Early fault warning for nuclear power machinery is conducive to timely troubleshooting and reductions in safety risks and unnecessary costs. This paper presents a novel intelligent fault prediction method, integrated ...Early fault warning for nuclear power machinery is conducive to timely troubleshooting and reductions in safety risks and unnecessary costs. This paper presents a novel intelligent fault prediction method, integrated probabilistic principal component analysis(PPCA), multi-resolution wavelet analysis, Bayesian inference, and RNN model for nuclear power machinery that consider data uncertainty and chaotic time series. After denoising the source data, the Bayesian PPCA method is employed for dimensional reduction to obtain a refined data group. A recurrent neural network(RNN) prediction model is constructed, and a Bayesian statistical inference approach is developed to quantitatively assess the prediction reliability of the model. By modeling and analyzing the data collected on the steam turbine and components of a nuclear power plant, the results of the goodness of fit, mean square error distribution, and Bayesian confidence indicate that the proposed RNN model can implement early warning in the fault creep period. The accuracy and reliability of the proposed model are quantitatively verified.展开更多
Fighters and other complex engineering systems have many characteristics such as difficult modeling and testing, multiple working situations, and high cost. Aim at these points, a new kind of real-time fault predictor...Fighters and other complex engineering systems have many characteristics such as difficult modeling and testing, multiple working situations, and high cost. Aim at these points, a new kind of real-time fault predictor is designed based on an improved k-nearest neighbor method, which needs neither the math model of system nc, the training data and prior knowledge. It can study and predict while system's running, so that it can overcome the difficulty of data acquirement. Besides, this predictor has a fast prediction speed, and the false alarm rate and missing alarm rate can be adjusted randomly. The method is simple and universalizable. The result of simulation on fighter F-16 proved the effidency.展开更多
The safety and reliability of mechatronics systems,particularly the high-end,large and key mechatronics equipment in service,can strongly influence on production efficiency,personnel safety,resources and environment.B...The safety and reliability of mechatronics systems,particularly the high-end,large and key mechatronics equipment in service,can strongly influence on production efficiency,personnel safety,resources and environment.Based on the demands of development of modern industries and technologies such as international industry 4.0,Made-in-China 2025 and Internet + and so on,this paper started from revealing the regularity of evolution of running state of equipment and the methods of signal processing of low signal noise ratio,proposed the key information technology of state monitoring and earlyfault-warning for equipment,put forward the typical technical line and major technical content,introduced the application of the technology to realize modern predictive maintenance of equipment and introduced the development of relevant safety monitoring instruments.The technology will play an important role in ensuring the safety of equipment in service,preventing accidents and realizing scientific maintenance.展开更多
Nowadays, the elevator has become an indispensable means of indoor transportation in people’s life, but in recent years this kind of traffic tools has caused many casualties because of the gate system fault. In order...Nowadays, the elevator has become an indispensable means of indoor transportation in people’s life, but in recent years this kind of traffic tools has caused many casualties because of the gate system fault. In order to ensure the safe and reliable operation of the elevator, the failure of elevator door system was predicted in this paper. Against the fault type of elevator door system: elevator door opened, excessive vibration when elevator door opened or closed, elevator door did not open or closed when reached the specified level. Three fault types were used as the output of the prediction model. There were 8 reasons for the failure, used them as input. A model based on particle swarm optimization (PSO) and BP neural network was established, using MATLAB to emulation;the results showed that: PSO-BP neural network algorithm was feasible in the fault prediction of the elevator door system.展开更多
Inertial system platforms are a kind of important precision devices,which have the characteristics of difficult acquisition for state data and small sample scale.Focusing on the model optimization for data-driven faul...Inertial system platforms are a kind of important precision devices,which have the characteristics of difficult acquisition for state data and small sample scale.Focusing on the model optimization for data-driven fault state prediction and quantitative degreemeasurement,a fast small-sample supersphere one-class SVMmodelingmethod using support vectors pre-selection is systematically studied in this paper.By theorem-proving the irrelevance between themodel’s learning result and the non-support vectors(NSVs),the distribution characters of the support vectors are analyzed.On this basis,a modeling method with selected samples having specific geometry character fromthe training sets is also proposed.The method can remarkably eliminate theNSVs and improve the algorithm’s efficiency.The experimental results testify that the scale of training samples and the modeling time consumption both give a sharply decrease using the support vectors pre-selection method.The experimental results on inertial devices also show good fault prediction capability and effectiveness of quantitative anomaly measurement.展开更多
Condition-based maintenance based on fault prediction has been widely concerned by the industry. Most of the contributions on fault prediction are based on various sensor data and mathematical models of the equipment....Condition-based maintenance based on fault prediction has been widely concerned by the industry. Most of the contributions on fault prediction are based on various sensor data and mathematical models of the equipment. The complexity of the model and data signal is the key factor affecting the practicability of the model. In addition, even for the same type and batch of equipment, the manufacturing process, operation environment and other factors also affect the model parameters. In this paper, a series event model is conducted to predict the fault of marine diesel engines. Numerical example illustrates that the proposed event model is feasible.展开更多
Software testing is an integral part of software development. Not only that testing exists in each software iteration cycle, but it also consumes a considerable amount of resources. While resources such as machinery a...Software testing is an integral part of software development. Not only that testing exists in each software iteration cycle, but it also consumes a considerable amount of resources. While resources such as machinery and manpower are often restricted, it is crucial to decide where and how much effort to put into testing. One way to address this problem is to identify which components of the subject under the test are more error-prone and thus demand more testing efforts. Recent development in machine learning techniques shows promising potential to predict faults in different components of a software system. This work conducts an empirical study to explore the feasibility of using static software metrics to predict software faults. We apply four machine learning techniques to construct fault prediction models from the PROMISE data set and evaluate the effectiveness of using static software metrics to build fault prediction models in four continuous versions of Apache Ant. The empirical results show that the combined software metrics generate the least misclassification errors. The fault prediction results vary significantly among different machine learning techniques and data set. Overall, fault prediction models built with the support vector machine (SVM) have the lowest misclassification errors.展开更多
Accurate fault prediction can obviously reduce cost and decrease the probability of accidents so as to improve the performance of the system testing and maintenance. Traditional fault prediction methods are always off...Accurate fault prediction can obviously reduce cost and decrease the probability of accidents so as to improve the performance of the system testing and maintenance. Traditional fault prediction methods are always offline that are not suitable for online and real-time processing. For the complicated nonlinear and non-stationary time series, it is hard to achieve exact predicting result with single models such as support vector regression (SVR), artifieial neural network (ANN), and autoregressive moving average (ARMA). Combined with the accurate online support vector regression (AOSVR) algorithm and ARMA model, a new online approach is presented to forecast fault with time series prediction. The fault trend feature can be extracted by the AOSVR with global kernel for general fault modes. Moreover, its prediction residual that represents the local high-frequency components is synchronously revised and compensated by the sliding time window ARMA model. Fault prediction with combined AOSVR and ARMA can be realized better than with the single one. Experiments on Tennessee Eastman process fault data show the new method is practical and effective.展开更多
Accurate fault prediction is essential to ensure the safety and reliability of combine harvester operation.In this study,a combine harvester fault prediction method based on a combination of stacked denoising autoenco...Accurate fault prediction is essential to ensure the safety and reliability of combine harvester operation.In this study,a combine harvester fault prediction method based on a combination of stacked denoising autoencoders(SDAE)and multi-classification support vector machines(SVM)is proposed to predict combine harvester faults by extracting operational features of key combine components.In general,SDAE contains autoencoders and uses a deep network architecture to learn complex non-linear input-output relationships in a hierarchical manner.Selected features are fed into the SDAE network,deep-level features of the input parameters are extracted by SDAE,and an SVM classifier is then added to its top layer to achieve combine harvester fault prediction.The experimental results show that the method can achieve accurate and efficient combine harvester fault prediction.In particular,the experiments used Gaussian noise with a distribution center of 0.05 to corrupt the test data samples obtained by random sampling of the whole population,and the results showed that the prediction accuracy of the method was 95.31%,which has better robustness and generalization ability compared to SVM(77.03%),BP(74.61%),and SAE(90.86%).展开更多
The integrated energy systems,usually including electric energy,natural gas and thermal energy,play a pivotal role in the energy Internet project,which could improve the accommodation of renewable energy through multi...The integrated energy systems,usually including electric energy,natural gas and thermal energy,play a pivotal role in the energy Internet project,which could improve the accommodation of renewable energy through multienergy complementary ways.Focusing on the regional integrated energy system composed of electrical microgrid and natural gas network,a fault risk warning method based on the improved RelieF-softmax method is proposed in this paper.The raw data-set was first clustered by the K-maxmin method to improve the preference of the random sampling process in the RelieF algorithm,and thereby achieved a hierarchical and non-repeated sampling.Then,the improved RelieF algorithm is used to identify the feature vectors,calculate the feature weights,and select the preferred feature subset according to the initially set threshold.In addition,a correlation coefficient method is applied to reduce the feature subset,and further eliminate the redundant feature vectors to obtain the optimal feature subset.Finally,the softmax classifier is used to obtain the early warnings of the integrated energy system.Case studies are conducted on an integrated energy system in the south of China to demonstrate the accuracy of fault risk warning method proposed in this paper.展开更多
Existing power anomaly detection is mainly based on a pattern matching algorithm.However,this method requires a lot of manual work,is time-consuming,and cannot detect unknown anomalies.Moreover,a large amount of label...Existing power anomaly detection is mainly based on a pattern matching algorithm.However,this method requires a lot of manual work,is time-consuming,and cannot detect unknown anomalies.Moreover,a large amount of labeled anomaly data is required in machine learning-based anomaly detection.Therefore,this paper proposes the application of a generative adversarial network(GAN)to massive data stream anomaly identification,diagnosis,and prediction in power dispatching automation systems.Firstly,to address the problem of the small amount of anomaly data,a GAN is used to obtain reliable labeled datasets for fault diagnosis model training based on a few labeled data points.Then,a two-step detection process is designed for the characteristics of grid anomalies,where the generated samples are first input to the XGBoost recognition system to identify the large class of anomalies in the first step.Thereafter,the data processed in the first step are input to the joint model of Convolutional Neural Networks(CNN)and Long short-term memory(LSTM)for fine-grained analysis to detect the small class of anomalies in the second step.Extensive experiments show that our work can reduce a lot of manual work and outperform the state-of-art anomalies classification algorithms for power dispatching data network.展开更多
Faults that develop in vehicle sensors have the potential to propagate unchecked throughout control systems if undetected.Automatic fault diagnosis and health monitoring algorithms will become necessary as automotive ...Faults that develop in vehicle sensors have the potential to propagate unchecked throughout control systems if undetected.Automatic fault diagnosis and health monitoring algorithms will become necessary as automotive applications become more autonomous.The current fault diagnosis systems are not effective for complex systems such as autonomous cars where the case of simultaneous faults in different sensors is highly possible.Therefore,this paper proposes a novel fault detection,isolation and identification architecture for multi-fault in multi-sensor systems with an efficient computational burden for real-time implementation.Support Vector Machine techniques are used to detect and identify faults in sensors for autonomous vehicle control systems.In addition,to identify degrading performance in a sensor and predict the time at which a fault will occur,a novel predictive algorithm is proposed.The effectiveness and accuracy of the architecture in detecting and identifying multiple faults as well as the accuracy of the proposed predictive fault detection algorithm are verified through a MATLAB/IPG CarMaker co-simulation platform.The results present detection and identification accuracies of 94.94%and 97.01%,respectively,as well as a prediction accuracy of 75.35%.展开更多
Despite advances in technological complexity and efforts,software repository maintenance requires reusing the data to reduce the effort and complexity.However,increasing ambiguity,irrelevance,and bugs while extracting...Despite advances in technological complexity and efforts,software repository maintenance requires reusing the data to reduce the effort and complexity.However,increasing ambiguity,irrelevance,and bugs while extracting similar data during software development generate a large amount of data from those data that reside in repositories.Thus,there is a need for a repository mining technique for relevant and bug-free data prediction.This paper proposes a fault prediction approach using a data-mining technique to find good predictors for high-quality software.To predict errors in mining data,the Apriori algorithm was used to discover association rules by fixing confidence at more than 40%and support at least 30%.The pruning strategy was adopted based on evaluation measures.Next,the rules were extracted from three projects of different domains;the extracted rules were then combined to obtain the most popular rules based on the evaluation measure values.To evaluate the proposed approach,we conducted an experimental study to compare the proposed rules with existing ones using four different industrial projects.The evaluation showed that the results of our proposal are promising.Practitioners and developers can utilize these rules for defect prediction during early software development.展开更多
Time stress includes all kinds of environment and operating stress such as shock, vibration, temperature and electric current that the electromechanical system suffers in the manufacture, transport and operating proce...Time stress includes all kinds of environment and operating stress such as shock, vibration, temperature and electric current that the electromechanical system suffers in the manufacture, transport and operating process. In this paper, the conception of time stress and prognostics and health management ( PHM) system are introduced. Then, in order to improve the false alarm recognition and fault prediction capabilities of the electromechanical equipment, a novel PHM architecture for electromechanical equipment is put forward based on a built-in test (BIT) system design technology and time stress analysis method. Finally, the structure, the design and implementing method and the functions of each module of this PHM system are described in detail.展开更多
Oil and gas facilities used in the petroleum industry can be considered as complex dynamic systems in that they require different types of equipment with various causal relationships among components and process varia...Oil and gas facilities used in the petroleum industry can be considered as complex dynamic systems in that they require different types of equipment with various causal relationships among components and process variables under monitoring.As the systems grow increasingly large,high speed,automated and intelligent,the nonlinear relations among these process variables and their effects on accidents are to be fully understood for both system reliability and safety assurance.Failures that occur during the process can both cause tremendous loss to the petroleum industry and compromise product quality and affect the environment.Therefore,failures should be detected as soon as possible,and the root causes need to be identified so that corrections can be made in time to avoid further loss,which relate to the safety prognostic technology.By investigation of the relationship of accident causing factors in complex systems,new progress into diagnosis and prognostic technology from international research institutions is reviewed,and research highlights from China University of Petroleum(Beijing) in this area are also presented.By analyzing the present domestic and overseas research situations,the current problems and future directions in the fundamental research and engineering applications are proposed.展开更多
As an important technology for predictive maintenance, failure prognosis has attracted more and more attentions in recent years. Real-time reliability prediction is one effective solution to failure prognosis. Conside...As an important technology for predictive maintenance, failure prognosis has attracted more and more attentions in recent years. Real-time reliability prediction is one effective solution to failure prognosis. Considering a dynamic system that is composed of normal, deteriorating and unreliable components, this paper proposes an integrated approach to perform real-time reliability prediction for such a class of systems. For a deteriorating component, the degradation is modeled by a time-varying fault process which is a linear or approximately linear function of time. The behavior of an unreliable component is described by a random variable which has two possible values corresponding to the operating and malfunction conditions of this component. The whole proposed approach contains three algorithms. A modified interacting multiple model particle filter is adopted to estimate the dynamic system's state variables and the unmeasurable time-varying fault. An exponential smoothing algorithm named the Holt's method is used to predict the fault process. In the end, the system's reliability is predicted in real time by use of the Monte Carlo strategy. The proposed approach can effectively predict the impending failure of a dynamic system, which is verified by computer simulations based on a three-vessel water tank system.展开更多
Many software systems are developed in a number of consecutive releases. In each release not only new code is added but also existing code is often modified. In this study we show that the modified code can be an impo...Many software systems are developed in a number of consecutive releases. In each release not only new code is added but also existing code is often modified. In this study we show that the modified code can be an important source of faults. Faults are widely recognized as one of the major cost drivers in software projects. Therefore, we look for methods that improve the fault detection in the modified code. We propose and evaluate a number of prediction models that increase the efficiency of fault detection. To build and evaluate our models we use data collected from two large telecommunication systems produced by Ericsson. We evaluate the performance of our models by applying them both to a different release of the system than the one they are built on and to a different system. The performance of our models is compared to the performance of the theoretical best model, a simple model based on size, as well as to analyzing the code in a random order (not using any model). We find that the use of our models provides a significant improvement over not using any model at all and over using a simple model based on the class size. The gain offered by our models corresponds to 38-57% of the theoretical maximum gain.展开更多
基金the National Natural Science Foundation of China(No.51875209)the Guangdong Basic and Applied Basic Research Foundation(No.2019B1515120060)the Open Funds of State Key Laboratory of Nuclear Power Safety Monitoring Technology and Equipment。
文摘Early fault warning for nuclear power machinery is conducive to timely troubleshooting and reductions in safety risks and unnecessary costs. This paper presents a novel intelligent fault prediction method, integrated probabilistic principal component analysis(PPCA), multi-resolution wavelet analysis, Bayesian inference, and RNN model for nuclear power machinery that consider data uncertainty and chaotic time series. After denoising the source data, the Bayesian PPCA method is employed for dimensional reduction to obtain a refined data group. A recurrent neural network(RNN) prediction model is constructed, and a Bayesian statistical inference approach is developed to quantitatively assess the prediction reliability of the model. By modeling and analyzing the data collected on the steam turbine and components of a nuclear power plant, the results of the goodness of fit, mean square error distribution, and Bayesian confidence indicate that the proposed RNN model can implement early warning in the fault creep period. The accuracy and reliability of the proposed model are quantitatively verified.
文摘Fighters and other complex engineering systems have many characteristics such as difficult modeling and testing, multiple working situations, and high cost. Aim at these points, a new kind of real-time fault predictor is designed based on an improved k-nearest neighbor method, which needs neither the math model of system nc, the training data and prior knowledge. It can study and predict while system's running, so that it can overcome the difficulty of data acquirement. Besides, this predictor has a fast prediction speed, and the false alarm rate and missing alarm rate can be adjusted randomly. The method is simple and universalizable. The result of simulation on fighter F-16 proved the effidency.
基金supported by National Natural Science Foundation of China(No.51275052)Beijing Natural Science Foundation(No.3131002)
文摘The safety and reliability of mechatronics systems,particularly the high-end,large and key mechatronics equipment in service,can strongly influence on production efficiency,personnel safety,resources and environment.Based on the demands of development of modern industries and technologies such as international industry 4.0,Made-in-China 2025 and Internet + and so on,this paper started from revealing the regularity of evolution of running state of equipment and the methods of signal processing of low signal noise ratio,proposed the key information technology of state monitoring and earlyfault-warning for equipment,put forward the typical technical line and major technical content,introduced the application of the technology to realize modern predictive maintenance of equipment and introduced the development of relevant safety monitoring instruments.The technology will play an important role in ensuring the safety of equipment in service,preventing accidents and realizing scientific maintenance.
文摘Nowadays, the elevator has become an indispensable means of indoor transportation in people’s life, but in recent years this kind of traffic tools has caused many casualties because of the gate system fault. In order to ensure the safe and reliable operation of the elevator, the failure of elevator door system was predicted in this paper. Against the fault type of elevator door system: elevator door opened, excessive vibration when elevator door opened or closed, elevator door did not open or closed when reached the specified level. Three fault types were used as the output of the prediction model. There were 8 reasons for the failure, used them as input. A model based on particle swarm optimization (PSO) and BP neural network was established, using MATLAB to emulation;the results showed that: PSO-BP neural network algorithm was feasible in the fault prediction of the elevator door system.
基金the National Natural Science Foundation of China(Grant No.61403397)the Natural Science Basic Research Plan in Shaanxi Province of China(Grant Nos.2020JM-358,2015JM6313).
文摘Inertial system platforms are a kind of important precision devices,which have the characteristics of difficult acquisition for state data and small sample scale.Focusing on the model optimization for data-driven fault state prediction and quantitative degreemeasurement,a fast small-sample supersphere one-class SVMmodelingmethod using support vectors pre-selection is systematically studied in this paper.By theorem-proving the irrelevance between themodel’s learning result and the non-support vectors(NSVs),the distribution characters of the support vectors are analyzed.On this basis,a modeling method with selected samples having specific geometry character fromthe training sets is also proposed.The method can remarkably eliminate theNSVs and improve the algorithm’s efficiency.The experimental results testify that the scale of training samples and the modeling time consumption both give a sharply decrease using the support vectors pre-selection method.The experimental results on inertial devices also show good fault prediction capability and effectiveness of quantitative anomaly measurement.
文摘Condition-based maintenance based on fault prediction has been widely concerned by the industry. Most of the contributions on fault prediction are based on various sensor data and mathematical models of the equipment. The complexity of the model and data signal is the key factor affecting the practicability of the model. In addition, even for the same type and batch of equipment, the manufacturing process, operation environment and other factors also affect the model parameters. In this paper, a series event model is conducted to predict the fault of marine diesel engines. Numerical example illustrates that the proposed event model is feasible.
文摘Software testing is an integral part of software development. Not only that testing exists in each software iteration cycle, but it also consumes a considerable amount of resources. While resources such as machinery and manpower are often restricted, it is crucial to decide where and how much effort to put into testing. One way to address this problem is to identify which components of the subject under the test are more error-prone and thus demand more testing efforts. Recent development in machine learning techniques shows promising potential to predict faults in different components of a software system. This work conducts an empirical study to explore the feasibility of using static software metrics to predict software faults. We apply four machine learning techniques to construct fault prediction models from the PROMISE data set and evaluate the effectiveness of using static software metrics to build fault prediction models in four continuous versions of Apache Ant. The empirical results show that the combined software metrics generate the least misclassification errors. The fault prediction results vary significantly among different machine learning techniques and data set. Overall, fault prediction models built with the support vector machine (SVM) have the lowest misclassification errors.
文摘Accurate fault prediction can obviously reduce cost and decrease the probability of accidents so as to improve the performance of the system testing and maintenance. Traditional fault prediction methods are always offline that are not suitable for online and real-time processing. For the complicated nonlinear and non-stationary time series, it is hard to achieve exact predicting result with single models such as support vector regression (SVR), artifieial neural network (ANN), and autoregressive moving average (ARMA). Combined with the accurate online support vector regression (AOSVR) algorithm and ARMA model, a new online approach is presented to forecast fault with time series prediction. The fault trend feature can be extracted by the AOSVR with global kernel for general fault modes. Moreover, its prediction residual that represents the local high-frequency components is synchronously revised and compensated by the sliding time window ARMA model. Fault prediction with combined AOSVR and ARMA can be realized better than with the single one. Experiments on Tennessee Eastman process fault data show the new method is practical and effective.
基金The work was sponsored by the Intelligent Manufacturing Comprehensive Standardization Project(No.2018GXZ1101011)the National Key Research and Development Program of China Sub-project(No.2016YFD0701802)the Natural Science Foundation of Henan(No.202300410124).
文摘Accurate fault prediction is essential to ensure the safety and reliability of combine harvester operation.In this study,a combine harvester fault prediction method based on a combination of stacked denoising autoencoders(SDAE)and multi-classification support vector machines(SVM)is proposed to predict combine harvester faults by extracting operational features of key combine components.In general,SDAE contains autoencoders and uses a deep network architecture to learn complex non-linear input-output relationships in a hierarchical manner.Selected features are fed into the SDAE network,deep-level features of the input parameters are extracted by SDAE,and an SVM classifier is then added to its top layer to achieve combine harvester fault prediction.The experimental results show that the method can achieve accurate and efficient combine harvester fault prediction.In particular,the experiments used Gaussian noise with a distribution center of 0.05 to corrupt the test data samples obtained by random sampling of the whole population,and the results showed that the prediction accuracy of the method was 95.31%,which has better robustness and generalization ability compared to SVM(77.03%),BP(74.61%),and SAE(90.86%).
基金Supported by National Natural Science Foundation of China(No.51777193).
文摘The integrated energy systems,usually including electric energy,natural gas and thermal energy,play a pivotal role in the energy Internet project,which could improve the accommodation of renewable energy through multienergy complementary ways.Focusing on the regional integrated energy system composed of electrical microgrid and natural gas network,a fault risk warning method based on the improved RelieF-softmax method is proposed in this paper.The raw data-set was first clustered by the K-maxmin method to improve the preference of the random sampling process in the RelieF algorithm,and thereby achieved a hierarchical and non-repeated sampling.Then,the improved RelieF algorithm is used to identify the feature vectors,calculate the feature weights,and select the preferred feature subset according to the initially set threshold.In addition,a correlation coefficient method is applied to reduce the feature subset,and further eliminate the redundant feature vectors to obtain the optimal feature subset.Finally,the softmax classifier is used to obtain the early warnings of the integrated energy system.Case studies are conducted on an integrated energy system in the south of China to demonstrate the accuracy of fault risk warning method proposed in this paper.
基金supported by the Technology Project of State Grid Jiangsu Electric Power Co.,Ltd.,China,under Grant J2021167.
文摘Existing power anomaly detection is mainly based on a pattern matching algorithm.However,this method requires a lot of manual work,is time-consuming,and cannot detect unknown anomalies.Moreover,a large amount of labeled anomaly data is required in machine learning-based anomaly detection.Therefore,this paper proposes the application of a generative adversarial network(GAN)to massive data stream anomaly identification,diagnosis,and prediction in power dispatching automation systems.Firstly,to address the problem of the small amount of anomaly data,a GAN is used to obtain reliable labeled datasets for fault diagnosis model training based on a few labeled data points.Then,a two-step detection process is designed for the characteristics of grid anomalies,where the generated samples are first input to the XGBoost recognition system to identify the large class of anomalies in the first step.Thereafter,the data processed in the first step are input to the joint model of Convolutional Neural Networks(CNN)and Long short-term memory(LSTM)for fine-grained analysis to detect the small class of anomalies in the second step.Extensive experiments show that our work can reduce a lot of manual work and outperform the state-of-art anomalies classification algorithms for power dispatching data network.
文摘Faults that develop in vehicle sensors have the potential to propagate unchecked throughout control systems if undetected.Automatic fault diagnosis and health monitoring algorithms will become necessary as automotive applications become more autonomous.The current fault diagnosis systems are not effective for complex systems such as autonomous cars where the case of simultaneous faults in different sensors is highly possible.Therefore,this paper proposes a novel fault detection,isolation and identification architecture for multi-fault in multi-sensor systems with an efficient computational burden for real-time implementation.Support Vector Machine techniques are used to detect and identify faults in sensors for autonomous vehicle control systems.In addition,to identify degrading performance in a sensor and predict the time at which a fault will occur,a novel predictive algorithm is proposed.The effectiveness and accuracy of the architecture in detecting and identifying multiple faults as well as the accuracy of the proposed predictive fault detection algorithm are verified through a MATLAB/IPG CarMaker co-simulation platform.The results present detection and identification accuracies of 94.94%and 97.01%,respectively,as well as a prediction accuracy of 75.35%.
基金This research was financially supported in part by the Ministry of Trade,Industry and Energy(MOTIE)and Korea Institute for Advancement of Technology(KIAT)through the International Cooperative R&D program.(Project No.P0016038)in part by the MSIT(Ministry of Science and ICT),Korea,under the ITRC(Information Technology Research Center)support program(IITP-2021-2016-0-00312)supervised by the IITP(Institute for Information&communications Technology Planning&Evaluation).
文摘Despite advances in technological complexity and efforts,software repository maintenance requires reusing the data to reduce the effort and complexity.However,increasing ambiguity,irrelevance,and bugs while extracting similar data during software development generate a large amount of data from those data that reside in repositories.Thus,there is a need for a repository mining technique for relevant and bug-free data prediction.This paper proposes a fault prediction approach using a data-mining technique to find good predictors for high-quality software.To predict errors in mining data,the Apriori algorithm was used to discover association rules by fixing confidence at more than 40%and support at least 30%.The pruning strategy was adopted based on evaluation measures.Next,the rules were extracted from three projects of different domains;the extracted rules were then combined to obtain the most popular rules based on the evaluation measure values.To evaluate the proposed approach,we conducted an experimental study to compare the proposed rules with existing ones using four different industrial projects.The evaluation showed that the results of our proposal are promising.Practitioners and developers can utilize these rules for defect prediction during early software development.
文摘Time stress includes all kinds of environment and operating stress such as shock, vibration, temperature and electric current that the electromechanical system suffers in the manufacture, transport and operating process. In this paper, the conception of time stress and prognostics and health management ( PHM) system are introduced. Then, in order to improve the false alarm recognition and fault prediction capabilities of the electromechanical equipment, a novel PHM architecture for electromechanical equipment is put forward based on a built-in test (BIT) system design technology and time stress analysis method. Finally, the structure, the design and implementing method and the functions of each module of this PHM system are described in detail.
基金supported by the Natural Science Foundation of China (Grant No. 51104168)the Excellent Doctoral Dissertation Supervisor Project of Beijing (Grant YB20111141401)+3 种基金the Program for New Century Excellent Talents in University (NCET-12-0972)PetroChina Innovation Foundation (Grant No. 2011D-5006-0408)Beijing Natural Science Foundation (3132027)Supported by Science Foundation of China University of Petroleum (No. YJRC-2013-35)
文摘Oil and gas facilities used in the petroleum industry can be considered as complex dynamic systems in that they require different types of equipment with various causal relationships among components and process variables under monitoring.As the systems grow increasingly large,high speed,automated and intelligent,the nonlinear relations among these process variables and their effects on accidents are to be fully understood for both system reliability and safety assurance.Failures that occur during the process can both cause tremendous loss to the petroleum industry and compromise product quality and affect the environment.Therefore,failures should be detected as soon as possible,and the root causes need to be identified so that corrections can be made in time to avoid further loss,which relate to the safety prognostic technology.By investigation of the relationship of accident causing factors in complex systems,new progress into diagnosis and prognostic technology from international research institutions is reviewed,and research highlights from China University of Petroleum(Beijing) in this area are also presented.By analyzing the present domestic and overseas research situations,the current problems and future directions in the fundamental research and engineering applications are proposed.
基金Supported by the National Basic Research Program of China (Grant Nos. 2009CB320602, 2010CB731800)the National Natural Science Foundation of China (Grant Nos. 60721003, 60736026)
文摘As an important technology for predictive maintenance, failure prognosis has attracted more and more attentions in recent years. Real-time reliability prediction is one effective solution to failure prognosis. Considering a dynamic system that is composed of normal, deteriorating and unreliable components, this paper proposes an integrated approach to perform real-time reliability prediction for such a class of systems. For a deteriorating component, the degradation is modeled by a time-varying fault process which is a linear or approximately linear function of time. The behavior of an unreliable component is described by a random variable which has two possible values corresponding to the operating and malfunction conditions of this component. The whole proposed approach contains three algorithms. A modified interacting multiple model particle filter is adopted to estimate the dynamic system's state variables and the unmeasurable time-varying fault. An exponential smoothing algorithm named the Holt's method is used to predict the fault process. In the end, the system's reliability is predicted in real time by use of the Monte Carlo strategy. The proposed approach can effectively predict the impending failure of a dynamic system, which is verified by computer simulations based on a three-vessel water tank system.
基金This paper is an extended version of a paper presented at APSEC 2005 ConferenceThis work was partly funded by The Knowledge Foundation in Sweden under a research grant for the project "Blekinge Engineering Software (qualities (BESQ)" (htt.p://www.bth.se/besq).
文摘Many software systems are developed in a number of consecutive releases. In each release not only new code is added but also existing code is often modified. In this study we show that the modified code can be an important source of faults. Faults are widely recognized as one of the major cost drivers in software projects. Therefore, we look for methods that improve the fault detection in the modified code. We propose and evaluate a number of prediction models that increase the efficiency of fault detection. To build and evaluate our models we use data collected from two large telecommunication systems produced by Ericsson. We evaluate the performance of our models by applying them both to a different release of the system than the one they are built on and to a different system. The performance of our models is compared to the performance of the theoretical best model, a simple model based on size, as well as to analyzing the code in a random order (not using any model). We find that the use of our models provides a significant improvement over not using any model at all and over using a simple model based on the class size. The gain offered by our models corresponds to 38-57% of the theoretical maximum gain.