic variables. A cross-cultural analysis of the above mentioned comparisons will also be carried out. (author)

Faults Diagnostics of Railway Axle Bearings Based on IMF’s Confidence Index Algorithm for Ensemble EMD

Science.gov (United States)

Yi, Cai; Lin, Jianhui; Zhang, Weihua; Ding, Jianming

2015-01-01

As train loads and travel speeds have increased over time, railway axle bearings have become critical elements which require more efficient non-destructive inspection and fault diagnostics methods. This paper presents a novel and adaptive procedure based on ensemble empirical mode decomposition (EEMD) and Hilbert marginal spectrum for multi-fault diagnostics of axle bearings. EEMD overcomes the limitations that often hypothesize about data and computational efforts that restrict the application of signal processing techniques. The outputs of this adaptive approach are the intrinsic mode functions that are treated with the Hilbert transform in order to obtain the Hilbert instantaneous frequency spectrum and marginal spectrum. Anyhow, not all the IMFs obtained by the decomposition should be considered into Hilbert marginal spectrum. The IMFs’ confidence index arithmetic proposed in this paper is fully autonomous, overcoming the major limit of selection by user with experience, and allows the development of on-line tools. The effectiveness of the improvement is proven by the successful diagnosis of an axle bearing with a single fault or multiple composite faults, e.g., outer ring fault, cage fault and pin roller fault. PMID:25970256

CRISP. Simulation tool for fault detection and diagnostics in high-DG power networks

International Nuclear Information System (INIS)

Fontela, M.; Andrieu, C.; Raison, B.

2004-08-01

This document gives a description of a tool proposed for fault detection and diagnostics. The main principles of the functions of fault localization are described and detailed for a given MV network that will be used for the ICT experiment in Grenoble (experiment 3B). The aim of the tool is to create a technical, simple and realistic context for testing ICT dedicated to an electrical application. The tool gives the expected inputs and outputs contents of the various distributed ICT components when a fault occurs in a given MV network. So the requirements for the ICT components are given in term of expected data collected, analysed and transmitted. Several examples are given in order to illustrate the inputs/outputs in case of different faults. The tool includes a topology description which is a main aspect to develop in the future for managing the distribution network. Updating topology in real time will become necessary for fault diagnostic and protection, but also necessary for the various possible added applications (local market balance and local electrical power quality for instance). The tool gives a context and a simple view for the ICT components behaviours assuming an ideal response and transmission from them. The real characteristics and possible limitations for the ICT (information latency, congestion, security) will be established during the experiments from the same context described in the HTFD tool

Gearbox tooth cut fault diagnostics using acoustic emission and vibration sensors--a comparative study.

Science.gov (United States)

Qu, Yongzhi; He, David; Yoon, Jae; Van Hecke, Brandon; Bechhoefer, Eric; Zhu, Junda

2014-01-14

In recent years, acoustic emission (AE) sensors and AE-based techniques have been developed and tested for gearbox fault diagnosis. In general, AE-based techniques require much higher sampling rates than vibration analysis-based techniques for gearbox fault diagnosis. Therefore, it is questionable whether an AE-based technique would give a better or at least the same performance as the vibration analysis-based techniques using the same sampling rate. To answer the question, this paper presents a comparative study for gearbox tooth damage level diagnostics using AE and vibration measurements, the first known attempt to compare the gearbox fault diagnostic performance of AE- and vibration analysis-based approaches using the same sampling rate. Partial tooth cut faults are seeded in a gearbox test rig and experimentally tested in a laboratory. Results have shown that the AE-based approach has the potential to differentiate gear tooth damage levels in comparison with the vibration-based approach. While vibration signals are easily affected by mechanical resonance, the AE signals show more stable performance.

Expert System for Diagnostics and Status Monitoring of NPP Water Chemistry Condition

International Nuclear Information System (INIS)

Shvedova, M.N.; Kritski, V.G.; Zakharova, S.V.; Nikolaev, F.V.; Benediktov, V.B.

2002-01-01

Water chemistry condition (WCC) has been the subject of constant study and improvement up to the present day. It is connected with the presence of a direct relationship between the violation of water chemistry regulation on the one hand and components reliability of the circuit's equipment and cost-effectiveness of their operation on the other. It dictates the necessity to apply different optimization methods in the field of monitoring and use of information - analytical and diagnostic systems to assess WCC quality, control and support. By now NPP experts have broad experience in revealing and removing the causes of WCC disturbances. However this knowledge is often of an intuitive, non-classified nature, scattered among various working documents, which makes their transfer difficult. Based on what has been mentioned above, special attention is currently being paid to the problem of creating expert diagnostic systems for supporting the optimum WCC. The existing developments in this field (DIWA, Smart chem Works, the water quality control system at the Onagava NPP etc. [1,3,4,5] are based on wide use of experts' knowledge. Such expert diagnostic systems for supporting WCC refer to the new generation of intellectual control methods, which allow the incorporation of the latest achievements both in the field of water chemistry simulation and in the field of artificial intelligence and computer technologies. LI 'VNIPIET' employees have, for several years, been developing an expert diagnostic system for supporting WCC and status monitoring of RBMK - reactor NPPs [2]. This system has not only conveniently organized the traditional functions of information acquisition and storage, a complete presentation of information in the form of tables, graphs of a dynamical changes of parameters and formation regular reports, diagnostic functions and issuing recommendations on WCC correction, but it also allows the assessment of confidence in the diagnosis made, relying on a wide

Development of fault diagnostic technique using reactor noise analysis

International Nuclear Information System (INIS)

Park, Jin Ho; Kim, J. S.; Oh, I. S.; Ryu, J. S.; Joo, Y. S.; Choi, S.; Yoon, D. B.

1999-04-01

The ultimate goal of this project is to establish the analysis technique to diagnose the integrity of reactor internals using reactor noise. The reactor noise analyses techniques for the PWR and CANDU NPP(Nuclear Power Plants) were established by which the dynamic characteristics of reactor internals and SPND instrumentations could be identified, and the noise database corresponding to each plant(both Korean and foreign one) was constructed and compared. Also the change of dynamic characteristics of the Ulchin 1 and 2 reactor internals were simulated under presumed fault conditions. Additionally portable reactor noise analysis system was developed so that real time noise analysis could directly be able to be performed at plant site. The reactor noise analyses techniques developed and the database obtained from the fault simulation, can be used to establish a knowledge based expert system to diagnose the NPP's abnormal conditions. And the portable reactor noise analysis system may be utilized as a substitute for plant IVMS(Internal Vibration Monitoring System). (author)

Development of fault diagnostic technique using reactor noise analysis

Energy Technology Data Exchange (ETDEWEB)

Park, Jin Ho; Kim, J. S.; Oh, I. S.; Ryu, J. S.; Joo, Y. S.; Choi, S.; Yoon, D. B

1999-04-01

The ultimate goal of this project is to establish the analysis technique to diagnose the integrity of reactor internals using reactor noise. The reactor noise analyses techniques for the PWR and CANDU NPP(Nuclear Power Plants) were established by which the dynamic characteristics of reactor internals and SPND instrumentations could be identified, and the noise database corresponding to each plant(both Korean and foreign one) was constructed and compared. Also the change of dynamic characteristics of the Ulchin 1 and 2 reactor internals were simulated under presumed fault conditions. Additionally portable reactor noise analysis system was developed so that real time noise analysis could directly be able to be performed at plant site. The reactor noise analyses techniques developed and the database obtained from the fault simulation, can be used to establish a knowledge based expert system to diagnose the NPP's abnormal conditions. And the portable reactor noise analysis system may be utilized as a substitute for plant IVMS(Internal Vibration Monitoring System). (author)

Sequential fault diagnosis for mechatronics system using diagnostic hybrid bond graph and composite harmony search

Directory of Open Access Journals (Sweden)

Ming Yu

2015-12-01

Full Text Available This article proposes a sequential fault diagnosis method to handle asynchronous distinct faults using diagnostic hybrid bond graph and composite harmony search. The faults under consideration include fault mode, abrupt fault, and intermittent fault. The faults can occur in different time instances, which add to the difficulty of decision making for fault diagnosis. This is because the earlier occurred fault can exhibit fault symptom which masks the fault symptom of latter occurred fault. In order to solve this problem, a sequential identification algorithm is developed in which the identification task is reactivated based on two conditions. The first condition is that the latter occurred fault has at least one inconsistent coherence vector element which is consistent in coherence vector of the earlier occurred fault, and the second condition is that the existing fault coherence vector has the ability to hide other faults and the second-level residual exceeds the threshold. A new composite harmony search which is capable of handling continuous variables and binary variables simultaneously is proposed for identification purpose. Experiments on a mobile robot system are conducted to assess the proposed sequential fault diagnosis algorithm.

Ares I-X Ground Diagnostic Prototype

Science.gov (United States)

Schwabacher, Mark A.; Martin, Rodney Alexander; Waterman, Robert D.; Oostdyk, Rebecca Lynn; Ossenfort, John P.; Matthews, Bryan

2010-01-01

The automation of pre-launch diagnostics for launch vehicles offers three potential benefits: improving safety, reducing cost, and reducing launch delays. The Ares I-X Ground Diagnostic Prototype demonstrated anomaly detection, fault detection, fault isolation, and diagnostics for the Ares I-X first-stage Thrust Vector Control and for the associated ground hydraulics while the vehicle was in the Vehicle Assembly Building at Kennedy Space Center (KSC) and while it was on the launch pad. The prototype combines three existing tools. The first tool, TEAMS (Testability Engineering and Maintenance System), is a model-based tool from Qualtech Systems Inc. for fault isolation and diagnostics. The second tool, SHINE (Spacecraft Health Inference Engine), is a rule-based expert system that was developed at the NASA Jet Propulsion Laboratory. We developed SHINE rules for fault detection and mode identification, and used the outputs of SHINE as inputs to TEAMS. The third tool, IMS (Inductive Monitoring System), is an anomaly detection tool that was developed at NASA Ames Research Center. The three tools were integrated and deployed to KSC, where they were interfaced with live data. This paper describes how the prototype performed during the period of time before the launch, including accuracy and computer resource usage. The paper concludes with some of the lessons that we learned from the experience of developing and deploying the prototype.

Vibrational methods of the overhead gas-pipelines technological equipment diagnostics

International Nuclear Information System (INIS)

Zakhezin, A.M.; Malysheva, T.V.

2001-01-01

The diagnostic methods of overhead gas-pipelines of the technical equipment of gas-compressor station are considered in this article by carrying out registration certification documentation. Some faults of overhead technical gas-pipelines have been proposed. This paper is devoted to the diagnostic methods of the whole gas- pipelines and their parts for some faults during expert checking fulfillment and carrying out registration certification documentation. The analysis of all defects allows to determine a 'between-repairs interval', to develop some operations to avoid these faults and to estimate the repair operation quality, to reduce failure probability. As an example of the effectiveness of technical condition service of vibrational methods by expertise fulfillment have been considered for some defects of the overhead pipelines. (author)

The development of the intelligent diagnostic expert system for high power dye-laser MOPA system

International Nuclear Information System (INIS)

Liu Lianhua; Yang Wenxi; Zhang Xiaowei; Dan Yongjun

2014-01-01

A intelligent diagnostic expert system was required to simulate the expert thinking process of solving problem in experiment and to real-time judge the running state of the experiment system. The intelligent diagnostic expert system for dye-laser MOPA system was build with the modular design of separated knowledge base and inference engine, the RETE algorithm rules match, the asynchronous operation, and multithreading technology. The experiment result indicated that the system could real-time analysis and diagnose the running state of dye-laser MOPA system with advantages of high diagnosis efficiency, good instantaneity and strong expansibility. (authors)

Gearbox Tooth Cut Fault Diagnostics Using Acoustic Emission and Vibration Sensors — A Comparative Study

Directory of Open Access Journals (Sweden)

Yongzhi Qu

2014-01-01

Full Text Available In recent years, acoustic emission (AE sensors and AE-based techniques have been developed and tested for gearbox fault diagnosis. In general, AE-based techniques require much higher sampling rates than vibration analysis-based techniques for gearbox fault diagnosis. Therefore, it is questionable whether an AE-based technique would give a better or at least the same performance as the vibration analysis-based techniques using the same sampling rate. To answer the question, this paper presents a comparative study for gearbox tooth damage level diagnostics using AE and vibration measurements, the first known attempt to compare the gearbox fault diagnostic performance of AE- and vibration analysis-based approaches using the same sampling rate. Partial tooth cut faults are seeded in a gearbox test rig and experimentally tested in a laboratory. Results have shown that the AE-based approach has the potential to differentiate gear tooth damage levels in comparison with the vibration-based approach. While vibration signals are easily affected by mechanical resonance, the AE signals show more stable performance.

Gearbox Tooth Cut Fault Diagnostics Using Acoustic Emission and Vibration Sensors — A Comparative Study

Science.gov (United States)

Qu, Yongzhi; He, David; Yoon, Jae; Van Hecke, Brandon; Bechhoefer, Eric; Zhu, Junda

2014-01-01

In recent years, acoustic emission (AE) sensors and AE-based techniques have been developed and tested for gearbox fault diagnosis. In general, AE-based techniques require much higher sampling rates than vibration analysis-based techniques for gearbox fault diagnosis. Therefore, it is questionable whether an AE-based technique would give a better or at least the same performance as the vibration analysis-based techniques using the same sampling rate. To answer the question, this paper presents a comparative study for gearbox tooth damage level diagnostics using AE and vibration measurements, the first known attempt to compare the gearbox fault diagnostic performance of AE- and vibration analysis-based approaches using the same sampling rate. Partial tooth cut faults are seeded in a gearbox test rig and experimentally tested in a laboratory. Results have shown that the AE-based approach has the potential to differentiate gear tooth damage levels in comparison with the vibration-based approach. While vibration signals are easily affected by mechanical resonance, the AE signals show more stable performance. PMID:24424467

Post-glacial faulting in the Lansjaerv area, Northern Sweden. Comments from the expert group on a field visit at the Molberget post-glacial fault area, 1991

International Nuclear Information System (INIS)

Stanfors, R.; Ericsson, L.O.

1993-05-01

Post-glacial faults have been recognized in the northern Baltic shield for several decades. It is important to evaluate whether such neotectonic movements can lead to new fracturing or decisively alter the geohydrological or geohydrochemical situation around a final repository for spent nuclear fuel. The post-glacial Lansjaerv fault was chosen for an interdisciplinary study because of its relative accessibility. The goals of the study were to assess the mechanisms that caused present day scraps, to clarify the extent of any recent fracturing and to clarify the extent of any ongoing movements. All these objectives were reasonably met through a series of studies, which have been performed by SKB during 1986-1992 in two phases. This report gives a summary of the first phase of the Lansjaerv study (1986-1989) and describes achievements that have been gained during the second phase of the study. As a final of the field-work in the Lansjaerv area a meeting combined with a field excursion was arranged by SKB in June 1991 for a group of international experts. Comments from the expert group on the excursion and the overall Lansjaerv project are presented. One of the major conclusions is that the Lansjaerv post-glacial fault reactivated pre-existing old structures and that the causes of the post-glacial movements is a combination of plate tectonics and deglaciation

Application Of The CSRL Language To The Design Of Diagnostic Expert Systems: The Moodis Experience, A Preliminary Report

Science.gov (United States)

Bravos, Angelo; Hill, Howard; Choca, James; Bresolin, Linda B.; Bresolin, Michael J.

1986-03-01

Computer technology is rapidly becoming an inseparable part of many health science specialties. Recently, a new area of computer technology, namely Artificial Intelligence, has been applied toward assisting the medical experts in their diagnostic and therapeutic decision making process. MOODIS is an experimental diagnostic expert system which assists Psychiatry specialists in diagnosing human Mood Disorders, better known as Affective Disorders. Its diagnostic methodology is patterned after MDX, a diagnostic expert system developed at LAIR (Laboratory for Artificial Intelligence Research) of Ohio State University. MOODIS is implemented in CSRL (Conceptual Structures Representation Language) also developed at LAIR. This paper describes MOODIS in terms of conceptualization and requirements, and discusses why the MDX approach and CSRL were chosen.

Intelligent systems in technical and medical diagnostics

CERN Document Server

Korbicz, Jozef

2013-01-01

For many years technical and medical diagnostics has been the area of intensive scientific research. It covers well-established topics as well as emerging developments in control engineering, artificial intelligence, applied mathematics, pattern recognition and statistics. At the same time, a growing number of applications of different fault diagnosis methods, especially in electrical, mechanical, chemical and medical engineering, is being observed. This monograph contains a collection of 44 carefully selected papers contributed by experts in technical and medical diagnostics, and constitutes

Final results from the development of the diagnostic expert system DESYRE

International Nuclear Information System (INIS)

Scherer, K.P.; Eggert, H.; Sheleisiek, K.; Stille, P.; Schoeller, H.

1997-01-01

In the Kernforschungszentrum Karlsruhe (KfK), a distributed knowledge based diagnostic system is developed to supervise the primary system including the core of the Kompakte Natriumgekuehlte Kernreaktoranlage (KNK II), a 20 MWe experimental fast reactor. The problem is to detect anomalies and disturbances in the beginning state before fault propagation - early diagnosis - and provide the scram analysis to detect the causality when a system shutdwon occurs. (author). 9 refs, 15 figs

Study on Unified Chaotic System-Based Wind Turbine Blade Fault Diagnostic System

Science.gov (United States)

Kuo, Ying-Che; Hsieh, Chin-Tsung; Yau, Her-Terng; Li, Yu-Chung

At present, vibration signals are processed and analyzed mostly in the frequency domain. The spectrum clearly shows the signal structure and the specific characteristic frequency band is analyzed, but the number of calculations required is huge, resulting in delays. Therefore, this study uses the characteristics of a nonlinear system to load the complete vibration signal to the unified chaotic system, applying the dynamic error to analyze the wind turbine vibration signal, and adopting extenics theory for artificial intelligent fault diagnosis of the analysis signal. Hence, a fault diagnostor has been developed for wind turbine rotating blades. This study simulates three wind turbine blade states, namely stress rupture, screw loosening and blade loss, and validates the methods. The experimental results prove that the unified chaotic system used in this paper has a significant effect on vibration signal analysis. Thus, the operating conditions of wind turbines can be quickly known from this fault diagnostic system, and the maintenance schedule can be arranged before the faults worsen, making the management and implementation of wind turbines smoother, so as to reduce many unnecessary costs.

Photolithography diagnostic expert systems: a systematic approach to problem solving in a wafer fabrication facility

Science.gov (United States)

Weatherwax Scott, Caroline; Tsareff, Christopher R.

1990-06-01

One of the main goals of process engineering in the semiconductor industry is to improve wafer fabrication productivity and throughput. Engineers must work continuously toward this goal in addition to performing sustaining and development tasks. To accomplish these objectives, managers must make efficient use of engineering resources. One of the tools being used to improve efficiency is the diagnostic expert system. Expert systems are knowledge based computer programs designed to lead the user through the analysis and solution of a problem. Several photolithography diagnostic expert systems have been implemented at the Hughes Technology Center to provide a systematic approach to process problem solving. This systematic approach was achieved by documenting cause and effect analyses for a wide variety of processing problems. This knowledge was organized in the form of IF-THEN rules, a common structure for knowledge representation in expert system technology. These rules form the knowledge base of the expert system which is stored in the computer. The systems also include the problem solving methodology used by the expert when addressing a problem in his area of expertise. Operators now use the expert systems to solve many process problems without engineering assistance. The systems also facilitate the collection of appropriate data to assist engineering in solving unanticipated problems. Currently, several expert systems have been implemented to cover all aspects of the photolithography process. The systems, which have been in use for over a year, include wafer surface preparation (HMDS), photoresist coat and softbake, align and expose on a wafer stepper, and develop inspection. These systems are part of a plan to implement an expert system diagnostic environment throughout the wafer fabrication facility. In this paper, the systems' construction is described, including knowledge acquisition, rule construction, knowledge refinement, testing, and evaluation. The roles

Detecting and diagnosing SSME faults using an autoassociative neural network topology

Science.gov (United States)

Ali, M.; Dietz, W. E.; Kiech, E. L.

1989-01-01

An effort is underway at the University of Tennessee Space Institute to develop diagnostic expert system methodologies based on the analysis of patterns of behavior of physical mechanisms. In this approach, fault diagnosis is conceptualized as the mapping or association of patterns of sensor data to patterns representing fault conditions. Neural networks are being investigated as a means of storing and retrieving fault scenarios. Neural networks offer several powerful features in fault diagnosis, including (1) general pattern matching capabilities, (2) resistance to noisy input data, (3) the ability to be trained by example, and (4) the potential for implementation on parallel computer architectures. This paper presents (1) an autoassociative neural network topology, i.e. the network input and output is identical when properly trained, and hence learning is unsupervised; (2) the training regimen used; and (3) the response of the system to inputs representing both previously observed and unkown fault scenarios. The effects of noise on the integrity of the diagnosis are also evaluated.

Expert system for diagnostics and status monitoring of NPP water chemistry condition

International Nuclear Information System (INIS)

Shvedova, M.N.; Kritski, V.G.; Zakharova, S.V.; Benediktov, V.B.; Nikolaev, F.V.

2002-01-01

Water chemistry condition (WCC) has been the subject of constant study and improvement up to the present day. It is connected with the presence of a direct relationship between the violation of water chemistry regulation on the one hand and components reliability of the circuit's equipment and cost-effectiveness of their operation on the other. It dictates the necessity to apply different optimization methods in the field of monitoring and use of information analytical and diagnostic systems to assess WCC quality, control and support. LI ''VNIPIET'' employees have, for several years, been developing an expert diagnostic system for supporting WCC and status monitoring of RBMK - reactor NPPs [2]. This system has not only conveniently organized the traditional functions of information acquisition and storage, a complete presentation of information in the form of tables, graphs of a dynamical changes of parameters and formation regular reports, diagnostic functions and issuing recommendations on WCC correction, but it also allows the assessment of confidence in the diagnosis made, relying on a wide range of numerical estimates, which were calculated by the use of expert data, and to make a credible prediction of an existing situation development. (authors)

Scratching the surface of tomorrow's diagnostics: the Editor-in-Chief's opinion at the 15th year of Expert Review of Molecular Diagnostics.

Science.gov (United States)

Lorincz, Attila; Raison, Claire

2015-01-01

Interview with Attila Lorincz by Claire Raison (Commissioning Editor) To mark the beginning of the 15th year of Expert Review of Molecular Diagnostics, the journal's Editor-in-Chief shares his expert knowledge on translational diagnostics, his opinion on recent controversies and his predictions for molecular diagnostics in 2015 and beyond. Attila Lorincz received his doctorate from Trinity College, Dublin, Republic of Ireland, and went on to become a research fellow at the University of California, Santa Barbara, CA, USA. During Professor Lorincz's research on human papillomavirus (HPV), he found several important and novel carcinogenic HPV types and pioneered the use of HPV DNA testing for clinical diagnostics. In 1988, Professor Lorincz's team produced the first HPV test to be FDA-approved for patients and in 2003, for general population cervical precancer screening. Now Professor of Molecular Epidemiology at the Centre for Cancer Prevention, Queen Mary University of London, UK, he and his team are furthering translational research into DNA methylation assays for cancer risk prediction.

An integrated real-time diagnostic concept using expert systems, qualitative reasoning and quantitative analysis

International Nuclear Information System (INIS)

Edwards, R.M.; Lee, K.Y.; Kumara, S.; Levine, S.H.

1989-01-01

An approach for an integrated real-time diagnostic system is being developed for inclusion as an integral part of a power plant automatic control system. In order to participate in control decisions and automatic closed loop operation, the diagnostic system must operate in real-time. Thus far, an expert system with real-time capabilities has been developed and installed on a subsystem at the Experimental Breeder Reactor (EBR-II) in Idaho, USA. Real-time simulation testing of advanced power plant concepts at the Pennsylvania State University has been developed and was used to support the expert system development and installation at EBR-II. Recently, the US National Science Foundation (NSF) and the US Department of Energy (DOE) have funded a Penn State research program to further enhance application of real-time diagnostic systems by pursuing implementation in a distributed power plant computer system including microprocessor based controllers. This paper summarizes past, current, planned, and possible future approaches to power plant diagnostic systems research at Penn State. 34 refs., 9 figs

Neural network application to diesel generator diagnostics

International Nuclear Information System (INIS)

Logan, K.P.

1990-01-01

Diagnostic problems typically begin with the observation of some system behavior which is recognized as a deviation from the expected. The fundamental underlying process is one involving pattern matching cf observed symptoms to a set of compiled symptoms belonging to a fault-symptom mapping. Pattern recognition is often relied upon for initial fault detection and diagnosis. Parallel distributed processing (PDP) models employing neural network paradigms are known to be good pattern recognition devices. This paper describes the application of neural network processing techniques to the malfunction diagnosis of subsystems within a typical diesel generator configuration. Neural network models employing backpropagation learning were developed to correctly recognize fault conditions from the input diagnostic symptom patterns pertaining to various engine subsystems. The resulting network models proved to be excellent pattern recognizers for malfunction examples within the training set. The motivation for employing network models in lieu of a rule-based expert system, however, is related to the network's potential for generalizing malfunctions outside of the training set, as in the case of noisy or partial symptom patterns

Expert system applications in support of system diagnostics and prognostics at EBR-II

International Nuclear Information System (INIS)

Lehto, W.K.; Gross, K.C.

1989-01-01

Expert systems have been developed to aid in the monitoring and diagnostics of the Experimental Breeder Reactor-II (EBR-II) at the Idaho National Engineering Laboratory (INEL) in Idaho Falls, Idaho. Systems have been developed for failed fuel surveillance and diagnostics and reactor coolant pump monitoring and diagnostics. A third project is being done jointly by ANL-W and EG ampersand G Idaho to develop a transient analysis system to enhance overall plant diagnostic and prognostic capability. The failed fuel surveillance and diagnosis system monitors, processes, and interprets information from nine key plant sensors. It displays to the reactor operator diagnostic information needed to make proper decisions regarding technical specification conformance during reactor operation with failed fuel. 8 refs., 9 figs., 2 tabs

Quantifying Novice and Expert Differences in Visual Diagnostic Reasoning in Veterinary Pathology Using Eye-Tracking Technology.

Science.gov (United States)

Warren, Amy L; Donnon, Tyrone L; Wagg, Catherine R; Priest, Heather; Fernandez, Nicole J

2018-01-18

Visual diagnostic reasoning is the cognitive process by which pathologists reach a diagnosis based on visual stimuli (cytologic, histopathologic, or gross imagery). Currently, there is little to no literature examining visual reasoning in veterinary pathology. The objective of the study was to use eye tracking to establish baseline quantitative and qualitative differences between the visual reasoning processes of novice and expert veterinary pathologists viewing cytology specimens. Novice and expert participants were each shown 10 cytology images and asked to formulate a diagnosis while wearing eye-tracking equipment (10 slides) and while concurrently verbalizing their thought processes using the think-aloud protocol (5 slides). Compared to novices, experts demonstrated significantly higher diagnostic accuracy (preasoning and script-inductive knowledge structures with system 2 (analytic) reasoning to verify their diagnosis.

The structure of expert diagnostic knowledge in occupational medicine.

Science.gov (United States)

Harber, P; McCoy, J M; Shimozaki, S; Coffman, P; Bailey, K

1991-01-01

Development of an artificial intelligence expert system for diagnosing occupational lung disease requires explicit specification of the structure of knowledge necessary in clinical occupational medicine independent of the process by which the knowledge is utilized. Furthermore, explicit recognition of sources of uncertainty is necessary. Seven categories of knowledge define the diagnostic knowledge base in occupational pulmonary medicine. These include four objects (jobs, industries, exposures, and diseases) and three relationships between pairs of objects. This analysis demonstrates some of the unique aspects of occupational medicine expertise.

Expert system for fault diagnosis in process control valves using fuzzy-logic

Energy Technology Data Exchange (ETDEWEB)

Carneiro, Alvaro L.G., E-mail: carneiro@ipen.br [Instituto de Pesquisas Energeticas e Nucleares (IPEN/CNEN-SP), Sao Paulo, SP (Brazil); Porto Junior, Almir C.S., E-mail: almir@ctmsp.mar.mil.br [Centro Tecnologico da Marinha em Sao Paulo (CIANA/CTMSP), Ipero, SP (Brazil). Centro de Instrucao e Adestramento Nuclear de ARAMAR

2013-07-01

The models of asset maintenance of a process plant basically are classified in corrective maintenance, preventive, predictive and proactive (online). The corrective maintenance is the elementary and most obvious way of the maintenance models. The preventive maintenance consists in a fault prevention work, based on statistical studies that can lead to low efficiency or even an unexpected shutdown of the plant. Predictive maintenance aims to prevent equipment or systems failures through monitoring and tracking of parameters, allowing continuous operation as long as possible. The proactive maintenance usually includes predictive maintenance, emphasizing the root cause analysis of the failure. The maintenance predictive/proactive planning frequently uses software that integrates data from different systems, which facilitates a quick and effective decision- making. In nuclear plants this model has an important role regarding the reliability of equipment and systems. The main focus of this work is to study the development of a model of non-intrusive monitoring and diagnosis applied to process control valves using artificial intelligence by fuzzy logic technique, contributing in the development of predictive methodologies identifying faults in incipient state. The control valve analyzed belongs to a steam plant which simulates the secondary circuit of a PWR nuclear reactor - Pressurized Water Reactor. This study makes use of MATLAB language through the fuzzy logic toolbox which uses the method of inference Mamdani, acting by fuzzy conjunction, through Triangular Norms (t-norm) and Triangular Conorms (t-conorm). As input variables are used air pressure and displacement of the valve stem. Input data coming into the fuzzy system by graph of the automation system Delta V ® available in the plant, which receives a signal of electric current from an 'intelligent' positioned installed on the valve. The output variable is the 'status' of the valve. Through a

Expert system for fault diagnosis in process control valves using fuzzy-logic

International Nuclear Information System (INIS)

Carneiro, Alvaro L.G.; Porto Junior, Almir C.S.

2013-01-01

The models of asset maintenance of a process plant basically are classified in corrective maintenance, preventive, predictive and proactive (online). The corrective maintenance is the elementary and most obvious way of the maintenance models. The preventive maintenance consists in a fault prevention work, based on statistical studies that can lead to low efficiency or even an unexpected shutdown of the plant. Predictive maintenance aims to prevent equipment or systems failures through monitoring and tracking of parameters, allowing continuous operation as long as possible. The proactive maintenance usually includes predictive maintenance, emphasizing the root cause analysis of the failure. The maintenance predictive/proactive planning frequently uses software that integrates data from different systems, which facilitates a quick and effective decision- making. In nuclear plants this model has an important role regarding the reliability of equipment and systems. The main focus of this work is to study the development of a model of non-intrusive monitoring and diagnosis applied to process control valves using artificial intelligence by fuzzy logic technique, contributing in the development of predictive methodologies identifying faults in incipient state. The control valve analyzed belongs to a steam plant which simulates the secondary circuit of a PWR nuclear reactor - Pressurized Water Reactor. This study makes use of MATLAB language through the fuzzy logic toolbox which uses the method of inference Mamdani, acting by fuzzy conjunction, through Triangular Norms (t-norm) and Triangular Conorms (t-conorm). As input variables are used air pressure and displacement of the valve stem. Input data coming into the fuzzy system by graph of the automation system Delta V ® available in the plant, which receives a signal of electric current from an 'intelligent' positioned installed on the valve. The output variable is the 'status' of the valve. Through a rule base

Laserjet Printer Troubleshooting Expert System | Adesola | West ...

African Journals Online (AJOL)

This paper model an expert system called LAPTEX for troubleshooting LaserJet printers' faults. Today, with the innumerable advances in information technologies, computerizing printer's fault troubleshooting and identifying faults is far becoming so vital. Also, printers' fault detection is a complicated process that requires a ...

A flexible simulator for training an early fault diagnostic system

International Nuclear Information System (INIS)

Marsiletti, M.; Santinelli, A.; Zuenkov, M.; Poletykin, A.

1997-01-01

An early fault diagnostic system has been developed addressed to timely trouble shooting in process plants during any operational modes. The theory of this diagnostic system is related with the usage of learning methods for automatic generation of knowledge bases. This approach enables the conversion of ''cause→effect'' relations into ''effect→possible-causes'' ones. The diagnostic rules are derived from the operation of a plant simulator according to a specific procedure. Flexibility, accuracy and high speed are the major characteristics of the training simulator, used to generate the diagnostic knowledge base. The simulator structure is very flexible, being based on LEGO code but allowing the use of practically any kind of FORTRAN routines (recently also ACSL macros has been introduced) as plant modules: this permits, when needed, a very accurate description of the malfunctions the diagnostic system should ''known''. The high speed is useful to shorten the ''learning'' phase of the diagnostic system. The feasibility of the overall system has been assessed, using as reference plant the conventional Sampierdarena (Italy) power station, that is a combined cycle plant dedicated to produce both electrical and heat power. The hardware configuration of this prototype system was made up of a network of a Hewlett-Packard workstation and a Digital VAX-Station. The paper illustrates the basic structure of the simulator used for this diagnostic system training purpose, as well as the theoretical background on which the diagnostic system is based. Some evidence of the effectiveness of the concept through the application to Sampierdarena 40 MW cogeneration plant is reported. Finally an outline of an ongoing application to a WWER-1000 plant is given; the operating system is, in this case, UNIX. (author)

Development of the Diagnostic Expert System for Tea Processing

Science.gov (United States)

Yoshitomi, Hitoshi; Yamaguchi, Yuichi

A diagnostic expert system for tea processing which can presume the cause of the defect of the processed tea was developed to contribute to the improvement of tea processing. This system that consists of some programs can be used through the Internet. The inference engine, the core of the system adopts production system which is well used on artificial intelligence, and is coded by Prolog as the artificial intelligence oriented language. At present, 176 rules for inference have been registered on this system. The system will be able to presume better if more rules are added to the system.

The Diagnostic Challenge Competition: Probabilistic Techniques for Fault Diagnosis in Electrical Power Systems

Science.gov (United States)

Ricks, Brian W.; Mengshoel, Ole J.

2009-01-01

Reliable systems health management is an important research area of NASA. A health management system that can accurately and quickly diagnose faults in various on-board systems of a vehicle will play a key role in the success of current and future NASA missions. We introduce in this paper the ProDiagnose algorithm, a diagnostic algorithm that uses a probabilistic approach, accomplished with Bayesian Network models compiled to Arithmetic Circuits, to diagnose these systems. We describe the ProDiagnose algorithm, how it works, and the probabilistic models involved. We show by experimentation on two Electrical Power Systems based on the ADAPT testbed, used in the Diagnostic Challenge Competition (DX 09), that ProDiagnose can produce results with over 96% accuracy and less than 1 second mean diagnostic time.

Subassembly faults diagnostic of an LMFBR type reactor by the measurement of temperature noise

International Nuclear Information System (INIS)

Kokorev, B.V.; Palkin, I.I.; Turchin, N.M.; Pallagi, D.; Horanyi, S.

1979-09-01

The subassembly faults detection possibility by temperature noise analysis of an LMFBR is described. The paper contains the results of diagnostical examinations obtained on electrically heated NaK test rigs. On the basis of these results the measurement of temperature noise RMS value seems to be a practicable method to detect local blockages in an early phase. (author)

Turbine engine rotor blade fault diagnostics through casing pressure and vibration sensors

International Nuclear Information System (INIS)

Cox, J; Anusonti-Inthra, P

2014-01-01

In this study, an exact solution is provided for a previously indeterminate equation used for rotor blade fault diagnostics. The method estimates rotor blade natural frequency through turbine engine casing pressure and vibration sensors. The equation requires accurate measurements of low-amplitude sideband signals in the frequency domain. With this in mind, statistical evaluation was also completed with the goal of determining the effect of sampling time and frequency on sideband resolution in the frequency domain

General review of diagnostic systems in EDF PWR units

International Nuclear Information System (INIS)

Chevalier, R.; Brasseur, S.; Ricard, B.

1998-01-01

Since the beginning of the French nuclear program, Electricite de France (EDF) has looked for ways to improve the availability and safety of its nuclear units. Therefore, monitoring systems on turbogenerators, reactor coolant pumps, primary circuits and core internal structures were designed by the Research and Development Division and implemented with technologies available during the 1970's. However, mainly because of difficulties for data interpretation by plant personnel, EDF subsequently decided to design and develop different tools to help plant operators to process a diagnosis: - a new generation of the Monitoring and Diagnostic System called PSAD, - expert systems for diagnosis on reactor coolant pumps (RCP) 'DIAPO' and turbogenerator units (TG) 'DIVA', - diagnostic guides written for most equipment pending the installation of new monitoring and diagnosis systems. The first version of PSAD, installed in five units, performs on-line monitoring of the turbogenerator shaft line, steam inlet valves, the reactor coolant pumps and the generator stator. The second version not yet implemented, will include Loose Part Detection (LPD) and Core Internal Structure Monitoring (CISM). The level of diagnosis achieved by PSAD depends on the component monitored. The TG and RCP monitoring functions of PSAD compute high level diagnosis descriptors such as natural frequencies and long term trends but do not elaborate a diagnosis automatically. However, a diagnostic assistance window is available on-line, whenever a warning message is displayed, whether for immediate or later action. The window presents a diagnostic approach whose purpose is to find the causes of the symptoms observed. This diagnosis approach is automated in the DIVA and DIAPO expert systems. Numerous potential faults can be identified for both systems thanks to a hierarchy of abnormal situations. The user interactively answers questions when information is needed to progress in the diagnosis. The resulting

Intelligent monitoring of water chemistry - Diagnostic expert system DIWATM

International Nuclear Information System (INIS)

Metzner, W.; Streit, K.

2002-01-01

For fast and comprehensive evaluation of power plant water chemistry conditions and reliable diagnosis in the event of disturbances considerable advantages are provided by employment of the Diagnostic Expert System DIWA. The interface to the process control system (I and C) and the integration of the DIWA system in the office PC network are the preconditions that DIWA operates as a monitoring system in real time. The performance of diagnosis, which are processed by a fuzzy-logic-supported knowledge base ensures not only the detection of all disturbances but also different analyses of the plant operation mode. By editing the knowledge base the Al of the system can increase without system programming. (authors)

Fault diagnostics of dynamic system operation using a fault tree based method

International Nuclear Information System (INIS)

Hurdle, E.E.; Bartlett, L.M.; Andrews, J.D.

2009-01-01

For conventional systems, their availability can be considerably improved by reducing the time taken to restore the system to the working state when faults occur. Fault identification can be a significant proportion of the time taken in the repair process. Having diagnosed the problem the restoration of the system back to its fully functioning condition can then take place. This paper expands the capability of previous approaches to fault detection and identification using fault trees for application to dynamically changing systems. The technique has two phases. The first phase is modelling and preparation carried out offline. This gathers information on the effects that sub-system failure will have on the system performance. Causes of the sub-system failures are developed in the form of fault trees. The second phase is application. Sensors are installed on the system to provide information about current system performance from which the potential causes can be deduced. A simple system example is used to demonstrate the features of the method. To illustrate the potential for the method to deal with additional system complexity and redundancy, a section from an aircraft fuel system is used. A discussion of the results is provided.

Subaru FATS (fault tracking system)

Science.gov (United States)

Winegar, Tom W.; Noumaru, Junichi

2000-07-01

The Subaru Telescope requires a fault tracking system to record the problems and questions that staff experience during their work, and the solutions provided by technical experts to these problems and questions. The system records each fault and routes it to a pre-selected 'solution-provider' for each type of fault. The solution provider analyzes the fault and writes a solution that is routed back to the fault reporter and recorded in a 'knowledge-base' for future reference. The specifications of our fault tracking system were unique. (1) Dual language capacity -- Our staff speak both English and Japanese. Our contractors speak Japanese. (2) Heterogeneous computers -- Our computer workstations are a mixture of SPARCstations, Macintosh and Windows computers. (3) Integration with prime contractors -- Mitsubishi and Fujitsu are primary contractors in the construction of the telescope. In many cases, our 'experts' are our contractors. (4) Operator scheduling -- Our operators spend 50% of their work-month operating the telescope, the other 50% is spent working day shift at the base facility in Hilo, or day shift at the summit. We plan for 8 operators, with a frequent rotation. We need to keep all operators informed on the current status of all faults, no matter the operator's location.

A methodology for the quantitative evaluation of NPP fault diagnostic systems' dynamic aspects

International Nuclear Information System (INIS)

Kim, J.H.; Seong, P.H.

2000-01-01

A fault diagnostic system (FDS) is an operator decision support system which is implemented both to increase NPP efficiency as well as to reduce human error and cognitive workload that may cause nuclear power plant (NPP) accidents. Evaluation is an indispensable activity in constructing a reliable FDS. We first define the dynamic aspects of fault diagnostic systems (FDSs) for evaluation in this work. The dynamic aspect is concerned with the way a FDS responds to input. Next, we present a hierarchical structure in the evaluation for the dynamic aspects of FDSs. Dynamic aspects include both what a FDS provides and how a FDS operates. We define the former as content and the latter as behavior. Content and behavior contain two elements and six elements in the lower hierarchies, respectively. Content is a criterion for evaluating the integrity of a FDS, the problem types which a FDS deals with, along with the level of information. Behavior contains robustness, understandability, timeliness, transparency, effectiveness, and communicativeness of FDSs. On the other hand, the static aspects are concerned with the hardware and the software of the system. For quantitative evaluation, the method used to gain and aggregate the priorities of the criteria in this work is the analytic hierarchy process (AHP). The criteria at the lowest level are quantified through simple numerical expressions and questionnaires developed in this work. these well describe the characteristics of the criteria and appropriately use subjective, empirical, and technical methods. Finally, in order to demonstrate the feasibility of our evaluation method, we have performed one case study for the fault diagnosis module of OASYS TM (On-Line Operator Aid SYStem for Nuclear Power Plant), which is an operator support system developed at the Korea Advanced Institute of Science and Technology (KAIST)

Vibration Feature Extraction and Analysis for Fault Diagnosis of Rotating Machinery-A Literature Survey

Directory of Open Access Journals (Sweden)

Saleem Riaz

2017-02-01

Full Text Available Safety, reliability, efficiency and performance of rotating machinery in all industrial applications are the main concerns. Rotating machines are widely used in various industrial applications. Condition monitoring and fault diagnosis of rotating machinery faults are very important and often complex and labor-intensive. Feature extraction techniques play a vital role for a reliable, effective and efficient feature extraction for the diagnosis of rotating machinery. Therefore, developing effective bearing fault diagnostic method using different fault features at different steps becomes more attractive. Bearings are widely used in medical applications, food processing industries, semi-conductor industries, paper making industries and aircraft components. This paper review has demonstrated that the latest reviews applied to rotating machinery on the available a variety of vibration feature extraction. Generally literature is classified into two main groups: frequency domain, time frequency analysis. However, fault detection and diagnosis of rotating machine vibration signal processing methods to present their own limitations. In practice, most healthy ingredients faulty vibration signal from background noise and mechanical vibration signals are buried. This paper also reviews that how the advanced signal processing methods, empirical mode decomposition and interference cancellation algorithm has been investigated and developed. The condition for rotating machines based rehabilitation, prevent failures increase the availability and reduce the cost of maintenance is becoming necessary too. Rotating machine fault detection and diagnostics in developing algorithms signal processing based on a key problem is the fault feature extraction or quantification. Currently, vibration signal, fault detection and diagnosis of rotating machinery based techniques most widely used techniques. Furthermore, the researchers are widely interested to make automatic

FADES: A tool for automated fault analysis of complex systems

International Nuclear Information System (INIS)

Wood, C.

1990-01-01

FADES is an Expert System for performing fault analyses on complex connected systems. By using a graphical editor to draw components and link them together the FADES system allows the analyst to describe a given system. The knowledge base created is used to qualitatively simulate the system behaviour. By inducing all possible component failures in the system and determining their effects, a set of facts is built up. These facts are then used to create Fault Trees, or FMEA tables. The facts may also be used for explanation effects and to generate diagnostic rules allowing system instrumentation to be optimised. The prototype system has been built and tested and is preently undergoing testing by users. All comments from these trials will be used to tailor the system to the requirements of the user so that the end product performs the exact task required

Probabilistic techniques using Monte Carlo sampling for multi- component system diagnostics

International Nuclear Information System (INIS)

Aumeier, S.E.; Lee, J.C.; Akcasu, A.Z.

1995-01-01

We outline the structure of a new approach at multi-component system fault diagnostics which utilizes detailed system simulation models, uncertain system observation data, statistical knowledge of system parameters, expert opinion, and component reliability data in an effort to identify incipient component performance degradations of arbitrary number and magnitude. The technique involves the use of multiple adaptive Kalman filters for fault estimation, the results of which are screened using standard hypothesis testing procedures to define a set of component events that could have transpired. Latin Hypercube sample each of these feasible component events in terms of uncertain component reliability data and filter estimates. The capabilities of the procedure are demonstrated through the analysis of a simulated small magnitude binary component fault in a boiling water reactor balance of plant. The results show that the procedure has the potential to be a very effective tool for incipient component fault diagnosis

Fault diagnosis

Science.gov (United States)

Abbott, Kathy

1990-01-01

The objective of the research in this area of fault management is to develop and implement a decision aiding concept for diagnosing faults, especially faults which are difficult for pilots to identify, and to develop methods for presenting the diagnosis information to the flight crew in a timely and comprehensible manner. The requirements for the diagnosis concept were identified by interviewing pilots, analyzing actual incident and accident cases, and examining psychology literature on how humans perform diagnosis. The diagnosis decision aiding concept developed based on those requirements takes abnormal sensor readings as input, as identified by a fault monitor. Based on these abnormal sensor readings, the diagnosis concept identifies the cause or source of the fault and all components affected by the fault. This concept was implemented for diagnosis of aircraft propulsion and hydraulic subsystems in a computer program called Draphys (Diagnostic Reasoning About Physical Systems). Draphys is unique in two important ways. First, it uses models of both functional and physical relationships in the subsystems. Using both models enables the diagnostic reasoning to identify the fault propagation as the faulted system continues to operate, and to diagnose physical damage. Draphys also reasons about behavior of the faulted system over time, to eliminate possibilities as more information becomes available, and to update the system status as more components are affected by the fault. The crew interface research is examining display issues associated with presenting diagnosis information to the flight crew. One study examined issues for presenting system status information. One lesson learned from that study was that pilots found fault situations to be more complex if they involved multiple subsystems. Another was pilots could identify the faulted systems more quickly if the system status was presented in pictorial or text format. Another study is currently under way to

Diagnostic reasoning strategies and diagnostic success.

Science.gov (United States)

Coderre, S; Mandin, H; Harasym, P H; Fick, G H

2003-08-01

Cognitive psychology research supports the notion that experts use mental frameworks or "schemes", both to organize knowledge in memory and to solve clinical problems. The central purpose of this study was to determine the relationship between problem-solving strategies and the likelihood of diagnostic success. Think-aloud protocols were collected to determine the diagnostic reasoning used by experts and non-experts when attempting to diagnose clinical presentations in gastroenterology. Using logistic regression analysis, the study found that there is a relationship between diagnostic reasoning strategy and the likelihood of diagnostic success. Compared to hypothetico-deductive reasoning, the odds of diagnostic success were significantly greater when subjects used the diagnostic strategies of pattern recognition and scheme-inductive reasoning. Two other factors emerged as independent determinants of diagnostic success: expertise and clinical presentation. Not surprisingly, experts outperformed novices, while the content area of the clinical cases in each of the four clinical presentations demonstrated varying degrees of difficulty and thus diagnostic success. These findings have significant implications for medical educators. It supports the introduction of "schemes" as a means of enhancing memory organization and improving diagnostic success.

A Deep Learning Approach for Fault Diagnosis of Induction Motors in Manufacturing

Science.gov (United States)

Shao, Si-Yu; Sun, Wen-Jun; Yan, Ru-Qiang; Wang, Peng; Gao, Robert X.

2017-11-01

Extracting features from original signals is a key procedure for traditional fault diagnosis of induction motors, as it directly influences the performance of fault recognition. However, high quality features need expert knowledge and human intervention. In this paper, a deep learning approach based on deep belief networks (DBN) is developed to learn features from frequency distribution of vibration signals with the purpose of characterizing working status of induction motors. It combines feature extraction procedure with classification task together to achieve automated and intelligent fault diagnosis. The DBN model is built by stacking multiple-units of restricted Boltzmann machine (RBM), and is trained using layer-by-layer pre-training algorithm. Compared with traditional diagnostic approaches where feature extraction is needed, the presented approach has the ability of learning hierarchical representations, which are suitable for fault classification, directly from frequency distribution of the measurement data. The structure of the DBN model is investigated as the scale and depth of the DBN architecture directly affect its classification performance. Experimental study conducted on a machine fault simulator verifies the effectiveness of the deep learning approach for fault diagnosis of induction motors. This research proposes an intelligent diagnosis method for induction motor which utilizes deep learning model to automatically learn features from sensor data and realize working status recognition.

Fault-tolerant quantum computing in the Pauli or Clifford frame with slow error diagnostics

Directory of Open Access Journals (Sweden)

Christopher Chamberland

2018-01-01

Full Text Available We consider the problem of fault-tolerant quantum computation in the presence of slow error diagnostics, either caused by measurement latencies or slow decoding algorithms. Our scheme offers a few improvements over previously existing solutions, for instance it does not require active error correction and results in a reduced error-correction overhead when error diagnostics is much slower than the gate time. In addition, we adapt our protocol to cases where the underlying error correction strategy chooses the optimal correction amongst all Clifford gates instead of the usual Pauli gates. The resulting Clifford frame protocol is of independent interest as it can increase error thresholds and could find applications in other areas of quantum computation.

Artificial intelligence applications to nuclear reactor diagnostics

International Nuclear Information System (INIS)

Lee, J.C.; Hassberger, J.A.; Wehe, D.K.

1987-01-01

The authors research into applications of artificial intelligence to nuclear reactor diagnostics involves three main areas. In the first area, the authors combine reactor simulation models and expert systems to diagnose the state of the plant. The second area examines ways in which the rule or knowledge base of an intelligent controller can be generated systematically from either fault trees or acquired plant data. Third, efforts are described to develop the capabilities to validate these techniques in a realistic reactor setting. The techniques are applicable to all reactor types, including fast reactors

CBDS: Constraint-based diagnostic system for malfunction identification in the nuclear power plant

International Nuclear Information System (INIS)

Ha, J.

1992-01-01

Traditional rule-based diagnostic expert systems use the experience of experts in the form of rules that associate symptoms with underlying faults. A commonly recognized failing of such systems is their narrow range of expertise and their inability to recognize problems outside this range of expertise. A model base diagnostic system isolating malfunctioning components-CBDS, the Constraint based Diagnostic System-has been developed. Since the intended behavior of a device is more predictable than unintended behaviors (faults), a model based system using the intended behavior has a potential to diagnose unexpected malfunctions by considering faults as open-quotes anything other than the intended behavior.close quotes As a knowledge base, the CBDS generates and decomposes a constraint network based on the structure and behavior model, which are represented symbolically in algebraic equations. Behaviors of generic components are organized in a component model library. Once the library is available, actual domain knowledge can be represented by declaring component types and their connections. To capture various plant knowledge, the mixed model was developed which allow the use of different parameter types in one equation by defining various operators. The CBDS uses the general idea of model based diagnosis. It detects a discrepancy between observation and prediction using constraint propagation, which carriers and accumulates the assumptions when parameter values are deduced. When measured plant parameters are asserted into a constraint network and are propagated through the network, a discrepancy will be detected if there exists any malfunctioning component. The CBDS was tested in the Recirculation Flow Control System of a BWR, and has been shown to be able to diagnose unexpected events

CONFIG - Adapting qualitative modeling and discrete event simulation for design of fault management systems

Science.gov (United States)

Malin, Jane T.; Basham, Bryan D.

1989-01-01

CONFIG is a modeling and simulation tool prototype for analyzing the normal and faulty qualitative behaviors of engineered systems. Qualitative modeling and discrete-event simulation have been adapted and integrated, to support early development, during system design, of software and procedures for management of failures, especially in diagnostic expert systems. Qualitative component models are defined in terms of normal and faulty modes and processes, which are defined by invocation statements and effect statements with time delays. System models are constructed graphically by using instances of components and relations from object-oriented hierarchical model libraries. Extension and reuse of CONFIG models and analysis capabilities in hybrid rule- and model-based expert fault-management support systems are discussed.

Diagnostic technology and an expert system for photovoltaic systems using the learning method

Energy Technology Data Exchange (ETDEWEB)

Yagi, Yasuhiro; Kishi, Hitoshi; Hagihara, Ryuzou; Tanaka, Toshiya; Kozuma, Shinichi; Ishida, Takeo; Waki, Masahiro; Tanaka, Makoto; Kiyama, Seiichi [SANYO Electric Co. Ltd., New Materials Research Center, Moriguchi City, Osaka (Japan)

2003-02-01

Diagnostic technology for photovoltaic (PV) systems was developed, using the learning method to take each site's conditions into account. This technology employs diagnostic criteria databases to analyze data acquired from the PV systems. These criteria are updated monthly for each site using analyzed data. To check the shadows on the PV modules and pyranometer, the sophisticated verification method was also applied to this technology. After the diagnosis, a basket method provides maintenance advice for the PV systems. Based on the results of precise diagnoses, this expert system offers quick and proper maintenance advice within a few minutes. This technology is highly useful, because it greatly simplifies the servicing and maintenance of PV systems. (Author)

Bayesian networks applied to process diagnostics. Applications in energy industry

Energy Technology Data Exchange (ETDEWEB)

Widarsson, Bjoern (ed.); Karlsson, Christer; Dahlquist, Erik [Maelardalen Univ., Vaesteraas (Sweden); Nielsen, Thomas D.; Jensen, Finn V. [Aalborg Univ. (Denmark)

2004-10-01

Uncertainty in process operation occurs frequently in heat and power industry. This makes it hard to find the occurrence of an abnormal process state from a number of process signals (measurements) or find the correct cause to an abnormality. Among several other methods, Bayesian Networks (BN) is a method to build a model which can handle uncertainty in both process signals and the process itself. The purpose of this project is to investigate the possibilities to use BN for fault detection and diagnostics in combined heat and power industries through execution of two different applications. Participants from Aalborg University represent the knowledge of BN and participants from Maelardalen University have the experience from modelling heat and power applications. The co-operation also includes two energy companies; Elsam A/S (Nordjyllandsverket) and Maelarenergi AB (Vaesteraas CHP-plant), where the two applications are made with support from the plant personnel. The project ended out in two quite different applications. At Nordjyllandsverket, an application based (due to the lack of process knowledge) on pure operation data is build with capability to detect an abnormal process state in a coal mill. Detection is made through a conflict analysis when entering process signals into a model built by analysing the operation database. The application at Maelarenergi is built with a combination of process knowledge and operation data and can detect various faults caused by the fuel. The process knowledge is used to build a causal network structure and the structure is then trained by data from the operation database. Both applications are made as off-online applications, but they are ready for being run on-line. The performance of fault detection and diagnostics are good, but a lack of abnormal process states with known cause reduces the evaluation possibilities. Advantages with combining expert knowledge of the process with operation data are the possibility to represent

Operational expert system applications in Europe

CERN Document Server

Zarri, Gian Piero

1992-01-01

Operational Expert System Applications in Europe describes the representative case studies of the operational expert systems (ESs) that are used in Europe.This compilation provides examples of operational ES that are realized in 10 different European countries, including countries not usually examined in the standard reviews of the field.This book discusses the decision support system using several artificial intelligence tools; expert systems for fault diagnosis on computerized numerical control (CNC) machines; and expert consultation system for personal portfolio management. The failure prob

Two Trees: Migrating Fault Trees to Decision Trees for Real Time Fault Detection on International Space Station

Science.gov (United States)

Lee, Charles; Alena, Richard L.; Robinson, Peter

2004-01-01

We started from ISS fault trees example to migrate to decision trees, presented a method to convert fault trees to decision trees. The method shows that the visualizations of root cause of fault are easier and the tree manipulating becomes more programmatic via available decision tree programs. The visualization of decision trees for the diagnostic shows a format of straight forward and easy understands. For ISS real time fault diagnostic, the status of the systems could be shown by mining the signals through the trees and see where it stops at. The other advantage to use decision trees is that the trees can learn the fault patterns and predict the future fault from the historic data. The learning is not only on the static data sets but also can be online, through accumulating the real time data sets, the decision trees can gain and store faults patterns in the trees and recognize them when they come.

Study on a self diagnostic monitoring system for an air-operated valve: development of a fault library

International Nuclear Information System (INIS)

Chai, Jang Bom; Kim, Yun Chul; Kim, Woo Shik; Cho, Hang Duke

2004-01-01

In the interest of nuclear power plant safety, a Self-Diagnostic Monitoring System (SDMS) is needed to monitor defects in safety-related components. An Air-Operated Valve (AOV) is one of the components to be monitored since the failure of its operation could potentially have catastrophic consequences. In this paper, a model of the AOV is developed with the parameters that affect the operational characteristics. The model is useful for both understanding the operation and correlating parameters and defects. Various defects are introduced in the experiments to construct a fault library, which will be used in a pattern recognition approach. Finally, the validity of the fault library is examined

Advanced diagnostic system for piston slap faults in IC engines, based on the non-stationary characteristics of the vibration signals

Science.gov (United States)

Chen, Jian; Randall, Robert Bond; Peeters, Bart

2016-06-01

Artificial Neural Networks (ANNs) have the potential to solve the problem of automated diagnostics of piston slap faults, but the critical issue for the successful application of ANN is the training of the network by a large amount of data in various engine conditions (different speed/load conditions in normal condition, and with different locations/levels of faults). On the other hand, the latest simulation technology provides a useful alternative in that the effect of clearance changes may readily be explored without recourse to cutting metal, in order to create enough training data for the ANNs. In this paper, based on some existing simplified models of piston slap, an advanced multi-body dynamic simulation software was used to simulate piston slap faults with different speeds/loads and clearance conditions. Meanwhile, the simulation models were validated and updated by a series of experiments. Three-stage network systems are proposed to diagnose piston faults: fault detection, fault localisation and fault severity identification. Multi Layer Perceptron (MLP) networks were used in the detection stage and severity/prognosis stage and a Probabilistic Neural Network (PNN) was used to identify which cylinder has faults. Finally, it was demonstrated that the networks trained purely on simulated data can efficiently detect piston slap faults in real tests and identify the location and severity of the faults as well.

Artificial neural network application for space station power system fault diagnosis

Science.gov (United States)

Momoh, James A.; Oliver, Walter E.; Dias, Lakshman G.

1995-01-01

This study presents a methodology for fault diagnosis using a Two-Stage Artificial Neural Network Clustering Algorithm. Previously, SPICE models of a 5-bus DC power distribution system with assumed constant output power during contingencies from the DDCU were used to evaluate the ANN's fault diagnosis capabilities. This on-going study uses EMTP models of the components (distribution lines, SPDU, TPDU, loads) and power sources (DDCU) of Space Station Alpha's electrical Power Distribution System as a basis for the ANN fault diagnostic tool. The results from the two studies are contrasted. In the event of a major fault, ground controllers need the ability to identify the type of fault, isolate the fault to the orbital replaceable unit level and provide the necessary information for the power management expert system to optimally determine a degraded-mode load schedule. To accomplish these goals, the electrical power distribution system's architecture can be subdivided into three major classes: DC-DC converter to loads, DC Switching Unit (DCSU) to Main bus Switching Unit (MBSU), and Power Sources to DCSU. Each class which has its own electrical characteristics and operations, requires a unique fault analysis philosophy. This study identifies these philosophies as Riddles 1, 2 and 3 respectively. The results of the on-going study addresses Riddle-1. It is concluded in this study that the combination of the EMTP models of the DDCU, distribution cables and electrical loads yields a more accurate model of the behavior and in addition yielded more accurate fault diagnosis using ANN versus the results obtained with the SPICE models.

Fault-tolerant architecture: Evaluation methodology

International Nuclear Information System (INIS)

Battle, R.E.; Kisner, R.A.

1992-08-01

The design and reliability of four fault-tolerant architectures that may be used in nuclear power plant control systems were evaluated. Two architectures are variations of triple-modular-redundant (TMR) systems, and two are variations of dual redundant systems. The evaluation includes a review of methods of implementing fault-tolerant control, the importance of automatic recovery from failures, methods of self-testing diagnostics, block diagrams of typical fault-tolerant controllers, review of fault-tolerant controllers operating in nuclear power plants, and fault tree reliability analyses of fault-tolerant systems

Expert and competent non-expert visual cues during simulated diagnosis in intensive care.

Science.gov (United States)

McCormack, Clare; Wiggins, Mark W; Loveday, Thomas; Festa, Marino

2014-01-01

The aim of this study was to examine the information acquisition strategies of expert and competent non-expert intensive care physicians during two simulated diagnostic scenarios involving respiratory distress in an infant. Specifically, the information acquisition performance of six experts and 12 competent non-experts was examined using an eye-tracker during the initial 90 s of the assessment of the patient. The results indicated that, in comparison to competent non-experts, experts recorded longer mean fixations, irrespective of the scenario. When the dwell times were examined against specific areas of interest, the results revealed that competent non-experts recorded greater overall dwell times on the nurse, where experts recorded relatively greater dwell times on the head and face of the manikin. In the context of the scenarios, experts recorded differential dwell times, spending relatively more time on the head and face during the seizure scenario than during the coughing scenario. The differences evident between experts and competent non-experts were interpreted as evidence of the relative availability of task-specific cues or heuristics in memory that might direct the process of information acquisition amongst expert physicians. The implications are discussed for the training and assessment of diagnostic skills.

Fault isolability with different forms of the faults–symptoms relation

Directory of Open Access Journals (Sweden)

Kóscielny Jan Maciej

2016-12-01

Full Text Available The definitions and conditions for fault isolability of single faults for various forms of the diagnostic relation are reviewed. Fault isolability and unisolability on the basis of a binary diagnostic matrix are analyzed. Definitions for conditional and unconditional isolability and unisolability on the basis of a fault information system (FIS, symptom sequences and directional residuals are formulated. General definitions for conditional and unconditional isolability and unisolability in the cases of simultaneous evaluation of diagnostic signal values and a sequence of symptoms are provided. A comprehensive example is discussed.

Fault diagnosis of power transformer based on fault-tree analysis (FTA)

Science.gov (United States)

Wang, Yongliang; Li, Xiaoqiang; Ma, Jianwei; Li, SuoYu

2017-05-01

Power transformers is an important equipment in power plants and substations, power distribution transmission link is made an important hub of power systems. Its performance directly affects the quality and health of the power system reliability and stability. This paper summarizes the five parts according to the fault type power transformers, then from the time dimension divided into three stages of power transformer fault, use DGA routine analysis and infrared diagnostics criterion set power transformer running state, finally, according to the needs of power transformer fault diagnosis, by the general to the section by stepwise refinement of dendritic tree constructed power transformer fault

Tools for functional analysis of faults and methods of fault-stable motion control

International Nuclear Information System (INIS)

Timofeev, A.V.

2003-01-01

In this article a big attention is given to the problems of functional diagnostics, when control and faults diagnostics are made in real time simultaneously in the process of functioning of controlled dynamical systems

Simultaneous Sensor and Process Fault Diagnostics for Propellant Feed System

Science.gov (United States)

Cao, J.; Kwan, C.; Figueroa, F.; Xu, R.

2006-01-01

The main objective of this research is to extract fault features from sensor faults and process faults by using advanced fault detection and isolation (FDI) algorithms. A tank system that has some common characteristics to a NASA testbed at Stennis Space Center was used to verify our proposed algorithms. First, a generic tank system was modeled. Second, a mathematical model suitable for FDI has been derived for the tank system. Third, a new and general FDI procedure has been designed to distinguish process faults and sensor faults. Extensive simulations clearly demonstrated the advantages of the new design.

Adapting plant measurement data to improve hardware fault detection performance in pressurised water reactors

International Nuclear Information System (INIS)

Cilliers, A.C.; Mulder, E.J.

2012-01-01

Highlights: ► Attempt was to use available resources at a nuclear plant in a value added fashion. ► Includes plant measurement data and plant training and engineering simulator capabilities. ► Solving the fault masking effect by the distributed control systems in the plant. ► Modelling the effect of inaccuracies in plant models used in the simulators. ► Combination of above resulted in the development of a deterministic fault identifications system. -- Abstract: With the fairly recent adoption of digital control and instrumentation systems in the nuclear industry a lot of research now focus on the development expert fault identification systems. The fault identification systems enable detecting early onset faults of fault causes which allows maintenance planning on the equipment showing signs of deterioration or failure. This includes valve and leaks and small cracks in steam generator tubes usually detected by means of ultrasonic inspection. Detecting faults early during transient operation in NPPs is problematic due to the absence of a reliable reference to compare plant measurements with during transients. The distributed application of control systems operating independently to keep the plant operating within the safe operating boundaries complicates the problem since the control systems would not only operate to reduce the effect of transient disturbances but fault disturbances as well. This paper provides a method to adapt the plant measurements that isolates the control actions on the fault and re-introduces it into the measurement data, thereby improving plant diagnostic performance.

Rectifier Fault Diagnosis and Fault Tolerance of a Doubly Fed Brushless Starter Generator

Directory of Open Access Journals (Sweden)

Liwei Shi

2015-01-01

Full Text Available This paper presents a rectifier fault diagnosis method with wavelet packet analysis to improve the fault tolerant four-phase doubly fed brushless starter generator (DFBLSG system reliability. The system components and fault tolerant principle of the high reliable DFBLSG are given. And the common fault of the rectifier is analyzed. The process of wavelet packet transforms fault detection/identification algorithm is introduced in detail. The fault tolerant performance and output voltage experiments were done to gather the energy characteristics with a voltage sensor. The signal is analyzed with 5-layer wavelet packets, and the energy eigenvalue of each frequency band is obtained. Meanwhile, the energy-eigenvalue tolerance was introduced to improve the diagnostic accuracy. With the wavelet packet fault diagnosis, the fault tolerant four-phase DFBLSG can detect the usual open-circuit fault and operate in the fault tolerant mode if there is a fault. The results indicate that the fault analysis techniques in this paper are accurate and effective.

Fuzzy fault diagnosis system of MCFC

Institute of Scientific and Technical Information of China (English)

Wang Zhenlei; Qian Feng; Cao Guangyi

2005-01-01

A kind of fault diagnosis system of molten carbonate fuel cell (MCFC) stack is proposed in this paper. It is composed of a fuzzy neural network (FNN) and a fault diagnosis element. FNN is able to deal with the information of the expert knowledge and the experiment data efficiently. It also has the ability to approximate any smooth system. FNN is used to identify the fault diagnosis model of MCFC stack. The fuzzy fault decision element can diagnose the state of the MCFC generating system, normal or fault, and can decide the type of the fault based on the outputs of FNN model and the MCFC system. Some simulation experiment results are demonstrated in this paper.

Application of support vector machine based on pattern spectrum entropy in fault diagnostics of rolling element bearings

International Nuclear Information System (INIS)

Hao, Rujiang; Chu, Fulei; Peng, Zhike; Feng, Zhipeng

2011-01-01

This paper presents a novel pattern classification approach for the fault diagnostics of rolling element bearings, which combines the morphological multi-scale analysis and the 'one to others' support vector machine (SVM) classifiers. The morphological pattern spectrum describes the shape characteristics of the inspected signal based on the morphological opening operation with multi-scale structuring elements. The pattern spectrum entropy and the barycenter scale location of the spectrum curve are extracted as the feature vectors presenting different faults of the bearing, which are more effective and representative than the kurtosis and the enveloping demodulation spectrum. The 'one to others' SVM algorithm is adopted to distinguish six kinds of fault signals which were measured in the experimental test rig under eight different working conditions. The recognition results of the SVM are ideal and more precise than those of the artificial neural network even though the training samples are few. The combination of the morphological pattern spectrum parameters and the 'one to others' multi-class SVM algorithm is suitable for the on-line automated fault diagnosis of the rolling element bearings. This application is promising and worth well exploiting

FTREX Testing Report (Fault Tree Reliability Evaluation eXpert) Version 1.5

International Nuclear Information System (INIS)

Jung, Woo Sik

2009-07-01

In order to verify FTREX functions and to confirm the correctness of FTREX 1.5, various tests were performed 1.fault trees with negates 2.fault trees with house events 3.fault trees with multiple tops 4.fault trees with logical loops 5.fault trees with initiators, house events, negates, logical loops, and flag events By using the automated cutest propagation test, the FTREX 1.5 functions are verified. FTREX version 1.3 and later versions have capability to perform bottom-up cutset-propagation test in order check cutest status. FTREX 1.5 always generates the proper minimal cut sets. All the output cutsets of the tested problems are MCSs (Minimal Cut Sets) and have no non-minimal cutsets and improper cutsets. The improper cutsets are those that have no effect to top, have multiple initiators, or have disjoint events A * -A

Expert and Competent Non-Expert Visual Cues during Simulated Diagnosis in Intensive Care

Directory of Open Access Journals (Sweden)

Clare eMcCormack

2014-08-01

Full Text Available The aim of this study was to examine the information acquisition strategies of expert and competent non-expert intensive care physicians during two simulated diagnostic scenarios involving respiratory distress in an infant. Specifically, the information acquisition performance of six experts and 12 competent non-experts was examined using an eye tracker during the initial 90 seconds of the assessment of the patient. The results indicated that, in comparison to competent non-experts, experts recorded longer mean fixations, irrespective of the scenario. When the dwell times were examined against specific areas of interest, the results revealed that competent non-experts recorded greater overall dwell times on the nurse, where experts recorded relatively greater dwell times on the head and face of the manikin. In the context of the scenarios, experts recorded differential dwell times, spending relatively more time on the head and face during the seizure scenario than during the coughing scenario. The differences evident between experts and competent non-experts were interpreted as evidence of the relative availability of task-specific cues or heuristics in memory that might direct the process of information acquisition amongst expert physicians. The implications are discussed for the training and assessment of diagnostic skills.

NuFTA: A CASE Tool for Automatic Software Fault Tree Analysis

International Nuclear Information System (INIS)

Yun, Sang Hyun; Lee, Dong Ah; Yoo, Jun Beom

2010-01-01

Software fault tree analysis (SFTA) is widely used for analyzing software requiring high-reliability. In SFTA, experts predict failures of system through HA-ZOP (Hazard and Operability study) or FMEA (Failure Mode and Effects Analysis) and draw software fault trees about the failures. Quality and cost of the software fault tree, therefore, depend on knowledge and experience of the experts. This paper proposes a CASE tool NuFTA in order to assist experts of safety analysis. The NuFTA automatically generate software fault trees from NuSCR formal requirements specification. NuSCR is a formal specification language used for specifying software requirements of KNICS RPS (Reactor Protection System) in Korea. We used the SFTA templates proposed by in order to generate SFTA automatically. The NuFTA also generates logical formulae summarizing the failure's cause, and we have a plan to use the formulae usefully through formal verification techniques

A diagnostic expert system for a boiling water reactor using a dynamic model

International Nuclear Information System (INIS)

Sonoda, Y.; Kanemoto, S.; Imaruoka, H.

1990-01-01

A diagnostic expert system for abnormal disturbances in a BWR (Boiling Water Reactor) plant has been developed. The peculiar feature of this system is a diagnostic method which combines artificial intelligence technique with numerical analysis technique. The system has three diagnostic functions, 1) identification of anomaly position (device or sensor), 2) identification of anomaly mode and 3) identification of anomaly cause. Function 1) is implemented as follows. First, a hypothesis about anomaly propagation paths is built up by qualitative reasoning, using knowledge of causal relations among observed signals. Next, the abnormal device or sensor is found by applying model reference method and fuzzy set theory to test the hypothesis, using knowledge of plant structure and function, heuristic strategy of diagnosis and module type dynamic simulator. This simulator is composed of basic transfer function modules. The simulation model for the testing region is built up automatically, according to the requirement from the diagnostic task. Function 2) means identification of dynamic characteristics for an anomaly. It is realized by tuning model parameters so as to reproduce the abnormal signal behavior using the non-linear programing method. Function 3) derives probable anomaly causes from heuristic rules between anomaly mode and cause. A basic plant dynamic model was built up and adjusted to dynamic characteristics for one BWR plant (1100MWe). In order to verify the diagnostic functions of this system, data for several abnormal events was compiled by modifying this model. The diagnostic functions were proved useful, through the simulated abnormal data

Development and testing of a diagnostic system for intelligen distributed control at EBR-2

International Nuclear Information System (INIS)

Edwards, R.M.; Ruhl, D.W.; Klevans, E.H.; Robinson, G.E.

1990-01-01

A diagnostic system is under development for demonstration of Intelligent Distributed Control at the Experimental Breeder Reactor (EBR--II). In the first phase of the project a diagnostic system is being developed for the EBR-II steam plant based on the DISYS expert systems approach. Current testing uses recorded plant data and data from simulated plant faults. The dynamical simulation of the EBR-II steam plant uses the Babcock and Wilcox (B ampersand W) Modular Modeling System (MMS). At EBR-II the diagnostic system operates in the UNIX workstation and receives live plant data from the plant Data Acquisition System (DAS). Future work will seek implementation of the steam plant diagnostic in a distributed manner using UNIX based computers and Bailey microprocessor-based control system. 10 refs., 6 figs

Use of an on-line Fuzzy-logic expert system for water chemistry

International Nuclear Information System (INIS)

Fandrich, J.; Metzner, W.

1998-01-01

The requirements for availability and operating economy of power plants have become steadily more stringent over the last few years. In addition to technological advances (e.g. in the form of new design measures, processes and materials), manufacturers have also increasingly applied secondary measures to enhance the safety and operating economy of power plant units. These include ever more sophisticated process monitoring and analytical systems and, (in recent times) diagnostic systems which perform continuous assessment of the plant condition to allow imminent changes that cam lead to damage and faults to be detected at the earliest possible time. The following paper presents an expert system, based on Fuzzy logic, which is used to perform a wide variety of tasks in the field of NPP water chemistry diagnostics. Thanks to the general nature of the approach selected, the system kernel is identical for all solutions which were implemented despite the wide variety of tasks and their diverse needs. This would not have been possible without the development and application of powerful and flexible engineering tools which can provide solutions to different types of problems at no extra effort. It will be shown in which way the system builds up diagnoses from the collected on-line data via a system -specific and easy- to-learn language and several tools. The presented module DIWA (Diagnostic System of Water Chemistry) was directly derived from the DIGEST system (diagnostic expert system for turbomachinery), which was developed over the last few years at the Power Generation Group (KWU) of the Siemens AG. (author)

Sliding Mode Fault Tolerant Control with Adaptive Diagnosis for Aircraft Engines

Science.gov (United States)

Xiao, Lingfei; Du, Yanbin; Hu, Jixiang; Jiang, Bin

2018-03-01

In this paper, a novel sliding mode fault tolerant control method is presented for aircraft engine systems with uncertainties and disturbances on the basis of adaptive diagnostic observer. By taking both sensors faults and actuators faults into account, the general model of aircraft engine control systems which is subjected to uncertainties and disturbances, is considered. Then, the corresponding augmented dynamic model is established in order to facilitate the fault diagnosis and fault tolerant controller design. Next, a suitable detection observer is designed to detect the faults effectively. Through creating an adaptive diagnostic observer and based on sliding mode strategy, the sliding mode fault tolerant controller is constructed. Robust stabilization is discussed and the closed-loop system can be stabilized robustly. It is also proven that the adaptive diagnostic observer output errors and the estimations of faults converge to a set exponentially, and the converge rate greater than some value which can be adjusted by choosing designable parameters properly. The simulation on a twin-shaft aircraft engine verifies the applicability of the proposed fault tolerant control method.

Fault detection and reliability, knowledge based and other approaches

International Nuclear Information System (INIS)

Singh, M.G.; Hindi, K.S.; Tzafestas, S.G.

1987-01-01

These proceedings are split up into four major parts in order to reflect the most significant aspects of reliability and fault detection as viewed at present. The first part deals with knowledge-based systems and comprises eleven contributions from leading experts in the field. The emphasis here is primarily on the use of artificial intelligence, expert systems and other knowledge-based systems for fault detection and reliability. The second part is devoted to fault detection of technological systems and comprises thirteen contributions dealing with applications of fault detection techniques to various technological systems such as gas networks, electric power systems, nuclear reactors and assembly cells. The third part of the proceedings, which consists of seven contributions, treats robust, fault tolerant and intelligent controllers and covers methodological issues as well as several applications ranging from nuclear power plants to industrial robots to steel grinding. The fourth part treats fault tolerant digital techniques and comprises five contributions. Two papers, one on reactor noise analysis, the other on reactor control system design, are indexed separately. (author)

A computer program to reduce the time of diagnosis in complex systems

International Nuclear Information System (INIS)

Arellano-Gomez, Juan; Romero-Rubio, Omar U.

2006-01-01

In Nuclear Power Plants (NPPs), the time that some systems are allowed to be down is frequently very limited. Thus, when one of these systems fails, diagnosis and repair must be quickly performed in order to get the system back to an operative state. Unfortunately, in complex systems, a considerable amount of the total repair time could be spent in the duty of diagnosis. For this reason, it seems very useful to provide maintenance personnel with a systematic approach to system failure diagnosis, capable to minimize the time required to effectively identify the causes of system malfunction. In this context, the expert systems technology has been widely applied in several disciplines to successfully develop diagnostic systems. Obviously, an important input to develop these expert systems is, of course, knowledge; this knowledge includes both formal knowledge and experience on what faults could occur, how these faults occur, which are the effects of these faults, what could be inferred from symptoms, etc. Due to their logical nature, those fault trees developed by expert analysts during risk studies could also be used as the source of knowledge of diagnostic expert systems (DES); however, these fault trees must be expanded to include symptoms because, typically, diagnosis is performed by inferring the causes of system malfunction from symptoms. This paper presents SANA (Symptom Analyzer), a new software package specially designed to develop diagnostic expert systems. The main feature of this software is that it exploits the knowledge stored in fault trees (in particular, expanded fault trees) to generate very efficient diagnostic strategies. These strategies guide diagnostic activities seeking to minimize the time required to identify those components which are responsible of the system failure. Besides, the generated strategies 'emulate' the way experienced technicians proceed in order to diagnose the causes of system failure (i.e. by recognizing categories of

Simultaneous-Fault Diagnosis of Gearboxes Using Probabilistic Committee Machine

Science.gov (United States)

Zhong, Jian-Hua; Wong, Pak Kin; Yang, Zhi-Xin

2016-01-01

This study combines signal de-noising, feature extraction, two pairwise-coupled relevance vector machines (PCRVMs) and particle swarm optimization (PSO) for parameter optimization to form an intelligent diagnostic framework for gearbox fault detection. Firstly, the noises of sensor signals are de-noised by using the wavelet threshold method to lower the noise level. Then, the Hilbert-Huang transform (HHT) and energy pattern calculation are applied to extract the fault features from de-noised signals. After that, an eleven-dimension vector, which consists of the energies of nine intrinsic mode functions (IMFs), maximum value of HHT marginal spectrum and its corresponding frequency component, is obtained to represent the features of each gearbox fault. The two PCRVMs serve as two different fault detection committee members, and they are trained by using vibration and sound signals, respectively. The individual diagnostic result from each committee member is then combined by applying a new probabilistic ensemble method, which can improve the overall diagnostic accuracy and increase the number of detectable faults as compared to individual classifiers acting alone. The effectiveness of the proposed framework is experimentally verified by using test cases. The experimental results show the proposed framework is superior to existing single classifiers in terms of diagnostic accuracies for both single- and simultaneous-faults in the gearbox. PMID:26848665

The commission of independent experts has labeled Mochovce as safe

International Nuclear Information System (INIS)

Grujbar, V.

1998-01-01

An independent commission of experts, appointed by IAEA, said that it did not find any faults concerning the integrity of the pressure vessel of the reactor in first block of the NPP Mochovce. The commission, comprising experts from the U.S.A., Belgium, Finland, Germany and Russia, was given the same documents as the Austrian mission, appointed by the office of the Austrian Chancellor, in May. The Austrian experts then expressed two serious concerns about the security of the first block in Mochovce.The experts of the IAEA agreed that the real condition of Mochovce is a lot better that shown in the technical documentation and they did not find any faults. IAEA was in this case, for the first time, an arbiter solving an international dispute about security of a NPP

CRISP. Fault detection, analysis and diagnostics in high-DG distribution systems

International Nuclear Information System (INIS)

Fontela, M.; Bacha, S.; Hadsjaid, N.; Andrieu, C.; Raison, B.; Penkov, D.

2004-04-01

The fault in the electrotechnical meaning is defined in the document. The main part of faults in overhead lines are non permanent faults, what entails the network operator to maintain the existing techniques to clear as fast as possible these faults. When a permanent fault occurs the operator has to detect and to limit the risks as soon as possible. Different axes are followed: limitation of the fault current, clearing the faulted feeder, locating the fault by test and try under possible fault condition. So the fault detection, fault clearing and fault localization are important functions of an EPS (electric power systems) to allow secure and safe operation of the system. The function may be improved by means of a better use of ICT components in the future sharing conveniently the intelligence needed near the distributed devices and a defined centralized intelligence. This improvement becomes necessary in distribution EPS with a high introduction of DR (distributed resources). The transmission and sub-transmission protection systems are already installed in order to manage power flow in all directions, so the DR issue is less critical for this part of the power system in term of fault clearing and diagnosis. Nevertheless the massive introduction of RES involves another constraints to the transmission system which are the bottlenecks caused by important local and fast installed production as wind power plants. Dealing with the distribution power system, and facing a permanent fault, two main actions must be achieved: identify the faulted elementary EPS area quickly and allow the field crew to locate and to repair the fault as soon as possible. The introduction of DR in distribution EPS involves some changes in fault location methods or equipment. The different existing neutral grounding systems make it difficult the achievement of a general method relevant for any distribution EPS in Europe. Some solutions are studied in the CRISP project in order to improve the

Diagnostic strategy and timing of intervention in infected necrotizing pancreatitis: an international expert survey and case vignette study

NARCIS (Netherlands)

van Grinsven, J. (Janneke); S. van Brunschot (Sandra); P. Fockens (Paul); J. van Grinsven (Janneke); O.J. Bakker (Olaf ); van Santvoort, H.C. (Hjalmar C.); T.L. Bollen (Thomas); M.A. Boermeester (Marja); C.H.J. van Eijck (Casper); M.G. Besselink (Marc); M.J. Bruno (Marco); C.H. Dejong (Cees); K.D. Horvath (Karen); van Eijck, C.H. (Casper H.); H. van Goor (Harry); H.G. Gooszen (Hein); Horvath, K.D. (Karen D.); K.P. van Lienden (Krijn); Abdelhafez, M.; Andersson, R.; Andren-Sandberg, A.; Ashley, S.; M.C. van Baal (Mark); Baron, T.; C. Bassi (Claudio); Bradley, E.; M.W. Buchler (M.); V.C. Cappendijk; Carter, R.; Charnley, R.; Coelho, D.; Connor, S.; Dellinger, P.; C. Dervenis (Christos); J. Devière (J.); Doctor, N.; Dudeja, V.; En-qiang, M.; Escourrou, J.; Fagenholz, P.; Farkas, G.; Forsmark, C.; Freeman, M.; P.C. Freeny (Patrick); French, J.; H. Friess; Gardner, T.; Goetzinger, P.; J.W. Haveman; S. Hofker (Sijbrand); Imrie, C.; Isaji, S.; Isenmann, R.; E. Klar (Ernst); J.S. Laméris (Johan ); M. Lerch (M.); P. Lévy (Philippe); Lillemoe, K.; Löhr, M.; J. Mayerle (Julia); Mayumi, T.; Mittal, A.; Moessner, J.; Morgan, D.; K.J. Mortele (Koenraad); Nealon, W.; J.P. Neoptolemos (John); V.B. Nieuwenhuijs (Vincent); Nordback, I.; Olah, A.; K. Oppong (K.); Padbury, R.; Papachristou, G.; Parks, R.; J.-W. Poley (Jan-Werner); Radenkovic, D.; Raraty, M.; Rau, B.; V. Rebours (Vinciane); Rische, S.; Runzi, M.; Sainani, N.; Sarr, M.; Schaapherder, S.; S. Seewald (Stefan); Seifert, H.; Shimosegawa, T.; Silverman, S.; Singh, V.; Siriwardena, A.; Steinberg, W.; Sutton, R.; Takeda, K.; R. Timmer (Robin); Vege, S.; R.P. Voermans (Rogier); J.J. De Waele (Jan J.); Wang, C. (Ch.); Warshaw, A.; J. Werner (Jens Martin); B.L. Weusten (Bas); Whitcomb, D.; Wig, J.; Windsor, J.; Zyromski, N.

2016-01-01

textabstractBackground The optimal diagnostic strategy and timing of intervention in infected necrotizing pancreatitis is subject to debate. We performed a survey on these topics amongst a group of international expert pancreatologists. Methods An online survey including case vignettes was sent to

Fault Management Metrics

Science.gov (United States)

Johnson, Stephen B.; Ghoshal, Sudipto; Haste, Deepak; Moore, Craig

2017-01-01

This paper describes the theory and considerations in the application of metrics to measure the effectiveness of fault management. Fault management refers here to the operational aspect of system health management, and as such is considered as a meta-control loop that operates to preserve or maximize the system's ability to achieve its goals in the face of current or prospective failure. As a suite of control loops, the metrics to estimate and measure the effectiveness of fault management are similar to those of classical control loops in being divided into two major classes: state estimation, and state control. State estimation metrics can be classified into lower-level subdivisions for detection coverage, detection effectiveness, fault isolation and fault identification (diagnostics), and failure prognosis. State control metrics can be classified into response determination effectiveness and response effectiveness. These metrics are applied to each and every fault management control loop in the system, for each failure to which they apply, and probabilistically summed to determine the effectiveness of these fault management control loops to preserve the relevant system goals that they are intended to protect.

DIAMS revisited: Taming the variety of knowledge in fault diagnosis expert systems

Science.gov (United States)

Haziza, M.; Ayache, S.; Brenot, J.-M.; Cayrac, D.; Vo, D.-P.

1994-01-01

The DIAMS program, initiated in 1986, led to the development of a prototype expert system, DIAMS-1 dedicated to the Telecom 1 Attitude and Orbit Control System, and to a near-operational system, DIAMS-2, covering a whole satellite (the Telecom 2 platform and its interfaces with the payload), which was installed in the Satellite Control Center in 1993. The refinement of the knowledge representation and reasoning is now being studied, focusing on the introduction of appropriate handling of incompleteness, uncertainty and time, and keeping in mind operational constraints. For the latest generation of the tool, DIAMS-3, a new architecture has been proposed, that enables the cooperative exploitation of various models and knowledge representations. On the same baseline, new solutions enabling higher integration of diagnostic systems in the operational environment and cooperation with other knowledge intensive systems such as data analysis, planning or procedure management tools have been introduced.

Diagnosis and fault-tolerant control

CERN Document Server

Blanke, Mogens; Lunze, Jan; Staroswiecki, Marcel

2016-01-01

Fault-tolerant control aims at a gradual shutdown response in automated systems when faults occur. It satisfies the industrial demand for enhanced availability and safety, in contrast to traditional reactions to faults, which bring about sudden shutdowns and loss of availability. The book presents effective model-based analysis and design methods for fault diagnosis and fault-tolerant control. Architectural and structural models are used to analyse the propagation of the fault through the process, to test the fault detectability and to find the redundancies in the process that can be used to ensure fault tolerance. It also introduces design methods suitable for diagnostic systems and fault-tolerant controllers for continuous processes that are described by analytical models of discrete-event systems represented by automata. The book is suitable for engineering students, engineers in industry and researchers who wish to get an overview of the variety of approaches to process diagnosis and fault-tolerant contro...

An expert system for diesel generator diagnostics

International Nuclear Information System (INIS)

Bley, D.C.; Read, J.W.; Kaplan, S.; Liming, J.K.; Brosee, N.M.; Hanley, D.W.

1987-01-01

The idea of developing artificial intelligence (AI) systems to capture the knowledge of human experts is receiving much attention these days. The idea is even more attractive when important expertise resides within a single individual, especially one who is nearing retirement and who has not otherwise recorded or passed along his important knowledge and thought processes. The diesel generators at Pilgrim Nuclear Power Station have performed exceptionally well, primarily due to the care and attention of one man. Therefore, the authors are constructing an expert system for the diagnosis of diesel generator problems at Pilgrim. This paper includes a description of the expert system design and operation, examples from the knowledge base, and sample diagnoses, so the reader can observe the process in action

Expert system for the diagnosis of the condition and performance of centrifugal pumps

Energy Technology Data Exchange (ETDEWEB)

Jantunen, E; Vaehae-Pietilae, K; Pesonen, K [Technical Research Centre of Finland, Manufacturing Technology, Espoo (Finland)

1998-12-31

A brief description of the results of a study concerning the maintenance and downtime costs in Finnish pumping is given. The leakage of seals was found to be the fault that causes the highest downtime and maintenance costs. A small laboratory arrangement has been used to test the effectiveness of various condition monitoring methods. This information has been used in the development of a diagnostic expert system called CEPDIA, which can be used for diagnosing the condition of a pump and its components. The diagnosis is based on measuring results obtained from sensors and on information about maintenance actions carried out with the pump and its components. The principles of the CEPDIA expert system are described. A database is included in the system for handling and saving the measurement results, technical information on the pumps and maintenance actions carried out with the pumps. The diagnosis can also be based on vibration signature analysis, which is quite effective in determining which fault is the actual cause of malfunction of the pump or its components. CEPDIA can also be used to calculate of the efficiency of the electrical motor and the pump. CEPDIA has been tested in the diagnosis of 63 pumps. The average efficiency in pumping was less than 40 %, and more than 10 % of the pumps were pumping with less than 10 % efficiency. (orig.) 11 refs.

Expert system for the diagnosis of the condition and performance of centrifugal pumps

Energy Technology Data Exchange (ETDEWEB)

Jantunen, E.; Vaehae-Pietilae, K.; Pesonen, K. [Technical Research Centre of Finland, Manufacturing Technology, Espoo (Finland)

1997-12-31

A brief description of the results of a study concerning the maintenance and downtime costs in Finnish pumping is given. The leakage of seals was found to be the fault that causes the highest downtime and maintenance costs. A small laboratory arrangement has been used to test the effectiveness of various condition monitoring methods. This information has been used in the development of a diagnostic expert system called CEPDIA, which can be used for diagnosing the condition of a pump and its components. The diagnosis is based on measuring results obtained from sensors and on information about maintenance actions carried out with the pump and its components. The principles of the CEPDIA expert system are described. A database is included in the system for handling and saving the measurement results, technical information on the pumps and maintenance actions carried out with the pumps. The diagnosis can also be based on vibration signature analysis, which is quite effective in determining which fault is the actual cause of malfunction of the pump or its components. CEPDIA can also be used to calculate of the efficiency of the electrical motor and the pump. CEPDIA has been tested in the diagnosis of 63 pumps. The average efficiency in pumping was less than 40 %, and more than 10 % of the pumps were pumping with less than 10 % efficiency. (orig.) 11 refs.

A prototype expert system to support the development of a fault-tree analysis software for nuclear reactor safety

International Nuclear Information System (INIS)

Mesko, L.

1990-01-01

The project called EMERIS is designed to provide a material testing nuclear reactor and experimental loops with a software for the 'acquisition, evaluation and archivation of measured data during the operation of the experimental facility'. The project which gives job a team has a duration of two years and involves three Vax compatible TPA-type computers and many smaller computers for data digitalization and graphical workstations. The detailed description of the project is not the task of the paper. One of its modules, however, plays an important role in the considerations. Namely the module for distrubance analysis (DA) which is planned to perform a rule based on-line evaluation of numerous predefined fault trees in an expert system like environment

A dynamic integrated fault diagnosis method for power transformers.

Science.gov (United States)

Gao, Wensheng; Bai, Cuifen; Liu, Tong

2015-01-01

In order to diagnose transformer fault efficiently and accurately, a dynamic integrated fault diagnosis method based on Bayesian network is proposed in this paper. First, an integrated fault diagnosis model is established based on the causal relationship among abnormal working conditions, failure modes, and failure symptoms of transformers, aimed at obtaining the most possible failure mode. And then considering the evidence input into the diagnosis model is gradually acquired and the fault diagnosis process in reality is multistep, a dynamic fault diagnosis mechanism is proposed based on the integrated fault diagnosis model. Different from the existing one-step diagnosis mechanism, it includes a multistep evidence-selection process, which gives the most effective diagnostic test to be performed in next step. Therefore, it can reduce unnecessary diagnostic tests and improve the accuracy and efficiency of diagnosis. Finally, the dynamic integrated fault diagnosis method is applied to actual cases, and the validity of this method is verified.

A Dynamic Integrated Fault Diagnosis Method for Power Transformers

Science.gov (United States)

Gao, Wensheng; Liu, Tong

2015-01-01

In order to diagnose transformer fault efficiently and accurately, a dynamic integrated fault diagnosis method based on Bayesian network is proposed in this paper. First, an integrated fault diagnosis model is established based on the causal relationship among abnormal working conditions, failure modes, and failure symptoms of transformers, aimed at obtaining the most possible failure mode. And then considering the evidence input into the diagnosis model is gradually acquired and the fault diagnosis process in reality is multistep, a dynamic fault diagnosis mechanism is proposed based on the integrated fault diagnosis model. Different from the existing one-step diagnosis mechanism, it includes a multistep evidence-selection process, which gives the most effective diagnostic test to be performed in next step. Therefore, it can reduce unnecessary diagnostic tests and improve the accuracy and efficiency of diagnosis. Finally, the dynamic integrated fault diagnosis method is applied to actual cases, and the validity of this method is verified. PMID:25685841

A framework for an on-line diagnostic expert system with intelligent sensor validation

International Nuclear Information System (INIS)

Kim, Young Jin

1997-01-01

This paper outlines a framework for performing two different but inter-related functions in diagnosis, i.e. sensor validation and reasoning under uncertainty. Sensor validation plays a vital role in the ability of the overall system to correctly determine the state of a plant monitored by imperfect sensors (Sopocy, 1990). Two subsystems, Algorithmic(ASV) and Heuristic(HSV) Sensor Validation, separate activities according to the degree of plant knowledge required and represent Sensor Validation Expert System when combined. Uncertain information in sensory values is represented through probability assignments on three discrete states, High, Normal, and Low, and additional sensor confidence measures in ASV. HSV exploits deeper knowledge about parameter interaction within the plant to cull sensor faults from the data stream. Finally the modified probability distributions and validated data are used as input to the reasoning scheme which is the run-time version of the influence diagram. The influence diagram represents the backbone of reasoning under uncertainty in Influence Diagram Knowledge Base. (author)

Investigation of display issues relevant to the presentation of aircraft fault information

Science.gov (United States)

Allen, Donald M.

1989-01-01

This research, performed as a part of NASA Langley's Faultfinder project, investigated display implementation issues related to the introduction of real time fault diagnostic systems into next generation commercial aircraft. Three major issues were investigated: visual display styles for presenting fault related information to the crew, the form the output from the expert system should take, and methods for filtering fault related information for presentation to the crew. Twenty-four flight familiar male volunteers participated as subjects. Five subjects were NASA test pilots, six were Commercial Airline Pilots, seven were Air Force Lear Jet pilots, and six were NASA personnel familiar with flight (non-pilots). Subjects were presented with aircraft subsystem information on a CRT screen. They were required to identify the subsystems presented in a display and to remember the state (normal or abnormal) of subsystem parameter information contained in the display. The results of the study indicated that in the simpler experimental test cases (i.e., those involving single subsystem failures and composite hypothesis displays) subjects' performance did not differ across the different display formats. However, for the more complex cases (i.e., those involving multiple subsystem faults and multiple hypotheses displays), subjects' performance was superior in the text- and picture-based display formats compared to the symbol-based format. In addition, the findings suggest that a layered approached to information display is appropriate.

A methodology and status of technology for fault diagnosis

International Nuclear Information System (INIS)

Kim, Jung Taek; Ham, Chang Shik; Kwon, Kee Choon; Lee, Dong Young; Hwang, In Koo; Song, Soon Ja; Park, Joo Hweon

1998-05-01

Since the 1980's, a nuclear industry has been attempting to apply an artificial intelligent system into MMIS. Such attempts have, especially, been led by U.S.A., Japan and Halden, which were more active for studying an artificial intelligent system. a diagnostic system is being developed such a small system that is the more frequent faults or directly effects fault into a operation and a safety of plants. Such a small diagnostic system gives a diagnostic information into the alarm processing systems or the plant information monitoring systems as integrated with these large systems. There are two major methods of diagnosis of faults. The first method is to make a misbehavior on components or processes into knowledge base and the other is to make a misbehavior on components or processes into processing model. The latter has the advantage of the former. There are OASYS and alarm processing system in ADIOS as the typical diagnostic systems on knowledge base. There are MOAS-II, Halden's diagnostic systems and diagnostic model in ADIOS as the typical diagnostic systems on model base. (author). 32 refs., 18 tabs., 28 figs

Recent advances in control and diagnostics development and application

International Nuclear Information System (INIS)

Monson, L.R.; King, R.W.; Lindsay, R.W.; Staffon, J.D.

1989-01-01

The power industry is undergoing rapid technological advances and cultural changes. Technologies are advancing and evolving so rapidly that the industry is hard pressed to keep up and take full advantage of the many developments now in progress. Recent advantages in state-of-the-art computer technology are making in-roads in the form of advanced computer control, expert systems, on-line performance monitoring and diagnostics. Validation and verification schemes are being developed which provide increased confidence in the correctness and reliability of both computer hardware and software. Our challenge in the nuclear community is to effectively apply these new technologies to improve the operation, safety, and reliability of our plants. This presentation discusses two areas of development that are essential to advanced control strategies: application of diagnostic systems to improve fault-tolerance, and model-based graphic displays. 4 refs., 4 figs

Knowledge acquisition and rapid protyping of an expert system: Dealing with real world problems

Science.gov (United States)

Bailey, Patrick A.; Doehr, Brett B.

1988-01-01

The knowledge engineering and rapid prototyping phases of an expert system that does fault handling for a Solid Amine, Water Desorbed CO2 removal assembly for the Environmental Control and Life Support System for space based platforms are addressed. The knowledge acquisition phase for this project was interesting because it could not follow the textbook examples. As a result of this, a variety of methods were used during the knowledge acquisition task. The use of rapid prototyping and the need for a flexible prototype suggested certain types of knowledge representation. By combining various techniques, a representative subset of faults and a method for handling those faults was achieved. The experiences should prove useful for developing future fault handling expert systems under similar constraints.

Application of Fault Tree Analysis and Fuzzy Neural Networks to Fault Diagnosis in the Internet of Things (IoT) for Aquaculture.

Science.gov (United States)

Chen, Yingyi; Zhen, Zhumi; Yu, Huihui; Xu, Jing

2017-01-14

In the Internet of Things (IoT) equipment used for aquaculture is often deployed in outdoor ponds located in remote areas. Faults occur frequently in these tough environments and the staff generally lack professional knowledge and pay a low degree of attention in these areas. Once faults happen, expert personnel must carry out maintenance outdoors. Therefore, this study presents an intelligent method for fault diagnosis based on fault tree analysis and a fuzzy neural network. In the proposed method, first, the fault tree presents a logic structure of fault symptoms and faults. Second, rules extracted from the fault trees avoid duplicate and redundancy. Third, the fuzzy neural network is applied to train the relationship mapping between fault symptoms and faults. In the aquaculture IoT, one fault can cause various fault symptoms, and one symptom can be caused by a variety of faults. Four fault relationships are obtained. Results show that one symptom-to-one fault, two symptoms-to-two faults, and two symptoms-to-one fault relationships can be rapidly diagnosed with high precision, while one symptom-to-two faults patterns perform not so well, but are still worth researching. This model implements diagnosis for most kinds of faults in the aquaculture IoT.

Application of Fault Tree Analysis and Fuzzy Neural Networks to Fault Diagnosis in the Internet of Things (IoT for Aquaculture

Directory of Open Access Journals (Sweden)

Yingyi Chen

2017-01-01

Full Text Available In the Internet of Things (IoT equipment used for aquaculture is often deployed in outdoor ponds located in remote areas. Faults occur frequently in these tough environments and the staff generally lack professional knowledge and pay a low degree of attention in these areas. Once faults happen, expert personnel must carry out maintenance outdoors. Therefore, this study presents an intelligent method for fault diagnosis based on fault tree analysis and a fuzzy neural network. In the proposed method, first, the fault tree presents a logic structure of fault symptoms and faults. Second, rules extracted from the fault trees avoid duplicate and redundancy. Third, the fuzzy neural network is applied to train the relationship mapping between fault symptoms and faults. In the aquaculture IoT, one fault can cause various fault symptoms, and one symptom can be caused by a variety of faults. Four fault relationships are obtained. Results show that one symptom-to-one fault, two symptoms-to-two faults, and two symptoms-to-one fault relationships can be rapidly diagnosed with high precision, while one symptom-to-two faults patterns perform not so well, but are still worth researching. This model implements diagnosis for most kinds of faults in the aquaculture IoT.

A diagnostic expert system for NPP based on hybrid knowledge approach

International Nuclear Information System (INIS)

Yang, Joon On; Chang, Soon Heung

1989-01-01

This paper describes a diagnostic expert system, HYPOSS (Hybrid Knowledge Based Plant Operation Supporting System), which has been developed to support operators' decision making during the transients of nuclear power plant. HYPOSS adopts the hybrid knowledge approach which combines shallow and deep knowledge to couple the merits of both approaches. In HYPOSS, four types of knowledge are used according to the steps of diagnosis procedure: structural, functional, behavioral and heuristic knowledge. The structural and functional knowledge is represented by three fundamental primitives and five types of functions respectively. The behavioral knowledge is represented using constraints. The inference procedure is based on the human problem solving behavior modeled in HYPOSS. For the validation of HYPOSS, several tests have been performed based on the data produced by a plant simulator. The results of validation studies showed a good applicability of HYPOSS to the anomaly diagnosis of nuclear power plant

FaultBuster: data driven fault detection and diagnosis for industrial systems

DEFF Research Database (Denmark)

Bergantino, Nicola; Caponetti, Fabio; Longhi, Sauro

2009-01-01

. Multivariate statistical models based on principal components are used to detect abnormal situations. Tailored to alarms, a probabilistic inference engine process the fault evidences to output the most probable diagnosis. Results from the DX 09 Diagnostic Challenge shown strong detection properties, while...

NN-Es Fault Diagnosis Method in Nuclear Power Equipment Based on Concept Lattice

International Nuclear Information System (INIS)

Liu Yongkuo; Xie Chunli; Xia Hong

2010-01-01

In order to improve the fault diagnosis accuracy of nuclear power plant,neural network and expert systems were combined to give full play to their advantages. In this paper, the concept lattice was applied to get the object properties, extracting the core attributes, dispensable attributes and relative necessary attributes from a large number raw data of fault symptoms.Based on these attributes, neural networks with different levels of importance were designed to improve the learning speed and diagnosis accuracy, and the diagnosis results of the neural networks were verified by using rule-based reasoning expert system. To verify the accuracy of this method, some simulation experiments about the typical faults of nuclear power plant were conducted. And the simulation results show that it is feasible to diagnose nuclear power plant faults with the confederation diagnosis methods combined the neural networks based on the concept lattice theory and expert system, with the distinctive features such as the efficiency of neural network learning, less calculation and reliability of diagnosis results and so on. (authors)

DIVA and DIAPO: two diagnostic knowledge based systems used for French nuclear power plants

International Nuclear Information System (INIS)

Porcheron, M.; Ricard, B.; Joussellin, A.

1997-01-01

In order to improve monitoring and diagnosis capabilities in nuclear power plants, Electricite de France (EDF) has designed an integrated monitoring and diagnosis assistance system: PSAD-Poste de Surveillance et d'Aide au Diagnostic. The development of such a sophisticated monitoring and data processing systems has emphasized the need for the addition of analysis and diagnosis assistance capabilities. Therefore, diagnostic knowledge based systems have been added to the functions monitored in PSAD: DIVA for turbine generators, and DIAPO for reactor coolant pumps. These systems were designed from a representation of the diagnostic reasoning process of experts and of the supporting knowledge. Diagnosis in both systems relies on an abduction reasoning process applied to component fault models and observations derived from their actual behavior, as provided by the monitoring functions. The basic theoretical elements of this diagnostic model are summarized in a first part. In a second part, DIVA and DIAPO specific elements are described

A knowledge based on-line diagnostic system for the fast breeder reactor KNKII

International Nuclear Information System (INIS)

Eggert, H.; Scherer, K.P.; Stiller, P.

1989-01-01

In the nuclear research center at Karlsruhe, a diagnostic expert system is developed to supervise a fast breeder process (KNKII). The problem is to detect critical phases in the beginning state before fault propagation. The expert system itself is integrated in a computer network (realized by a local area network), where different computers are involved as special detection systems (for example acoustic noise, temperature noise, covergas monitoring and so on), which produce partial diagnoses, based on intelligent signal processing techniques like pattern recognition. Additional to the detection systems a process computer is integrated as well as a test computer, which simulates hypothetical and real fault data. On the logical top level the expert system manages the partial diagnoses of the detection systems with the operating data of the process computer and to produce a final diagnosis including the explanation part for operator support. The knowledge base is developed by typical Artificial Intelligence tools. Both fact based and rule based knowledge representations are stored in form of flavors and predications. The inference engine operates on a rule based approach. Specific detail knowledge, based on experience about any years, is available to influence the decision process by increasing or decreasing of the generated hypotheses. In a meta knowledge base, a rule master triggers the special domain experts and contributes the tasks to the specific rule complexes. Such a system management guarantees a problem solving strategy, which operates event triggered and situation specific in a local inference domain. (author). 3 refs, 6 figs, 2 tabs

Knowledge acquisition for nuclear power plant unit diagnostic system

International Nuclear Information System (INIS)

Li Xiaodong; Xi Shuren

2003-01-01

The process of acquiring knowledge and building a knowledge base is critical to realize fault diagnostic system at unit level in a nuclear power plant. It directly determines whether the diagnostic system can be applied eventually in a commercial plant. A means to acquire knowledge and its procedures was presented in this paper for fault diagnostic system in a nuclear power plant. The work can be carried out step by step and it is feasible in a commercial nuclear power plant. The knowledge base of the fault diagnostic system for a nuclear power plant can be built after the staff finish the tasks according to the framework presented in this paper

Distributed bearing fault diagnosis based on vibration analysis

Science.gov (United States)

Dolenc, Boštjan; Boškoski, Pavle; Juričić, Đani

2016-01-01

Distributed bearing faults appear under various circumstances, for example due to electroerosion or the progression of localized faults. Bearings with distributed faults tend to generate more complex vibration patterns than those with localized faults. Despite the frequent occurrence of such faults, their diagnosis has attracted limited attention. This paper examines a method for the diagnosis of distributed bearing faults employing vibration analysis. The vibrational patterns generated are modeled by incorporating the geometrical imperfections of the bearing components. Comparing envelope spectra of vibration signals shows that one can distinguish between localized and distributed faults. Furthermore, a diagnostic procedure for the detection of distributed faults is proposed. This is evaluated on several bearings with naturally born distributed faults, which are compared with fault-free bearings and bearings with localized faults. It is shown experimentally that features extracted from vibrations in fault-free, localized and distributed fault conditions form clearly separable clusters, thus enabling diagnosis.

Simultaneous-Fault Diagnosis of Gas Turbine Generator Systems Using a Pairwise-Coupled Probabilistic Classifier

Directory of Open Access Journals (Sweden)

Zhixin Yang

2013-01-01

Full Text Available A reliable fault diagnostic system for gas turbine generator system (GTGS, which is complicated and inherent with many types of component faults, is essential to avoid the interruption of electricity supply. However, the GTGS diagnosis faces challenges in terms of the existence of simultaneous-fault diagnosis and high cost in acquiring the exponentially increased simultaneous-fault vibration signals for constructing the diagnostic system. This research proposes a new diagnostic framework combining feature extraction, pairwise-coupled probabilistic classifier, and decision threshold optimization. The feature extraction module adopts wavelet packet transform and time-domain statistical features to extract vibration signal features. Kernel principal component analysis is then applied to further reduce the redundant features. The features of single faults in a simultaneous-fault pattern are extracted and then detected using a probabilistic classifier, namely, pairwise-coupled relevance vector machine, which is trained with single-fault patterns only. Therefore, the training dataset of simultaneous-fault patterns is unnecessary. To optimize the decision threshold, this research proposes to use grid search method which can ensure a global solution as compared with traditional computational intelligence techniques. Experimental results show that the proposed framework performs well for both single-fault and simultaneous-fault diagnosis and is superior to the frameworks without feature extraction and pairwise coupling.

A rule-based fault detection method for air handling units

Energy Technology Data Exchange (ETDEWEB)

Schein, J.; Bushby, S. T.; Castro, N. S. [National Institute of Standards and Technology, Gaithersburg, MD (United States); House, J. M. [Iowa Energy Center, Ankeny, IA (United States)

2006-07-01

Air handling unit performance assessment rules (APAR) is a fault detection tool that uses a set of expert rules derived from mass and energy balances to detect faults in air handling units (AHUs). Control signals are used to determine the mode of operation of the AHU. A subset of the expert rules which correspond to that mode of operation are then evaluated to determine whether a fault exists. APAR is computationally simple enough that it can be embedded in commercial building automation and control systems and relies only upon the sensor data and control signals that are commonly available in these systems. APAR was tested using data sets collected from a 'hardware-in-the-loop' emulator and from several field sites. APAR was also embedded in commercial AHU controllers and tested in the emulator. (author)

Fuzzy probability based fault tree analysis to propagate and quantify epistemic uncertainty

International Nuclear Information System (INIS)

Purba, Julwan Hendry; Sony Tjahyani, D.T.; Ekariansyah, Andi Sofrany; Tjahjono, Hendro

2015-01-01

Highlights: • Fuzzy probability based fault tree analysis is to evaluate epistemic uncertainty in fuzzy fault tree analysis. • Fuzzy probabilities represent likelihood occurrences of all events in a fault tree. • A fuzzy multiplication rule quantifies epistemic uncertainty of minimal cut sets. • A fuzzy complement rule estimate epistemic uncertainty of the top event. • The proposed FPFTA has successfully evaluated the U.S. Combustion Engineering RPS. - Abstract: A number of fuzzy fault tree analysis approaches, which integrate fuzzy concepts into the quantitative phase of conventional fault tree analysis, have been proposed to study reliabilities of engineering systems. Those new approaches apply expert judgments to overcome the limitation of the conventional fault tree analysis when basic events do not have probability distributions. Since expert judgments might come with epistemic uncertainty, it is important to quantify the overall uncertainties of the fuzzy fault tree analysis. Monte Carlo simulation is commonly used to quantify the overall uncertainties of conventional fault tree analysis. However, since Monte Carlo simulation is based on probability distribution, this technique is not appropriate for fuzzy fault tree analysis, which is based on fuzzy probabilities. The objective of this study is to develop a fuzzy probability based fault tree analysis to overcome the limitation of fuzzy fault tree analysis. To demonstrate the applicability of the proposed approach, a case study is performed and its results are then compared to the results analyzed by a conventional fault tree analysis. The results confirm that the proposed fuzzy probability based fault tree analysis is feasible to propagate and quantify epistemic uncertainties in fault tree analysis

Diagnostic accuracy of semi-automatic quantitative metrics as an alternative to expert reading of CT myocardial perfusion in the CORE320 study.

Science.gov (United States)

Ostovaneh, Mohammad R; Vavere, Andrea L; Mehra, Vishal C; Kofoed, Klaus F; Matheson, Matthew B; Arbab-Zadeh, Armin; Fujisawa, Yasuko; Schuijf, Joanne D; Rochitte, Carlos E; Scholte, Arthur J; Kitagawa, Kakuya; Dewey, Marc; Cox, Christopher; DiCarli, Marcelo F; George, Richard T; Lima, Joao A C

2018-04-03

To determine the diagnostic accuracy of semi-automatic quantitative metrics compared to expert reading for interpretation of computed tomography perfusion (CTP) imaging. The CORE320 multicenter diagnostic accuracy clinical study enrolled patients between 45 and 85 years of age who were clinically referred for invasive coronary angiography (ICA). Computed tomography angiography (CTA), CTP, single photon emission computed tomography (SPECT), and ICA images were interpreted manually in blinded core laboratories by two experienced readers. Additionally, eight quantitative CTP metrics as continuous values were computed semi-automatically from myocardial and blood attenuation and were combined using logistic regression to derive a final quantitative CTP metric score. For the reference standard, hemodynamically significant coronary artery disease (CAD) was defined as a quantitative ICA stenosis of 50% or greater and a corresponding perfusion defect by SPECT. Diagnostic accuracy was determined by area under the receiver operating characteristic curve (AUC). Of the total 377 included patients, 66% were male, median age was 62 (IQR: 56, 68) years, and 27% had prior myocardial infarction. In patient based analysis, the AUC (95% CI) for combined CTA-CTP expert reading and combined CTA-CTP semi-automatic quantitative metrics was 0.87(0.84-0.91) and 0.86 (0.83-0.9), respectively. In vessel based analyses the AUC's were 0.85 (0.82-0.88) and 0.84 (0.81-0.87), respectively. No significant difference in AUC was found between combined CTA-CTP expert reading and CTA-CTP semi-automatic quantitative metrics in patient based or vessel based analyses(p > 0.05 for all). Combined CTA-CTP semi-automatic quantitative metrics is as accurate as CTA-CTP expert reading to detect hemodynamically significant CAD. Copyright © 2018 Society of Cardiovascular Computed Tomography. Published by Elsevier Inc. All rights reserved.

A novel vibration-based fault diagnostic algorithm for gearboxes under speed fluctuations without rotational speed measurement

Science.gov (United States)

Hong, Liu; Qu, Yongzhi; Dhupia, Jaspreet Singh; Sheng, Shuangwen; Tan, Yuegang; Zhou, Zude

2017-09-01

The localized failures of gears introduce cyclic-transient impulses in the measured gearbox vibration signals. These impulses are usually identified from the sidebands around gear-mesh harmonics through the spectral analysis of cyclo-stationary signals. However, in practice, several high-powered applications of gearboxes like wind turbines are intrinsically characterized by nonstationary processes that blur the measured vibration spectra of a gearbox and deteriorate the efficacy of spectral diagnostic methods. Although order-tracking techniques have been proposed to improve the performance of spectral diagnosis for nonstationary signals measured in such applications, the required hardware for the measurement of rotational speed of these machines is often unavailable in industrial settings. Moreover, existing tacho-less order-tracking approaches are usually limited by the high time-frequency resolution requirement, which is a prerequisite for the precise estimation of the instantaneous frequency. To address such issues, a novel fault-signature enhancement algorithm is proposed that can alleviate the spectral smearing without the need of rotational speed measurement. This proposed tacho-less diagnostic technique resamples the measured acceleration signal of the gearbox based on the optimal warping path evaluated from the fast dynamic time-warping algorithm, which aligns a filtered shaft rotational harmonic signal with respect to a reference signal assuming a constant shaft rotational speed estimated from the approximation of operational speed. The effectiveness of this method is validated using both simulated signals from a fixed-axis gear pair under nonstationary conditions and experimental measurements from a 750-kW planetary wind turbine gearbox on a dynamometer test rig. The results demonstrate that the proposed algorithm can identify fault information from typical gearbox vibration measurements carried out in a resource-constrained industrial environment.

Diagnostic and Prognostic Models for Generator Step-Up Transformers

Energy Technology Data Exchange (ETDEWEB)

Vivek Agarwal; Nancy J. Lybeck; Binh T. Pham

2014-09-01

In 2014, the online monitoring (OLM) of active components project under the Light Water Reactor Sustainability program at Idaho National Laboratory (INL) focused on diagnostic and prognostic capabilities for generator step-up transformers. INL worked with subject matter experts from the Electric Power Research Institute (EPRI) to augment and revise the GSU fault signatures previously implemented in the Electric Power Research Institute’s (EPRI’s) Fleet-Wide Prognostic and Health Management (FW-PHM) Suite software. Two prognostic models were identified and implemented for GSUs in the FW-PHM Suite software. INL and EPRI demonstrated the use of prognostic capabilities for GSUs. The complete set of fault signatures developed for GSUs in the Asset Fault Signature Database of the FW-PHM Suite for GSUs is presented in this report. Two prognostic models are described for paper insulation: the Chendong model for degree of polymerization, and an IEEE model that uses a loading profile to calculates life consumption based on hot spot winding temperatures. Both models are life consumption models, which are examples of type II prognostic models. Use of the models in the FW-PHM Suite was successfully demonstrated at the 2014 August Utility Working Group Meeting, Idaho Falls, Idaho, to representatives from different utilities, EPRI, and the Halden Research Project.

The Development of Expertise in Radiology: In Chest Radiograph Interpretation, "Expert" Search Pattern May Predate "Expert" Levels of Diagnostic Accuracy for Pneumothorax Identification.

Science.gov (United States)

Kelly, Brendan S; Rainford, Louise A; Darcy, Sarah P; Kavanagh, Eoin C; Toomey, Rachel J

2016-07-01

Purpose To investigate the development of chest radiograph interpretation skill through medical training by measuring both diagnostic accuracy and eye movements during visual search. Materials and Methods An institutional exemption from full ethical review was granted for the study. Five consultant radiologists were deemed the reference expert group, and four radiology registrars, five senior house officers (SHOs), and six interns formed four clinician groups. Participants were shown 30 chest radiographs, 14 of which had a pneumothorax, and were asked to give their level of confidence as to whether a pneumothorax was present. Receiver operating characteristic (ROC) curve analysis was carried out on diagnostic decisions. Eye movements were recorded with a Tobii TX300 (Tobii Technology, Stockholm, Sweden) eye tracker. Four eye-tracking metrics were analyzed. Variables were compared to identify any differences between groups. All data were compared by using the Friedman nonparametric method. Results The average area under the ROC curve for the groups increased with experience (0.947 for consultants, 0.792 for registrars, 0.693 for SHOs, and 0.659 for interns; P = .009). A significant difference in diagnostic accuracy was found between consultants and registrars (P = .046). All four eye-tracking metrics decreased with experience, and there were significant differences between registrars and SHOs. Total reading time decreased with experience; it was significantly lower for registrars compared with SHOs (P = .046) and for SHOs compared with interns (P = .025). Conclusion Chest radiograph interpretation skill increased with experience, both in terms of diagnostic accuracy and visual search. The observed level of experience at which there was a significant difference was higher for diagnostic accuracy than for eye-tracking metrics. (©) RSNA, 2016 Online supplemental material is available for this article.

Implementing artificial neural networks in nuclear power plants diagnostic systems: issues and challenges

International Nuclear Information System (INIS)

Boger, Z.

1998-01-01

A recent review of artificial intelligence applications in nuclear power plants (NPP) diagnostics and fault detection finds that mostly expert systems (ES) and artificial neural networks (ANN) techniques were researched and proposed, but the number of actual implementations in NPP diagnostics systems is very small. It lists the perceived obstacles to the ANN-based system acceptance and implementation. This paper analyses this list. Some of ANN limitations relate to 'quantitative' difficulties of designing and training large-scale ANNs. The availability of an efficient large-scale ANN training algorithm may alleviate most of these concerns. Other perceived drawbacks refer to the 'qualitative' aspects of ANN acceptance - how and when can we rely on the quality of the advice given by the ANN model. Several techniques are available that help to brighten the 'black box' image of the ANN. Analysis of the trained ANN can identify the significant inputs. Calculation of the Causal Indices may reveal the magnitude and sign of the influence of each input on each output. Both these techniques increase the confidence of the users when they conform to known knowledge, or point to plausible relationships. Analysis of the behavior of the neurons in the hidden layer can identify false ANN classification when presented with noisy or corrupt data. Auto-associative NN can identify faulty sensors or data. Two examples of the ANN capabilities as possible diagnostic tools are given, using NPP data, one classifying internal reactor disturbances by neutron noise spectra analysis, the other identifying the faults causes of several transients. To use these techniques the ANN developers need large amount of training data of as many transients as possible. Such data is routinely generated in NPP simulators during the periodic qualification of NPP operators. The IAEA can help by encouraging the saving and distributing the transient data to developers of ANN diagnostic system, to serve as

Knowledge Representation Using Multilevel Flow Model in Expert System

International Nuclear Information System (INIS)

Wang, Wenlin; Yang, Ming

2015-01-01

As for the knowledge representation, of course, there are a great many methods available for knowledge representation. These include frames, causal models, and many others. This paper presents a novel method called Multilevel Flow Model (MFM), which is used for knowledge representation in G2 expert system. Knowledge representation plays a vital role in constructing knowledge bases. Moreover, it also has impact on building of generic fault model as well as knowledge bases. The MFM is particularly useful to describe system knowledge concisely as domain map in expert system when domain experts are not available

Knowledge Representation Using Multilevel Flow Model in Expert System

Energy Technology Data Exchange (ETDEWEB)

Wang, Wenlin; Yang, Ming [Harbin Engineering University, Harbin (China)

2015-05-15

As for the knowledge representation, of course, there are a great many methods available for knowledge representation. These include frames, causal models, and many others. This paper presents a novel method called Multilevel Flow Model (MFM), which is used for knowledge representation in G2 expert system. Knowledge representation plays a vital role in constructing knowledge bases. Moreover, it also has impact on building of generic fault model as well as knowledge bases. The MFM is particularly useful to describe system knowledge concisely as domain map in expert system when domain experts are not available.

Modeling, control and fault diagnosis of an isolated wind energy conversion system with a self-excited induction generator subject to electrical faults

International Nuclear Information System (INIS)

Attoui, Issam; Omeiri, Amar

2014-01-01

Highlights: • A new model of the SEIG is developed to simulate both the rotor and stator faults. • This model takes iron loss, main flux and cross flux saturation into account. • A new control strategy based on Fractional-Order Controller (FOC) is proposed. • The control strategy is developed for the control of the wind turbine speed. • An on-line diagnostic procedure based on the stator currents analysis is presented. - Abstract: In this paper, a contribution to modeling and fault diagnosis of rotor and stator faults of a Self-Excited Induction Generator (SEIG) in an Isolated Wind Energy Conversion System (IWECS) is proposed. In order to control the speed of the wind turbine, while basing on the linear model of wind turbine system about a specified operating point, a new Fractional-Order Controller (FOC) with a simple and practical design method is proposed. The FOC ensures the stability of the nonlinear system in both healthy and faulty conditions. Furthermore, in order to detect the stator and rotor faults in the squirrel-cage self-excited induction generator, an on-line fault diagnostic technique based on the spectral analysis of stator currents of the squirrel-cage SEIG by a Fast Fourier Transform (FFT) algorithm is used. Additionally, a generalized model of the squirrel-cage SEIG is developed to simulate both the rotor and stator faults taking iron loss, main flux and cross flux saturation into account. The efficiencies of generalized model, control strategy and diagnostic procedure are illustrated with simulation results

Fault Diagnosis for Actuators in a Class of Nonlinear Systems Based on an Adaptive Fault Detection Observer

Directory of Open Access Journals (Sweden)

Runxia Guo

2016-01-01

Full Text Available The problem of actuators’ fault diagnosis is pursued for a class of nonlinear control systems that are affected by bounded measurement noise and external disturbances. A novel fault diagnosis algorithm has been proposed by combining the idea of adaptive control theory and the approach of fault detection observer. The asymptotical stability of the fault detection observer is guaranteed by setting the adaptive adjusting law of the unknown fault vector. A theoretically rigorous proof of asymptotical stability has been given. Under the condition that random measurement noise generated by the sensors of control systems and external disturbances exist simultaneously, the designed fault diagnosis algorithm is able to successfully give specific estimated values of state variables and failures rather than just giving a simple fault warning. Moreover, the proposed algorithm is very simple and concise and is easy to be applied to practical engineering. Numerical experiments are carried out to evaluate the performance of the fault diagnosis algorithm. Experimental results show that the proposed diagnostic strategy has a satisfactory estimation effect.

A living PSA based on use of expert systems

International Nuclear Information System (INIS)

Ancelin, C.; Bouissou, M.; Le, P.; De Saint-Quentin, S.; Villatte, N.

1989-01-01

This paper presents the expert systems that are developed by EDF in the framework of the French PSA. Aimed at automatically generating reliability models (fault trees, state graphs....), these expert systems are used for the reliability studies of safety systems in the Paluel nuclear power plant. Beyond the description of the implemented method, this paper insists on the new approach proposed to the reliability engineer, when using artificial intelligence techniques

Development of a component centered fault monitoring and diagnosis knowledge based system for space power system

Science.gov (United States)

Lee, S. C.; Lollar, Louis F.

1988-01-01

The overall approach currently being taken in the development of AMPERES (Autonomously Managed Power System Extendable Real-time Expert System), a knowledge-based expert system for fault monitoring and diagnosis of space power systems, is discussed. The system architecture, knowledge representation, and fault monitoring and diagnosis strategy are examined. A 'component-centered' approach developed in this project is described. Critical issues requiring further study are identified.

Fuzzy Concurrent Object Oriented Expert System for Fault Diagnosis in 8085 Microprocessor Based System Board

OpenAIRE

Mr.D. V. Kodavade; Dr. Mrs.S.D.Apte

2014-01-01

With the acceptance of artificial intelligence paradigm, a number of successful artificial intelligence systems were created. Fault diagnosis in microprocessor based boards needs lot of empirical knowledge and expertise and is a true artificial intelligence problem. Research on fault diagnosis in microprocessor based system boards using new fuzzy-object oriented approach is presented in this paper. There are many uncertain situations observed during fault diagnosis. These uncertain situations...

A Fault Diagnosis Methodology for Gear Pump Based on EEMD and Bayesian Network.

Science.gov (United States)

Liu, Zengkai; Liu, Yonghong; Shan, Hongkai; Cai, Baoping; Huang, Qing

2015-01-01

This paper proposes a fault diagnosis methodology for a gear pump based on the ensemble empirical mode decomposition (EEMD) method and the Bayesian network. Essentially, the presented scheme is a multi-source information fusion based methodology. Compared with the conventional fault diagnosis with only EEMD, the proposed method is able to take advantage of all useful information besides sensor signals. The presented diagnostic Bayesian network consists of a fault layer, a fault feature layer and a multi-source information layer. Vibration signals from sensor measurement are decomposed by the EEMD method and the energy of intrinsic mode functions (IMFs) are calculated as fault features. These features are added into the fault feature layer in the Bayesian network. The other sources of useful information are added to the information layer. The generalized three-layer Bayesian network can be developed by fully incorporating faults and fault symptoms as well as other useful information such as naked eye inspection and maintenance records. Therefore, diagnostic accuracy and capacity can be improved. The proposed methodology is applied to the fault diagnosis of a gear pump and the structure and parameters of the Bayesian network is established. Compared with artificial neural network and support vector machine classification algorithms, the proposed model has the best diagnostic performance when sensor data is used only. A case study has demonstrated that some information from human observation or system repair records is very helpful to the fault diagnosis. It is effective and efficient in diagnosing faults based on uncertain, incomplete information.

An examination of expert systems activities within the nuclear industry

International Nuclear Information System (INIS)

Bernard, J.A.; Washio, Takashi.

1988-01-01

This paper provides an overview of a detailed evaluation that the authors recently completed on expert systems applications within the nuclear industry. That evaluation examined the motivation for utilizing expert systems, identified the areas to which they were being applied, and provided an assessment of their utility. Listed here are some of the salient findings of that report. (1) Utilities are developing their own artificial intelligence tools rather than using commercial products. (2) Few expert systems are being developed for the express purpose of capturing human expertise. (3) A number of successful expert systems have been developed to assist in plant design, management, and maintenance scheduling. (4) Interactive diagnostic systems are being developed for the analysis of physical processes that vary slowly. (5) Real-time diagnostic expert systems are currently at the cutting edge of the technology. (6) Operator adviser and emergency response expert systems constitute ∼25% of the total. (7) Research on the use of expert systems for reactor control is quite active. (8) Too few quantitative evaluations of the benefits of expert systems to reactor operators have been performed. The operator's need is for timely, factual information on plant status. Hence, the true challenge to expert systems is real-time diagnostics

An expert system for sensor data validation and malfunction detection

International Nuclear Information System (INIS)

Hashemi, S.; Hajek, B.K.; Miller, D.W.

1987-01-01

Nuclear power plant operation and monitoring in general is a complex task which requires a large number of sensors, alarms and displays. At any instant in time, the operator is required to make a judgment about the state of the plant and to react accordingly. During abnormal situations, operators are further burdened with time constraints. The possibility of an undetected faulty instrumentation line, adds to the complexity of operators' reasoning tasks. Recent work at The Ohio State University Laboratory of Artificial Intelligence Research (LAIR) and the nuclear engineering program has concentrated on the problem of diagnostic expert systems performance and their applicability to the nuclear power plant domain. The authors have also been concerned about the diagnostic expert systems performance when using potentially invalid sensor data. Because of this research, they have developed an expert system that can perform diagnostic problem solving despite the existence of some conflicting data in the domain. This work has resulted in enhancement of a programming tool, CSRL, that allows domain experts to create a diagnostic system that will be to some degree, tolerant of bad data while performing diagnosis. This expert system is described here

The application of expert systems and neural networks to gas turbine prognostics and diagnostics

Energy Technology Data Exchange (ETDEWEB)

DePold, H.R.; Gass, F.D.

1999-10-01

Condition monitoring of engine gas generators plays an essential role in airline fleet management. Adaptive diagnostic systems are becoming available that interpret measured data, furnish diagnosis of problems, provide a prognosis of engine health for planning purposes, and rank engines for scheduled maintenance. More than four hundred operations worldwide currently use versions of the first or second generation diagnostic tools. Development of a third generation system is underway which will provide additional system enhancements and combine the functions of the existing tools. Proposed enhancements include the use of artificial intelligence to automate, improve the quality of the analysis, provide timely alerts, and the use of an Internet link for collaboration. One objective of these enhancements is to have the intelligent system do more of the analysis and decision making, while continuing to support the depth of analysis currently available at experienced operations. This paper presents recent developments in technology and strategies in engine condition monitoring including: (1) application of statistical analysis and artificial neural network filters to improve data quality, (2) neural networks for trend change detection, and classification to diagnose performance change, and (3) expert systems to diagnose, provide alerts and to rank maintenance action recommendations.

Expert system for nuclear power plant feedwater system diagnosis

International Nuclear Information System (INIS)

Meguro, R.; Kinoshita, Y.; Sato, T.; Yokota, Y.; Yokota, M.

1987-01-01

The Expert System for Nuclear Power Plant Feedwater System Diagnosis has been developed to assist maintenance engineers in nuclear power plants. This system adopts the latest process computer TOSBAC G8050 and the expert system developing tool TDES2, and has a large scale knowledge base which consists of the expert knowledge and experience of engineers in many fields. The man-machine system, which has been developed exclusively for diagnosis, improves the man-machine interface and realizes the graphic displays of diagnostic process and path, stores diagnostic results and searches past reference

Diagnosing battery behavior with an expert system in Prolog

International Nuclear Information System (INIS)

Kirkwood, N.; Weeks, D.J.

1986-01-01

Power for the Hubble Space Telescope comes from a system of 20 solar panel assemblies (SPAs) and six nickel-cadmium batteries. The HST battery system is simulated by the HST Electrical Power System (EPS) testbed at Marshall Space Flight Center. The Nickel Cadmium Battery Expert System (NICBES) is being used to diagnose faults of the testbed system, evaluate battery status and provide decision support for the engineer. Extensive telemetry of system operating conditions is relayed through a DEC LSI-11, and sent on to an IBM PC-AT. A BASIC program running on the PC monitors the flow of data, figures cell divergence and recharge ratio and stores these values, along with other selected data, for use by the expert system. The expert system is implemented in the logic programming language Prolog. It has three modes of operation: fault diagnosis, status and advice, and decision support. An alert or failure of the system will trigger a diagnosis by the system to assist the operator. The operator can also request battery status information as well as a number of plots and histograms of recent battery behavior. Trends in EOC and EOD voltage, recharge ratio and divergence are used by the expert system in its analysis of battery status. A future enhancement to the system includes the statistical prediction of battery life. Incorporating learning into the expert system is another possible enhancement; This is a difficult task, but one which could promise great rewards in improved battery performance

A Three-Dimensional Receiver Operator Characteristic Surface Diagnostic Metric

Science.gov (United States)

Simon, Donald L.

2011-01-01

Receiver Operator Characteristic (ROC) curves are commonly applied as metrics for quantifying the performance of binary fault detection systems. An ROC curve provides a visual representation of a detection system s True Positive Rate versus False Positive Rate sensitivity as the detection threshold is varied. The area under the curve provides a measure of fault detection performance independent of the applied detection threshold. While the standard ROC curve is well suited for quantifying binary fault detection performance, it is not suitable for quantifying the classification performance of multi-fault classification problems. Furthermore, it does not provide a measure of diagnostic latency. To address these shortcomings, a novel three-dimensional receiver operator characteristic (3D ROC) surface metric has been developed. This is done by generating and applying two separate curves: the standard ROC curve reflecting fault detection performance, and a second curve reflecting fault classification performance. A third dimension, diagnostic latency, is added giving rise to 3D ROC surfaces. Applying numerical integration techniques, the volumes under and between the surfaces are calculated to produce metrics of the diagnostic system s detection and classification performance. This paper will describe the 3D ROC surface metric in detail, and present an example of its application for quantifying the performance of aircraft engine gas path diagnostic methods. Metric limitations and potential enhancements are also discussed

An Effective Fault Feature Extraction Method for Gas Turbine Generator System Diagnosis

Directory of Open Access Journals (Sweden)

Jian-Hua Zhong

2016-01-01

Full Text Available Fault diagnosis is very important to maintain the operation of a gas turbine generator system (GTGS in power plants, where any abnormal situations will interrupt the electricity supply. The fault diagnosis of the GTGS faces the main challenge that the acquired data, vibration or sound signals, contain a great deal of redundant information which extends the fault identification time and degrades the diagnostic accuracy. To improve the diagnostic performance in the GTGS, an effective fault feature extraction framework is proposed to solve the problem of the signal disorder and redundant information in the acquired signal. The proposed framework combines feature extraction with a general machine learning method, support vector machine (SVM, to implement an intelligent fault diagnosis. The feature extraction method adopts wavelet packet transform and time-domain statistical features to extract the features of faults from the vibration signal. To further reduce the redundant information in extracted features, kernel principal component analysis is applied in this study. Experimental results indicate that the proposed feature extracted technique is an effective method to extract the useful features of faults, resulting in improvement of the performance of fault diagnosis for the GTGS.

Development of a diagnostic expert system for eddy current data analysis using applied artificial intelligence methods

International Nuclear Information System (INIS)

Upadhyaya, B.R.; Yan, W.; Henry, G.

1999-01-01

A diagnostic expert system that integrates database management methods, artificial neural networks, and decision-making using fuzzy logic has been developed for the automation of steam generator eddy current test (ECT) data analysis. The new system, known as EDDYAI, considers the following key issues: (1) digital eddy current test data calibration, compression, and representation; (2) development of robust neural networks with low probability of misclassification for flaw depth estimation; (3) flaw detection using fuzzy logic; (4) development of an expert system for database management, compilation of a trained neural network library, and a decision module; and (5) evaluation of the integrated approach using eddy current data. The implementation to field test data includes the selection of proper feature vectors for ECT data analysis, development of a methodology for large eddy current database management, artificial neural networks for flaw depth estimation, and a fuzzy logic decision algorithm for flaw detection. A large eddy current inspection database from the Electric Power Research Institute NDE Center is being utilized in this research towards the development of an expert system for steam generator tube diagnosis. The integration of ECT data pre-processing as part of the data management, fuzzy logic flaw detection technique, and tube defect parameter estimation using artificial neural networks are the fundamental contributions of this research. (orig.)

Development of a diagnostic expert system for eddy current data analysis using applied artificial intelligence methods

Energy Technology Data Exchange (ETDEWEB)

Upadhyaya, B.R.; Yan, W. [Tennessee Univ., Knoxville, TN (United States). Dept. of Nuclear Engineering; Behravesh, M.M. [Electric Power Research Institute, Palo Alto, CA (United States); Henry, G. [EPRI NDE Center, Charlotte, NC (United States)

1999-09-01

A diagnostic expert system that integrates database management methods, artificial neural networks, and decision-making using fuzzy logic has been developed for the automation of steam generator eddy current test (ECT) data analysis. The new system, known as EDDYAI, considers the following key issues: (1) digital eddy current test data calibration, compression, and representation; (2) development of robust neural networks with low probability of misclassification for flaw depth estimation; (3) flaw detection using fuzzy logic; (4) development of an expert system for database management, compilation of a trained neural network library, and a decision module; and (5) evaluation of the integrated approach using eddy current data. The implementation to field test data includes the selection of proper feature vectors for ECT data analysis, development of a methodology for large eddy current database management, artificial neural networks for flaw depth estimation, and a fuzzy logic decision algorithm for flaw detection. A large eddy current inspection database from the Electric Power Research Institute NDE Center is being utilized in this research towards the development of an expert system for steam generator tube diagnosis. The integration of ECT data pre-processing as part of the data management, fuzzy logic flaw detection technique, and tube defect parameter estimation using artificial neural networks are the fundamental contributions of this research. (orig.)

A Fault Alarm and Diagnosis Method Based on Sensitive Parameters and Support Vector Machine

Science.gov (United States)

Zhang, Jinjie; Yao, Ziyun; Lv, Zhiquan; Zhu, Qunxiong; Xu, Fengtian; Jiang, Zhinong

2015-08-01

Study on the extraction of fault feature and the diagnostic technique of reciprocating compressor is one of the hot research topics in the field of reciprocating machinery fault diagnosis at present. A large number of feature extraction and classification methods have been widely applied in the related research, but the practical fault alarm and the accuracy of diagnosis have not been effectively improved. Developing feature extraction and classification methods to meet the requirements of typical fault alarm and automatic diagnosis in practical engineering is urgent task. The typical mechanical faults of reciprocating compressor are presented in the paper, and the existing data of online monitoring system is used to extract fault feature parameters within 15 types in total; the inner sensitive connection between faults and the feature parameters has been made clear by using the distance evaluation technique, also sensitive characteristic parameters of different faults have been obtained. On this basis, a method based on fault feature parameters and support vector machine (SVM) is developed, which will be applied to practical fault diagnosis. A better ability of early fault warning has been proved by the experiment and the practical fault cases. Automatic classification by using the SVM to the data of fault alarm has obtained better diagnostic accuracy.

A Study on Satellite Diagnostic Expert Systems Using Case-Based Approach

Directory of Open Access Journals (Sweden)

Young-Tack Park

1997-06-01

Full Text Available Many research works are on going to monitor and diagnose diverse malfunctions of satellite systems as the complexity and number of satellites increase. Currently, many works on monitoring and diagnosis are carried out by human experts but there are needs to automate much of the routine works of them. Hence, it is necessary to study on using expert systems which can assist human experts routine work by doing automatically, thereby allow human experts devote their expertise more critical and important areas of monitoring and diagnosis. In this paper, we are employing artificial intelligence techniques to model human experts' knowledge and inference the constructed knowledge. Especially, case-based approaches are used to construct a knowledge base to model human expert capabilities which use previous typical exemplars. We have designed and implemented a prototype case-based system for diagnosing satellite malfunctions using cases. Our system remembers typical failure cases and diagnoses a current malfunction by indexing the case base. Diverse methods are used to build a more user friendly interface which allows human experts can build a knowledge base in as easy way.

Observer-based FDI for Gain Fault Detection in Ship Propulsion Benchmark

DEFF Research Database (Denmark)

Lootsma, T.F.; Izadi-Zamanabadi, Roozbeh; Nijmeijer, H.

2001-01-01

A geometric approach for input-affine nonlinear systems is briefly described and then applied to a ship propulsion benchmark. The obtained results are used to design a diagnostic nonlinear observer for successful FDI of the diesel engine gain fault......A geometric approach for input-affine nonlinear systems is briefly described and then applied to a ship propulsion benchmark. The obtained results are used to design a diagnostic nonlinear observer for successful FDI of the diesel engine gain fault...

Observer-based FDI for Gain Fault Detection in Ship Propulsion Benchmark

DEFF Research Database (Denmark)

Lootsma, T.F.; Izadi-Zamanabadi, Roozbeh; Nijmeijer, H.

2001-01-01

A geometric approach for input-affine nonlinear systems is briefly described and then applied to a ship propulsion benchmark. The obtained results are used to design a diagnostic nonlinear observer for successful FDI of the diesel engine gain fault.......A geometric approach for input-affine nonlinear systems is briefly described and then applied to a ship propulsion benchmark. The obtained results are used to design a diagnostic nonlinear observer for successful FDI of the diesel engine gain fault....

Studying the effects of operators' problem solving behaviour when using a diagnostic expert system developed for the nuclear industry

International Nuclear Information System (INIS)

Holmstroem, C.B.O.; Volden, F.S.; Endestad, T.

1992-01-01

This paper describes an experiment with the purpose to also illustrate and discuss some of the methodological problems when empirically studying problem solving. The experiment which was the second in a series, conducted at the OECD Halden Reactor Project, aimed to assess the effect on nuclear power plant operators diagnostic behaviour when using a rule-based diagnostic expert system. The rule-based expert system used in the experiment is called DISKET (Diagnosis System Using Knowledge Engineering Technique) and was originally developed by the Japan Atomic Energy Research Institute (JAERI). The experiment was performed in the Halden man-machine laboratory using a full scope pressurized water reactor simulator. Existing data collection methods and experimental design principles includes possibilities but also limitations. This is discussed and experiences are presented. Operator performance in terms of quality of diagnosis is improved by the use of DISKET. The use of the DISKET system also influences operators problem solving behaviour. The main difference between the two experimental conditions can be characterized as while the DISKET users during the diagnosis process are following a strategy which is direct and narrowed, the non-DISKET users are using a much broader and less focused search when trying to diagnose a disturbance. (author)

Advanced features of the fault tree solver FTREX

International Nuclear Information System (INIS)

Jung, Woo Sik; Han, Sang Hoon; Ha, Jae Joo

2005-01-01

This paper presents advanced features of a fault tree solver FTREX (Fault Tree Reliability Evaluation eXpert). Fault tree analysis is one of the most commonly used methods for the safety analysis of industrial systems especially for the probabilistic safety analysis (PSA) of nuclear power plants. Fault trees are solved by the classical Boolean algebra, conventional Binary Decision Diagram (BDD) algorithm, coherent BDD algorithm, and Bayesian networks. FTREX could optionally solve fault trees by the conventional BDD algorithm or the coherent BDD algorithm and could convert the fault trees into the form of the Bayesian networks. The algorithm based on the classical Boolean algebra solves a fault tree and generates MCSs. The conventional BDD algorithm generates a BDD structure of the top event and calculates the exact top event probability. The BDD structure is a factorized form of the prime implicants. The MCSs of the top event could be extracted by reducing the prime implicants in the BDD structure. The coherent BDD algorithm is developed to overcome the shortcomings of the conventional BDD algorithm such as the huge memory requirements and a long run time

Fault Diagnosis of Power Systems Using Intelligent Systems

Science.gov (United States)

Momoh, James A.; Oliver, Walter E. , Jr.

1996-01-01

The power system operator's need for a reliable power delivery system calls for a real-time or near-real-time Al-based fault diagnosis tool. Such a tool will allow NASA ground controllers to re-establish a normal or near-normal degraded operating state of the EPS (a DC power system) for Space Station Alpha by isolating the faulted branches and loads of the system. And after isolation, re-energizing those branches and loads that have been found not to have any faults in them. A proposed solution involves using the Fault Diagnosis Intelligent System (FDIS) to perform near-real time fault diagnosis of Alpha's EPS by downloading power transient telemetry at fault-time from onboard data loggers. The FDIS uses an ANN clustering algorithm augmented with a wavelet transform feature extractor. This combination enables this system to perform pattern recognition of the power transient signatures to diagnose the fault type and its location down to the orbital replaceable unit. FDIS has been tested using a simulation of the LeRC Testbed Space Station Freedom configuration including the topology from the DDCU's to the electrical loads attached to the TPDU's. FDIS will work in conjunction with the Power Management Load Scheduler to determine what the state of the system was at the time of the fault condition. This information is used to activate the appropriate diagnostic section, and to refine if necessary the solution obtained. In the latter case, if the FDIS reports back that it is equally likely that the faulty device as 'start tracker #1' and 'time generation unit,' then based on a priori knowledge of the system's state, the refined solution would be 'star tracker #1' located in cabinet ITAS2. It is concluded from the present studies that artificial intelligence diagnostic abilities are improved with the addition of the wavelet transform, and that when such a system such as FDIS is coupled to the Power Management Load Scheduler, a faulty device can be located and isolated

Knowledge-based fault diagnosis system for refuse collection vehicle

International Nuclear Information System (INIS)

Tan, CheeFai; Juffrizal, K.; Khalil, S. N.; Nidzamuddin, M. Y.

2015-01-01

The refuse collection vehicle is manufactured by local vehicle body manufacturer. Currently; the company supplied six model of the waste compactor truck to the local authority as well as waste management company. The company is facing difficulty to acquire the knowledge from the expert when the expert is absence. To solve the problem, the knowledge from the expert can be stored in the expert system. The expert system is able to provide necessary support to the company when the expert is not available. The implementation of the process and tool is able to be standardize and more accurate. The knowledge that input to the expert system is based on design guidelines and experience from the expert. This project highlighted another application on knowledge-based system (KBS) approached in trouble shooting of the refuse collection vehicle production process. The main aim of the research is to develop a novel expert fault diagnosis system framework for the refuse collection vehicle

Knowledge-based fault diagnosis system for refuse collection vehicle

Energy Technology Data Exchange (ETDEWEB)

Tan, CheeFai; Juffrizal, K.; Khalil, S. N.; Nidzamuddin, M. Y. [Centre of Advanced Research on Energy, Universiti Teknikal Malaysia Melaka, Hang Tuah Jaya, Durian Tunggal, Melaka (Malaysia)

2015-05-15

The refuse collection vehicle is manufactured by local vehicle body manufacturer. Currently; the company supplied six model of the waste compactor truck to the local authority as well as waste management company. The company is facing difficulty to acquire the knowledge from the expert when the expert is absence. To solve the problem, the knowledge from the expert can be stored in the expert system. The expert system is able to provide necessary support to the company when the expert is not available. The implementation of the process and tool is able to be standardize and more accurate. The knowledge that input to the expert system is based on design guidelines and experience from the expert. This project highlighted another application on knowledge-based system (KBS) approached in trouble shooting of the refuse collection vehicle production process. The main aim of the research is to develop a novel expert fault diagnosis system framework for the refuse collection vehicle.

Optimization of a dynamic uncertain causality graph for fault diagnosis in nuclear power plant

Institute of Scientific and Technical Information of China (English)

Yue Zhao; Francesco Di Maio; Enrico Zio; Qin Zhang; Chun-Ling Dong; Jin-Ying Zhang

2017-01-01

Fault diagnostics is important for safe operation of nuclear power plants (NPPs).In recent years,data-driven approaches have been proposed and implemented to tackle the problem,e.g.,neural networks,fuzzy and neurofuzzy approaches,support vector machine,K-nearest neighbor classifiers and inference methodologies.Among these methods,dynamic uncertain causality graph (DUCG)has been proved effective in many practical cases.However,the causal graph construction behind the DUCG is complicate and,in many cases,results redundant on the symptoms needed to correctly classify the fault.In this paper,we propose a method to simplify causal graph construction in an automatic way.The method consists in transforming the expert knowledge-based DCUG into a fuzzy decision tree (FDT) by extracting from the DUCG a fuzzy rule base that resumes the used symptoms at the basis of the FDT.Genetic algorithm (GA) is,then,used for the optimization of the FDT,by performing a wrapper search around the FDT:the set of symptoms selected during the iterative search are taken as the best set of symptoms for the diagnosis of the faults that can occur in the system.The effectiveness of the approach is shown with respect to a DUCG model initially built to diagnose 23 faults originally using 262 symptoms of Unit-1 in the Ningde NPP of the China Guangdong Nuclear Power Corporation.The results show that the FDT,with GA-optimized symptoms and diagnosis strategy,can drive the construction of DUCG and lower the computational burden without loss of accuracy in diagnosis.

Optimization of a dynamic uncertain causality graph for fault diagnosis in nuclear power plant

Institute of Scientific and Technical Information of China (English)

Yue Zhao; Francesco Di Maio; Enrico Zio; Qin Zhang; Chun-Ling Dong; Jin-Ying Zhang

2017-01-01

Fault diagnostics is important for safe operation of nuclear power plants (NPPs).In recent years,data-driven approaches have been proposed and implemented to tackle the problem,e.g.,neural networks,fuzzy and neurofuzzy approaches,support vector machine,K-nearest neighbor classifiers and inference methodologies.Among these methods,dynamic uncertain causality graph (DUCG) has been proved effective in many practical cases.However,the causal graph construction behind the DUCG is complicate and,in many cases,results redundant on the symptoms needed to correctly classify the fault.In this paper,we propose a method to simplify causal graph construction in an automatic way.The method consists in transforming the expert knowledge-based DCUG into a fuzzy decision tree (FDT) by extracting from the DUCG a fuzzy rule base that resumes the used symptoms at the basis of the FDT.Genetic algorithm (GA) is,then,used for the optimization of the FDT,by performing a wrapper search around the FDT:the set of symptoms selected during the iterative search are taken as the best set of symptoms for the diagnosis of the faults that can occur in the system.The effectiveness of the approach is shown with respect to a DUCG model initially built to diagnose 23 faults originally using 262 symptoms of Unit-1 in the Ningde NPP of the China Guangdong Nuclear Power Corporation.The results show that the FDT,with GA-optimized symptoms and diagnosis strategy,can drive the construction of DUCG and lower the computational burden without loss of accuracy in diagnosis.

Hypothetical Scenario Generator for Fault-Tolerant Diagnosis

Science.gov (United States)

James, Mark

2007-01-01

The Hypothetical Scenario Generator for Fault-tolerant Diagnostics (HSG) is an algorithm being developed in conjunction with other components of artificial- intelligence systems for automated diagnosis and prognosis of faults in spacecraft, aircraft, and other complex engineering systems. By incorporating prognostic capabilities along with advanced diagnostic capabilities, these developments hold promise to increase the safety and affordability of the affected engineering systems by making it possible to obtain timely and accurate information on the statuses of the systems and predicting impending failures well in advance. The HSG is a specific instance of a hypothetical- scenario generator that implements an innovative approach for performing diagnostic reasoning when data are missing. The special purpose served by the HSG is to (1) look for all possible ways in which the present state of the engineering system can be mapped with respect to a given model and (2) generate a prioritized set of future possible states and the scenarios of which they are parts.

Using Expert Systems in Evaluation of the State of High Voltage Machine Insulation Systems

Directory of Open Access Journals (Sweden)

K. Záliš

2000-01-01

Full Text Available Expert systems are used for evaluating the actual state and future behavior of insulating systems of high voltage electrical machines and equipment. Several rule-based expert systems have been developed in cooperation with top diagnostic workplaces in the Czech Republic for this purpose. The IZOLEX expert system evaluates diagnostic measurement data from commonly used offline diagnostic methods for the diagnostic of high voltage insulation of rotating machines, non-rotating machines and insulating oils. The CVEX expert system evaluates the discharge activity on high voltage electrical machines and equipment by means of an off-line measurement. The CVEXON expert system is for evaluating the discharge activity by on-line measurement, and the ALTONEX expert system is the expert system for on-line monitoring of rotating machines. These developed expert systems are also used for educating students (in bachelor, master and post-graduate studies and in courses which are organized for practicing engineers and technicians and for specialists in the electrical power engineering branch. A complex project has recently been set up to evaluate the measurement of partial discharges. Two parallel expert systems for evaluating partial dischatge activity on high voltage electrical machines will work at the same time in this complex evaluating system.

Expert system for failures detection and non-monotonic reasoning

International Nuclear Information System (INIS)

Assis, Abilio de; Schirru, Roberto

1997-01-01

This paper presents the development of a shell denominated TIGER that has the purpose to serve as environment to the development of expert systems in diagnosis of faults in industrial complex plants. A model of knowledge representation and an inference engine based on non monotonic reasoning has been developed in order to provide flexibility in the representation of complex plants as well as performance to satisfy restrictions of real time. The TIGER is able to provide both the occurred fault and a hierarchical view of the several reasons that caused the fault to happen. As a validation of the developed shell a monitoring system of the critical safety functions of Angra-1 has been developed. 7 refs., 7 figs., 2 tabs

Vibration-based Fault Diagnostic of a Spur Gearbox

Directory of Open Access Journals (Sweden)

Hartono Dennis

2016-01-01

Full Text Available This paper presents comparative studies of Fast Fourier Transform (FFT, Short Time Fourier Transform (STFT and Continuous Wavelet Transform (CWT as several advanced time-frequency analysis methods for diagnosing an early stage of spur gear tooth failure. An incipient fault of a chipped tooth was investigated in this work using vibration measurements from a spur gearbox test rig. Time Synchronous Averaging was implemented for the analysis to enhance the clarity of fault feature from the gear of interest. Based on the experimental results and analysis, it was shown that FFT method could identify the location of the faulty gear with sufficient accuracy. On the other hand, Short Time Fourier Transform method could not provide the angular location information of the faulty gear. It was found that the Continuous Wavelet Transform method offered the best representation of angle-frequency representation. It was not only able to distinguish the difference between the normal and faulty gearboxes from the joint angle-frequency results but could also provide an accurate angular location of the faulty gear tooth in the gearbox.

Fault capability problem about seams in Shika NPP

International Nuclear Information System (INIS)

Katagawa, H.

2016-01-01

Against the opinion of the Nuclear Regulation Authority that insists that the on-site seams of Shika Nuclear Power Plant is fault, Hokuriku Electric Power Company shows the view that they are not the fault. Additional survey result was submitted by Hokuriku Electric Power Company, and the evaluation draft for it by the expert meeting of Nuclear Regulation Authority, as well as the peer review were published. The evaluation draft mentioned that the seams cannot be denied for the possibility to become active, and the peer review issued many evaluations different from the evaluation draft. This paper describes the contents of the evaluation draft and peer review summarized by Hokuriku Electric Power Company. Against the three major points of the evaluation draft, the peer review pointed out the defect of fact recognition in every issue of discussion that lacks in examination on the points that should have been checked, and questioned the eligibility of the contents of evaluation. Many of the suggestions and comments of the peer review were the contents that approved the on-site survey and the report at the expert meeting made by Hokuriku Electric Power Company. In addition, this paper summarizes the focal points of the evaluation draft, and points out the question for fault assumption and discrepancies in the case of existence of fault. Hokuriku Electric Power Company has published a rebuttal to the evaluation draft as the written opinion. (A.O.)

Estimation of Faults in DC Electrical Power System

Science.gov (United States)

Gorinevsky, Dimitry; Boyd, Stephen; Poll, Scott

2009-01-01

This paper demonstrates a novel optimization-based approach to estimating fault states in a DC power system. Potential faults changing the circuit topology are included along with faulty measurements. Our approach can be considered as a relaxation of the mixed estimation problem. We develop a linear model of the circuit and pose a convex problem for estimating the faults and other hidden states. A sparse fault vector solution is computed by using 11 regularization. The solution is computed reliably and efficiently, and gives accurate diagnostics on the faults. We demonstrate a real-time implementation of the approach for an instrumented electrical power system testbed, the ADAPT testbed at NASA ARC. The estimates are computed in milliseconds on a PC. The approach performs well despite unmodeled transients and other modeling uncertainties present in the system.

Various Indices for Diagnosis of Air-gap Eccentricity Fault in Induction Motor-A Review

Science.gov (United States)

Nikhil; Mathew, Lini, Dr.; Sharma, Amandeep

2018-03-01

From the past few years, research has gained an ardent pace in the field of fault detection and diagnosis in induction motors. In the current scenario, software is being introduced with diagnostic features to improve stability and reliability in fault diagnostic techniques. Human involvement in decision making for fault detection is slowly being replaced by Artificial Intelligence techniques. In this paper, a brief introduction of eccentricity fault is presented along with their causes and effects on the health of induction motors. Various indices used to detect eccentricity are being introduced along with their boundary conditions and their future scope of research. At last, merits and demerits of all indices are discussed and a comparison is made between them.

Earthquakes and Tectonics Expert Judgment Elicitation Project

International Nuclear Information System (INIS)

Coppersmith, K.J.; Perman, R.C.; Youngs, R.R.

1993-02-01

This report summarizes the results of the Earthquakes and Tectonics Expert Judgement Excitation Project sponsored by the Electric Power Research Institute (EPRI). The objectives of this study were two-fold: (1) to demonstrate methods for the excitation of expert judgement, and (2) to quantify the uncertainties associated with earthquake and tectonics issues for use in the EPRI-HLW performance assessment. Specifically, the technical issue considered is the probability of differential fault displacement through the proposed repository at Yucca Mountain, Nevada. For this study, a strategy for quantifying uncertainties was developed that relies on the judgements of multiple experts. A panel of seven geologists and seismologists was assembled to quantify the uncertainties associated with earthquake and tectonics issues for the performance assessment model. A series of technical workshops focusing on these issues were conducted. Finally, each expert was individually interviewed in order to elicit his judgement regarding the technical issues and to provide the technical basis for his assessment. This report summarizes the methodologies used to elicit the judgements of the earthquakes and tectonics experts (termed ''specialists''), and summarizes the technical assessments made by the expert panel

Industrial disasters - the expert systems solution

International Nuclear Information System (INIS)

Sachs, P.

1986-01-01

Six mistakes by the operators led to the accident at the Cherobyl nuclear reactor. These have been studied. It is suggested that an expert systems approach could prevent similar accidents. The expert system is a new approach to software programming where programs are required to perform intelligent analyses of complex situations. It separates the knowledge of a problem from the procedural code that performs the decision. An expert system will evaluate data and indicate a priority on alarms in real time. Now software systems can detect the cause of a problem in a process plant and present their findings to the operators in the control room. This should enable operators to make the correct decisions as they will know which underlying process faults are causing the alarms to operate. The Chernobyl post-mortem meeting made 13 proposals for improving safety. Two in particular are noted as relevant to expert advice systems; international collaboration on man-reactor relationships and a conference to explore the balance of automation and human action to minimise operating errors. (U.K.)

Classification of neuropathic pain in cancer patients: A Delphi expert survey report and EAPC/IASP proposal of an algorithm for diagnostic criteria.

Science.gov (United States)

Brunelli, Cinzia; Bennett, Michael I; Kaasa, Stein; Fainsinger, Robin; Sjøgren, Per; Mercadante, Sebastiano; Løhre, Erik T; Caraceni, Augusto

2014-12-01

Neuropathic pain (NP) in cancer patients lacks standards for diagnosis. This study is aimed at reaching consensus on the application of the International Association for the Study of Pain (IASP) special interest group for neuropathic pain (NeuPSIG) criteria to the diagnosis of NP in cancer patients and on the relevance of patient-reported outcome (PRO) descriptors for the screening of NP in this population. An international group of 42 experts was invited to participate in a consensus process through a modified 2-round Internet-based Delphi survey. Relevant topics investigated were: peculiarities of NP in patients with cancer, IASP NeuPSIG diagnostic criteria adaptation and assessment, and standardized PRO assessment for NP screening. Median consensus scores (MED) and interquartile ranges (IQR) were calculated to measure expert consensus after both rounds. Twenty-nine experts answered, and good agreement was found on the statement "the pathophysiology of NP due to cancer can be different from non-cancer NP" (MED=9, IQR=2). Satisfactory consensus was reached for the first 3 NeuPSIG criteria (pain distribution, history, and sensory findings; MEDs⩾8, IQRs⩽3), but not for the fourth one (diagnostic test/imaging; MED=6, IQR=3). Agreement was also reached on clinical examination by soft brush or pin stimulation (MEDs⩾7 and IQRs⩽3) and on the use of PRO descriptors for NP screening (MED=8, IQR=3). Based on the study results, a clinical algorithm for NP diagnostic criteria in cancer patients with pain was proposed. Clinical research on PRO in the screening phase and on the application of the algorithm will be needed to examine their effectiveness in classifying NP in cancer patients. Copyright © 2014 International Association for the Study of Pain. Published by Elsevier B.V. All rights reserved.

ECG Rhythm Analysis with Expert and Learner-Generated Schemas in Novice Learners

Science.gov (United States)

Blissett, Sarah; Cavalcanti, Rodrigo; Sibbald, Matthew

2015-01-01

Although instruction using expert-generated schemas is associated with higher diagnostic performance, implementation is resource intensive. Learner-generated schemas are an alternative, but may be limited by increases in cognitive load. We compared expert- and learner-generated schemas for learning ECG rhythm interpretation on diagnostic accuracy,…

Case-based reasoning combined with statistics for diagnostics and prognosis

International Nuclear Information System (INIS)

Olsson, T; Funk, P

2012-01-01

Many approaches used for diagnostics today are based on a precise model. This excludes diagnostics of many complex types of machinery that cannot be modelled and simulated easily or without great effort. Our aim is to show that by including human experience it is possible to diagnose complex machinery when there is no or limited models or simulations available. This also enables diagnostics in a dynamic application where conditions change and new cases are often added. In fact every new solved case increases the diagnostic power of the system. We present a number of successful projects where we have used feature extraction together with case-based reasoning to diagnose faults in industrial robots, welding, cutting machinery and we also present our latest project for diagnosing transmissions by combining Case-Based Reasoning (CBR) with statistics. We view the fault diagnosis process as three consecutive steps. In the first step, sensor fault signals from machines and/or input from human operators are collected. Then, the second step consists of extracting relevant fault features. In the final diagnosis/prognosis step, status and faults are identified and classified. We view prognosis as a special case of diagnosis where the prognosis module predicts a stream of future features.

Hybrid Model-Based and Data-Driven Fault Detection and Diagnostics for Commercial Buildings: Preprint

Energy Technology Data Exchange (ETDEWEB)

Frank, Stephen; Heaney, Michael; Jin, Xin; Robertson, Joseph; Cheung, Howard; Elmore, Ryan; Henze, Gregor

2016-08-01

Commercial buildings often experience faults that produce undesirable behavior in building systems. Building faults waste energy, decrease occupants' comfort, and increase operating costs. Automated fault detection and diagnosis (FDD) tools for buildings help building owners discover and identify the root causes of faults in building systems, equipment, and controls. Proper implementation of FDD has the potential to simultaneously improve comfort, reduce energy use, and narrow the gap between actual and optimal building performance. However, conventional rule-based FDD requires expensive instrumentation and valuable engineering labor, which limit deployment opportunities. This paper presents a hybrid, automated FDD approach that combines building energy models and statistical learning tools to detect and diagnose faults noninvasively, using minimal sensors, with little customization. We compare and contrast the performance of several hybrid FDD algorithms for a small security building. Our results indicate that the algorithms can detect and diagnose several common faults, but more work is required to reduce false positive rates and improve diagnosis accuracy.

Cafts: computer aided fault tree analysis

International Nuclear Information System (INIS)

Poucet, A.

1985-01-01

The fault tree technique has become a standard tool for the analysis of safety and reliability of complex system. In spite of the costs, which may be high for a complete and detailed analysis of a complex plant, the fault tree technique is popular and its benefits are fully recognized. Due to this applications of these codes have mostly been restricted to simple academic examples and rarely concern complex, real world systems. In this paper an interactive approach to fault tree construction is presented. The aim is not to replace the analyst, but to offer him an intelligent tool which can assist him in modeling complex systems. Using the CAFTS-method, the analyst interactively constructs a fault tree in two phases: (1) In a first phase he generates an overall failure logic structure of the system; the macrofault tree. In this phase, CAFTS features an expert system approach to assist the analyst. It makes use of a knowledge base containing generic rules on the behavior of subsystems and components; (2) In a second phase the macrofault tree is further refined and transformed in a fully detailed and quantified fault tree. In this phase a library of plant-specific component failure models is used

System diagnostic builder: a rule-generation tool for expert systems that do intelligent data evaluation

Science.gov (United States)

Nieten, Joseph L.; Burke, Roger

1993-03-01

The system diagnostic builder (SDB) is an automated knowledge acquisition tool using state- of-the-art artificial intelligence (AI) technologies. The SDB uses an inductive machine learning technique to generate rules from data sets that are classified by a subject matter expert (SME). Thus, data is captured from the subject system, classified by an expert, and used to drive the rule generation process. These rule-bases are used to represent the observable behavior of the subject system, and to represent knowledge about this system. The rule-bases can be used in any knowledge based system which monitors or controls a physical system or simulation. The SDB has demonstrated the utility of using inductive machine learning technology to generate reliable knowledge bases. In fact, we have discovered that the knowledge captured by the SDB can be used in any number of applications. For example, the knowledge bases captured from the SMS can be used as black box simulations by intelligent computer aided training devices. We can also use the SDB to construct knowledge bases for the process control industry, such as chemical production, or oil and gas production. These knowledge bases can be used in automated advisory systems to ensure safety, productivity, and consistency.

Fault Diagnosis of Nonlinear Systems Using Structured Augmented State Models

Institute of Scientific and Technical Information of China (English)

Jochen Aβfalg; Frank Allg(o)wer

2007-01-01

This paper presents an internal model approach for modeling and diagnostic functionality design for nonlinear systems operating subject to single- and multiple-faults. We therefore provide the framework of structured augmented state models. Fault characteristics are considered to be generated by dynamical exosystems that are switched via equality constraints to overcome the augmented state observability limiting the number of diagnosable faults. Based on the proposed model, the fault diagnosis problem is specified as an optimal hybrid augmented state estimation problem. Sub-optimal solutions are motivated and exemplified for the fault diagnosis of the well-known three-tank benchmark. As the considered class of fault diagnosis problems is large, the suggested approach is not only of theoretical interest but also of high practical relevance.

Fault diagnosis in spur gears based on genetic algorithm and random forest

Science.gov (United States)

Cerrada, Mariela; Zurita, Grover; Cabrera, Diego; Sánchez, René-Vinicio; Artés, Mariano; Li, Chuan

2016-03-01

There are growing demands for condition-based monitoring of gearboxes, and therefore new methods to improve the reliability, effectiveness, accuracy of the gear fault detection ought to be evaluated. Feature selection is still an important aspect in machine learning-based diagnosis in order to reach good performance of the diagnostic models. On the other hand, random forest classifiers are suitable models in industrial environments where large data-samples are not usually available for training such diagnostic models. The main aim of this research is to build up a robust system for the multi-class fault diagnosis in spur gears, by selecting the best set of condition parameters on time, frequency and time-frequency domains, which are extracted from vibration signals. The diagnostic system is performed by using genetic algorithms and a classifier based on random forest, in a supervised environment. The original set of condition parameters is reduced around 66% regarding the initial size by using genetic algorithms, and still get an acceptable classification precision over 97%. The approach is tested on real vibration signals by considering several fault classes, one of them being an incipient fault, under different running conditions of load and velocity.

Evaluation of fault coverage for digitalized system in nuclear power plants using VHDL

International Nuclear Information System (INIS)

Kim, Suk Joon; Lee, Jun Suk; Seong, Poong Hyun

2003-01-01

Fault coverage of digital systems is found to be one of the most important factors in the safety analysis of nuclear power plants. Several axiomatic models for the estimation of fault coverage of digital systems have been proposed, but to apply those axiomatic models to real digital systems, parameters that the axiomatic models require should be approximated using analytic methods, empirical methods or expert opinions. In this paper, we apply the fault injection method to VHDL computer simulation model of a real digital system which provides the protection function to nuclear power plants, for the approximation of fault detection coverage of the digital system. As a result, the fault detection coverage of the digital system could be obtained

Failure characteristics analysis and fault diagnosis for liquid rocket engines

CERN Document Server

Zhang, Wei

2016-01-01

This book concentrates on the subject of health monitoring technology of Liquid Rocket Engine (LRE), including its failure analysis, fault diagnosis and fault prediction. Since no similar issue has been published, the failure pattern and mechanism analysis of the LRE from the system stage are of particular interest to the readers. Furthermore, application cases used to validate the efficacy of the fault diagnosis and prediction methods of the LRE are different from the others. The readers can learn the system stage modeling, analyzing and testing methods of the LRE system as well as corresponding fault diagnosis and prediction methods. This book will benefit researchers and students who are pursuing aerospace technology, fault detection, diagnostics and corresponding applications.

The opinion of experts in the assessment of reliability in nuclear power plant operation

International Nuclear Information System (INIS)

Akersten, P.A.; Wirstad, J.

1983-06-01

An inventory of methods used for quantifying of the opinion of experts for use in fault tree evaluations is presented. A number of different methods are evaluated and future research is recommended for three, namely 1. Saatys Analytical Hierarchy Process. 2. Embreys SLIM-method with variations. 3. Methods for feed-back from the expert group during evaluation.(authors)

Qualitative Event-Based Diagnosis: Case Study on the Second International Diagnostic Competition

Science.gov (United States)

Daigle, Matthew; Roychoudhury, Indranil

2010-01-01

We describe a diagnosis algorithm entered into the Second International Diagnostic Competition. We focus on the first diagnostic problem of the industrial track of the competition in which a diagnosis algorithm must detect, isolate, and identify faults in an electrical power distribution testbed and provide corresponding recovery recommendations. The diagnosis algorithm embodies a model-based approach, centered around qualitative event-based fault isolation. Faults produce deviations in measured values from model-predicted values. The sequence of these deviations is matched to those predicted by the model in order to isolate faults. We augment this approach with model-based fault identification, which determines fault parameters and helps to further isolate faults. We describe the diagnosis approach, provide diagnosis results from running the algorithm on provided example scenarios, and discuss the issues faced, and lessons learned, from implementing the approach

Realization of multi-parameter and multi-state in fault tree computer-aided building software

International Nuclear Information System (INIS)

Guo Xiaoli; Tong Jiejuan; Xue Dazhi

2004-01-01

More than one parameter and more than one failed state of a parameter are often involved in building fault tree, so it is necessary for fault tree computer-aided building software to deal with multi-parameter and multi-state. Fault Tree Expert System (FTES) has the target of aiding the FT-building work of hydraulic systems. This paper expatiates on how to realize multi-parameter and multi-state in FTES with focus on Knowledge Base and Illation Engine. (author)

Comparative Study of Fault Diagnostic Methods in Voltage Source Inverter Fed Three Phase Induction Motor Drive

Science.gov (United States)

Dhumale, R. B.; Lokhande, S. D.

2017-05-01

Three phase Pulse Width Modulation inverter plays vital role in industrial applications. The performance of inverter demeans as several types of faults take place in it. The widely used switching devices in power electronics are Insulated Gate Bipolar Transistors (IGBTs) and Metal Oxide Field Effect Transistors (MOSFET). The IGBTs faults are broadly classified as base or collector open circuit fault, misfiring fault and short circuit fault. To develop consistency and performance of inverter, knowledge of fault mode is extremely important. This paper presents the comparative study of IGBTs fault diagnosis. Experimental set up is implemented for data acquisition under various faulty and healthy conditions. Recent methods are executed using MATLAB-Simulink and compared using key parameters like average accuracy, fault detection time, implementation efforts, threshold dependency, and detection parameter, resistivity against noise and load dependency.

Classification of data patterns using an autoassociative neural network topology

Science.gov (United States)

Dietz, W. E.; Kiech, E. L.; Ali, M.

1989-01-01

A diagnostic expert system based on neural networks is developed and applied to the real-time diagnosis of jet and rocket engines. The expert system methodologies are based on the analysis of patterns of behavior of physical mechanisms. In this approach, fault diagnosis is conceptualized as the mapping or association of patterns of sensor data to patterns representing fault conditions. The approach addresses deficiencies inherent in many feedforward neural network models and greatly reduces the number of networks necessary to identify the existence of a fault condition and estimate the duration and severity of the identified fault. The network topology used in the present implementation of the diagnostic system is described, as well as the training regimen used and the response of the system to inputs representing both previously observed and unknown fault scenarios. Noise effects on the integrity of the diagnosis are also evaluated.

Expert system strategies for the diagnostic in a particle physics experiment

International Nuclear Information System (INIS)

D'Antone, I.; Mandrioli, G.; Matteuzzi, P.

1990-01-01

The maintenance of a particle detector functionality requires the knowledge of more experts: physicists and engineers for the detector and the electronic system. The integration of different knowledges and experiences can be easily done using an Expert System. A real-time Expert System allows us to diagnose the detector and data acquisition system anomalies; it makes an on-line diagnosis and, if an abnormal condition is identified, takes the appropriate action to reduce the unavailability of the apparatus. A method based on structural and behavioral reasoning is considered. Reasoning on the structure and on the functionality of the apparatus all the possible failures that can explain the sensor readings are searched. The behaviour of the apparatus components are described in qualitative terms to write the rules for the expert system

Bevel Gearbox Fault Diagnosis using Vibration Measurements

Directory of Open Access Journals (Sweden)

Hartono Dennis

2016-01-01

Full Text Available The use of vibration measurementanalysis has been proven to be effective for gearbox fault diagnosis. However, the complexity of vibration signals observed from a gearbox makes it difficult to accurately detectfaults in the gearbox. This work is based on a comparative studyof several time-frequency signal processing methods that can be used to extract information from transient vibration signals containing useful diagnostic information. Experiments were performed on a bevel gearbox test rig using vibration measurements obtained from accelerometers. Initially, thediscrete wavelet transform was implementedfor vibration signal analysis to extract the frequency content of signal from the relevant frequency region. Several time-frequency signal processing methods werethen incorporated to extract the fault features of vibration signals and their diagnostic performances were compared. It was shown thatthe Short Time Fourier Transform (STFT could not offer a good time resolution to detect the periodicity of the faulty gear tooth due the difficulty in choosing an appropriate window length to capture the impulse signal. The Continuous Wavelet Transform (CWT, on the other hand, was suitable to detection of vibration transients generated by localized fault from a gearbox due to its multi-scale property. However, both methods still require a thorough visual inspection. In contrast, it was shown from the experiments that the diagnostic method using the Cepstrumanalysis could provide a direct indication of the faulty tooth without the need of a thorough visual inspection as required by CWT and STFT.

DIAGNOSTICS OF META-INSTABLE STATE OF SEISMICALLY ACTIVE FAULT

Directory of Open Access Journals (Sweden)

S. A. Bornyakov

2017-01-01

Full Text Available Based on the results of a laboratory simulation of the seismic fault reactivation by “stick-slip” process, it was shown that the system of two blocks just before an impulse offset goes through the meta-instable dynamic state, with early and late stages of meta-instability [Ma et al., 2012]. In the first stage the offset begins in slow stationary mode with slow stresses relaxation on contact between blocks. In the second stage of the “accelerated synergies” strain rate increases and, subsequently, the deformation process through a process of self-organization came to dynamic impulse offset. The experimental results were used for interpretation of the results of spectral analysis of the deformation monitoring data. The data were held within the southern part ofLakeBaikal, where Kultuk earthquake (27.08.2008, Ms=6.1. took place. Its epicenter was located in the South end zone of the main Sayan fault. Monitoring of deformations of rocks was carried out from April to November2008 in tunnel, located at30 km from the epicenter of the earthquake. The time series data was divided into month periods and then the periods were processed by the method of spectral analysis. The results showed that before the earthquake has ordered view spectrogram, whereas in other time intervals, both before and after the earthquake such orderliness in spectrograms is missing. An ordered view spectrograms for deformation monitoring data can be interpreted as a consequence of the self-organiza­tion of deformation process in the transition of seismically active fault into meta-unstable before the Kultuk earthquake.

Considerations in development of expert systems for real-time space applications

Science.gov (United States)

Murugesan, S.

1988-01-01

Over the years, demand on space systems has increased tremendously and this trend will continue for the near future. Enhanced capabilities of space systems, however, can only be met with increased complexity and sophistication of onboard and ground systems. Artificial Intelligence and expert system techniques have great potential in space applications. Expert systems could facilitate autonomous decision making, improve in-orbit fault diagnosis and repair, enhance performance and reduce reliance on ground support. However, real-time expert systems, unlike conventional off-line consultative systems, have to satisfy certain special stringent requirements before they could be used for onboard space applications. Challenging and interesting new environments are faced while developing expert system space applications. This paper discusses the special characteristics, requirements and typical life cycle issues for onboard expert systems. Further, it also describes considerations in design, development, and implementation which are particularly important to real-time expert systems for space applications.

A Knowledge-Based Expert System Using MFM Model for Operator Supporting

International Nuclear Information System (INIS)

Mo, Kun; Seong, Poong Hyun

2005-01-01

In this paper, a knowledge-based expert system using MFM (Multi-level Flow Modeling) is proposed for enhancing the operators' ability to cope with various situations in nuclear power plant. There are many complicated situations, in which regular and suitable operations should be done by operators accordingly. In order to help the operator to assess the situations promptly and accurately, and to regulate their operations according to these situations. it is necessary to develop an expert systems to help the operator for the fault diagnosis, alarm analysis, and operation results estimation for each operation. Many kinds of operator supporting systems focusing on different functions have been developed. Most of them used various methodologies for single diagnosis function or operation permission function. The proposed system integrated functions of fault diagnosis, alarm analysis and operation results estimation by the MFM basic algorithm for the operator supporting

AFTC Code for Automatic Fault Tree Construction: Users Manual

International Nuclear Information System (INIS)

Gopika Vinod; Saraf, R.K.; Babar, A.K.

1999-04-01

Fault Trees perform a predominant role in reliability and safety analysis of system. Manual construction of fault tree is a very time consuming task and moreover, it won't give a formalized result, since it relies highly on analysts experience and heuristics. This necessitates a computerised fault tree construction, which is still attracting interest of reliability analysts. AFTC software is a user friendly software model for constructing fault trees based on decision tables. Software is equipped with libraries of decision tables for components commonly used in various Nuclear Power Plant (NPP) systems. User is expected to make a nodal diagram of the system, for which fault tree is to be constructed, from the flow sheets available. The text nodal diagram goes as the sole input defining the system flow chart. AFTC software is a rule based expert system which draws the fault tree from the system flow chart and component decision tables. AFTC software gives fault tree in both text and graphic format. Help is provided as how to enter system flow chart and component decision tables. The software is developed in 'C' language. Software is verified with simplified version of the fire water system of an Indian PHWR. Code conversion will be undertaken to create a window based version. (author)

Fan fault diagnosis based on symmetrized dot pattern analysis and image matching

Science.gov (United States)

Xu, Xiaogang; Liu, Haixiao; Zhu, Hao; Wang, Songling

2016-07-01

To detect the mechanical failure of fans, a new diagnostic method based on the symmetrized dot pattern (SDP) analysis and image matching is proposed. Vibration signals of 13 kinds of running states are acquired on a centrifugal fan test bed and reconstructed by the SDP technique. The SDP pattern templates of each running state are established. An image matching method is performed to diagnose the fault. In order to improve the diagnostic accuracy, the single template, multiple templates and clustering fault templates are used to perform the image matching.

TREDRA, Minimal Cut Sets Fault Tree Plot Program

International Nuclear Information System (INIS)

Fussell, J.B.

1983-01-01

1 - Description of problem or function: TREDRA is a computer program for drafting report-quality fault trees. The input to TREDRA is similar to input for standard computer programs that find minimal cut sets from fault trees. Output includes fault tree plots containing all standard fault tree logic and event symbols, gate and event labels, and an output description for each event in the fault tree. TREDRA contains the following features: a variety of program options that allow flexibility in the program output; capability for automatic pagination of the output fault tree, when necessary; input groups which allow labeling of gates, events, and their output descriptions; a symbol library which includes standard fault tree symbols plus several less frequently used symbols; user control of character size and overall plot size; and extensive input error checking and diagnostic oriented output. 2 - Method of solution: Fault trees are generated by user-supplied control parameters and a coded description of the fault tree structure consisting of the name of each gate, the gate type, the number of inputs to the gate, and the names of these inputs. 3 - Restrictions on the complexity of the problem: TREDRA can produce fault trees with a minimum of 3 and a maximum of 56 levels. The width of each level may range from 3 to 37. A total of 50 transfers is allowed during pagination

A Diagnostic and Predictive Framework for Wind Turbine Drive Train Monitoring

DEFF Research Database (Denmark)

Bach-Andersen, Martin

Vast amount of data are collected minute by minute from wind turbines around the world. This thesis represents a focused research effort into discovering new ways of processing these data streams in order to gain insights which can be used to lower the maintenance costs of wind turbines and increase......, early fault identification based on analysis of complex vibration patterns which is a domain previously reserved for human experts, is shown to be solved with high accuracy using deep learning architecture strained in a fully supervised sense from the data collected in a large scale wind turbine...... monitoring platform. The research shows a way towards a fully automatized data-driven wind turbine diagnostic processing system that is highly scalable and requires little or no feature engineering and system modeling....

Applications of Expert Systems within the Scottish Electricity Supply Industry

International Nuclear Information System (INIS)

McWhirter, A.F.

1990-01-01

This paper describes the areas of application of Expert Systems within the South of Scotland Electricity Board (SSEB). The SSEB interest in Expert Systems was initiated by a fault in a conventional power station however the paper describes how the development associated with that work, has resulted in applications for the Nuclear Power Stations. The paper contrasts the cost benefits and project risks associated with the uses of probabilistic systems and concludes that the cost benefits of these are at present too low to justify their use in on-line applications

Multiscale Permutation Entropy Based Rolling Bearing Fault Diagnosis

Directory of Open Access Journals (Sweden)

Jinde Zheng

2014-01-01

Full Text Available A new rolling bearing fault diagnosis approach based on multiscale permutation entropy (MPE, Laplacian score (LS, and support vector machines (SVMs is proposed in this paper. Permutation entropy (PE was recently proposed and defined to measure the randomicity and detect dynamical changes of time series. However, for the complexity of mechanical systems, the randomicity and dynamic changes of the vibration signal will exist in different scales. Thus, the definition of MPE is introduced and employed to extract the nonlinear fault characteristics from the bearing vibration signal in different scales. Besides, the SVM is utilized to accomplish the fault feature classification to fulfill diagnostic procedure automatically. Meanwhile, in order to avoid a high dimension of features, the Laplacian score (LS is used to refine the feature vector by ranking the features according to their importance and correlations with the main fault information. Finally, the rolling bearing fault diagnosis method based on MPE, LS, and SVM is proposed and applied to the experimental data. The experimental data analysis results indicate that the proposed method could identify the fault categories effectively.

Evaluation of tuberculosis diagnostics in children: 1. Proposed clinical case definitions for classification of intrathoracic tuberculosis disease. Consensus from an expert panel.

Science.gov (United States)

Graham, Stephen M; Ahmed, Tahmeed; Amanullah, Farhana; Browning, Renee; Cardenas, Vicky; Casenghi, Martina; Cuevas, Luis E; Gale, Marianne; Gie, Robert P; Grzemska, Malgosia; Handelsman, Ed; Hatherill, Mark; Hesseling, Anneke C; Jean-Philippe, Patrick; Kampmann, Beate; Kabra, Sushil Kumar; Lienhardt, Christian; Lighter-Fisher, Jennifer; Madhi, Shabir; Makhene, Mamodikoe; Marais, Ben J; McNeeley, David F; Menzies, Heather; Mitchell, Charles; Modi, Surbhi; Mofenson, Lynne; Musoke, Philippa; Nachman, Sharon; Powell, Clydette; Rigaud, Mona; Rouzier, Vanessa; Starke, Jeffrey R; Swaminathan, Soumya; Wingfield, Claire

2012-05-15

There is a critical need for improved diagnosis of tuberculosis in children, particularly in young children with intrathoracic disease as this represents the most common type of tuberculosis in children and the greatest diagnostic challenge. There is also a need for standardized clinical case definitions for the evaluation of diagnostics in prospective clinical research studies that include children in whom tuberculosis is suspected but not confirmed by culture of Mycobacterium tuberculosis. A panel representing a wide range of expertise and child tuberculosis research experience aimed to develop standardized clinical research case definitions for intrathoracic tuberculosis in children to enable harmonized evaluation of new tuberculosis diagnostic technologies in pediatric populations. Draft definitions and statements were proposed and circulated widely for feedback. An expert panel then considered each of the proposed definitions and statements relating to clinical definitions. Formal group consensus rules were established and consensus was reached for each statement. The definitions presented in this article are intended for use in clinical research to evaluate diagnostic assays and not for individual patient diagnosis or treatment decisions. A complementary article addresses methodological issues to consider for research of diagnostics in children with suspected tuberculosis.

Evaluation of Tuberculosis Diagnostics in Children: 1. Proposed Clinical Case Definitions for Classification of Intrathoracic Tuberculosis Disease. Consensus From an Expert Panel

Science.gov (United States)

Graham, Stephen M.; Ahmed, Tahmeed; Amanullah, Farhana; Browning, Renee; Cardenas, Vicky; Casenghi, Martina; Cuevas, Luis E.; Gale, Marianne; Gie, Robert P.; Grzemska, Malgosia; Handelsman, Ed; Hatherill, Mark; Hesseling, Anneke C.; Jean-Philippe, Patrick; Kampmann, Beate; Kabra, Sushil Kumar; Lienhardt, Christian; Lighter-Fisher, Jennifer; Madhi, Shabir; Makhene, Mamodikoe; Marais, Ben J.; McNeeley, David F.; Menzies, Heather; Mitchell, Charles; Modi, Surbhi; Mofenson, Lynne; Musoke, Philippa; Nachman, Sharon; Powell, Clydette; Rigaud, Mona; Rouzier, Vanessa; Starke, Jeffrey R.; Swaminathan, Soumya; Wingfield, Claire

2012-01-01

There is a critical need for improved diagnosis of tuberculosis in children, particularly in young children with intrathoracic disease as this represents the most common type of tuberculosis in children and the greatest diagnostic challenge. There is also a need for standardized clinical case definitions for the evaluation of diagnostics in prospective clinical research studies that include children in whom tuberculosis is suspected but not confirmed by culture of Mycobacterium tuberculosis. A panel representing a wide range of expertise and child tuberculosis research experience aimed to develop standardized clinical research case definitions for intrathoracic tuberculosis in children to enable harmonized evaluation of new tuberculosis diagnostic technologies in pediatric populations. Draft definitions and statements were proposed and circulated widely for feedback. An expert panel then considered each of the proposed definitions and statements relating to clinical definitions. Formal group consensus rules were established and consensus was reached for each statement. The definitions presented in this article are intended for use in clinical research to evaluate diagnostic assays and not for individual patient diagnosis or treatment decisions. A complementary article addresses methodological issues to consider for research of diagnostics in children with suspected tuberculosis. PMID:22448023

Fault diagnosis of locomotive electro-pneumatic brake through uncertain bond graph modeling and robust online monitoring

Science.gov (United States)

Niu, Gang; Zhao, Yajun; Defoort, Michael; Pecht, Michael

2015-01-01

To improve reliability, safety and efficiency, advanced methods of fault detection and diagnosis become increasingly important for many technical fields, especially for safety related complex systems like aircraft, trains, automobiles, power plants and chemical plants. This paper presents a robust fault detection and diagnostic scheme for a multi-energy domain system that integrates a model-based strategy for system fault modeling and a data-driven approach for online anomaly monitoring. The developed scheme uses LFT (linear fractional transformations)-based bond graph for physical parameter uncertainty modeling and fault simulation, and employs AAKR (auto-associative kernel regression)-based empirical estimation followed by SPRT (sequential probability ratio test)-based threshold monitoring to improve the accuracy of fault detection. Moreover, pre- and post-denoising processes are applied to eliminate the cumulative influence of parameter uncertainty and measurement uncertainty. The scheme is demonstrated on the main unit of a locomotive electro-pneumatic brake in a simulated experiment. The results show robust fault detection and diagnostic performance.

In-flight Fault Detection and Isolation in Aircraft Flight Control Systems

Science.gov (United States)

Azam, Mohammad; Pattipati, Krishna; Allanach, Jeffrey; Poll, Scott; Patterson-Hine, Ann

2005-01-01

In this paper we consider the problem of test design for real-time fault detection and isolation (FDI) in the flight control system of fixed-wing aircraft. We focus on the faults that are manifested in the control surface elements (e.g., aileron, elevator, rudder and stabilizer) of an aircraft. For demonstration purposes, we restrict our focus on the faults belonging to nine basic fault classes. The diagnostic tests are performed on the features extracted from fifty monitored system parameters. The proposed tests are able to uniquely isolate each of the faults at almost all severity levels. A neural network-based flight control simulator, FLTZ(Registered TradeMark), is used for the simulation of various faults in fixed-wing aircraft flight control systems for the purpose of FDI.

SDG multiple fault diagnosis by real-time inverse inference

International Nuclear Information System (INIS)

Zhang Zhaoqian; Wu Chongguang; Zhang Beike; Xia Tao; Li Anfeng

2005-01-01

In the past 20 years, one of the qualitative simulation technologies, signed directed graph (SDG) has been widely applied in the field of chemical fault diagnosis. However, the assumption of single fault origin was usually used by many former researchers. As a result, this will lead to the problem of combinatorial explosion and has limited SDG to the realistic application on the real process. This is mainly because that most of the former researchers used forward inference engine in the commercial expert system software to carry out the inverse diagnosis inference on the SDG model which violates the internal principle of diagnosis mechanism. In this paper, we present a new SDG multiple faults diagnosis method by real-time inverse inference. This is a method of multiple faults diagnosis from the genuine significance and the inference engine use inverse mechanism. At last, we give an example of 65t/h furnace diagnosis system to demonstrate its applicability and efficiency

SDG multiple fault diagnosis by real-time inverse inference

Energy Technology Data Exchange (ETDEWEB)

Zhang Zhaoqian; Wu Chongguang; Zhang Beike; Xia Tao; Li Anfeng

2005-02-01

In the past 20 years, one of the qualitative simulation technologies, signed directed graph (SDG) has been widely applied in the field of chemical fault diagnosis. However, the assumption of single fault origin was usually used by many former researchers. As a result, this will lead to the problem of combinatorial explosion and has limited SDG to the realistic application on the real process. This is mainly because that most of the former researchers used forward inference engine in the commercial expert system software to carry out the inverse diagnosis inference on the SDG model which violates the internal principle of diagnosis mechanism. In this paper, we present a new SDG multiple faults diagnosis method by real-time inverse inference. This is a method of multiple faults diagnosis from the genuine significance and the inference engine use inverse mechanism. At last, we give an example of 65t/h furnace diagnosis system to demonstrate its applicability and efficiency.

A Research on the Electrical Test Fault Diagnostic and Data Mining of a Manned Spacecraft

Directory of Open Access Journals (Sweden)

Yang Feng

2017-01-01

Full Text Available The paper introduces the modeling method and modeling tool for the fault diagnosis of manned spacecraft, the multi-signal flow graph model of a manned space equipment was established using this method; the framework of the fault detection and diagnosis system of manned spacecraft is proposed, the function of ground system and function of the spacecraft are clearly defined. The structure of the functional module is given separately; finally, the tool builds the fault detection and diagnosis system, the application of fault diagnosis method for manned spacecraft is used for reference.

Stator fault detection for multi-phase machines with multiple reference frames transformation

DEFF Research Database (Denmark)

Bianchini, Claudio; Fornasiero, Emanuele; Matzen, T.N.

2009-01-01

The paper focuses on a new diagnostic index for fault detection of a five-phase permanent-magnet machine. This machine has been designed for fault tolerant applications, and it is characterized by a mutual inductance equal to zero and a high self inductance, in order to limit the short-circuit cu...

The introduction of compulsory compliance testing of medical diagnostic x-ray equipment in Western Australia

International Nuclear Information System (INIS)

Rafferty, M. W.; Jacob, C. S.

1995-01-01

Performance testing of medical diagnostic X-ray equipment can reveal equipment faults which, while not always clinically detectable, may contribute to reduced image quality and unnecessary radiation exposure of both patients and staff. Routine testing of such equipment is highly desirable to identify such faults and allows them to be rectified. The Radiological council of Western Australia is moving towards requiring compulsory compliance testing of all (new and existing) medical diagnostic X-ray equipment that all new mobile radiographic and new mammographic X-ray equipment be issued with a compliance test certificate as a prerequisite for registration. Workbooks which provide details of the tests required and recommended test methods have been prepared for medical radiographic (mobile and fixed), fluoroscopic and mammographic X-ray equipment. It is intended that future workbooks include details of the tests and methods for dental and computed tomography X-ray units. The workbooks are not limited to the compliance testing of items as specified in the Regulations, but include tests for other items such as film processing, darkrooms and image quality (for fluoroscopic equipment). Many of the workbook tests could be used within a regular quality assurance program for diagnostic X-ray equipment. Persons who conduct such compliance tests will need to be licensed and have all test certificates endorsed by a qualified expert. Suitable training and assessment of compliance testers will be required. Notification of such tests (including non-compliant items and corrective actions taken) will be required by the Radiological Council as a condition of equipment registration. 9 refs

A distributed fault tolerant architecture for nuclear reactor control and safety functions

International Nuclear Information System (INIS)

Hecht, M.; Agron, J.; Hochhauser, S.

1989-01-01

This paper reports on a fault tolerance architecture that provides tolerance to a broad scope of hardware, software, and communications faults which is being developed. This architecture relies on widely commercially available operating systems, local area networks, and software standards. Thus, development time is significantly shortened, and modularity allows for continuous and inexpensive system enhancement throughout the expected 20- year life. The fault containment and parallel processing capabilites of computers network are being exploited to provide a high performance, high availability network capable of tolerating a broad scope of hardware software, and operating system faults. The system can tolerate all but one known (and avoidable) single fault, two known and avoidable dual faults, and will detect all higher order fault sequences and provide diagnostics to allow for rapid manual recovery

Expert system application to fault diagnosis and procedure synthesis

International Nuclear Information System (INIS)

Hajek, B.K.; Hashemi, S.; Bhatnagar, R.; Miller, D.W.; Stasenko, J.

1987-01-01

Two knowledge based systems have been developed to detect plant faults, to validate sensor data in a nuclear power plant, and to synthesize procedures to assure safety goals are met when a transient occurs. These two systems are being combined into a single system through a Plant Status Monitoring System (PSMS) and a common data base accessed by all the components of the integrated system. The system is designed to sit on top of an existing Safety Parameter Display System (SPDS), and to use the existing data acquisition and data control software of the SPDS. The integrated system will communicate with the SPDS software through a single database. This database will receive sensor values and equipment status indications in a form acceptable to the knowledge based system and according to an update plan designed specifically for the system

A Framework for Diagnosis of Critical Faults in Unmanned Aerial Vehicles

DEFF Research Database (Denmark)

Hansen, Søren; Blanke, Mogens; Adrian, Jens

2014-01-01

, and based on a large number of data logged during flights, diagnostic methods are employed to diagnose faults and the performance of these fault detectors are evaluated against light data. The paper demonstrates a significant potential for reducing the risk of unplanned loss of remotely piloted vehicles......Unmanned Aerial Vehicles (UAVs) need a large degree of tolerance towards faults. If not diagnosed and handled in time, many types of faults can have catastrophic consequences if they occur during flight. Prognosis of faults is also valuable and so is the ability to distinguish the severity...... of the different faults in terms of both consequences and the frequency with which they appear. In this paper flight data from a fleet of UAVs is analysed with respect to certain faults and their frequency of appearance. Data is taken from a group of UAV's of the same type but with small differences in weight...

FAULT DIAGNOSIS IN ROTATING MACHINE USING FULL SPECTRUM OF VIBRATION AND FUZZY LOGIC

Directory of Open Access Journals (Sweden)

ROGER R. DA SILVA

2017-11-01

Full Text Available Industries are always looking for more efficient maintenance systems to minimize machine downtime and productivity liabilities. Among several approaches, artificial intelligence techniques have been increasingly applied to machine diagnosis. Current paper forwards the development of a system for the diagnosis of mechanical faults in the rotating structures of machines, based on fuzzy logic, using rules foregrounded on the full spectrum of the machine´s complex vibration signal. The diagnostic system was developed in Matlab and it was applied to a rotor test rig where different faults were introduced. Results showed that the diagnostic system based on full spectra and fuzzy logic is capable of identifying with precision different types of faults, which have similar half spectrum. The methodology has a great potential to be implemented in predictive maintenance programs in industries and may be expanded to include the identification of other types of faults not covered in the case study under analysis.

An expert system for sensor data validation and malfunction detection

International Nuclear Information System (INIS)

Hashemi, S.; Hajek, B.K.; Miller, D.W.

1987-01-01

Nuclear power plant operation and monitoring in general is a complex task which requires a large number of sensors, alarms and displays. At any instant in time, the operator is required to make a judgment about the state of the plant and to react accordingly. During abnormal situations, operators are further burdened with time constraints. The possibility of an undetected faulty instrumentation line, adds to the complexity of operators' reasoning tasks. Failure of human operators to cope with the conceptual complexity of abnormal situations often leads to more serious malfunctions and further damages to plant (TMI-2 as an example). During these abnormalities, operators rely on the information provided by the plant sensors and associated alarms. Their usefulness however, is quickly diminished by their large number and the extremely difficult task of interpreting and comprehending the information provided by them. The need for an aid to assist the operator in interpreting the available data and diagnosis of problems is obvious. Recent work at the Ohio State University Laboratory of Artificial Intelligence Research (LAIR) and the nuclear engineering program has concentrated on the problem of diagnostic expert systems performance and their applicability to the nuclear power plant domain. There has also been concern about the diagnostic expert systems performance when using potentially invalid sensor data. Because of this research, an expert system has been developed that can perform diagnostic problem solving despite the existence of some conflicting data in the domain. This work has resulted in enhancement of a programming tool, that allows domain experts to create a diagnostic system that will be to some degree, tolerant of bad data while performing diagnosis. This expert system is described here

Combining principles of Cognitive Load Theory and diagnostic error analysis for designing job aids: Effects on motivation and diagnostic performance in a process control task.

Science.gov (United States)

Kluge, Annette; Grauel, Britta; Burkolter, Dina

2013-03-01

Two studies are presented in which the design of a procedural aid and the impact of an additional decision aid for process control were assessed. In Study 1, a procedural aid was developed that avoids imposing unnecessary extraneous cognitive load on novices when controlling a complex technical system. This newly designed procedural aid positively affected germane load, attention, satisfaction, motivation, knowledge acquisition and diagnostic speed for novel faults. In Study 2, the effect of a decision aid for use before the procedural aid was investigated, which was developed based on an analysis of diagnostic errors committed in Study 1. Results showed that novices were able to diagnose both novel faults and practised faults, and were even faster at diagnosing novel faults. This research contributes to the question of how to optimally support novices in dealing with technical faults in process control. Copyright © 2012 Elsevier Ltd and The Ergonomics Society. All rights reserved.

Rolling bearing fault diagnosis based on information fusion using Dempster-Shafer evidence theory

Science.gov (United States)

Pei, Di; Yue, Jianhai; Jiao, Jing

2017-10-01

This paper presents a fault diagnosis method for rolling bearing based on information fusion. Acceleration sensors are arranged at different position to get bearing vibration data as diagnostic evidence. The Dempster-Shafer (D-S) evidence theory is used to fuse multi-sensor data to improve diagnostic accuracy. The efficiency of the proposed method is demonstrated by the high speed train transmission test bench. The results of experiment show that the proposed method in this paper improves the rolling bearing fault diagnosis accuracy compared with traditional signal analysis methods.

Incorporating ''fuzzy'' data and logical relations in the design of expert systems for nuclear reactors

International Nuclear Information System (INIS)

Guth, M.A.S.

1987-01-01

This paper applies the method of assigning probability in Dempster-Shafer Theory (DST) to the components of rule-based expert systems used in the control of nuclear reactors. Probabilities are assigned to premises, consequences, and rules themselves. This paper considers how uncertainty can propagate through a system of Boolean equations, such as fault trees or expert systems. The probability masses assigned to primary initiating events in the expert system can be derived from observing a nuclear reactor in operation or based on engineering knowledge of the reactor parts. Use of DST mass assignments offers greater flexibility to the construction of expert systems

Unsupervised Fault Diagnosis of a Gear Transmission Chain Using a Deep Belief Network

Directory of Open Access Journals (Sweden)

Jun He

2017-07-01

Full Text Available Artificial intelligence (AI techniques, which can effectively analyze massive amounts of fault data and automatically provide accurate diagnosis results, have been widely applied to fault diagnosis of rotating machinery. Conventional AI methods are applied using features selected by a human operator, which are manually extracted based on diagnostic techniques and field expertise. However, developing robust features for each diagnostic purpose is often labour-intensive and time-consuming, and the features extracted for one specific task may be unsuitable for others. In this paper, a novel AI method based on a deep belief network (DBN is proposed for the unsupervised fault diagnosis of a gear transmission chain, and the genetic algorithm is used to optimize the structural parameters of the network. Compared to the conventional AI methods, the proposed method can adaptively exploit robust features related to the faults by unsupervised feature learning, thus requires less prior knowledge about signal processing techniques and diagnostic expertise. Besides, it is more powerful at modelling complex structured data. The effectiveness of the proposed method is validated using datasets from rolling bearings and gearbox. To show the superiority of the proposed method, its performance is compared with two well-known classifiers, i.e., back propagation neural network (BPNN and support vector machine (SVM. The fault classification accuracies are 99.26% for rolling bearings and 100% for gearbox when using the proposed method, which are much higher than that of the other two methods.

Unsupervised Fault Diagnosis of a Gear Transmission Chain Using a Deep Belief Network.

Science.gov (United States)

He, Jun; Yang, Shixi; Gan, Chunbiao

2017-07-04

Artificial intelligence (AI) techniques, which can effectively analyze massive amounts of fault data and automatically provide accurate diagnosis results, have been widely applied to fault diagnosis of rotating machinery. Conventional AI methods are applied using features selected by a human operator, which are manually extracted based on diagnostic techniques and field expertise. However, developing robust features for each diagnostic purpose is often labour-intensive and time-consuming, and the features extracted for one specific task may be unsuitable for others. In this paper, a novel AI method based on a deep belief network (DBN) is proposed for the unsupervised fault diagnosis of a gear transmission chain, and the genetic algorithm is used to optimize the structural parameters of the network. Compared to the conventional AI methods, the proposed method can adaptively exploit robust features related to the faults by unsupervised feature learning, thus requires less prior knowledge about signal processing techniques and diagnostic expertise. Besides, it is more powerful at modelling complex structured data. The effectiveness of the proposed method is validated using datasets from rolling bearings and gearbox. To show the superiority of the proposed method, its performance is compared with two well-known classifiers, i.e., back propagation neural network (BPNN) and support vector machine (SVM). The fault classification accuracies are 99.26% for rolling bearings and 100% for gearbox when using the proposed method, which are much higher than that of the other two methods.

Bayesian Based Diagnostic Model for Condition Based Maintenance of Offshore Wind Farms

Directory of Open Access Journals (Sweden)

Masoud Asgarpour

2018-01-01

Full Text Available Operation and maintenance costs are a major contributor to the Levelized Cost of Energy for electricity produced by offshore wind and can be significantly reduced if existing corrective actions are performed as efficiently as possible and if future corrective actions are avoided by performing sufficient preventive actions. This paper presents an applied and generic diagnostic model for fault detection and condition based maintenance of offshore wind components. The diagnostic model is based on two probabilistic matrices; first, a confidence matrix, representing the probability of detection using each fault detection method, and second, a diagnosis matrix, representing the individual outcome of each fault detection method. Once the confidence and diagnosis matrices of a component are defined, the individual diagnoses of each fault detection method are combined into a final verdict on the fault state of that component. Furthermore, this paper introduces a Bayesian updating model based on observations collected by inspections to decrease the uncertainty of initial confidence matrix. The framework and implementation of the presented diagnostic model are further explained within a case study for a wind turbine component based on vibration, temperature, and oil particle fault detection methods. The last part of the paper will have a discussion of the case study results and present conclusions.

Support vector machine in machine condition monitoring and fault diagnosis

Science.gov (United States)

Widodo, Achmad; Yang, Bo-Suk

2007-08-01

Recently, the issue of machine condition monitoring and fault diagnosis as a part of maintenance system became global due to the potential advantages to be gained from reduced maintenance costs, improved productivity and increased machine availability. This paper presents a survey of machine condition monitoring and fault diagnosis using support vector machine (SVM). It attempts to summarize and review the recent research and developments of SVM in machine condition monitoring and diagnosis. Numerous methods have been developed based on intelligent systems such as artificial neural network, fuzzy expert system, condition-based reasoning, random forest, etc. However, the use of SVM for machine condition monitoring and fault diagnosis is still rare. SVM has excellent performance in generalization so it can produce high accuracy in classification for machine condition monitoring and diagnosis. Until 2006, the use of SVM in machine condition monitoring and fault diagnosis is tending to develop towards expertise orientation and problem-oriented domain. Finally, the ability to continually change and obtain a novel idea for machine condition monitoring and fault diagnosis using SVM will be future works.

Use of expert systems in nuclear power plants

International Nuclear Information System (INIS)

Uhrig, R.E.

1989-01-01

The application of technologies, particularly expert systems, to the control room activities in a nuclear power plant has the potential to reduce operator error and increase plant safety, reliability, and efficiency. Furthermore, there are a large number of nonoperating activities (testing, routine maintenance, outage planning, equipment diagnostics, and fuel management) in which expert systems can increase the efficiency and effectiveness of overall plant and corporate operations. This document presents a number of potential applications of expert systems in the nuclear power field. 36 refs., 2 tabs

Expert Meeting Report: HVAC Fault Detection, DIagnosis, and Repair/Replacement

Energy Technology Data Exchange (ETDEWEB)

Springer, David [Alliance for Residential Building Innovation (ARBI), Davis, CA (United States)

2016-05-01

The concept for the expert meeting described in this report was to bring together most of the stakeholders in the area of FDD, including academic researchers, manufacturers, educators, program managers and implementers, representatives of standards organizations, utilities, HVAC contractors, and home performance contractors to identify the major gaps and to develop ideas about what can be done to capitalize on the residential HVAC efficiency resource.

Expert Meeting Report: HVAC Fault Detection, Diagnosis, and Repair/Replacement

Energy Technology Data Exchange (ETDEWEB)

Springer, David [Alliance for Residential Building Innovation (ARBI), Davis, CA (United States). Davis Energy Group

2016-05-01

The concept for the expert meeting described in this report was to bring together most of the stakeholders in the area of FDD, including academic researchers, manufacturers, educators, program managers and implementers, representatives of standards organizations, utilities, HVAC contractors, and home performance contractors to identify the major gaps and to develop ideas about what can be done to capitalize on the residential HVAC efficiency resource.

Fault diagnostics in power transformer model winding for different alpha values

Directory of Open Access Journals (Sweden)

G.H. Kusumadevi

2015-09-01

Full Text Available Transient overvoltages appearing at line terminal of power transformer HV windings can cause failure of winding insulation. The failure can be from winding to ground or between turns or sections of winding. In most of the cases, failure from winding to ground can be detected by changes in the wave shape of surge voltage appearing at line terminal. However, detection of insulation failure between turns may be difficult due to intricacies involved in identifications of faults. In this paper, simulation investigations carried out on a power transformer model winding for identifying faults between turns of winding has been reported. The power transformer HV winding has been represented by 8 sections, 16 sections and 24 sections. Neutral current waveform has been analyzed for same model winding represented by different number of sections. The values of α (‘α’ value is the square root of total ground capacitance to total series capacitance of winding considered for windings are 5, 10 and 20. Standard lightning impulse voltage (1.2/50 μs wave shape have been considered for analysis. Computer simulations have been carried out using software PSPICE version 10.0. Neutral current and frequency response analysis methods have been used for identification of faults within sections of transformer model winding.

Rolling element bearings diagnostics using the Symbolic Aggregate approXimation

Science.gov (United States)

Georgoulas, George; Karvelis, Petros; Loutas, Theodoros; Stylios, Chrysostomos D.

2015-08-01

Rolling element bearings are a very critical component in various engineering assets. Therefore it is of paramount importance the detection of possible faults, especially at an early stage, that may lead to unexpected interruptions of the production or worse, to severe accidents. This research work introduces a novel, in the field of bearing fault detection, method for the extraction of diagnostic representations of vibration recordings using the Symbolic Aggregate approXimation (SAX) framework and the related intelligent icons representation. SAX essentially transforms the original real valued time-series into a discrete one, which is then represented by a simple histogram form summarizing the occurrence of the chosen symbols/words. Vibration signals from healthy bearings and bearings with three different fault locations and with three different severity levels, as well as loading conditions, are analyzed. Considering the diagnostic problem as a classification one, the analyzed vibration signals and the resulting feature vectors feed simple classifiers achieving remarkably high classification accuracies. Moreover a sliding window scheme combined with a simple majority voting filter further increases the reliability and robustness of the diagnostic method. The results encourage the potential use of the proposed methodology for the diagnosis of bearing faults.

Method of fault diagnosis in nuclear power plant base on genetic algorithm and knowledge base

International Nuclear Information System (INIS)

Zhou Yangping; Zhao Bingquan

2000-01-01

Via using the knowledge base, combining Genetic Algorithm and classical probability and contraposing the characteristic of the fault diagnosis of NPP. The authors put forward a method of fault diagnosis. In the process of fault diagnosis, this method contact the state of NPP with the colony in GA and transform the colony to get the individual that adapts to the condition. On the 950MW full size simulator in Beijing NPP simulation training center, experimentation shows it has comparative adaptability to the imperfection of expert knowledge, illusive signal and other instance

Range of expert system for control, modeling and safely operation in nuclear energy

International Nuclear Information System (INIS)

Gorlin, A.; Semenov, S.

1990-01-01

The paper describes expert system projects which had been developed formerly and are under the development now in NVIIAES Institute, Moscow. One of the accomplished systems (PEX) is a ES-shell of classical type able to manipulate fuzzy expert assessments. The system is used as a shell for ES-advisor for MCP failures diagnostics and in some applications of the same sort. Another realized system (EDES) is on-line express-diagnostical ES for NPP unit emergency regimes identification. EDES is implemented now as a component of NPP system of control and operation conditions diagnostics. Both systems are realized on conventional programming languages Pascal and C, respectively. The presentation describes current developments in ES as well, including classification system for material researches, the project of training ES for second circuit diagnostics based on event tree generating and expert planner for neutron-physical three-dimensional reactor calculations. All this projects are implemented on different versions of PROLOG programming language

PC based diagnostic system for nitrogen production unit of HWP

International Nuclear Information System (INIS)

Lamba, D.S.; Rao, V.C.; Krishnan, S.; Kamaraj, T.; Krishnaswamy, C.

1992-01-01

The plant diagnostic system monitors the input data from local processing unit and tries to diagnose the cause of the failure. The system is a rule based application program that can perform tasks itself using fault tree model which displays the logical relationships between critical events and their possible ways occurrence, i.e. hardware failure, process faults and human error etc. Unit 37 Nitrogen Plant is taken as a prototype model for trying the plant diagnostics system. (author). 3 refs., 2 figs

Application of the Systematic Sensor Selection Strategy for Turbofan Engine Diagnostics

Science.gov (United States)

Sowers, T. Shane; Kopasakis, George; Simon, Donald L.

2008-01-01

The data acquired from available system sensors forms the foundation upon which any health management system is based, and the available sensor suite directly impacts the overall diagnostic performance that can be achieved. While additional sensors may provide improved fault diagnostic performance, there are other factors that also need to be considered such as instrumentation cost, weight, and reliability. A systematic sensor selection approach is desired to perform sensor selection from a holistic system-level perspective as opposed to performing decisions in an ad hoc or heuristic fashion. The Systematic Sensor Selection Strategy is a methodology that optimally selects a sensor suite from a pool of sensors based on the system fault diagnostic approach, with the ability of taking cost, weight, and reliability into consideration. This procedure was applied to a large commercial turbofan engine simulation. In this initial study, sensor suites tailored for improved diagnostic performance are constructed from a prescribed collection of candidate sensors. The diagnostic performance of the best performing sensor suites in terms of fault detection and identification are demonstrated, with a discussion of the results and implications for future research.

Design and implementation of real-time diagnostic expert system in nuclear power plant

International Nuclear Information System (INIS)

Zhang Yan; Zhou Zhiwei; Dong Xiuchen

2006-01-01

In order to decrease the probability of malfunctions in nuclear power plant, a real-time expert system to be applied to malfunction diagnosis was designed. Based on the expert system theory the system converts the expert knowledge for diagnosing failures into the rules stored in database, and it can display real-time information of the abnormal symptoms, perform real-time diagnosis of malfunctions and suggest the operation actions related to malfunctions, etc. The results indicate that several typical malfunctions in nuclear power plant are diagnosed automatically and the corresponding operation schedules are given out by present expert system. (authors)

Human engineering in the design of expert systems for microcomputer system troubleshooting

International Nuclear Information System (INIS)

Easter, J.R.; Elm, W.C.

1988-01-01

The man-machine interfaces of the first generation of expert systems have usually received little or no explicit design effort. As a result, many of these systems when placed in their productive environment have only served to collect dust. One of the more aggravating attributes of such systems has been the demand that the user of such systems religiously follow the pre-determined and fixed problem solving path the domain expert designed in the expert system. Westinghouse has embarked on a program aimed at improving the productivity of the I and C maintenance staff responsible for caring for these new systems, the focus of which is the development of a computer based expert system to be used as a trouble-shooting aid. To date, Westinghouse has created a knowledge structure for such an expert system that describes the purposes or design objectives of the faulted microcomputer system

Climate Prediction Center: ENSO Diagnostic Discussion

Science.gov (United States)

Organization Search Go Search the CPC Go Expert Assessments ENSO Diagnostic Discussion Archive About Us Our Assessments > ENSO Diagnostic Discussion El Niño/Southern Oscillation (ENSO) Diagnostic Discussion PDF : English Version Spanish Version Adobe PDF Reader (Click icon for Adobe PDF Reader) Word: English Version

Modeling of HVAC operational faults in building performance simulation

International Nuclear Information System (INIS)

Zhang, Rongpeng; Hong, Tianzhen

2017-01-01

Highlights: •Discuss significance of capturing operational faults in existing buildings. •Develop a novel feature in EnergyPlus to model operational faults of HVAC systems. •Compare three approaches to faults modeling using EnergyPlus. •A case study demonstrates the use of the fault-modeling feature. •Future developments of new faults are discussed. -- Abstract: Operational faults are common in the heating, ventilating, and air conditioning (HVAC) systems of existing buildings, leading to a decrease in energy efficiency and occupant comfort. Various fault detection and diagnostic methods have been developed to identify and analyze HVAC operational faults at the component or subsystem level. However, current methods lack a holistic approach to predicting the overall impacts of faults at the building level—an approach that adequately addresses the coupling between various operational components, the synchronized effect between simultaneous faults, and the dynamic nature of fault severity. This study introduces the novel development of a fault-modeling feature in EnergyPlus which fills in the knowledge gap left by previous studies. This paper presents the design and implementation of the new feature in EnergyPlus and discusses in detail the fault-modeling challenges faced. The new fault-modeling feature enables EnergyPlus to quantify the impacts of faults on building energy use and occupant comfort, thus supporting the decision making of timely fault corrections. Including actual building operational faults in energy models also improves the accuracy of the baseline model, which is critical in the measurement and verification of retrofit or commissioning projects. As an example, EnergyPlus version 8.6 was used to investigate the impacts of a number of typical operational faults in an office building across several U.S. climate zones. The results demonstrate that the faults have significant impacts on building energy performance as well as on occupant

Knowledge based diagnostics in nuclear power plants

International Nuclear Information System (INIS)

Baldeweg, F.; Fiedler, U.; Weiss, F.P.; Werner, M.

1987-01-01

In this paper a special process diagnostic system (PDS) is presented. It must be seen as the result of a long term work on computerized process surveillance and control; it includes a model based system for noise analysis of mechanical vibrations, which has recently been enhanced by using of knowledge based technique (expert systems). The paper discusses the process diagnostic frame concept and emphasize the vibration analysis expert system

An on-line diagnostic expert system

International Nuclear Information System (INIS)

Felkel, L.

1987-01-01

As experience with on-line information systems, experts systems and artificial intelligence tools grows, the authors retreat from the first euphoria that AI could help them solve the problem they were unable to solve with conventional programming. The major effort of the development time goes into building the knowledge-base. There is no such thing as a generic knowledge-base for nuclear power plants as there is, for example, for the diagnosis of a Boeing 747 aircraft. AI-methods, tools and hardware are still in a state which does not optimally lend itself to real-time application. The ability of developing prototype systems to investigate variants otherwise too costly to justify is one advantage that the authors gladly accept. Last, but no least the tools provide a flexible and adaptable user interface (desktop window systems) etc. The development of such tools in a project would be prohibitive and room for experimentation would be limited

SIDES - Segment Interconnect Diagnostic Expert System

International Nuclear Information System (INIS)

Booth, A.W.; Forster, R.; Gustafsson, L.; Ho, N.

1989-01-01

It is well known that the FASTBUS Segment Interconnect (SI) provides a communication path between two otherwise independent, asynchronous bus segments. The SI is probably the most important module in any FASTBUS data acquisition network since it's failure to function can cause whole segments of the network to be inaccessible and sometimes inoperable. This paper describes SIDES, an intelligent program designed to diagnose SI's both in situ as they operate in a data acquisition network, and in the laboratory in an acceptance/repair environment. The paper discusses important issues such as knowledge acquisition; extracting knowledge from human experts and other knowledge sources. SIDES can benefit high energy physics experiments, where SI problems can be diagnosed and solved more quickly. Equipment pool technicians can also benefit from SIDES, first by decreasing the number of SI's erroneously turned in for repair, and secondly as SIDES acts as an intelligent assistant to the technician in the diagnosis and repair process

Risk evaluation method for faults by engineering approach. (1) Nuclear safety for accident scenario and measures for fault movement

International Nuclear Information System (INIS)

Narabayashi, Tadashi; Chiba, Go; Okamoto, Koji; Kameda, Hiroyuki; Ebisawa, Katsumi; Yamazaki, Haruo; Konagai, Kazuo; Kamiya, Masanobu; Nagasawa, Kazuyuki

2016-01-01

Japan, as a frequent earthquake country, has a responsibility to resolve efficient measures to enhance nuclear safety, to continue utilizing the nuclear power, based on the risks and importance levels in the scientific and rational manner. In his paper describes how to evaluate the risk of faults movement by engineering approach. An open fruitful discussion by experts in the various area of earthquake, geology, geotechnical, civil, and a seismic design as well as other stakeholders such as academia professors, nuclear reactor engineers, regulators, and licensees. The Atomic Energy Society established an Investigation Committee on Development of Activity and Risk Evaluation Method for Faults by Engineering Approach (IC-DAREFEA) on October 1st, a 2014. The Investigation Committee utilizes the most advanced scientific and rational judgement, and continuous discussions and efforts in the global field, in order to collect and organize these knowledge and reflect the global standards and nuclear regulations, such as risk evaluation method for the faults movements and prevention of severe accidents, based on the accumulated database in the world, including Chuetsuoki Earthquake, North Nagano Earthquake and Kumamoto Earthquake. (author)

Clustering of the Self-Organizing Map based Approach in Induction Machine Rotor Faults Diagnostics

Directory of Open Access Journals (Sweden)

Ahmed TOUMI

2009-12-01

Full Text Available Self-Organizing Maps (SOM is an excellent method of analyzingmultidimensional data. The SOM based classification is attractive, due to itsunsupervised learning and topology preserving properties. In this paper, theperformance of the self-organizing methods is investigated in induction motorrotor fault detection and severity evaluation. The SOM is based on motor currentsignature analysis (MCSA. The agglomerative hierarchical algorithms using theWard’s method is applied to automatically dividing the map into interestinginterpretable groups of map units that correspond to clusters in the input data. Theresults obtained with this approach make it possible to detect a rotor bar fault justdirectly from the visualization results. The system is also able to estimate theextent of rotor faults.

Expert systems for automated maintenance of a Mars oxygen production system

Science.gov (United States)

Huang, Jen-Kuang; Ho, Ming-Tsang; Ash, Robert L.

1992-08-01

Application of expert system concepts to a breadboard Mars oxygen processor unit have been studied and tested. The research was directed toward developing the methodology required to enable autonomous operation and control of these simple chemical processors at Mars. Failure detection and isolation was the key area of concern, and schemes using forward chaining, backward chaining, knowledge-based expert systems, and rule-based expert systems were examined. Tests and simulations were conducted that investigated self-health checkout, emergency shutdown, and fault detection, in addition to normal control activities. A dynamic system model was developed using the Bond-Graph technique. The dynamic model agreed well with tests involving sudden reductions in throughput. However, nonlinear effects were observed during tests that incorporated step function increases in flow variables. Computer simulations and experiments have demonstrated the feasibility of expert systems utilizing rule-based diagnosis and decision-making algorithms.

Imaging spectroscopy: Earth and planetary remote sensing with the USGS Tetracorder and expert systems

Science.gov (United States)

Clark, Roger N.; Swayze, Gregg A.; Livo, K. Eric; Kokaly, Raymond F.; Sutley, Steve J.; Dalton, J. Brad; McDougal, Robert R.; Gent, Carol A.

2003-01-01

Imaging spectroscopy is a tool that can be used to spectrally identify and spatially map materials based on their specific chemical bonds. Spectroscopic analysis requires significantly more sophistication than has been employed in conventional broadband remote sensing analysis. We describe a new system that is effective at material identification and mapping: a set of algorithms within an expert system decision‐making framework that we call Tetracorder. The expertise in the system has been derived from scientific knowledge of spectral identification. The expert system rules are implemented in a decision tree where multiple algorithms are applied to spectral analysis, additional expert rules and algorithms can be applied based on initial results, and more decisions are made until spectral analysis is complete. Because certain spectral features are indicative of specific chemical bonds in materials, the system can accurately identify and map those materials. In this paper we describe the framework of the decision making process used for spectral identification, describe specific spectral feature analysis algorithms, and give examples of what analyses and types of maps are possible with imaging spectroscopy data. We also present the expert system rules that describe which diagnostic spectral features are used in the decision making process for a set of spectra of minerals and other common materials. We demonstrate the applications of Tetracorder to identify and map surface minerals, to detect sources of acid rock drainage, and to map vegetation species, ice, melting snow, water, and water pollution, all with one set of expert system rules. Mineral mapping can aid in geologic mapping and fault detection and can provide a better understanding of weathering, mineralization, hydrothermal alteration, and other geologic processes. Environmental site assessment, such as mapping source areas of acid mine drainage, has resulted in the acceleration of site cleanup, saving

Staged-Fault Testing of Distance Protection Relay Settings

Science.gov (United States)

Havelka, J.; Malarić, R.; Frlan, K.

2012-01-01

In order to analyze the operation of the protection system during induced fault testing in the Croatian power system, a simulation using the CAPE software has been performed. The CAPE software (Computer-Aided Protection Engineering) is expert software intended primarily for relay protection engineers, which calculates current and voltage values during faults in the power system, so that relay protection devices can be properly set up. Once the accuracy of the simulation model had been confirmed, a series of simulations were performed in order to obtain the optimal fault location to test the protection system. The simulation results were used to specify the test sequence definitions for the end-to-end relay testing using advanced testing equipment with GPS synchronization for secondary injection in protection schemes based on communication. The objective of the end-to-end testing was to perform field validation of the protection settings, including verification of the circuit breaker operation, telecommunication channel time and the effectiveness of the relay algorithms. Once the end-to-end secondary injection testing had been completed, the induced fault testing was performed with three-end lines loaded and in service. This paper describes and analyses the test procedure, consisting of CAPE simulations, end-to-end test with advanced secondary equipment and staged-fault test of a three-end power line in the Croatian transmission system.

Advanced and intelligent computations in diagnosis and control

CERN Document Server

2016-01-01

This book is devoted to the demands of research and industrial centers for diagnostics, monitoring and decision making systems that result from the increasing complexity of automation and systems, the need to ensure the highest level of reliability and safety, and continuing research and the development of innovative approaches to fault diagnosis. The contributions combine domains of engineering knowledge for diagnosis, including detection, isolation, localization, identification, reconfiguration and fault-tolerant control. The book is divided into six parts:  (I) Fault Detection and Isolation; (II) Estimation and Identification; (III) Robust and Fault Tolerant Control; (IV) Industrial and Medical Diagnostics; (V) Artificial Intelligence; (VI) Expert and Computer Systems.

Designing Fault-Injection Experiments for the Reliability of Embedded Systems

Science.gov (United States)

White, Allan L.

2012-01-01

This paper considers the long-standing problem of conducting fault-injections experiments to establish the ultra-reliability of embedded systems. There have been extensive efforts in fault injection, and this paper offers a partial summary of the efforts, but these previous efforts have focused on realism and efficiency. Fault injections have been used to examine diagnostics and to test algorithms, but the literature does not contain any framework that says how to conduct fault-injection experiments to establish ultra-reliability. A solution to this problem integrates field-data, arguments-from-design, and fault-injection into a seamless whole. The solution in this paper is to derive a model reduction theorem for a class of semi-Markov models suitable for describing ultra-reliable embedded systems. The derivation shows that a tight upper bound on the probability of system failure can be obtained using only the means of system-recovery times, thus reducing the experimental effort to estimating a reasonable number of easily-observed parameters. The paper includes an example of a system subject to both permanent and transient faults. There is a discussion of integrating fault-injection with field-data and arguments-from-design.

Layered clustering multi-fault diagnosis for hydraulic piston pump

Science.gov (United States)

Du, Jun; Wang, Shaoping; Zhang, Haiyan

2013-04-01

Efficient diagnosis is very important for improving reliability and performance of aircraft hydraulic piston pump, and it is one of the key technologies in prognostic and health management system. In practice, due to harsh working environment and heavy working loads, multiple faults of an aircraft hydraulic pump may occur simultaneously after long time operations. However, most existing diagnosis methods can only distinguish pump faults that occur individually. Therefore, new method needs to be developed to realize effective diagnosis of simultaneous multiple faults on aircraft hydraulic pump. In this paper, a new method based on the layered clustering algorithm is proposed to diagnose multiple faults of an aircraft hydraulic pump that occur simultaneously. The intensive failure mechanism analyses of the five main types of faults are carried out, and based on these analyses the optimal combination and layout of diagnostic sensors is attained. The three layered diagnosis reasoning engine is designed according to the faults' risk priority number and the characteristics of different fault feature extraction methods. The most serious failures are first distinguished with the individual signal processing. To the desultory faults, i.e., swash plate eccentricity and incremental clearance increases between piston and slipper, the clustering diagnosis algorithm based on the statistical average relative power difference (ARPD) is proposed. By effectively enhancing the fault features of these two faults, the ARPDs calculated from vibration signals are employed to complete the hypothesis testing. The ARPDs of the different faults follow different probability distributions. Compared with the classical fast Fourier transform-based spectrum diagnosis method, the experimental results demonstrate that the proposed algorithm can diagnose the multiple faults, which occur synchronously, with higher precision and reliability.

Distance and Density Similarity Based Enhanced k-NN Classifier for Improving Fault Diagnosis Performance of Bearings

Directory of Open Access Journals (Sweden)

Sharif Uddin

2016-01-01

Full Text Available An enhanced k-nearest neighbor (k-NN classification algorithm is presented, which uses a density based similarity measure in addition to a distance based similarity measure to improve the diagnostic performance in bearing fault diagnosis. Due to its use of distance based similarity measure alone, the classification accuracy of traditional k-NN deteriorates in case of overlapping samples and outliers and is highly susceptible to the neighborhood size, k. This study addresses these limitations by proposing the use of both distance and density based measures of similarity between training and test samples. The proposed k-NN classifier is used to enhance the diagnostic performance of a bearing fault diagnosis scheme, which classifies different fault conditions based upon hybrid feature vectors extracted from acoustic emission (AE signals. Experimental results demonstrate that the proposed scheme, which uses the enhanced k-NN classifier, yields better diagnostic performance and is more robust to variations in the neighborhood size, k.

Application of CMAC Neural Network to Solar Energy Heliostat Field Fault Diagnosis

Directory of Open Access Journals (Sweden)

Neng-Sheng Pai

2013-01-01

Full Text Available Solar energy heliostat fields comprise numerous sun tracking platforms. As a result, fault detection is a highly challenging problem. Accordingly, the present study proposes a cerebellar model arithmetic computer (CMAC neutral network for automatically diagnosing faults within the heliostat field in accordance with the rotational speed, vibration, and temperature characteristics of the individual heliostat transmission systems. As compared with radial basis function (RBF neural network and back propagation (BP neural network in the heliostat field fault diagnosis, the experimental results show that the proposed neural network has a low training time, good robustness, and a reliable diagnostic performance. As a result, it provides an ideal solution for fault diagnosis in modern, large-scale heliostat fields.

A modular neural network scheme applied to fault diagnosis in electric power systems.

Science.gov (United States)

Flores, Agustín; Quiles, Eduardo; García, Emilio; Morant, Francisco; Correcher, Antonio

2014-01-01

This work proposes a new method for fault diagnosis in electric power systems based on neural modules. With this method the diagnosis is performed by assigning a neural module for each type of component comprising the electric power system, whether it is a transmission line, bus or transformer. The neural modules for buses and transformers comprise two diagnostic levels which take into consideration the logic states of switches and relays, both internal and back-up, with the exception of the neural module for transmission lines which also has a third diagnostic level which takes into account the oscillograms of fault voltages and currents as well as the frequency spectrums of these oscillograms, in order to verify if the transmission line had in fact been subjected to a fault. One important advantage of the diagnostic system proposed is that its implementation does not require the use of a network configurator for the system; it does not depend on the size of the power network nor does it require retraining of the neural modules if the power network increases in size, making its application possible to only one component, a specific area, or the whole context of the power system.

Geometric analysis of alternative models of faulting at Yucca Mountain, Nevada

International Nuclear Information System (INIS)

Young, S.R.; Stirewalt, G.L.; Morris, A.P.

1993-01-01

Realistic cross section tectonic models must be retrodeformable to geologically reasonable pre-deformation states. Furthermore, it must be shown that geologic structures depicted on cross section tectonic models can have formed by kinematically viable deformation mechanisms. Simple shear (i.e., listric fault models) is consistent with extensional geologic structures and fault patterns described at Yucca Mountain, Nevada. Flexural slip models yield results similar to oblique simple shear mechanisms, although there is no strong geological evidence for flexural slip deformation. Slip-line deformation is shown to generate fault block geometrics that are a close approximation to observed fault block structures. However, slip-line deformation implies a degree of general ductility for which there is no direct geological evidence. Simple and hybrid 'domino' (i.e., planar fault) models do not adequately explain observed variations of fault block dip or the development of 'rollover' folds adjacent to major bounding faults. Overall tectonic extension may be underestimated because of syn-tectonic deposition (growth faulting) of the Tertiary pyroclastic rocks that comprise Yucca Mountain. A strong diagnostic test of the applicability of the domino model may be provided by improved knowledge of Tertiary volcanic stratigraphy

Combinatorial Optimization Algorithms for Dynamic Multiple Fault Diagnosis in Automotive and Aerospace Applications

Science.gov (United States)

Kodali, Anuradha

facility, respectively. The set-covering matrix encapsulates the relationship among the rows (tests or demand points) and columns (faults or locations) of the system at each time. By relaxing the coupling constraints using Lagrange multipliers, the DSC problem can be decoupled into independent subproblems, one for each column. Each subproblem is solved using the Viterbi decoding algorithm, and a primal feasible solution is constructed by modifying the Viterbi solutions via a heuristic. The proposed Viterbi-Lagrangian relaxation algorithm (VLRA) provides a measure of suboptimality via an approximate duality gap. As a major practical extension of the above problem, we also consider the problem of diagnosing faults with delayed test outcomes, termed delay-dynamic set-covering (DDSC), and experiment with real-world problems that exhibit masking faults. Also, we present simulation results on OR-library datasets (set-covering formulations are predominantly validated on these matrices in the literature), posed as facility location problems. Finally, we implement these algorithms to solve problems in aerospace and automotive applications. Firstly, we address the diagnostic ambiguity problem in aerospace and automotive applications by developing a dynamic fusion framework that includes dynamic multiple fault diagnosis algorithms. This improves the correct fault isolation rate, while minimizing the false alarm rates, by considering multiple faults instead of the traditional data-driven techniques based on single fault (class)-single epoch (static) assumption. The dynamic fusion problem is formulated as a maximum a posteriori decision problem of inferring the fault sequence based on uncertain outcomes of multiple binary classifiers over time. The fusion process involves three steps: the first step transforms the multi-class problem into dichotomies using error correcting output codes (ECOC), thereby solving the concomitant binary classification problems; the second step fuses the

Use of Fuzzy Logic Systems for Assessment of Primary Faults

Science.gov (United States)

Petrović, Ivica; Jozsa, Lajos; Baus, Zoran

2015-09-01

In electric power systems, grid elements are often subjected to very complex and demanding disturbances or dangerous operating conditions. Determining initial fault or cause of those states is a difficult task. When fault occurs, often it is an imperative to disconnect affected grid element from the grid. This paper contains an overview of possibilities for using fuzzy logic in an assessment of primary faults in the transmission grid. The tool for this task is SCADA system, which is based on information of currents, voltages, events of protection devices and status of circuit breakers in the grid. The function model described with the membership function and fuzzy logic systems will be presented in the paper. For input data, diagnostics system uses information of protection devices tripping, states of circuit breakers and measurements of currents and voltages before and after faults.

PRODIAG -- Dynamic qualitative analysis for process fault diagnosis

International Nuclear Information System (INIS)

Reifman, J.; Wei, T.Y.C.

1995-01-01

The authors present a method for handling the dynamic effects of process component malfunctions through time-independent rule-based diagnostic systems. The method's theory is discussed and a simplified version is implemented in the process diagnostic expert system PRODIAG. Simulation results from a full-scope operator training simulator of a nuclear power plant are used to illustrate the method

Analysis of core damage frequency from internal events: Expert judgment elicitation. Part 1: Expert panel results. Part 2: Project staff results

Energy Technology Data Exchange (ETDEWEB)

Wheeler, T A; Cramond, W R [Sandia National Laboratories, Albuquerque, NM (United States); Hora, S C [University of Hawii at Hilo (United States); Unwin, S D [Brookhaven National Laboratory (United States)

1989-04-01

Quantitative modeling techniques have limitations as to the resolution of important issues in probabilistic risk assessment (PRA). Not all issues can be resolved via the existing set of methods such as fault trees, event trees, statistical analyses, data collection, and computer simulation. Therefore, an expert judgment process was developed to address issues perceived as important to risk in the NUREG-1150 analysis but which could not be resolved with existing techniques. This process was applied to several issues that could significantly affect the internal event core damage frequencies of the PRAs performed on six light water reactors. Detailed descriptions of these issues and the results of the expert judgment elicitation are reported here, as well as an explanation of the methodology used and the procedure followed in performing the overall elicitation task. The process is time-consuming and expensive. However, the results are very useful, and represent an improvement over the draft NUREG-1150 analysis in the areas of expert selection, elicitation training, issue selection and presentation, elicitation of judgment and aggregation of results. The results are presented in two parts. Part documents the expert panel elicitations, where the most important issues were presented to a panel of experts convened from throughout the nuclear power risk assessment community. Part 2 documents the process by which the project staff performed expert judgment on other important issues, using the project staff as panel members. (author)

Techniques and implementation of the embedded rule-based expert system using Ada

Science.gov (United States)

Liberman, Eugene M.; Jones, Robert E.

1991-01-01

Ada is becoming an increasingly popular programming language for large Government-funded software projects. Ada with its portability, transportability, and maintainability lends itself well to today's complex programming environment. In addition, expert systems have also assured a growing role in providing human-like reasoning capability and expertise for computer systems. The integration of expert system technology with Ada programming language, specifically a rule-based expert system using an ART-Ada (Automated Reasoning Tool for Ada) system shell is discussed. The NASA Lewis Research Center was chosen as a beta test site for ART-Ada. The test was conducted by implementing the existing Autonomous Power EXpert System (APEX), a Lisp-base power expert system, in ART-Ada. Three components, the rule-based expert system, a graphics user interface, and communications software make up SMART-Ada (Systems fault Management with ART-Ada). The main objective, to conduct a beta test on the ART-Ada rule-based expert system shell, was achieved. The system is operational. New Ada tools will assist in future successful projects. ART-Ada is one such tool and is a viable alternative to the straight Ada code when an application requires a rule-based or knowledge-based approach.

Diagnostic Analyzer for Gearboxes (DAG): User's Guide. Version 3.1 for Microsoft Windows 3.1

Science.gov (United States)

Jammu, Vinay B.; Kourosh, Danai

1997-01-01

This documentation describes the Diagnostic Analyzer for Gearboxes (DAG) software for performing fault diagnosis of gearboxes. First, the user would construct a graphical representation of the gearbox using the gear, bearing, shaft, and sensor tools contained in the DAG software. Next, a set of vibration features obtained by processing the vibration signals recorded from the gearbox using a signal analyzer is required. Given this information, the DAG software uses an unsupervised neural network referred to as the Fault Detection Network (FDN) to identify the occurrence of faults, and a pattern classifier called Single Category-Based Classifier (SCBC) for abnormality scaling of individual vibration features. The abnormality-scaled vibration features are then used as inputs to a Structure-Based Connectionist Network (SBCN) for identifying faults in gearbox subsystems and components. The weights of the SBCN represent its diagnostic knowledge and are derived from the structure of the gearbox graphically presented in DAG. The outputs of SBCN are fault possibility values between 0 and 1 for individual subsystems and components in the gearbox with a 1 representing a definite fault and a 0 representing normality. This manual describes the steps involved in creating the diagnostic gearbox model, along with the options and analysis tools of the DAG software.

A Combined Fault Diagnosis Method for Power Transformer in Big Data Environment

Directory of Open Access Journals (Sweden)

Yan Wang

2017-01-01

Full Text Available The fault diagnosis method based on dissolved gas analysis (DGA is of great significance to detect the potential faults of the transformer and improve the security of the power system. The DGA data of transformer in smart grid have the characteristics of large quantity, multiple types, and low value density. In view of DGA big data’s characteristics, the paper first proposes a new combined fault diagnosis method for transformer, in which a variety of fault diagnosis models are used to make a preliminary diagnosis, and then the support vector machine is used to make the second diagnosis. The method adopts the intelligent complementary and blending thought, which overcomes the shortcomings of single diagnosis model in transformer fault diagnosis, and improves the diagnostic accuracy and the scope of application of the model. Then, the training and deployment strategy of the combined diagnosis model is designed based on Storm and Spark platform, which provides a solution for the transformer fault diagnosis in big data environment.

Model-based Diagnostics for Propellant Loading Systems

Data.gov (United States)

National Aeronautics and Space Administration — The loading of spacecraft propellants is a complex, risky operation. Therefore, diagnostic solutions are neces- sary to quickly identify when a fault occurs, so that...

Operation and Structure of an Artificial Intelligence Expert Consultative System for Reading and Learning.

Science.gov (United States)

Balajthy, Ernest

1989-01-01

The article examines decision-making expert systems and discusses their implications for diagnosis and prescription of reading difficulties. A detailed description of how a reading diagnostic expert system might operate to aid classroom teachers is followed by a discussion of advantages and limitations of expert systems for educational use.…

Distributed expert systems for nuclear reactor control

International Nuclear Information System (INIS)

Otaduy, P.J.

1992-01-01

A network of distributed expert systems is the heart of a prototype supervisory control architecture developed at the Oak Ridge National Laboratory (ORNL) for an advanced multimodular reactor. Eight expert systems encode knowledge on signal acquisition, diagnostics, safeguards, and control strategies in a hybrid rule-based, multiprocessing and object-oriented distributed computing environment. An interactive simulation of a power block consisting of three reactors and one turbine provides a realistic, testbed for performance analysis of the integrated control system in real-time. Implementation details and representative reactor transients are discussed

Research on Model-Based Fault Diagnosis for a Gas Turbine Based on Transient Performance

Directory of Open Access Journals (Sweden)

Detang Zeng

2018-01-01

Full Text Available It is essential to monitor and to diagnose faults in rotating machinery with a high thrust–weight ratio and complex structure for a variety of industrial applications, for which reliable signal measurements are required. However, the measured values consist of the true values of the parameters, the inertia of measurements, random errors and systematic errors. Such signals cannot reflect the true performance state and the health state of rotating machinery accurately. High-quality, steady-state measurements are necessary for most current diagnostic methods. Unfortunately, it is hard to obtain these kinds of measurements for most rotating machinery. Diagnosis based on transient performance is a useful tool that can potentially solve this problem. A model-based fault diagnosis method for gas turbines based on transient performance is proposed in this paper. The fault diagnosis consists of a dynamic simulation model, a diagnostic scheme, and an optimization algorithm. A high-accuracy, nonlinear, dynamic gas turbine model using a modular modeling method is presented that involves thermophysical properties, a component characteristic chart, and system inertial. The startup process is simulated using this model. The consistency between the simulation results and the field operation data shows the validity of the model and the advantages of transient accumulated deviation. In addition, a diagnostic scheme is designed to fulfill this process. Finally, cuckoo search is selected to solve the optimization problem in fault diagnosis. Comparative diagnostic results for a gas turbine before and after washing indicate the improved effectiveness and accuracy of the proposed method of using data from transient processes, compared with traditional methods using data from the steady state.

Enhanced Bank of Kalman Filters Developed and Demonstrated for In-Flight Aircraft Engine Sensor Fault Diagnostics

Science.gov (United States)

Kobayashi, Takahisa; Simon, Donald L.

2005-01-01

In-flight sensor fault detection and isolation (FDI) is critical to maintaining reliable engine operation during flight. The aircraft engine control system, which computes control commands on the basis of sensor measurements, operates the propulsion systems at the demanded conditions. Any undetected sensor faults, therefore, may cause the control system to drive the engine into an undesirable operating condition. It is critical to detect and isolate failed sensors as soon as possible so that such scenarios can be avoided. A challenging issue in developing reliable sensor FDI systems is to make them robust to changes in engine operating characteristics due to degradation with usage and other faults that can occur during flight. A sensor FDI system that cannot appropriately account for such scenarios may result in false alarms, missed detections, or misclassifications when such faults do occur. To address this issue, an enhanced bank of Kalman filters was developed, and its performance and robustness were demonstrated in a simulation environment. The bank of filters is composed of m + 1 Kalman filters, where m is the number of sensors being used by the control system and, thus, in need of monitoring. Each Kalman filter is designed on the basis of a unique fault hypothesis so that it will be able to maintain its performance if a particular fault scenario, hypothesized by that particular filter, takes place.

Fault morphology of the lyo Fault, the Median Tectonic Line Active Fault System

OpenAIRE

後藤, 秀昭

1996-01-01

In this paper, we investigated the various fault features of the lyo fault and depicted fault lines or detailed topographic map. The results of this paper are summarized as follows; 1) Distinct evidence of the right-lateral movement is continuously discernible along the lyo fault. 2) Active fault traces are remarkably linear suggesting that the angle of fault plane is high. 3) The lyo fault can be divided into four segments by jogs between left-stepping traces. 4) The mean slip rate is 1.3 ～ ...

A simulation-based expert system for nuclear power plant diagnostics

International Nuclear Information System (INIS)

Hassberger, J.A.; Lee, J.C.

1989-01-01

An expert system for diagnosing operational transients in a nuclear power plant is discussed. Hypothesis and test is used as the problem-solving strategy with hypotheses generated by an expert system that monitors the plant for patterns of data symptomatic of known failure modes. Fuzzy logic is employed as the inferencing mechanism with two complementary implication schemes to handle scenarios involving competing failures. Hypothesis testing is performed. An artificial intelligence framework based on a critical functions approach is used to deal with the complexity of a nuclear plant. A prototype system for diagnosing transients in the reactor coolant system of a pressurized water reactor has been developed to test the algorithms described here. Results are presented for the diagnosis of data from the Three Mile Island Unit 2 loss-of-feedwater/small-break loss-of-collant accident

Development of a low cost test rig for standalone WECS subject to electrical faults.

Science.gov (United States)

Himani; Dahiya, Ratna

2016-11-01

In this paper, a contribution to the development of low-cost wind turbine (WT) test rig for stator fault diagnosis of wind turbine generator is proposed. The test rig is developed using a 2.5kW, 1750 RPM DC motor coupled to a 1.5kW, 1500 RPM self-excited induction generator interfaced with a WT mathematical model in LabVIEW. The performance of the test rig is benchmarked with already proven wind turbine test rigs. In order to detect the stator faults using non-stationary signals in self-excited induction generator, an online fault diagnostic technique of DWT-based multi-resolution analysis is proposed. It has been experimentally proven that for varying wind conditions wavelet decomposition allows good differentiation between faulty and healthy conditions leading to an effective diagnostic procedure for wind turbine condition monitoring. Copyright © 2016 ISA. Published by Elsevier Ltd. All rights reserved.

Deep learning for automated drivetrain fault detection

DEFF Research Database (Denmark)

Bach-Andersen, Martin; Rømer-Odgaard, Bo; Winther, Ole

2018-01-01

A novel data-driven deep-learning system for large-scale wind turbine drivetrain monitoring applications is presented. It uses convolutional neural network processing on complex vibration signal inputs. The system is demonstrated to learn successfully from the actions of human diagnostic experts...... the fleet-wide diagnostic model performance. The analysis also explores the time dependence of the diagnostic performance, providing a detailed view of the timeliness and accuracy of the diagnostic outputs across the different architectures. Deep architectures are shown to outperform the human analyst...... as well as shallow-learning architectures, and the results demonstrate that when applied in a large-scale monitoring system, machine intelligence is now able to handle some of the most challenging diagnostic tasks related to wind turbines....

A Modular Neural Network Scheme Applied to Fault Diagnosis in Electric Power Systems

Directory of Open Access Journals (Sweden)

Agustín Flores

2014-01-01

Full Text Available This work proposes a new method for fault diagnosis in electric power systems based on neural modules. With this method the diagnosis is performed by assigning a neural module for each type of component comprising the electric power system, whether it is a transmission line, bus or transformer. The neural modules for buses and transformers comprise two diagnostic levels which take into consideration the logic states of switches and relays, both internal and back-up, with the exception of the neural module for transmission lines which also has a third diagnostic level which takes into account the oscillograms of fault voltages and currents as well as the frequency spectrums of these oscillograms, in order to verify if the transmission line had in fact been subjected to a fault. One important advantage of the diagnostic system proposed is that its implementation does not require the use of a network configurator for the system; it does not depend on the size of the power network nor does it require retraining of the neural modules if the power network increases in size, making its application possible to only one component, a specific area, or the whole context of the power system.

Reactor accident diagnostic expert system: DISKET

International Nuclear Information System (INIS)

Yoshida, Kazuo; Yokobayashi, Masao

1989-11-01

A reactor accident diagnostic system DISKET has been developed to identify the cause and the type of an abnormal transient of a nuclear power plant. The system is based on the knowledge engineering and consists of an inference engine IERIAS and a knowledge base. The main features of DISKET are the following: Time-varying characteristics of transient can be treated and knowledge base can be divided into several knowledge units to handle a lot of rules effectively. This report has been provided for the convenience of DISKET's users and consists of three parts. The first part is the description of the whole system, the details of the knowledge base of DISKET are described in the second part, and how to use the DISKET system is explained in the third part. (author)

Fault-Tolerant Vision for Vehicle Guidance in Agriculture

DEFF Research Database (Denmark)

Blas, Morten Rufus

, and aiding sensors such as GPS provide means to detect and isolate single faults in the system. In addition, learning is employed to adapt the system to variational changes in the natural environment. 3D vision is enhanced by learning texture and color information. Intensity gradients on small neighborhoods...... dropout of 3D vision, faults in classification, or other defects, redundant information should be utilized. Such information can be used to diagnose faulty behavior and to temporarily continue operation with a reduced set of sensors when faults or artifacts occur. Additional sensors include GPS receivers...... and inertial sensors. To fully utilize the possibilities in 3D vision, the system must also be able to learn and adapt to changing environments. By learning features of the environment new diagnostic relations can be generated by creating redundant feed-forward information about crop location. Also, by mapping...

Aircraft Engine Sensor/Actuator/Component Fault Diagnosis Using a Bank of Kalman Filters

Science.gov (United States)

Kobayashi, Takahisa; Simon, Donald L. (Technical Monitor)

2003-01-01

In this report, a fault detection and isolation (FDI) system which utilizes a bank of Kalman filters is developed for aircraft engine sensor and actuator FDI in conjunction with the detection of component faults. This FDI approach uses multiple Kalman filters, each of which is designed based on a specific hypothesis for detecting a specific sensor or actuator fault. In the event that a fault does occur, all filters except the one using the correct hypothesis will produce large estimation errors, from which a specific fault is isolated. In the meantime, a set of parameters that indicate engine component performance is estimated for the detection of abrupt degradation. The performance of the FDI system is evaluated against a nonlinear engine simulation for various engine faults at cruise operating conditions. In order to mimic the real engine environment, the nonlinear simulation is executed not only at the nominal, or healthy, condition but also at aged conditions. When the FDI system designed at the healthy condition is applied to an aged engine, the effectiveness of the FDI system is impacted by the mismatch in the engine health condition. Depending on its severity, this mismatch can cause the FDI system to generate incorrect diagnostic results, such as false alarms and missed detections. To partially recover the nominal performance, two approaches, which incorporate information regarding the engine s aging condition in the FDI system, will be discussed and evaluated. The results indicate that the proposed FDI system is promising for reliable diagnostics of aircraft engines.

Integrated Fault Diagnostics of Networks and IT Systems

Data.gov (United States)

National Aeronautics and Space Administration — The lecture of the Stanford-IVHM lecture series will give an overview of the approaches in building diagnostic solutions for networks and complex systems. The...

Incipient multiple fault diagnosis in real time with applications to large-scale systems

International Nuclear Information System (INIS)

Chung, H.Y.; Bien, Z.; Park, J.H.; Seon, P.H.

1994-01-01

By using a modified signed directed graph (SDG) together with the distributed artificial neutral networks and a knowledge-based system, a method of incipient multi-fault diagnosis is presented for large-scale physical systems with complex pipes and instrumentations such as valves, actuators, sensors, and controllers. The proposed method is designed so as to (1) make a real-time incipient fault diagnosis possible for large-scale systems, (2) perform the fault diagnosis not only in the steady-state case but also in the transient case as well by using a concept of fault propagation time, which is newly adopted in the SDG model, (3) provide with highly reliable diagnosis results and explanation capability of faults diagnosed as in an expert system, and (4) diagnose the pipe damage such as leaking, break, or throttling. This method is applied for diagnosis of a pressurizer in the Kori Nuclear Power Plant (NPP) unit 2 in Korea under a transient condition, and its result is reported to show satisfactory performance of the method for the incipient multi-fault diagnosis of such a large-scale system in a real-time manner

Reactor coolant pump monitoring and diagnostic system

International Nuclear Information System (INIS)

Singer, R.M.; Gross, K.C.; Walsh, M.; Humenik, K.E.

1990-01-01

In order to reliably and safely operate a nuclear power plant, it is necessary to continuously monitor the performance of numerous subsystems to confirm that the plant state is within its prescribed limits. An important function of a properly designed monitoring system is the detection of incipient faults in all subsystems (with the avoidance of false alarms) coupled with an information system that provides the operators with fault diagnosis, prognosis of fault progression and recommended (either automatic or prescriptive) corrective action. In this paper, such a system is described that has been applied to reactor coolant pumps. This system includes a sensitive pattern-recognition technique based upon the sequential probability ratio test (SPRT) that detects incipient faults from validated signals, an expert system embodying knowledge bases on pump and sensor performance, extensive hypertext files containing operating and emergency procedures as well as pump and sensor information and a graphical interface providing the operator with easily perceived information on the location and character of the fault as well as recommended corrective action. This system is in the prototype stage and is currently being validated utilizing data from a liquid-metal cooled fast reactor (EBR-II). 3 refs., 4 figs

Expert systems and nuclear safety

International Nuclear Information System (INIS)

Beltracchi, L.

1990-01-01

The US Nuclear Regulatory Commission (NRC) and the Electric Power Research Institute have initiated a broad-based exploration of means to evaluate the potential applications of expert systems in the nuclear industry. This exploratory effort will assess the use of expert systems to augment the diagnostic and decision-making capabilities of personnel with the goal of enhancing productivity, reliability, and performance. The initial research effort is the development and documentation of guidelines for verifying and validating (V and V) expert systems. An initial application of expert systems in the nuclear industry is to aid operations and maintenance personnel in decision-making tasks. The scope of the decision aiding covers all types of cognitive behavior consisting of skill, rule, and knowledge-based behavior. For example, procedure trackers were designed and tested to support rule-based behavior. Further, these systems automate many of the tedious, error-prone human monitoring tasks, thereby reducing the potential for human error. The paper version of the procedure contains the knowledge base and the rules and thus serves as the basis of the design verification of the procedure tracker. Person-in-the-loop tests serve as the basis for the validation of a procedure tracker. When conducting validation tests, it is important to ascertain that the human retains the locus of control in the use of the expert system

An artificial neural network ensemble method for fault diagnosis of proton exchange membrane fuel cell system

International Nuclear Information System (INIS)

Shao, Meng; Zhu, Xin-Jian; Cao, Hong-Fei; Shen, Hai-Feng

2014-01-01

The commercial viability of PEMFC (proton exchange membrane fuel cell) systems depends on using effective fault diagnosis technologies in PEMFC systems. However, many researchers have experimentally studied PEMFC (proton exchange membrane fuel cell) systems without considering certain fault conditions. In this paper, an ANN (artificial neural network) ensemble method is presented that improves the stability and reliability of the PEMFC systems. In the first part, a transient model giving it flexibility in application to some exceptional conditions is built. The PEMFC dynamic model is built and simulated using MATLAB. In the second, using this model and experiments, the mechanisms of four different faults in PEMFC systems are analyzed in detail. Third, the ANN ensemble for the fault diagnosis is built and modeled. This model is trained and tested by the data. The test result shows that, compared with the previous method for fault diagnosis of PEMFC systems, the proposed fault diagnosis method has higher diagnostic rate and generalization ability. Moreover, the partial structure of this method can be altered easily, along with the change of the PEMFC systems. In general, this method for diagnosis of PEMFC has value for certain applications. - Highlights: • We analyze the principles and mechanisms of the four faults in PEMFC (proton exchange membrane fuel cell) system. • We design and model an ANN (artificial neural network) ensemble method for the fault diagnosis of PEMFC system. • This method has high diagnostic rate and strong generalization ability

Physical Modeling for Anomaly Diagnostics and Prognostics, Phase II

Data.gov (United States)

National Aeronautics and Space Administration — Ridgetop developed an innovative, model-driven anomaly diagnostic and fault characterization system for electromechanical actuator (EMA) systems to mitigate...

Methods for Probabilistic Fault Diagnosis: An Electrical Power System Case Study

Science.gov (United States)

Ricks, Brian W.; Mengshoel, Ole J.

2009-01-01

Health management systems that more accurately and quickly diagnose faults that may occur in different technical systems on-board a vehicle will play a key role in the success of future NASA missions. We discuss in this paper the diagnosis of abrupt continuous (or parametric) faults within the context of probabilistic graphical models, more specifically Bayesian networks that are compiled to arithmetic circuits. This paper extends our previous research, within the same probabilistic setting, on diagnosis of abrupt discrete faults. Our approach and diagnostic algorithm ProDiagnose are domain-independent; however we use an electrical power system testbed called ADAPT as a case study. In one set of ADAPT experiments, performed as part of the 2009 Diagnostic Challenge, our system turned out to have the best performance among all competitors. In a second set of experiments, we show how we have recently further significantly improved the performance of the probabilistic model of ADAPT. While these experiments are obtained for an electrical power system testbed, we believe they can easily be transitioned to real-world systems, thus promising to increase the success of future NASA missions.

Diagnostics aid for mass spectrometer trouble-shooting

International Nuclear Information System (INIS)

Filby, E.E.; Rankin, R.A.; Webb, G.W.

1987-01-01

The ''MS Expert'' system provides problem diagnostics for instruments used in the Mass Spectrometry Laboratory (MSL). The most critical results generated on these mass spectrometers are the uranium concentration and isotopic content data used for process control and materials accountability at the Idaho Chemical Processing Plant. The two purposes of the system are: (1) to minimize instrument downtime and thereby provide the best possible support to the Plant, and (2) to improve long-term data quality. This system combines the knowledge of several experts on mass spectrometry to provide a diagnostic tool, and can make these skills avilable on a more timely basis. It integrates code written in the Pascal language with a knowledge base entered into a commercial expert system ''shell.'' The user performs some preliminary status checks, and then selects from among several broad diagnostic categories. These initial steps provide input to the rule base. The overall analysis provides the user with a set of possible solutions to the observed problems, graded as to their probabilities. Besides the trouble-shooting benefits expected from this system, it will also provide structures diagnostic training for lab personnel. In addition, development of the system knowledge base has already produced a better understanding of instrument behavior. Two key findings are that a good user interface is necessary for full acceptance of the tool, and a development system should include standard programming capabilities as well as the expert system shell. 22 refs., 5 figs

Diagnostics aid for mass spectrometer trouble-shooting

International Nuclear Information System (INIS)

Filby, E.E.; Rankin, R.A.; Webb, G.W.

1987-01-01

The MS Expert system provides problem diagnostics for instruments used in the Mass Spectrometry Laboratory (MSL). The most critical results generated on these mass spectrometers are the uranium concentration and isotopic content data used for process control and materials accountability at the Idaho General Processing Plant. The two purposes of the system are: (1) to minimize instrument downtime and thereby provide the best possible support to the Plant, and (2) to improve long-term data quality. This system combines the knowledge of several experts on mass spectrometry to provide a diagnostic tool, and can make these skills available on a more timely basis. It integrates code written in the Pascal language with a knowledge base entered into a commercial expert system shell. The user performs some preliminary status checks, and then selects from among several broad diagnostic categories. These initial steps provide input to the rule base. The overall analysis provides the user with a set of possible solutions to the observed problems, graded as to their probabilities. Besides the trouble-shooting benefits expected from this system, it also provides structured diagnostic training for lab personnel. In addition, development of the system knowledge base has already produced a better understanding of instrument behavior. Two key findings are that a good user interface is necessary for full acceptance of the tool, and, a development system should include standard programming capabilities as well as the expert system shell

The definition and diagnosis of cold hypersensitivity in the hands and feet: Finding from the experts survey.

Science.gov (United States)

Bae, Kwang-Ho; Jeong, Young-Seok; Go, Ho-Yeon; Sun, Seung-Ho; Kim, Tae-Hoon; Jung, Ki-Yong; Song, Yun-Kyung; Ko, Seong-Gyu; Choi, You-Kyung; Park, Jong-Hyeong; Lee, Siwoo; Lee, Youngseop; Jeon, Chan-Yong

2018-03-01

Cold hypersensitivity in the hands and feet (CHHF) is a symptom patients usually feel cold in their hands and feet, but not dealt with a disease in western medicine. However, it is often appealed by patients at a clinic of Korean medicine (KM), considered to be a sort of key diagnostic indicator, and actively treated by physicians. Nevertheless, there is no standardized diagnostic definition for CHHF. Therefore, we surveyed KM experts' opinions to address the clinical definition, diagnostic criteria, and other relevant things on CHHF. We developed a survey to assess the definition, diagnosis, causes, and accompanying symptoms on CHHF. 31 experts who work at specialized university hospitals affiliated with KM hospitals consented to participation. Experts responded to survey questions by selecting multiple-choice answers or stating their opinions. Vast majority of experts (83.8%) agreed with our definition on CHHF ("a feeling of cold as a symptom; that one's hands or feet become colder than those of average people in temperatures that are not normally perceived as cold"). 77.4% of experts considered subjective symptoms on CHHF were more important than medical instrument results. Constitution or genetic factors (87.1%) and stress (64.5%) were the most common causes reported for CHHF. This study offers an expert consensus regarding the themes, opinions, and experiences of practitioners with CHHF. Our results underscore the need for standardized definitions and diagnostic criteria for CHHF.

Process plant alarm diagnosis using synthesised fault tree knowledge

International Nuclear Information System (INIS)

Trenchard, A.J.

1990-01-01

The development of computer based tools, to assist process plant operators in their task of fault/alarm diagnosis, has received much attention over the last twenty five years. More recently, with the emergence of Artificial Intelligence (AI) technology, the research activity in this subject area has heightened. As a result, there are a great variety of fault diagnosis methodologies, using many different approaches to represent the fault propagation behaviour of process plant. These range in complexity from steady state quantitative models to more abstract definitions of the relationships between process alarms. Unfortunately, very few of the techniques have been tried and tested on process plant and even fewer have been judged to be commercial successes. One of the outstanding problems still remains the time and effort required to understand and model the fault propagation behaviour of each considered process. This thesis describes the development of an experimental knowledge based system (KBS) to diagnose process plant faults, as indicated by process variable alarms. In an attempt to minimise the modelling effort, the KBS has been designed to infer diagnoses using a fault tree representation of the process behaviour, generated using an existing fault tree synthesis package (FAULTFINDER). The process is described to FAULTFINDER as a configuration of unit models, derived from a standard model library or by tailoring existing models. The resultant alarm diagnosis methodology appears to work well for hard (non-rectifying) faults, but is likely to be less robust when attempting to diagnose intermittent faults and transient behaviour. The synthesised fault trees were found to contain the bulk of the information required for the diagnostic task, however, this needed to be augmented with extra information in certain circumstances. (author)

Fault tolerant control based on active fault diagnosis

DEFF Research Database (Denmark)

Niemann, Hans Henrik

2005-01-01

An active fault diagnosis (AFD) method will be considered in this paper in connection with a Fault Tolerant Control (FTC) architecture based on the YJBK parameterization of all stabilizing controllers. The architecture consists of a fault diagnosis (FD) part and a controller reconfiguration (CR......) part. The FTC architecture can be applied for additive faults, parametric faults, and for system structural changes. Only parametric faults will be considered in this paper. The main focus in this paper is on the use of the new approach of active fault diagnosis in connection with FTC. The active fault...... diagnosis approach is based on including an auxiliary input in the system. A fault signature matrix is introduced in connection with AFD, given as the transfer function from the auxiliary input to the residual output. This can be considered as a generalization of the passive fault diagnosis case, where...

Early fault detection and on-line diagnosis in real-time environments

Directory of Open Access Journals (Sweden)

Andreas Bye

1993-01-01

Full Text Available This paper describes an approach to fault detection and diagnosis involving the simultaneous employment of quantitative and qualitative reasoning techniques. We show that early identification of process anomalies by means of a separate fault detection module paves the way for a fast and accuratc follow-up diagnosis. The diagnosis task is dramatically simplified because the diagnostic inferences can be performed at the soonest possible time: when the detection module first spots deviations between its calculated reference points and the corresponding measurements from the process.

Fault diagnosis method based on FFT-RPCA-SVM for Cascaded-Multilevel Inverter.

Science.gov (United States)

Wang, Tianzhen; Qi, Jie; Xu, Hao; Wang, Yide; Liu, Lei; Gao, Diju

2016-01-01

Thanks to reduced switch stress, high quality of load wave, easy packaging and good extensibility, the cascaded H-bridge multilevel inverter is widely used in wind power system. To guarantee stable operation of system, a new fault diagnosis method, based on Fast Fourier Transform (FFT), Relative Principle Component Analysis (RPCA) and Support Vector Machine (SVM), is proposed for H-bridge multilevel inverter. To avoid the influence of load variation on fault diagnosis, the output voltages of the inverter is chosen as the fault characteristic signals. To shorten the time of diagnosis and improve the diagnostic accuracy, the main features of the fault characteristic signals are extracted by FFT. To further reduce the training time of SVM, the feature vector is reduced based on RPCA that can get a lower dimensional feature space. The fault classifier is constructed via SVM. An experimental prototype of the inverter is built to test the proposed method. Compared to other fault diagnosis methods, the experimental results demonstrate the high accuracy and efficiency of the proposed method. Copyright © 2015 ISA. Published by Elsevier Ltd. All rights reserved.

Application of expert systems in damage assessment of reinforced concrete structures

International Nuclear Information System (INIS)

Fazel Zarandi, M. H.; Sobhani, J.

2003-01-01

Expert systems are receiving great attentions in construction industry to support decision making processes in diagnostics, design, repair and rehabilitation of the structures. Although several expert systems have been examined in engineering since the 1970's, their applications in construction industry are rate. This was largely due to the lack of expert system tools available to represent the domain knowledge. Lack of flexibility, applicability, and robustness of the classical models, have forced the scientists to discover the ability of the expert systems in problem solving of civil engineering. This paper present an expert system for diagnosis the deterioration of concrete structures. This expert system emphasizes on cracking distress in reinforced concrete elements. A case study has been presented to examine and evaluate the proposed expert system. The system demonstrates a straightforward method for diagnosing the cause of reinforced concrete elements cracking

Feature Selection and Fault Classification of Reciprocating Compressors using a Genetic Algorithm and a Probabilistic Neural Network

Energy Technology Data Exchange (ETDEWEB)

Ahmed, M; Gu, F; Ball, A, E-mail: M.Ahmed@hud.ac.uk [Diagnostic Engineering Research Group, University of Huddersfield, HD1 3DH (United Kingdom)

2011-07-19

Reciprocating compressors are widely used in industry for various purposes and faults occurring in them can degrade their performance, consume additional energy and even cause severe damage to the machine. Vibration monitoring techniques are often used for early fault detection and diagnosis, but it is difficult to prescribe a given set of effective diagnostic features because of the wide variety of operating conditions and the complexity of the vibration signals which originate from the many different vibrating and impact sources. This paper studies the use of genetic algorithms (GAs) and neural networks (NNs) to select effective diagnostic features for the fault diagnosis of a reciprocating compressor. A large number of common features are calculated from the time and frequency domains and envelope analysis. Applying GAs and NNs to these features found that envelope analysis has the most potential for differentiating three common faults: valve leakage, inter-cooler leakage and a loose drive belt. Simultaneously, the spread parameter of the probabilistic NN was also optimised. The selected subsets of features were examined based on vibration source characteristics. The approach developed and the trained NN are confirmed as possessing general characteristics for fault detection and diagnosis.

Feature Selection and Fault Classification of Reciprocating Compressors using a Genetic Algorithm and a Probabilistic Neural Network

International Nuclear Information System (INIS)

Ahmed, M; Gu, F; Ball, A

2011-01-01

Reciprocating compressors are widely used in industry for various purposes and faults occurring in them can degrade their performance, consume additional energy and even cause severe damage to the machine. Vibration monitoring techniques are often used for early fault detection and diagnosis, but it is difficult to prescribe a given set of effective diagnostic features because of the wide variety of operating conditions and the complexity of the vibration signals which originate from the many different vibrating and impact sources. This paper studies the use of genetic algorithms (GAs) and neural networks (NNs) to select effective diagnostic features for the fault diagnosis of a reciprocating compressor. A large number of common features are calculated from the time and frequency domains and envelope analysis. Applying GAs and NNs to these features found that envelope analysis has the most potential for differentiating three common faults: valve leakage, inter-cooler leakage and a loose drive belt. Simultaneously, the spread parameter of the probabilistic NN was also optimised. The selected subsets of features were examined based on vibration source characteristics. The approach developed and the trained NN are confirmed as possessing general characteristics for fault detection and diagnosis.

Pitfalls in diagnostic radiology

International Nuclear Information System (INIS)

Peh, Wilfred C.G.

2015-01-01

Only textbook to focus primarily on the topic of pitfalls in diagnostic radiology. Highlights the pitfalls in a comprehensive and systematic manner. Written by experts in different imaging modalities and subspecialties from reputable centers across the world. The practice of diagnostic radiology has become increasingly complex, with the use of numerous imaging modalities and division into many subspecialty areas. It is becoming ever more difficult for subspecialist radiologists, general radiologists, and residents to keep up with the advances that are occurring year on year, and this is particularly true for less familiar topics. Failure to appreciate imaging pitfalls often leads to diagnostic error and misinterpretation, and potential medicolegal problems. Diagnostic errors may be due to various factors such as inadequate imaging technique, imaging artifacts, failure to recognize normal structures or variants, lack of correlation with clinical and other imaging findings, and poor training or inexperience. Many, if not most, of these factors are potentially recognizable, preventable, or correctable. This textbook, written by experts from reputable centers across the world, systematically and comprehensively highlights the pitfalls that may occur in diagnostic radiology. Both pitfalls specific to different modalities and techniques and those specific to particular organ systems are described with the help of numerous high-quality illustrations. Recognition of these pitfalls is crucial in helping the practicing radiologist to achieve a more accurate diagnosis.

Pitfalls in diagnostic radiology

Energy Technology Data Exchange (ETDEWEB)

Peh, Wilfred C.G. (ed.) [Khoo Teck Puat Hospital (Singapore). Dept. of Diagnostic Radiology

2015-04-01

Only textbook to focus primarily on the topic of pitfalls in diagnostic radiology. Highlights the pitfalls in a comprehensive and systematic manner. Written by experts in different imaging modalities and subspecialties from reputable centers across the world. The practice of diagnostic radiology has become increasingly complex, with the use of numerous imaging modalities and division into many subspecialty areas. It is becoming ever more difficult for subspecialist radiologists, general radiologists, and residents to keep up with the advances that are occurring year on year, and this is particularly true for less familiar topics. Failure to appreciate imaging pitfalls often leads to diagnostic error and misinterpretation, and potential medicolegal problems. Diagnostic errors may be due to various factors such as inadequate imaging technique, imaging artifacts, failure to recognize normal structures or variants, lack of correlation with clinical and other imaging findings, and poor training or inexperience. Many, if not most, of these factors are potentially recognizable, preventable, or correctable. This textbook, written by experts from reputable centers across the world, systematically and comprehensively highlights the pitfalls that may occur in diagnostic radiology. Both pitfalls specific to different modalities and techniques and those specific to particular organ systems are described with the help of numerous high-quality illustrations. Recognition of these pitfalls is crucial in helping the practicing radiologist to achieve a more accurate diagnosis.

Fault detection and isolation in systems with parametric faults

DEFF Research Database (Denmark)

Stoustrup, Jakob; Niemann, Hans Henrik

1999-01-01

The problem of fault detection and isolation of parametric faults is considered in this paper. A fault detection problem based on parametric faults are associated with internal parameter variations in the dynamical system. A fault detection and isolation method for parametric faults is formulated...

Employing expert systems for process control

International Nuclear Information System (INIS)

Ahrens, W.

1987-01-01

The characteristic features of expert systems are explained in detail, and the systems' application in process control engineering. Four points of main interest are there, namely: Applications for diagnostic tasks, for safety analyses, planning, and training and expert training. For the modelling of the technical systems involved in all four task fields mentioned above, an object-centred approach has shown to be the suitable method, as process control techniques are determined by technical objects that in principle are specified by data sheets, schematic representations, flow charts, and plans. The graphical surface allows these data to be taken into account, so that the object can be displayed in the way best suited to the individual purposes. (orig./GL) [de

Comparison of Cenozoic Faulting at the Savannah River Site to Fault Characteristics of the Atlantic Coast Fault Province: Implications for Fault Capability

International Nuclear Information System (INIS)

Cumbest, R.J.

2000-01-01

This study compares the faulting observed on the Savannah River Site and vicinity with the faults of the Atlantic Coastal Fault Province and concludes that both sets of faults exhibit the same general characteristics and are closely associated. Based on the strength of this association it is concluded that the faults observed on the Savannah River Site and vicinity are in fact part of the Atlantic Coastal Fault Province. Inclusion in this group means that the historical precedent established by decades of previous studies on the seismic hazard potential for the Atlantic Coastal Fault Province is relevant to faulting at the Savannah River Site. That is, since these faults are genetically related the conclusion of ''not capable'' reached in past evaluations applies.In addition, this study establishes a set of criteria by which individual faults may be evaluated in order to assess their inclusion in the Atlantic Coast Fault Province and the related association of the ''not capable'' conclusion

Entropy-Based Voltage Fault Diagnosis of Battery Systems for Electric Vehicles

Directory of Open Access Journals (Sweden)

Peng Liu

2018-01-01

Full Text Available The battery is a key component and the major fault source in electric vehicles (EVs. Ensuring power battery safety is of great significance to make the diagnosis more effective and predict the occurrence of faults, for the power battery is one of the core technologies of EVs. This paper proposes a voltage fault diagnosis detection mechanism using entropy theory which is demonstrated in an EV with a multiple-cell battery system during an actual operation situation. The preliminary analysis, after collecting and preprocessing the typical data periods from Operation Service and Management Center for Electric Vehicle (OSMC-EV in Beijing, shows that overvoltage fault for Li-ion batteries cell can be observed from the voltage curves. To further locate abnormal cells and predict faults, an entropy weight method is established to calculate the objective weight, which reduces the subjectivity and improves the reliability. The result clearly identifies the abnormity of cell voltage. The proposed diagnostic model can be used for EV real-time diagnosis without laboratory testing methods. It is more effective than traditional methods based on contrastive analysis.

A fuzzy logic intelligent diagnostic system for spacecraft integrated vehicle health management

Science.gov (United States)

Wu, G. Gordon

1995-01-01

Due to the complexity of future space missions and the large amount of data involved, greater autonomy in data processing is demanded for mission operations, training, and vehicle health management. In this paper, we develop a fuzzy logic intelligent diagnostic system to perform data reduction, data analysis, and fault diagnosis for spacecraft vehicle health management applications. The diagnostic system contains a data filter and an inference engine. The data filter is designed to intelligently select only the necessary data for analysis, while the inference engine is designed for failure detection, warning, and decision on corrective actions using fuzzy logic synthesis. Due to its adaptive nature and on-line learning ability, the diagnostic system is capable of dealing with environmental noise, uncertainties, conflict information, and sensor faults.

A Method for Aileron Actuator Fault Diagnosis Based on PCA and PGC-SVM

Directory of Open Access Journals (Sweden)

Wei-Li Qin

2016-01-01

Full Text Available Aileron actuators are pivotal components for aircraft flight control system. Thus, the fault diagnosis of aileron actuators is vital in the enhancement of the reliability and fault tolerant capability. This paper presents an aileron actuator fault diagnosis approach combining principal component analysis (PCA, grid search (GS, 10-fold cross validation (CV, and one-versus-one support vector machine (SVM. This method is referred to as PGC-SVM and utilizes the direct drive valve input, force motor current, and displacement feedback signal to realize fault detection and location. First, several common faults of aileron actuators, which include force motor coil break, sensor coil break, cylinder leakage, and amplifier gain reduction, are extracted from the fault quadrantal diagram; the corresponding fault mechanisms are analyzed. Second, the data feature extraction is performed with dimension reduction using PCA. Finally, the GS and CV algorithms are employed to train a one-versus-one SVM for fault classification, thus obtaining the optimal model parameters and assuring the generalization of the trained SVM, respectively. To verify the effectiveness of the proposed approach, four types of faults are introduced into the simulation model established by AMESim and Simulink. The results demonstrate its desirable diagnostic performance which outperforms that of the traditional SVM by comparison.

Research and design of distributed intelligence fault diagnosis system in nuclear power plant

International Nuclear Information System (INIS)

Liu Yongkuo; Xie Chunli; Cheng Shouyu; Xia Hong

2011-01-01

In order to further reduce the misoperation after the faults occurring of nuclear power plant, according to the function distribution of nuclear power equipment and the distributed control features of digital instrument control system, a nuclear power plant distributed condition monitoring and fault diagnosis system was researched and designed. Based on decomposition-integrated diagnostic thinking, a fuzzy neural network and RBF neural network was presented to do the distributed local diagnosis and multi-source information fusion technology for the global integrated diagnosis. Simulation results show that the developed distributed status monitoring and fault diagnosis system can diagnose more typical accidents of PWR to provide effective diagnosis and operation information. (authors)

In Depth Diagnostics for RF System Operation in the PEP-II B Factory

International Nuclear Information System (INIS)

Van Winkle, Daniel; Fox, John; Teytelman, Dmitry; SLAC

2005-01-01

The PEP-II RF systems incorporate numerous feedback loops in the low-level processing for impedance control and operating point regulation. The interaction of the multiple loops with the beam is complicated, and the systems incorporate online diagnostic tools to configure the feedback loops as well as to record fault files in the case of an RF abort. Rapid and consistent analysis of the RF-related beam aborts and other failures is critical to the reliable operation of the B-Factory, especially at the recently achieved high beam currents. Procedures and algorithms used to extract diagnostic information from time domain fault files are presented and illustrated via example interpretations of PEP-II fault file data. Example faults presented will highlight the subtle interpretation required to determine the root cause. Some such examples are: abort kicker firing asynchronously, klystron and cavity arcs, beam loss leading to longitudinal instability, tuner read back jumps and poorly configured low-level RF feedback loop

Expert system for assisting the repair operations on the control racks of the control rods assembly in a 900 MW PWR type reactor

International Nuclear Information System (INIS)

Monnier, B.; Doutre, J.L.; Franco, A.

1990-01-01

The expert system presented was developed for assisting the repair operations on the control equipment of the control rod assembly in a PWR type reactor. The expert system allows the representation of expert knowledge and diagnostic reasoning. The objective of the expert system is to achieve the most precise diagnostic and localizing of the breakdown elements, by processing the data acquired during breakdown. The development steps, the structure and the applications of the expert system are summarized. The expert system operates in an IBM PC equipped with a AMAIA 8 Mo card. A time schedule of 18 months is predicted [fr

Expert systems and advanced automation for space missions operations

Science.gov (United States)

Durrani, Sajjad H.; Perkins, Dorothy C.; Carlton, P. Douglas

1990-01-01

Increased complexity of space missions during the 1980s led to the introduction of expert systems and advanced automation techniques in mission operations. This paper describes several technologies in operational use or under development at the National Aeronautics and Space Administration's Goddard Space Flight Center. Several expert systems are described that diagnose faults, analyze spacecraft operations and onboard subsystem performance (in conjunction with neural networks), and perform data quality and data accounting functions. The design of customized user interfaces is discussed, with examples of their application to space missions. Displays, which allow mission operators to see the spacecraft position, orientation, and configuration under a variety of operating conditions, are described. Automated systems for scheduling are discussed, and a testbed that allows tests and demonstrations of the associated architectures, interface protocols, and operations concepts is described. Lessons learned are summarized.

Automated fault-management in a simulated spaceflight micro-world

Science.gov (United States)

Lorenz, Bernd; Di Nocera, Francesco; Rottger, Stefan; Parasuraman, Raja

2002-01-01

BACKGROUND: As human spaceflight missions extend in duration and distance from Earth, a self-sufficient crew will bear far greater onboard responsibility and authority for mission success. This will increase the need for automated fault management (FM). Human factors issues in the use of such systems include maintenance of cognitive skill, situational awareness (SA), trust in automation, and workload. This study examine the human performance consequences of operator use of intelligent FM support in interaction with an autonomous, space-related, atmospheric control system. METHODS: An expert system representing a model-base reasoning agent supported operators at a low level of automation (LOA) by a computerized fault finding guide, at a medium LOA by an automated diagnosis and recovery advisory, and at a high LOA by automate diagnosis and recovery implementation, subject to operator approval or veto. Ten percent of the experimental trials involved complete failure of FM support. RESULTS: Benefits of automation were reflected in more accurate diagnoses, shorter fault identification time, and reduced subjective operator workload. Unexpectedly, fault identification times deteriorated more at the medium than at the high LOA during automation failure. Analyses of information sampling behavior showed that offloading operators from recovery implementation during reliable automation enabled operators at high LOA to engage in fault assessment activities CONCLUSIONS: The potential threat to SA imposed by high-level automation, in which decision advisories are automatically generated, need not inevitably be counteracted by choosing a lower LOA. Instead, freeing operator cognitive resources by automatic implementation of recover plans at a higher LOA can promote better fault comprehension, so long as the automation interface is designed to support efficient information sampling.

A novelty detection diagnostic methodology for gearboxes operating under fluctuating operating conditions using probabilistic techniques

Science.gov (United States)

Schmidt, S.; Heyns, P. S.; de Villiers, J. P.

2018-02-01

In this paper, a fault diagnostic methodology is developed which is able to detect, locate and trend gear faults under fluctuating operating conditions when only vibration data from a single transducer, measured on a healthy gearbox are available. A two-phase feature extraction and modelling process is proposed to infer the operating condition and based on the operating condition, to detect changes in the machine condition. Information from optimised machine and operating condition hidden Markov models are statistically combined to generate a discrepancy signal which is post-processed to infer the condition of the gearbox. The discrepancy signal is processed and combined with statistical methods for automatic fault detection and localisation and to perform fault trending over time. The proposed methodology is validated on experimental data and a tacholess order tracking methodology is used to enhance the cost-effectiveness of the diagnostic methodology.

The Design and Implementation of a Remote Fault Reasoning Diagnosis System for Meteorological Satellites Data Acquisition

Directory of Open Access Journals (Sweden)

Zhu Jie

2017-01-01

Full Text Available Under the background of the trouble shooting requirements of FENGYUN-3 (FY-3 meteorological satellites data acquisition in domestic and oversea ground stations, a remote fault reasoning diagnosis system is developed by Java 1.6 in eclipse 3.6 platform. The general framework is analyzed, the workflow is introduced. Based on the system, it can realize the remote and centralized monitoring of equipment running status in ground stations，triggering automatic fault diagnosis and rule based fault reasoning by parsing the equipment quality logs, generating trouble tickets and importing expert experience database, providing text and graphics query methods. Through the practical verification, the system can assist knowledge engineers in remote precise and rapid fault location with friendly graphical user interface, boost the fault diagnosis efficiency, enhance the remote monitoring ability of integrity operating control system. The system has a certain practical significance to improve reliability of FY-3 meteorological satellites data acquisition.

Bond graphs for modelling, control and fault diagnosis of engineering systems

CERN Document Server

2017-01-01

This book presents theory and latest application work in Bond Graph methodology with a focus on: • Hybrid dynamical system models, • Model-based fault diagnosis, model-based fault tolerant control, fault prognosis • and also addresses • Open thermodynamic systems with compressible fluid flow, • Distributed parameter models of mechanical subsystems. In addition, the book covers various applications of current interest ranging from motorised wheelchairs, in-vivo surgery robots, walking machines to wind-turbines.The up-to-date presentation has been made possible by experts who are active members of the worldwide bond graph modelling community. This book is the completely revised 2nd edition of the 2011 Springer compilation text titled Bond Graph Modelling of Engineering Systems – Theory, Applications and Software Support. It extends the presentation of theory and applications of graph methodology by new developments and latest research results. Like the first edition, this book addresses readers in a...

Experimental Investigation for Fault Diagnosis Based on a Hybrid Approach Using Wavelet Packet and Support Vector Classification

Directory of Open Access Journals (Sweden)

Pengfei Li

2014-01-01

Full Text Available To deal with the difficulty to obtain a large number of fault samples under the practical condition for mechanical fault diagnosis, a hybrid method that combined wavelet packet decomposition and support vector classification (SVC is proposed. The wavelet packet is employed to decompose the vibration signal to obtain the energy ratio in each frequency band. Taking energy ratios as feature vectors, the pattern recognition results are obtained by the SVC. The rolling bearing and gear fault diagnostic results of the typical experimental platform show that the present approach is robust to noise and has higher classification accuracy and, thus, provides a better way to diagnose mechanical faults under the condition of small fault samples.

Team building and diagnostic training

International Nuclear Information System (INIS)

Bulmer, S.

1987-01-01

While developing a commercial training program to improve teamwork in control room crews, General Electric's Nuclear Training Services made an important discovery. Traditional training methods for developing teamwork and enhancing diagnostics capabilities are incomplete. Traditional methods generally help, but fail to fulfill the long-term needs of most teams. Teamwork has been treated as a short-term performance problem. Traditional diagnostic training suffers from a similar problem. Too often, it covers only the basic principles of decision-making, ignoring the development of expert diagnostic capabilities. In response to this discovery, they have developed comprehensive training in Team Building and Diagnostics

Aircraft engine sensor fault diagnostics using an on-line OBEM update method.

Directory of Open Access Journals (Sweden)

Xiaofeng Liu

Full Text Available This paper proposed a method to update the on-line health reference baseline of the On-Board Engine Model (OBEM to maintain the effectiveness of an in-flight aircraft sensor Fault Detection and Isolation (FDI system, in which a Hybrid Kalman Filter (HKF was incorporated. Generated from a rapid in-flight engine degradation, a large health condition mismatch between the engine and the OBEM can corrupt the performance of the FDI. Therefore, it is necessary to update the OBEM online when a rapid degradation occurs, but the FDI system will lose estimation accuracy if the estimation and update are running simultaneously. To solve this problem, the health reference baseline for a nonlinear OBEM was updated using the proposed channel controller method. Simulations based on the turbojet engine Linear-Parameter Varying (LPV model demonstrated the effectiveness of the proposed FDI system in the presence of substantial degradation, and the channel controller can ensure that the update process finishes without interference from a single sensor fault.

Incorporating fuzzy data and logical relations in the design of expert systems for nuclear reactors

International Nuclear Information System (INIS)

Guth, M.A.S.

1987-01-01

This paper applies the method of assigning probability in Dempster-Shafer Theory (DST) to the components of rule-based expert systems used in the control of nuclear reactors. Probabilities are assigned to premises, consequences, and rules themselves. This paper considers how uncertainty can propagate through a system of Boolean equations, such as fault trees or expert systems. The probability masses assigned to primary initiating events in the expert system can be derived from observing a nuclear reactor in operation or based on engineering knowledge of the reactor parts. Use of DST mass assignments offers greater flexibility to the construction of expert systems in two important respects. First, DST mass assignments have the advantage over classical probability methods of accommodating when necessary uncommitted probability assignments. Thus the DST probability framework can incorporate expert system inputs from imprecise or fuzzy data. Second, DST applied to the Boolean rules themselves leads to a probabilistic logic, where a given rule may be valid with probability less than unity: fuzzy logical rules

Research on fault diagnosis with SDG method for nuclear power plant

International Nuclear Information System (INIS)

Liu Yongkuo; Liu Zhen; Wu Xiaotian

2014-01-01

Abstract: The diagnosis of the operational state of a nuclear power plant (NPP) plays an important role for the safety and reliability of NPP operation. In this paper, the qualitative method for fault diagnosis based on signed directed graph (SDG) was applied in a complex NPP system because the mathematical model of NPP is difficult to be built. The reactor coolant system (RCS) was taken as the diagnostic object, and the approach of building SDG model was presented and the SDG model of the RCS was built. Based on the SDG model, a fault diagnosis system of RCS was developed, and the steam generator tube rupture (SGTR) and rod ejection accidents were taken as example to analyze the process of diagnosis inference. The simulation results show that the method based on SDG can effectively diagnose the fault in RCS, and it can also provide good explanation for the fault propagation paths. Therefore, this method can help operators to make correct decisions. (authors)

Development of Monitoring and Diagnostic Methods for Robots Used In Remediation of Waste Sites - Final Report

International Nuclear Information System (INIS)

Martin, M.

2000-01-01

This project is the first evaluation of model-based diagnostics to hydraulic robot systems. A greater understanding of fault detection for hydraulic robots has been gained, and a new theoretical fault detection model developed and evaluated

Simultaneous-Fault Diagnosis of Automotive Engine Ignition Systems Using Prior Domain Knowledge and Relevance Vector Machine

Directory of Open Access Journals (Sweden)

Chi-Man Vong

2013-01-01

Full Text Available Engine ignition patterns can be analyzed to identify the engine fault according to both the specific prior domain knowledge and the shape features of the patterns. One of the challenges in ignition system diagnosis is that more than one fault may appear at a time. This kind of problem refers to simultaneous-fault diagnosis. Another challenge is the acquisition of a large amount of costly simultaneous-fault ignition patterns for constructing the diagnostic system because the number of the training patterns depends on the combination of different single faults. The above problems could be resolved by the proposed framework combining feature extraction, probabilistic classification, and decision threshold optimization. With the proposed framework, the features of the single faults in a simultaneous-fault pattern are extracted and then detected using a new probabilistic classifier, namely, pairwise coupling relevance vector machine, which is trained with single-fault patterns only. Therefore, the training dataset of simultaneous-fault patterns is not necessary. Experimental results show that the proposed framework performs well for both single-fault and simultaneous-fault diagnoses and is superior to the existing approach.

A Framework to Debug Diagnostic Matrices

Science.gov (United States)

Kodal, Anuradha; Robinson, Peter; Patterson-Hine, Ann

2013-01-01

Diagnostics is an important concept in system health and monitoring of space operations. Many of the existing diagnostic algorithms utilize system knowledge in the form of diagnostic matrix (D-matrix, also popularly known as diagnostic dictionary, fault signature matrix or reachability matrix) gleaned from physical models. But, sometimes, this may not be coherent to obtain high diagnostic performance. In such a case, it is important to modify this D-matrix based on knowledge obtained from other sources such as time-series data stream (simulated or maintenance data) within the context of a framework that includes the diagnostic/inference algorithm. A systematic and sequential update procedure, diagnostic modeling evaluator (DME) is proposed to modify D-matrix and wrapper logic considering least expensive solution first. This iterative procedure includes conditions ranging from modifying 0s and 1s in the matrix, or adding/removing the rows (failure sources) columns (tests). We will experiment this framework on datasets from DX challenge 2009.

From fault classification to fault tolerance for multi-agent systems

CERN Document Server

Potiron, Katia; Taillibert, Patrick

2013-01-01

Faults are a concern for Multi-Agent Systems (MAS) designers, especially if the MAS are built for industrial or military use because there must be some guarantee of dependability. Some fault classification exists for classical systems, and is used to define faults. When dependability is at stake, such fault classification may be used from the beginning of the system's conception to define fault classes and specify which types of faults are expected. Thus, one may want to use fault classification for MAS; however, From Fault Classification to Fault Tolerance for Multi-Agent Systems argues that

Summary: beyond fault trees to fault graphs

International Nuclear Information System (INIS)

Alesso, H.P.; Prassinos, P.; Smith, C.F.

1984-09-01

Fault Graphs are the natural evolutionary step over a traditional fault-tree model. A Fault Graph is a failure-oriented directed graph with logic connectives that allows cycles. We intentionally construct the Fault Graph to trace the piping and instrumentation drawing (P and ID) of the system, but with logical AND and OR conditions added. Then we evaluate the Fault Graph with computer codes based on graph-theoretic methods. Fault Graph computer codes are based on graph concepts, such as path set (a set of nodes traveled on a path from one node to another) and reachability (the complete set of all possible paths between any two nodes). These codes are used to find the cut-sets (any minimal set of component failures that will fail the system) and to evaluate the system reliability

Fault-related clay authigenesis along the Moab Fault: Implications for calculations of fault rock composition and mechanical and hydrologic fault zone properties

Science.gov (United States)

Solum, J.G.; Davatzes, N.C.; Lockner, D.A.

2010-01-01

The presence of clays in fault rocks influences both the mechanical and hydrologic properties of clay-bearing faults, and therefore it is critical to understand the origin of clays in fault rocks and their distributions is of great importance for defining fundamental properties of faults in the shallow crust. Field mapping shows that layers of clay gouge and shale smear are common along the Moab Fault, from exposures with throws ranging from 10 to ???1000 m. Elemental analyses of four locations along the Moab Fault show that fault rocks are enriched in clays at R191 and Bartlett Wash, but that this clay enrichment occurred at different times and was associated with different fluids. Fault rocks at Corral and Courthouse Canyons show little difference in elemental composition from adjacent protolith, suggesting that formation of fault rocks at those locations is governed by mechanical processes. Friction tests show that these authigenic clays result in fault zone weakening, and potentially influence the style of failure along the fault (seismogenic vs. aseismic) and potentially influence the amount of fluid loss associated with coseismic dilation. Scanning electron microscopy shows that authigenesis promotes that continuity of slip surfaces, thereby enhancing seal capacity. The occurrence of the authigenesis, and its influence on the sealing properties of faults, highlights the importance of determining the processes that control this phenomenon. ?? 2010 Elsevier Ltd.

A gas turbine diagnostic approach with transient measurements.

OpenAIRE

Li, Y. G.

2003-01-01

Most gas turbine performance analysis based diagnostic methods use the information from steady state measurements. Unfortunately, steady state measurement may not be obtained easily in some situations, and some types of gas turbine fault contribute little to performance deviation at steady state operating conditions but significantly during transient processes. Therefore, gas turbine diagnostics with transient measurement is superior to that with steady state measurement. In this paper, an ac...

3SE: Expert system for the survey of electric sources - CPN of Bugey

International Nuclear Information System (INIS)

Ancelin, J.; Cheriaux, F.; Drelon, R.; Gaussot, J.P.; Marion, B.; Maurin, S.; Pichot, D.; Sancerni, G.; Voisin, C.; Legaud, P.

1990-01-01

The 3SE is an expert system for surveying the electric sources of a 900 MW PWR nuclear power plant. The main objectives of the expert system are: to provide a continuous and a real time support for electric faults data processing; to provide assistance in the electric equipment maintenance; to contribute to the instruction of operators as well as to the data base management of the electric system. Data bases and artificial intelligence techniques are applied. The system's application is based on the accurate knowledge of the nuclear power plant operation and topology, as well as on a model approach. The expert system is applied in the section 2 of the Bugey nuclear power plant. The system which required the effort of 20 engineers x years, is an example of the progress performed in the artificial intelligence field [fr

Fast architecture-level synthesis of fault-tolerant flow-based microfluidic biochips

DEFF Research Database (Denmark)

Huang, Wei Lun; Gupta, Ankur; Roy, Sudip

2017-01-01

Microfluidic-based lab-on-a-chips have emerged as a popular technology for implementation of different biochemical test protocols used in medical diagnostics. However, in the manufacturing process or during operation of such chips, some faults may occur that leads to damage of the chip, which...

Demonstration of artificial intelligence technology for transit railcar diagnostics

Science.gov (United States)

1999-01-01

This report will be of interest to railcar maintenance professionals concerned with improving railcar maintenance fault-diagnostic capabilities through the use of artificial intelligence (AI) technologies. It documents the results of a demonstration ...

An expert system for vibration based diagnostics of rotating machines

International Nuclear Information System (INIS)

Korteniemi, A.

1990-01-01

Very often changes in the mechanical condition of the rotating machinery can be observed as changes in its vibration. This paper presents an expert system for vibration-based diagnosis of rotating machines by describing the architecture of the developed prototype system. The importance of modelling the problem solving knowledge as well as the domain knowledge is emphasized by presenting the knowledge in several levels

Optimal Sequential Diagnostic Strategy Generation Considering Test Placement Cost for Multimode Systems

Directory of Open Access Journals (Sweden)

Shigang Zhang

2015-10-01

Full Text Available Sequential fault diagnosis is an approach that realizes fault isolation by executing the optimal test step by step. The strategy used, i.e., the sequential diagnostic strategy, has great influence on diagnostic accuracy and cost. Optimal sequential diagnostic strategy generation is an important step in the process of diagnosis system construction, which has been studied extensively in the literature. However, previous algorithms either are designed for single mode systems or do not consider test placement cost. They are not suitable to solve the sequential diagnostic strategy generation problem considering test placement cost for multimode systems. Therefore, this problem is studied in this paper. A formulation is presented. Two algorithms are proposed, one of which is realized by system transformation and the other is newly designed. Extensive simulations are carried out to test the effectiveness of the algorithms. A real-world system is also presented. All the results show that both of them have the ability to solve the diagnostic strategy generation problem, and they have different characteristics.

Optimal Sequential Diagnostic Strategy Generation Considering Test Placement Cost for Multimode Systems

Science.gov (United States)

Zhang, Shigang; Song, Lijun; Zhang, Wei; Hu, Zheng; Yang, Yongmin

2015-01-01

Sequential fault diagnosis is an approach that realizes fault isolation by executing the optimal test step by step. The strategy used, i.e., the sequential diagnostic strategy, has great influence on diagnostic accuracy and cost. Optimal sequential diagnostic strategy generation is an important step in the process of diagnosis system construction, which has been studied extensively in the literature. However, previous algorithms either are designed for single mode systems or do not consider test placement cost. They are not suitable to solve the sequential diagnostic strategy generation problem considering test placement cost for multimode systems. Therefore, this problem is studied in this paper. A formulation is presented. Two algorithms are proposed, one of which is realized by system transformation and the other is newly designed. Extensive simulations are carried out to test the effectiveness of the algorithms. A real-world system is also presented. All the results show that both of them have the ability to solve the diagnostic strategy generation problem, and they have different characteristics. PMID:26457709

Third Conference on Artificial Intelligence for Space Applications, part 1

Science.gov (United States)

Denton, Judith S. (Compiler); Freeman, Michael S. (Compiler); Vereen, Mary (Compiler)

1987-01-01

The application of artificial intelligence to spacecraft and aerospace systems is discussed. Expert systems, robotics, space station automation, fault diagnostics, parallel processing, knowledge representation, scheduling, man-machine interfaces and neural nets are among the topics discussed.

Expert system for assisting the diagnostic and localisation of breakdowns on the fuel elements loading machine

International Nuclear Information System (INIS)

Merlin, J.; Pradal, B.

1990-01-01

An expert system is developed in order to minimize the time lost through breakdowns of the fuel loading device. The expert system developed by FRAMATOME uses MAINTEX software. The expert systems MACHA and SEDMAC were designed respectively for use on 1300 MWe and 900 MWe loading machines [fr

Cooperative research and development for artificial intelligence based reactor diagnostic system

International Nuclear Information System (INIS)

Reifman, J.; Wei, T.Y.C.; Abboud, R.G.; Chasensky, T.M.

1994-01-01

Artificial Intelligence (AI) techniques in the form of knowledge-based Expert Systems (ESs) have been proposed to provide on-line decision-making support for plant operators during both normal and emergency conditions. However, in spite of the great interest in these advanced techniques, their application in the diagnosis of large-scale processes has not yet reached its full potential because of limitations of the knowledge base. These limitations include problems with knowledge acquisition and the use of an event-oriented approach for process diagnosis. To investigate the capabilities of this two-level hierarchical knowledge structure, Commonwealth Research Corporation (CRC) and Argonne National Laboratory (ANL)are collaborating on a DOE-sponsored Cooperative Research and Development Agreement (CRADA) project to perform feasibility studies on the proposed diagnostic system. Investigations are being performed in the construction of a physics-based plant level process diagnostic ES and the characterization of component-level fault project is to develop a computer-based system using this Al approach to assist process plant operators during off-normal plant conditions. The proposed computer-based system will use T-H signals complemented by other non-T-H signals available in the data stream to provide the process operator with the component which most likely caused the observed process disturbance. To demonstrate the scale-up feasibility of the proposed diagnostic system it is being developed for use with the Chemical Volume Control System (CVCS) of a nuclear power plant. This is an ongoing multi-year project and the remainder of this paper presents a mid-term status report

Fault tolerant control for uncertain systems with parametric faults

DEFF Research Database (Denmark)

Niemann, Hans Henrik; Poulsen, Niels Kjølstad

2006-01-01

A fault tolerant control (FTC) architecture based on active fault diagnosis (AFD) and the YJBK (Youla, Jarb, Bongiorno and Kucera)parameterization is applied in this paper. Based on the FTC architecture, fault tolerant control of uncertain systems with slowly varying parametric faults...... is investigated. Conditions are given for closed-loop stability in case of false alarms or missing fault detection/isolation....

LAMPF first-fault identifier for fast transient faults

International Nuclear Information System (INIS)

Swanson, A.R.; Hill, R.E.

1979-01-01

The LAMPF accelerator is presently producing 800-MeV proton beams at 0.5 mA average current. Machine protection for such a high-intensity accelerator requires a fast shutdown mechanism, which can turn off the beam within a few microseconds of the occurrence of a machine fault. The resulting beam unloading transients cause the rf systems to exceed control loop tolerances and consequently generate multiple fault indications for identification by the control computer. The problem is to isolate the primary fault or cause of beam shutdown while disregarding as many as 50 secondary fault indications that occur as a result of beam shutdown. The LAMPF First-Fault Identifier (FFI) for fast transient faults is operational and has proven capable of first-fault identification. The FFI design utilized features of the Fast Protection System that were previously implemented for beam chopping and rf power conservation. No software changes were required

Detection of inter-turn faults in transformer winding using the capacitor discharge method

Science.gov (United States)

Michna, Michał; Wilk, Andrzej; Ziółko, Michał; Wołoszyk, Marek; Swędrowski, Leon; Szwangruber, Piotr

2017-12-01

The paper presents results of an analysis of inter-turn fault effects on the voltage and current waveforms of a capacitor discharge through transformer windings. The research was conducted in the frame of the Facility of Antiproton and Ion Research project which goal is to build a new international accelerator facility that utilizes superconducting magnets. For the sake of electrical quality assurance of the superconducting magnet circuits, a measurement and diagnostic system is currently under development at Gdansk University of Technology (GUT). Appropriate measurements and simulations of the special transformer system were performed to verify the proposed diagnostic method. In order to take into account the nonlinearity and hysteresis of the magnetic yoke, a novel mathematical model of the transformer was developed. A special test bench was constructed to emulate the inter-turn faults within transformer windings.

Detection of inter-turn faults in transformer winding using the capacitor discharge method

Directory of Open Access Journals (Sweden)

Michna Michał

2017-12-01

Full Text Available The paper presents results of an analysis of inter-turn fault effects on the voltage and current waveforms of a capacitor discharge through transformer windings. The research was conducted in the frame of the Facility of Antiproton and Ion Research project which goal is to build a new international accelerator facility that utilizes superconducting magnets. For the sake of electrical quality assurance of the superconducting magnet circuits, a measurement and diagnostic system is currently under development at Gdansk University of Technology (GUT. Appropriate measurements and simulations of the special transformer system were performed to verify the proposed diagnostic method. In order to take into account the nonlinearity and hysteresis of the magnetic yoke, a novel mathematical model of the transformer was developed. A special test bench was constructed to emulate the inter-turn faults within transformer windings.

System Diagnostic Builder - A rule generation tool for expert systems that do intelligent data evaluation. [applied to Shuttle Mission Simulator

Science.gov (United States)

Nieten, Joseph; Burke, Roger

1993-01-01

Consideration is given to the System Diagnostic Builder (SDB), an automated knowledge acquisition tool using state-of-the-art AI technologies. The SDB employs an inductive machine learning technique to generate rules from data sets that are classified by a subject matter expert. Thus, data are captured from the subject system, classified, and used to drive the rule generation process. These rule bases are used to represent the observable behavior of the subject system, and to represent knowledge about this system. The knowledge bases captured from the Shuttle Mission Simulator can be used as black box simulations by the Intelligent Computer Aided Training devices. The SDB can also be used to construct knowledge bases for the process control industry, such as chemical production or oil and gas production.

Scaling-Up the Functional Diagnostic Systems

International Nuclear Information System (INIS)

Mohamed, A.H.

2008-01-01

Functional diagnostic systems received a lot of attention in the last decade. They have proven their powerful for diagnosis the new faults of some complex systems. But, they still have some complexity in both the representation and reasoning about the large-scale systems. This paper introduces a new functional diagnostic system that can divide its small functions into main and auxiliary ones. This process enables the diagnostic system to scale -up the representation of the tested system and simplify the diagnostic mechanism tasks. Thus, it can improve both the representation and reasoning complexity. Also,it can decrease the required analysis, cost, and time. Proposed system can be applied for a wide area of the large-scale systems. It has been proven its acceptance to be applied practically for the Complex real-time systems

The effect of information types on diagnostic strategies in the information aid

International Nuclear Information System (INIS)

Kim, Jong Hyun; Seong, Poong Hyun

2007-01-01

Through experiments, this paper investigates the compatibility of information types with the diagnostic strategy in information aid. Compatibility with operator strategies is an important requirement for information aiding systems in nuclear power plants (NPPs). This paper used three typical types of information aids for MCR operators to investigate the effect of the aids on diagnostic strategies: 'alarm (A),' 'hypothesis on faults (H),' and 'hypothesis on faults and expected symptoms (HS).' The experimental results indicate that the effectiveness of information aid types can vary, dependent on the strategies subjects employ. The results also show that the HS aid improved the diagnosis performance in the hypothesis-and-test strategy

Why the 2002 Denali fault rupture propagated onto the Totschunda fault: implications for fault branching and seismic hazards

Science.gov (United States)

Schwartz, David P.; Haeussler, Peter J.; Seitz, Gordon G.; Dawson, Timothy E.

2012-01-01

The propagation of the rupture of the Mw7.9 Denali fault earthquake from the central Denali fault onto the Totschunda fault has provided a basis for dynamic models of fault branching in which the angle of the regional or local prestress relative to the orientation of the main fault and branch plays a principal role in determining which fault branch is taken. GeoEarthScope LiDAR and paleoseismic data allow us to map the structure of the Denali-Totschunda fault intersection and evaluate controls of fault branching from a geological perspective. LiDAR data reveal the Denali-Totschunda fault intersection is structurally simple with the two faults directly connected. At the branch point, 227.2 km east of the 2002 epicenter, the 2002 rupture diverges southeast to become the Totschunda fault. We use paleoseismic data to propose that differences in the accumulated strain on each fault segment, which express differences in the elapsed time since the most recent event, was one important control of the branching direction. We suggest that data on event history, slip rate, paleo offsets, fault geometry and structure, and connectivity, especially on high slip rate-short recurrence interval faults, can be used to assess the likelihood of branching and its direction. Analysis of the Denali-Totschunda fault intersection has implications for evaluating the potential for a rupture to propagate across other types of fault intersections and for characterizing sources of future large earthquakes.

Fault Detection of Reciprocating Compressors using a Model from Principles Component Analysis of Vibrations

International Nuclear Information System (INIS)

Ahmed, M; Gu, F; Ball, A D

2012-01-01

Traditional vibration monitoring techniques have found it difficult to determine a set of effective diagnostic features due to the high complexity of the vibration signals originating from the many different impact sources and wide ranges of practical operating conditions. In this paper Principal Component Analysis (PCA) is used for selecting vibration feature and detecting different faults in a reciprocating compressor. Vibration datasets were collected from the compressor under baseline condition and five common faults: valve leakage, inter-cooler leakage, suction valve leakage, loose drive belt combined with intercooler leakage and belt loose drive belt combined with suction valve leakage. A model using five PCs has been developed using the baseline data sets and the presence of faults can be detected by comparing the T 2 and Q values from the features of fault vibration signals with corresponding thresholds developed from baseline data. However, the Q -statistic procedure produces a better detection as it can separate the five faults completely.

A diagnostic expert system for the nuclear power plant b ased on the hybrid knowledge approach

International Nuclear Information System (INIS)

Yang, J.O.; Chang, S.H.

1989-01-01

A diagnostic expert system, the hybrid knowledge based plant operation supporting system (HYPOSS), which has been developed to support operators' decisionmaking during the transients of the nuclear power plant, is described. HYPOSS adopts the hybrid knowledge approach, which combines both shallow and deep knowledge to take advantage of the merits of both approaches. In HYPOSS, four types of knowledge are used according to the steps of diagnosis procedure. They are structural, functional, behavioral, and heuristic knowledge. The structural and functional knowledge is represented by three fundamental primitives and five types of functions, respectively. The behavioral knowledge is represented using constraints. The inference procedure is based on the human problem-solving behavior modeled in HYPOSS. The event-based operational guidelines are provided to the operator according to the diagnosed results. If the exact anomalies cannot be identified while some of the critical safety functions are challenged, the function-based operational guidelines are provided to the operator. For the validation of HYPOSS, several tests have been performed based on the data produced by a plant simulator. The results of validation studies show good applicability of HYPOSS to the anomaly diagnosis of nuclear power plant

Fear of Progression in Parents of Children with Cancer: Results of An Online Expert Survey in Pediatric Oncology.

Science.gov (United States)

Clever, Katharina; Schepper, Florian; Küpper, Luise; Christiansen, Holger; Martini, Julia

2018-04-01

Fear of Progression (FoP) is a commonly reported psychological strain in parents of children with cancer. This expert survey investigates how professionals in pediatric oncology estimate the burden and consequences of FoP in parents and how they assess and treat parental FoP. N=77 professionals in pediatric oncology (members and associates of the Psychosocial Association in Paediatric Oncology and Haematology, PSAPOH) were examined in an online survey with a self-developed questionnaire. Data were analyzed via descriptive statistics and qualitative content analysis. Three of four experts in clinical practice were (very) often confronted with parental FoP which was associated with more negative (e. g., psychosomatic reactions, reduced family functioning) than positive (e. g., active illness processing) consequences. N=40 experts indicated that they mainly assess parents' anxiety via clinical judgment (72.5%) and/or according to ICD-10/DSM-5 diagnostic criteria (37.5%), whereas standardized methods such as psycho-oncological questionnaires (12.5%) were applied less often. Only n=6 experts named a specific diagnostic approach to assess parental FoP. The most common treatment approaches for FoP were supportive counseling (74.0%), psychotherapy (59.7%) and/or relaxation techniques (55.8%). Parental FoP is frequently perceived by experts in clinical practice. A standardized diagnostic procedure would increase comparability of diagnostic judgments and harmonize treatment indications. © Georg Thieme Verlag KG Stuttgart · New York.

Intelligent fault diagnosis of rolling bearing based on kernel neighborhood rough sets and statistical features

Energy Technology Data Exchange (ETDEWEB)

Zhu, Xiao Ran; Zhang, You Yun; Zhu, Yong Sheng [Xi' an Jiaotong Univ., Xi' an (China)

2012-09-15

Intelligent fault diagnosis benefits from efficient feature selection. Neighborhood rough sets are effective in feature selection. However, determining the neighborhood value accurately remains a challenge. The wrapper feature selection algorithm is designed by combining the kernel method and neighborhood rough sets to self-adaptively select sensitive features. The combination effectively solves the shortcomings in selecting the neighborhood value in the previous application process. The statistical features of time and frequency domains are used to describe the characteristic of the rolling bearing to make the intelligent fault diagnosis approach work. Three classification algorithms, namely, classification and regression tree (CART), commercial version 4.5 (C4.5), and radial basis function support vector machines (RBFSVM), are used to test UCI datasets and 10 fault datasets of rolling bearing. The results indicate that the diagnostic approach presented could effectively select the sensitive fault features and simultaneously identify the type and degree of the fault.

Intelligent fault diagnosis of rolling bearing based on kernel neighborhood rough sets and statistical features

International Nuclear Information System (INIS)

Zhu, Xiao Ran; Zhang, You Yun; Zhu, Yong Sheng

2012-01-01

Intelligent fault diagnosis benefits from efficient feature selection. Neighborhood rough sets are effective in feature selection. However, determining the neighborhood value accurately remains a challenge. The wrapper feature selection algorithm is designed by combining the kernel method and neighborhood rough sets to self-adaptively select sensitive features. The combination effectively solves the shortcomings in selecting the neighborhood value in the previous application process. The statistical features of time and frequency domains are used to describe the characteristic of the rolling bearing to make the intelligent fault diagnosis approach work. Three classification algorithms, namely, classification and regression tree (CART), commercial version 4.5 (C4.5), and radial basis function support vector machines (RBFSVM), are used to test UCI datasets and 10 fault datasets of rolling bearing. The results indicate that the diagnostic approach presented could effectively select the sensitive fault features and simultaneously identify the type and degree of the fault

Understanding diagnostic variability in breast pathology: lessons learned from an expert consensus review panel

Science.gov (United States)

Allison, Kimberly H; Reisch, Lisa M; Carney, Patricia A; Weaver, Donald L; Schnitt, Stuart J; O’Malley, Frances P; Geller, Berta M; Elmore, Joann G

2015-01-01

Aims To gain a better understanding of the reasons for diagnostic variability, with the aim of reducing the phenomenon. Methods and results In preparation for a study on the interpretation of breast specimens (B-PATH), a panel of three experienced breast pathologists reviewed 336 cases to develop consensus reference diagnoses. After independent assessment, cases coded as diagnostically discordant were discussed at consensus meetings. By the use of qualitative data analysis techniques, transcripts of 16 h of consensus meetings for a subset of 201 cases were analysed. Diagnostic variability could be attributed to three overall root causes: (i) pathologist-related; (ii) diagnostic coding/study methodology-related; and (iii) specimen-related. Most pathologist-related root causes were attributable to professional differences in pathologists’ opinions about whether the diagnostic criteria for a specific diagnosis were met, most frequently in cases of atypia. Diagnostic coding/study methodology-related root causes were primarily miscategorizations of descriptive text diagnoses, which led to the development of a standardized electronic diagnostic form (BPATH-Dx). Specimen-related root causes included artefacts, limited diagnostic material, and poor slide quality. After re-review and discussion, a consensus diagnosis could be assigned in all cases. Conclusions Diagnostic variability is related to multiple factors, but consensus conferences, standardized electronic reporting formats and comments on suboptimal specimen quality can be used to reduce diagnostic variability. PMID:24511905

Novel neural networks-based fault tolerant control scheme with fault alarm.

Science.gov (United States)

Shen, Qikun; Jiang, Bin; Shi, Peng; Lim, Cheng-Chew

2014-11-01

In this paper, the problem of adaptive active fault-tolerant control for a class of nonlinear systems with unknown actuator fault is investigated. The actuator fault is assumed to have no traditional affine appearance of the system state variables and control input. The useful property of the basis function of the radial basis function neural network (NN), which will be used in the design of the fault tolerant controller, is explored. Based on the analysis of the design of normal and passive fault tolerant controllers, by using the implicit function theorem, a novel NN-based active fault-tolerant control scheme with fault alarm is proposed. Comparing with results in the literature, the fault-tolerant control scheme can minimize the time delay between fault occurrence and accommodation that is called the time delay due to fault diagnosis, and reduce the adverse effect on system performance. In addition, the FTC scheme has the advantages of a passive fault-tolerant control scheme as well as the traditional active fault-tolerant control scheme's properties. Furthermore, the fault-tolerant control scheme requires no additional fault detection and isolation model which is necessary in the traditional active fault-tolerant control scheme. Finally, simulation results are presented to demonstrate the efficiency of the developed techniques.

Power System Transient Diagnostics Based on Novel Traveling Wave Detection

Science.gov (United States)

Hamidi, Reza Jalilzadeh

Modern electrical power systems demand novel diagnostic approaches to enhancing the system resiliency by improving the state-of-the-art algorithms. The proliferation of high-voltage optical transducers and high time-resolution measurements provide opportunities to develop novel diagnostic methods of very fast transients in power systems. At the same time, emerging complex configuration, such as multi-terminal hybrid transmission systems, limits the applications of the traditional diagnostic methods, especially in fault location and health monitoring. The impedance-based fault-location methods are inefficient for cross-bounded cables, which are widely used for connection of offshore wind farms to the main grid. Thus, this dissertation first presents a novel traveling wave-based fault-location method for hybrid multi-terminal transmission systems. The proposed method utilizes time-synchronized high-sampling voltage measurements. The traveling wave arrival times (ATs) are detected by observation of the squares of wavelet transformation coefficients. Using the ATs, an over-determined set of linear equations are developed for noise reduction, and consequently, the faulty segment is determined based on the characteristics of the provided equation set. Then, the fault location is estimated. The accuracy and capabilities of the proposed fault location method are evaluated and also compared to the existing traveling-wave-based method for a wide range of fault parameters. In order to improve power systems stability, auto-reclosing (AR), single-phase auto-reclosing (SPAR), and adaptive single-phase auto-reclosing (ASPAR) methods have been developed with the final objectives of distinguishing between the transient and permanent faults to clear the transient faults without de-energization of the solid phases. However, the features of the electrical arcs (transient faults) are severely influenced by a number of random parameters, including the convection of the air and plasma

Expert system in OPS5 for intelligent processing of the alarms in nuclear plants

International Nuclear Information System (INIS)

Cavalcante Junior, Jose Airton Chaves

1997-11-01

This work intends to establish a model of knowledge representation based on a expert system to supervise either security or operating to be applied generally on monitoring and detecting faults of industrial processes. The model structure proposed here let the system represent the knowledge related to faults on a process using a combination of rules either basic or associative. Besides, the model proposed has a mechanism of propagation of events in real time that acts on this structure making it possible to have an intelligent alarm processing. The rules used by the system define faults from the data acquired by instrumentation (basic rules), or from the establishment of a conjunction of faults already existent (associate rules). The computing implementation of the model defined in this work was developed in OPS5. It was applied on an example consisting of the shutdown of the Angra-I's power plant and was called FDAX (FDA Extended). For the simulated tests the FDAX was connected to the SICA (Integrated System of Angra-I Computers). It results save validity to the model, confirming thus its performance to real time applications. (author)

Fault tree handbook

International Nuclear Information System (INIS)

Haasl, D.F.; Roberts, N.H.; Vesely, W.E.; Goldberg, F.F.

1981-01-01

This handbook describes a methodology for reliability analysis of complex systems such as those which comprise the engineered safety features of nuclear power generating stations. After an initial overview of the available system analysis approaches, the handbook focuses on a description of the deductive method known as fault tree analysis. The following aspects of fault tree analysis are covered: basic concepts for fault tree analysis; basic elements of a fault tree; fault tree construction; probability, statistics, and Boolean algebra for the fault tree analyst; qualitative and quantitative fault tree evaluation techniques; and computer codes for fault tree evaluation. Also discussed are several example problems illustrating the basic concepts of fault tree construction and evaluation

How and when do expert emergency physicians generate and evaluate diagnostic hypotheses? A qualitative study using head-mounted video cued-recall interviews.

Science.gov (United States)

Pelaccia, Thierry; Tardif, Jacques; Triby, Emmanuel; Ammirati, Christine; Bertrand, Catherine; Dory, Valérie; Charlin, Bernard

2014-12-01

The ability to make a diagnosis is a crucial skill in emergency medicine. Little is known about the way emergency physicians reach a diagnosis. This study aims to identify how and when, during the initial patient examination, emergency physicians generate and evaluate diagnostic hypotheses. We carried out a qualitative research project based on semistructured interviews with emergency physicians. The interviews concerned management of an emergency situation during routine medical practice. They were associated with viewing the video recording of emergency situations filmed in an "own-point-of-view" perspective. The emergency physicians generated an average of 5 diagnostic hypotheses. Most of these hypotheses were generated before meeting the patient or within the first 5 minutes of the meeting. The hypotheses were then rank ordered within the context of a verification procedure based on identifying key information. These tasks were usually accomplished without conscious effort. No hypothesis was completely confirmed or refuted until the results of investigations were available. The generation and rank ordering of diagnostic hypotheses is based on the activation of cognitive processes, enabling expert emergency physicians to process environmental information and link it to past experiences. The physicians seemed to strive to avoid the risk of error by remaining aware of the possibility of alternative hypotheses as long as they did not have the results of investigations. Understanding the diagnostic process used by emergency physicians provides interesting ideas for training residents in a specialty in which the prevalence of reasoning errors leading to incorrect diagnoses is high. Copyright © 2014 American College of Emergency Physicians. Published by Elsevier Inc. All rights reserved.

Fault isolability conditions for linear systems with additive faults

DEFF Research Database (Denmark)

Niemann, Hans Henrik; Stoustrup, Jakob

2006-01-01

In this paper, we shall show that an unlimited number of additive single faults can be isolated under mild conditions if a general isolation scheme is applied. Multiple faults are also covered. The approach is algebraic and is based on a set representation of faults, where all faults within a set...

Integrated control and diagnostic system architectures for future installations

International Nuclear Information System (INIS)

Wood, R.; March-Leuba, J.

2000-01-01

Nuclear reactors of the 21st century will employ increasing levels of automation and fault tolerance to increase availability, reduce accident risk, and lower operating costs. Key developments in control algorithms, fault diagnostics, fault tolerance, and distributed communications are needed to implement the fully automated plant. It will be equally challenging to integrate developments in separate information and control fields into a cohesive system, which collectively achieves the overall goals of improved safety, reliability, maintainability, and cost-effectiveness. Under the Nuclear Energy Research Initiative (NERI), the US Department of Energy is sponsoring a project to address some of the technical issues involved in meeting the long-range goal of 21st century reactor control systems. This project involves researchers from Oak Ridge National Laboratory, the University of Tennessee, and North Carolina State University. The research tasks under this project focus on some of the first-level breakthroughs in control design, diagnostic techniques, and information system design that will provide a path to enable the design process to be automated in the future. This paper describes the conceptual development of an integrated nuclear plant control and information system architecture, which incorporates automated control system development that can be traced to a set of technical requirements. The expectation is that an integrated plant architecture with optimal control and efficient use of diagnostic information can reduce the potential for operational errors and minimize challenges to the plant safety systems

IMPLEMENTATION OF TURNOUTS TECHNICAL DIAGNOSTICS SYSTEMS

Directory of Open Access Journals (Sweden)

S. YU. Buryak

2015-06-01

Full Text Available Purpose. In the paper it is necessary to: 1 find out the causes of turnouts faults to determine diagnostic features failures; 2 consider the requirements structure, purpose components of turnouts, work and technology of their maintenance to determine the construction of the economic activities related to system to the turnout’s maintenance; 3 substantiate the possibility, necessity and prospects of automated diagnostics turnout’s implementation; 4 elaborate a prototype of an automated hardware and software system for the turnouts control parameters and perform diagnostics on them. Methodology. In the paper possible turnouts faults were presented and manifestations and influence on its work were shown. According to the current technology works the process analyze of turnouts’ maintenance was conducted, were defined the basic performed operations during the examination of appearance, parameters and check the repair or replacement of parts and assemblies. Based on the analysis of reasons of turnouts malfunctioning and their fixes were systematized types of damages and ways to deal with them, an information scheme of troubleshooting were created, opportunities and limits of automating the process of diagnostics were identified and compared with the existing method of turnouts maintenance. A diagnostics system block diagram was created, an algorithm of its work was developed and established main basic principles of operation. Software and hardware to determine the turnout’s state considering diagnostic performance of points in use were applied. Findings. During the experiment was created a method of automated turnout’s diagnostics with AC electric drives, managed centrally. The results of automated hardware and software system make it possible to control turnout’s parameters and perform diagnostics on them. Originality. Authors created the method of turnout’s state determination by current curve and its spectral composition in the

Expert Systems: What Is an Expert System?

Science.gov (United States)

Duval, Beverly K.; Main, Linda

1994-01-01

Describes expert systems and discusses their use in libraries. Highlights include parts of an expert system; expert system shells; an example of how to build an expert system; a bibliography of 34 sources of information on expert systems in libraries; and a list of 10 expert system shells used in libraries. (Contains five references.) (LRW)

An Ensemble Deep Convolutional Neural Network Model with Improved D-S Evidence Fusion for Bearing Fault Diagnosis.

Science.gov (United States)

Li, Shaobo; Liu, Guokai; Tang, Xianghong; Lu, Jianguang; Hu, Jianjun

2017-07-28

Intelligent machine health monitoring and fault diagnosis are becoming increasingly important for modern manufacturing industries. Current fault diagnosis approaches mostly depend on expert-designed features for building prediction models. In this paper, we proposed IDSCNN, a novel bearing fault diagnosis algorithm based on ensemble deep convolutional neural networks and an improved Dempster-Shafer theory based evidence fusion. The convolutional neural networks take the root mean square (RMS) maps from the FFT (Fast Fourier Transformation) features of the vibration signals from two sensors as inputs. The improved D-S evidence theory is implemented via distance matrix from evidences and modified Gini Index. Extensive evaluations of the IDSCNN on the Case Western Reserve Dataset showed that our IDSCNN algorithm can achieve better fault diagnosis performance than existing machine learning methods by fusing complementary or conflicting evidences from different models and sensors and adapting to different load conditions.

Fault diagnosis and fault-tolerant control based on adaptive control approach

CERN Document Server

Shen, Qikun; Shi, Peng

2017-01-01

This book provides recent theoretical developments in and practical applications of fault diagnosis and fault tolerant control for complex dynamical systems, including uncertain systems, linear and nonlinear systems. Combining adaptive control technique with other control methodologies, it investigates the problems of fault diagnosis and fault tolerant control for uncertain dynamic systems with or without time delay. As such, the book provides readers a solid understanding of fault diagnosis and fault tolerant control based on adaptive control technology. Given its depth and breadth, it is well suited for undergraduate and graduate courses on linear system theory, nonlinear system theory, fault diagnosis and fault tolerant control techniques. Further, it can be used as a reference source for academic research on fault diagnosis and fault tolerant control, and for postgraduates in the field of control theory and engineering. .

Development of an expert system for signal validation

International Nuclear Information System (INIS)

Qualls, A.L.; Uhrig, R.E.; Upadhyaya, B.R.

1988-01-01

Diagnosis of malfunctions in power plants has traditionally been in the domain of the process operator, who relies on training, experience, and reasoning ability to diagnose faults. The authors describe a method of signal validation using expert system technology, which detects possible anomalies in an instrument channel's output, similar to the procedure used by an operator. The system can be used to scan quickly over an array of sensor outputs and flag those that are observed to have possible anomalies. This system, when implemented in an operating power plant, could be used for continuous, on-line instrument anomaly detection with a minimum of computational effort

A summary of the active fault investigation in the extension sea area of Kikugawa fault and the Nishiyama fault , N-S direction fault in south west Japan

Science.gov (United States)

Abe, S.

2010-12-01

In this study, we carried out two sets of active fault investigation by the request from Ministry of Education, Culture, Sports, Science and Technology in the sea area of the extension of Kikugawa fault and the Nishiyama fault. We want to clarify the five following matters about both active faults based on those results. (1)Fault continuity of the land and the sea. (2) The length of the active fault. (3) The division of the segment. (4) Activity characteristics. In this investigation, we carried out a digital single channel seismic reflection survey in the whole area of both active faults. In addition, a high-resolution multichannel seismic reflection survey was carried out to recognize the detailed structure of a shallow stratum. Furthermore, the sampling with the vibrocoring to get information of the sedimentation age was carried out. The reflection profile of both active faults was extremely clear. The characteristics of the lateral fault such as flower structure, the dispersion of the active fault were recognized. In addition, from analysis of the age of the stratum, it was recognized that the thickness of the sediment was extremely thin in Holocene epoch on the continental shelf in this sea area. It was confirmed that the Kikugawa fault extended to the offing than the existing results of research by a result of this investigation. In addition, the width of the active fault seems to become wide toward the offing while dispersing. At present, we think that we can divide Kikugawa fault into some segments based on the distribution form of the segment. About the Nishiyama fault, reflection profiles to show the existence of the active fault was acquired in the sea between Ooshima and Kyushu. From this result and topographical existing results of research in Ooshima, it is thought that Nishiyama fault and the Ooshima offing active fault are a series of structure. As for Ooshima offing active fault, the upheaval side changes, and a direction changes too. Therefore, we

Fault detection for piecewise affine systems with application to ship propulsion systems.

Science.gov (United States)

Yang, Ying; Linlin, Li; Ding, Steven X; Qiu, Jianbin; Peng, Kaixiang

2017-09-09

In this paper, the design approach of non-synchronized diagnostic observer-based fault detection (FD) systems is investigated for piecewise affine processes via continuous piecewise Lyapunov functions. Considering that the dynamics of piecewise affine systems in different regions can be considerably different, the weighting matrices are used to weight the residual of each region, so as to optimize the fault detectability. A numerical example and a case study on a ship propulsion system are presented in the end to demonstrate the effectiveness of the proposed results. Copyright © 2017 ISA. Published by Elsevier Ltd. All rights reserved.

A Comparison of Hybrid Approaches for Turbofan Engine Gas Path Fault Diagnosis

Science.gov (United States)

Lu, Feng; Wang, Yafan; Huang, Jinquan; Wang, Qihang

2016-09-01

A hybrid diagnostic method utilizing Extended Kalman Filter (EKF) and Adaptive Genetic Algorithm (AGA) is presented for performance degradation estimation and sensor anomaly detection of turbofan engine. The EKF is used to estimate engine component performance degradation for gas path fault diagnosis. The AGA is introduced in the integrated architecture and applied for sensor bias detection. The contributions of this work are the comparisons of Kalman Filters (KF)-AGA algorithms and Neural Networks (NN)-AGA algorithms with a unified framework for gas path fault diagnosis. The NN needs to be trained off-line with a large number of prior fault mode data. When new fault mode occurs, estimation accuracy by the NN evidently decreases. However, the application of the Linearized Kalman Filter (LKF) and EKF will not be restricted in such case. The crossover factor and the mutation factor are adapted to the fitness function at each generation in the AGA, and it consumes less time to search for the optimal sensor bias value compared to the Genetic Algorithm (GA). In a word, we conclude that the hybrid EKF-AGA algorithm is the best choice for gas path fault diagnosis of turbofan engine among the algorithms discussed.

Fault finder

Science.gov (United States)

Bunch, Richard H.

1986-01-01

A fault finder for locating faults along a high voltage electrical transmission line. Real time monitoring of background noise and improved filtering of input signals is used to identify the occurrence of a fault. A fault is detected at both a master and remote unit spaced along the line. A master clock synchronizes operation of a similar clock at the remote unit. Both units include modulator and demodulator circuits for transmission of clock signals and data. All data is received at the master unit for processing to determine an accurate fault distance calculation.

A Statistical Parameter Analysis and SVM Based Fault Diagnosis Strategy for Dynamically Tuned Gyroscopes

Institute of Scientific and Technical Information of China (English)

无

2007-01-01

Gyro's fault diagnosis plays a critical role in inertia navigation systems for higher reliability and precision. A new fault diagnosis strategy based on the statistical parameter analysis (SPA) and support vector machine(SVM) classification model was proposed for dynamically tuned gyroscopes (DTG). The SPA, a kind of time domain analysis approach, was introduced to compute a set of statistical parameters of vibration signal as the state features of DTG, with which the SVM model, a novel learning machine based on statistical learning theory (SLT), was applied and constructed to train and identify the working state of DTG. The experimental results verify that the proposed diagnostic strategy can simply and effectively extract the state features of DTG, and it outperforms the radial-basis function (RBF) neural network based diagnostic method and can more reliably and accurately diagnose the working state of DTG.

The Sorong Fault Zone, Indonesia: Mapping a Fault Zone Offshore

Science.gov (United States)

Melia, S.; Hall, R.

2017-12-01

The Sorong Fault Zone is a left-lateral strike-slip fault zone in eastern Indonesia, extending westwards from the Bird's Head peninsula of West Papua towards Sulawesi. It is the result of interactions between the Pacific, Caroline, Philippine Sea, and Australian Plates and much of it is offshore. Previous research on the fault zone has been limited by the low resolution of available data offshore, leading to debates over the extent, location, and timing of movements, and the tectonic evolution of eastern Indonesia. Different studies have shown it north of the Sula Islands, truncated south of Halmahera, continuing to Sulawesi, or splaying into a horsetail fan of smaller faults. Recently acquired high resolution multibeam bathymetry of the seafloor (with a resolution of 15-25 meters), and 2D seismic lines, provide the opportunity to trace the fault offshore. The position of different strands can be identified. On land, SRTM topography shows that in the northern Bird's Head the fault zone is characterised by closely spaced E-W trending faults. NW of the Bird's Head offshore there is a fold and thrust belt which terminates some strands. To the west of the Bird's Head offshore the fault zone diverges into multiple strands trending ENE-WSW. Regions of Riedel shearing are evident west of the Bird's Head, indicating sinistral strike-slip motion. Further west, the ENE-WSW trending faults turn to an E-W trend and there are at least three fault zones situated immediately south of Halmahera, north of the Sula Islands, and between the islands of Sanana and Mangole where the fault system terminates in horsetail strands. South of the Sula islands some former normal faults at the continent-ocean boundary with the North Banda Sea are being reactivated as strike-slip faults. The fault zone does not currently reach Sulawesi. The new fault map differs from previous interpretations concerning the location, age and significance of different parts of the Sorong Fault Zone. Kinematic

Enhanced DET-Based Fault Signature Analysis for Reliable Diagnosis of Single and Multiple-Combined Bearing Defects

Directory of Open Access Journals (Sweden)

In-Kyu Jeong

2015-01-01

Full Text Available To early identify cylindrical roller bearing failures, this paper proposes a comprehensive bearing fault diagnosis method, which consists of spectral kurtosis analysis for finding the most informative subband signal well representing abnormal symptoms about the bearing failures, fault signature calculation using this subband signal, enhanced distance evaluation technique- (EDET- based fault signature analysis that outputs the most discriminative fault features for accurate diagnosis, and identification of various single and multiple-combined cylindrical roller bearing defects using the simplified fuzzy adaptive resonance map (SFAM. The proposed comprehensive bearing fault diagnosis methodology is effective for accurate bearing fault diagnosis, yielding an average classification accuracy of 90.35%. In this paper, the proposed EDET specifically addresses shortcomings in the conventional distance evaluation technique (DET by accurately estimating the sensitivity of each fault signature for each class. To verify the efficacy of the EDET-based fault signature analysis for accurate diagnosis, a diagnostic performance comparison is carried between the proposed EDET and the conventional DET in terms of average classification accuracy. In fact, the proposed EDET achieves up to 106.85% performance improvement over the conventional DET in average classification accuracy.

Dynamics Modeling and Analysis of Local Fault of Rolling Element Bearing

Directory of Open Access Journals (Sweden)

Lingli Cui

2015-01-01

Full Text Available This paper presents a nonlinear vibration model of rolling element bearings with 5 degrees of freedom based on Hertz contact theory and relevant bearing knowledge of kinematics and dynamics. The slipping of ball, oil film stiffness, and the nonlinear time-varying stiffness of the bearing are taken into consideration in the model proposed here. The single-point local fault model of rolling element bearing is introduced into the nonlinear model with 5 degrees of freedom according to the loss of the contact deformation of ball when it rolls into and out of the local fault location. The functions of spall depth corresponding to defects of different shapes are discussed separately in this paper. Then the ode solver in Matlab is adopted to perform a numerical solution on the nonlinear vibration model to simulate the vibration response of the rolling elements bearings with local fault. The simulation signals analysis results show a similar behavior and pattern to that observed in the processed experimental signals of rolling element bearings in both time domain and frequency domain which validated the nonlinear vibration model proposed here to generate typical rolling element bearings local fault signals for possible and effective fault diagnostic algorithms research.

Bayesian based Diagnostic Model for Condition based Maintenance of Offshore Wind Farms

DEFF Research Database (Denmark)

Asgarpour, Masoud; Sørensen, John Dalsgaard

2018-01-01

Operation and maintenance costs are a major contributor to the Levelized Cost of Energy for electricity produced by offshore wind and can be significantly reduced if existing corrective actions are performed as efficiently as possible and if future corrective actions are avoided by performing...... sufficient preventive actions. This paper presents an applied and generic diagnostic model for fault detection and condition based maintenance of offshore wind components. The diagnostic model is based on two probabilistic matrices; first, a confidence matrix, representing the probability of detection using...... for a wind turbine component based on vibration, temperature, and oil particle fault detection methods. The last part of the paper will have a discussion of the case study results and present conclusions....

A fault diagnosis method based on signed directed graph and matrix for nuclear power plants

International Nuclear Information System (INIS)

Liu, Yong-Kuo; Wu, Guo-Hua; Xie, Chun-Li; Duan, Zhi-Yong; Peng, Min-Jun; Li, Meng-Kun

2016-01-01

Highlights: • “Rules matrix” is proposed for FDD. • “State matrix” is proposed to solve SDG online inference. • SDG inference and search method are combined for FDD. - Abstract: In order to solve SDG online fault diagnosis and inference, matrix diagnosis and inference methods are proposed for fault detection and diagnosis (FDD). Firstly, “rules matrix” based on SDG model is used for FDD. Secondly, “status matrix” is proposed to achieve SDG online inference. According to different diagnosis results, “status matrix” is applied for the depth-first search and the breadth-first search respectively to find the propagation paths of each fault. Finally, the SDG model of the secondary-loop system in pressurized water reactor (PWR) is built to verify the effectiveness of the proposed method. The simulation experiment results indicate that the “status matrix” used for online inference can be used to find the fault propagation paths and to explain the causes for fault. Therefore, it can be concluded that the proposed method is one of the fault diagnosis for nuclear power plants (NPPs), which can be used to facilitate the development of fault diagnostic system.

A fault diagnosis method based on signed directed graph and matrix for nuclear power plants

Energy Technology Data Exchange (ETDEWEB)

Liu, Yong-Kuo, E-mail: LYK08@126.com [Fundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University, Harbin 150001 (China); Wu, Guo-Hua [Fundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University, Harbin 150001 (China); Institute of Nuclear Energy Technology, Tsinghua University, Beijing 100084 (China); Xie, Chun-Li [Traffic College, Northeast Forestry University, Harbin, 150040 (China); Duan, Zhi-Yong; Peng, Min-Jun; Li, Meng-Kun [Fundamental Science on Nuclear Safety and Simulation Technology Laboratory, Harbin Engineering University, Harbin 150001 (China)

2016-02-15

Highlights: • “Rules matrix” is proposed for FDD. • “State matrix” is proposed to solve SDG online inference. • SDG inference and search method are combined for FDD. - Abstract: In order to solve SDG online fault diagnosis and inference, matrix diagnosis and inference methods are proposed for fault detection and diagnosis (FDD). Firstly, “rules matrix” based on SDG model is used for FDD. Secondly, “status matrix” is proposed to achieve SDG online inference. According to different diagnosis results, “status matrix” is applied for the depth-first search and the breadth-first search respectively to find the propagation paths of each fault. Finally, the SDG model of the secondary-loop system in pressurized water reactor (PWR) is built to verify the effectiveness of the proposed method. The simulation experiment results indicate that the “status matrix” used for online inference can be used to find the fault propagation paths and to explain the causes for fault. Therefore, it can be concluded that the proposed method is one of the fault diagnosis for nuclear power plants (NPPs), which can be used to facilitate the development of fault diagnostic system.

Wind turbine fault detection and fault tolerant control

DEFF Research Database (Denmark)

Odgaard, Peter Fogh; Johnson, Kathryn

2013-01-01

In this updated edition of a previous wind turbine fault detection and fault tolerant control challenge, we present a more sophisticated wind turbine model and updated fault scenarios to enhance the realism of the challenge and therefore the value of the solutions. This paper describes...

Diagnostic dilemma

DEFF Research Database (Denmark)

Feldt-Rasmussen, Ulla; Dobrovolny, Robert; Nazarenko, Irina

2011-01-01

Fabry disease, an X-linked lysosomal storage disorder, results from the deficient activity of a-galactosidase A (a-Gal A). In affected males, the clinical diagnosis is confirmed by the markedly decreased a-Gal A activity. However, in female heterozygotes, the a-Gal A activity can range from low t...... on enzyme replacement therapy. Thus, gene dosage analyses can detect large deletions (>50bp) in suspect heterozygotes for X-linked and autosomal dominant diseases that are "sequencing cryptic," resolving molecular diagnostic dilemmas....... to normal due to random X-chromosomal inactivation, and diagnostic confirmation requires identification of the family's a-Gal A gene mutation. In a young female who had occasional acroparesthesias, corneal opacities, and 15 to 50% of the lower limit of normal leukocyte a-Gal A activity, a-Gal A sequencing...... in two expert laboratories did not identify a confirmatory mutation, presenting a diagnostic dilemma. A renal biopsy proved diagnostic and renewed efforts to detect an a-Gal A mutation. Subsequent gene dosage analyses identified a large a-Gal A deletion confirming her heterozygosity, and she was started...