Taking advantage of the cyclostationarity property of the vibration signal when fault arises in rolling bearing, the paper proposes a new fault diagnosis method of rolling bearing based on Slice Energy Entropy Spectral Correlation Density- Continuous Hidden Markov Model (SEESCD-CHMM). Firstly, the method of SEESCD is used to extract the feature of rolling bearing four states’ (normal, inner race fault, outer race fault and ball element fault) data to form the training feature vectors. Then the training feature vectors are used to train a CHMM and the optimal parameters of CHMM are obtained. At last, the SEESCD method is used to extract the test data to form the test feature vectors. The trained CHMM model is used to diagnose the test feature vectors and perfect diagnosis results are got which is 100% accurate. In the end, the advantages and the much higher accuracy of the proposed method is verified by comparing with other intelligent diagnosis methods.
{"title":"Rolling bearing fault diagnosis based on Slice Energy Entropy Spectral Correlation Density-Continuous Hidden Markov Model","authors":"Hongchao Wang, Wenliao Du","doi":"10.1109/SDPC.2019.00092","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00092","url":null,"abstract":"Taking advantage of the cyclostationarity property of the vibration signal when fault arises in rolling bearing, the paper proposes a new fault diagnosis method of rolling bearing based on Slice Energy Entropy Spectral Correlation Density- Continuous Hidden Markov Model (SEESCD-CHMM). Firstly, the method of SEESCD is used to extract the feature of rolling bearing four states’ (normal, inner race fault, outer race fault and ball element fault) data to form the training feature vectors. Then the training feature vectors are used to train a CHMM and the optimal parameters of CHMM are obtained. At last, the SEESCD method is used to extract the test data to form the test feature vectors. The trained CHMM model is used to diagnose the test feature vectors and perfect diagnosis results are got which is 100% accurate. In the end, the advantages and the much higher accuracy of the proposed method is verified by comparing with other intelligent diagnosis methods.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129992829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This paper analyzes the importance of reliability accelerated test. In view of the limitations of current accelerated test of electronic products in multiple failure modes, this paper proposes an accelerated test method of multi-failure mode assembly electronic products based on reliability allocation. The reliability allocation method based on failure modes is presented. At the same time, the design method of accelerated test load spectrum and the calculation method of acceleration factor of assembly electronic products are proposed. Finally, the method proposed has been verified by typical case application.
{"title":"Multi-failure mode assembly electronic product accelerated test method","authors":"Chunlei Bai, Xianglei Kong, Yuexuan Ma, Chao Peng","doi":"10.1109/SDPC.2019.00044","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00044","url":null,"abstract":"This paper analyzes the importance of reliability accelerated test. In view of the limitations of current accelerated test of electronic products in multiple failure modes, this paper proposes an accelerated test method of multi-failure mode assembly electronic products based on reliability allocation. The reliability allocation method based on failure modes is presented. At the same time, the design method of accelerated test load spectrum and the calculation method of acceleration factor of assembly electronic products are proposed. Finally, the method proposed has been verified by typical case application.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"40 5","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120905973","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The power system is a vital sub-system for satellite operated successfully. With test and working environment limitations, the telemetry data from sensors and actuators is the only message to communicate with the ground about the status of satellites. In this term, an efficient and accuracy anomaly detection method for satellite power system could promote a powerful manner for identifying fault and trend that decrease safe margins. However, mostly anomaly detectors have to seriously rely on the prior expert knowledge and a nonlinear dimension reduction on telemetry data as the preliminary to reduce the computation scale and complexity. In this paper, a deep learning-based multiple sensors monitoring and abnormal discovery method for satellite power system is proposed to alleviate the limitations mentioned above. Firstly, an overview of the abnormal discovery method for satellite telemetry data is described. Then, a LSTMs-based prediction model and anomaly detection method for satellite power system are established. The data of multi sensors are monitored in one-time-step prediction model simultaneously, and are detected with an unsupervised method to alleviate the dependency of experts’ knowledge. Finally, the experiments are performed with the telemetry data from a simulated satellite power system. With the experiments, the proposed method shows great performance on the anomaly detection in a different type of faults with a high precision rate.
{"title":"Deep Learning based Multiple Sensors Monitoring and Abnormal Discovery for Satellite Power System","authors":"Jingyi Dong, Yuntong Ma, Datong Liu","doi":"10.1109/SDPC.2019.00120","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00120","url":null,"abstract":"The power system is a vital sub-system for satellite operated successfully. With test and working environment limitations, the telemetry data from sensors and actuators is the only message to communicate with the ground about the status of satellites. In this term, an efficient and accuracy anomaly detection method for satellite power system could promote a powerful manner for identifying fault and trend that decrease safe margins. However, mostly anomaly detectors have to seriously rely on the prior expert knowledge and a nonlinear dimension reduction on telemetry data as the preliminary to reduce the computation scale and complexity. In this paper, a deep learning-based multiple sensors monitoring and abnormal discovery method for satellite power system is proposed to alleviate the limitations mentioned above. Firstly, an overview of the abnormal discovery method for satellite telemetry data is described. Then, a LSTMs-based prediction model and anomaly detection method for satellite power system are established. The data of multi sensors are monitored in one-time-step prediction model simultaneously, and are detected with an unsupervised method to alleviate the dependency of experts’ knowledge. Finally, the experiments are performed with the telemetry data from a simulated satellite power system. With the experiments, the proposed method shows great performance on the anomaly detection in a different type of faults with a high precision rate.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126071582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Exploding foil initiator is a kind of electric explosive device and the primary energy source of weapon system. Importantly, the reliability for the whole weapon depends on the performance of exploding foil initiator. The firing sensitivity distribution model of exploding foil initiator was studied by both experimental test and mathematical statistics. The results indicate that the ignition sensitivity obeys the normal distribution, which provides theoretical guidance for the selecting the ignition sensitivity distribution model in the reliability evaluation of exploding foil initiator.
{"title":"Study on the distribution model of exploding foil initiator's ignition sensitivity","authors":"Qing Zhou, Simin He, Long Zhang, Fei Guo, Yi Li","doi":"10.1109/SDPC.2019.00189","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00189","url":null,"abstract":"Exploding foil initiator is a kind of electric explosive device and the primary energy source of weapon system. Importantly, the reliability for the whole weapon depends on the performance of exploding foil initiator. The firing sensitivity distribution model of exploding foil initiator was studied by both experimental test and mathematical statistics. The results indicate that the ignition sensitivity obeys the normal distribution, which provides theoretical guidance for the selecting the ignition sensitivity distribution model in the reliability evaluation of exploding foil initiator.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125954261","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In order to enhance the adaptive ability of Q factor wavelet and realize the multi-resolution decomposition of signal in the analysis filter bank, a sparse feature extraction method based on the multi-resolution decomposition of Q factor wavelet is proposed. In this method, the multi-order binary analysis filter banks are firstly constructed by using the Q factor wavelet, and then the optimal sub-band is selected by optimizing the iterative Q factor. Then, the shock interval of the optimal sub-band is selected as the atom, and the atom forms a complete dictionary through toeplitz extension to realize the sparse decomposition of the signal. Finally, the sparse signal is analyzed by envelope demodulation, and the fault characteristic frequency can be extracted effectively, which proves that the sparse signal has the ability to express fault features. The simulation and experimental results show that this method can effectively extract sparse feature of signals compared with DCT and DHT dictionaries. It not only overcomes the weakness of adaptive ability of traditional complete dictionaries, but also can effectively express sparsely.
{"title":"A Sparse Fault Feature Extraction Method for Rotating Machinery Based on Q Factor Wavelet Multi-resolution Decomposition","authors":"Junlin Li, L. Song, Lingli Cui, Huaqing Wang","doi":"10.1109/SDPC.2019.00121","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00121","url":null,"abstract":"In order to enhance the adaptive ability of Q factor wavelet and realize the multi-resolution decomposition of signal in the analysis filter bank, a sparse feature extraction method based on the multi-resolution decomposition of Q factor wavelet is proposed. In this method, the multi-order binary analysis filter banks are firstly constructed by using the Q factor wavelet, and then the optimal sub-band is selected by optimizing the iterative Q factor. Then, the shock interval of the optimal sub-band is selected as the atom, and the atom forms a complete dictionary through toeplitz extension to realize the sparse decomposition of the signal. Finally, the sparse signal is analyzed by envelope demodulation, and the fault characteristic frequency can be extracted effectively, which proves that the sparse signal has the ability to express fault features. The simulation and experimental results show that this method can effectively extract sparse feature of signals compared with DCT and DHT dictionaries. It not only overcomes the weakness of adaptive ability of traditional complete dictionaries, but also can effectively express sparsely.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125440128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the rapid development of artificial intelligence technology, intelligent recognition, diagnostic technology and trend prediction research on power production equipment failure are gradually being carried out. This paper does research into the induced draft fan based on the vibration signal data of the fan. It uses K-Means clustering and least squares support vector machine (LSSVM) to diagnose and trend the collected faults. Next, the trend prediction method for cracking failure of induced draft fan is also studied. Aiming at the large residual error caused by LSSVM regression prediction and actual value, a parameter optimization scheme based on PSO-LSSVM is proposed to improve the prediction accuracy.
{"title":"Research on Fault Diagnosis and Prediction of Power Plant Fans","authors":"Rongda Jiao, F. Fang","doi":"10.1109/SDPC.2019.00119","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00119","url":null,"abstract":"With the rapid development of artificial intelligence technology, intelligent recognition, diagnostic technology and trend prediction research on power production equipment failure are gradually being carried out. This paper does research into the induced draft fan based on the vibration signal data of the fan. It uses K-Means clustering and least squares support vector machine (LSSVM) to diagnose and trend the collected faults. Next, the trend prediction method for cracking failure of induced draft fan is also studied. Aiming at the large residual error caused by LSSVM regression prediction and actual value, a parameter optimization scheme based on PSO-LSSVM is proposed to improve the prediction accuracy.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128500967","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Due to a variety of noise interference, received signal strength indicator (RSSI)-based fingerprint data are often accompanied by uncertain factors. In order to solve the problem of positioning with high precision and accuracy in a complex indoor environment, this study designs a fingerprint positioning algorithm based on extended Dempster-Shafer evidence inference. First, a recognition framework is built to design a basic probability distribution function. Then a new evidence combination rule is proposed to assign different trust levels to the signal strength messages received from multiple sources, and the final position is obtained by converging the RSSI values. Finally, simulation experiments are conducted to show that the proposed algorithm is more valuable for improving the accuracy and accuracy of indoor positioning.
{"title":"An Information Fusion Positioning Algorithm Based on Extended Dempster-Shafer Evidence Theory","authors":"Lu Bai, Chenglie Du, Jinchao Chen","doi":"10.1109/SDPC.2019.00153","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00153","url":null,"abstract":"Due to a variety of noise interference, received signal strength indicator (RSSI)-based fingerprint data are often accompanied by uncertain factors. In order to solve the problem of positioning with high precision and accuracy in a complex indoor environment, this study designs a fingerprint positioning algorithm based on extended Dempster-Shafer evidence inference. First, a recognition framework is built to design a basic probability distribution function. Then a new evidence combination rule is proposed to assign different trust levels to the signal strength messages received from multiple sources, and the final position is obtained by converging the RSSI values. Finally, simulation experiments are conducted to show that the proposed algorithm is more valuable for improving the accuracy and accuracy of indoor positioning.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127127769","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With the development of microgrid technology, the installed capacity is increasing rapidly. To ensure the economy and reliability of the microgrid integrated with wind, photovoltaic and gas, the installed capacity should be configured rationally. In order to solve the problem of capacity allocation, this paper proposes an optimization model based on game theory, where the relationship among the distributed generations (DGs) and the power supply rules are considered. With particle swarm algorithm, the Nash equilibrium of the game model for the microgrid is worked out, as the reference for the decision-making of DG capacity allocation problem. Last, a case study is analyzed to verify the correction and the optimization of the proposed game model.
{"title":"Optimization of Microgrid Capacity Allocation Based on Game Theory","authors":"Shunping Jin, F. Fang","doi":"10.1109/SDPC.2019.00089","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00089","url":null,"abstract":"With the development of microgrid technology, the installed capacity is increasing rapidly. To ensure the economy and reliability of the microgrid integrated with wind, photovoltaic and gas, the installed capacity should be configured rationally. In order to solve the problem of capacity allocation, this paper proposes an optimization model based on game theory, where the relationship among the distributed generations (DGs) and the power supply rules are considered. With particle swarm algorithm, the Nash equilibrium of the game model for the microgrid is worked out, as the reference for the decision-making of DG capacity allocation problem. Last, a case study is analyzed to verify the correction and the optimization of the proposed game model.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130732873","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The basic conditions for intelligent mobile robots to achieve the corresponding functions are positioning, composition and navigation. However, when the robot is in a completely unknown environment and cannot obtain its own position using GPS, it can only use its own laser radar, IMU and odometer to complete the positioning and map construction. IMU has low cost, low power consumption and light weight, but its accuracy is not high and its error is large. Odometer works stably, but it can't locate independently. Lidar has high precision, but it is easy to be disturbed by environment, resulting in position loss of the robot. This paper combines the fusion algorithm of IMU inertial sensor, odometer and lidar. Based on Kalman filtering algorithm, the odometer-assisted IMU system and lidar feature extraction matching system are combined to obtain the real-time position of the robot. The simulation results show that the algorithm can correct the error of IMU inertial navigation system in real time, improve the stability of lidar and improve the positioning accuracy of the navigation system.
{"title":"Design of Intelligent Mobile Robot Positioning Algorithm Based on IMU/Odometer/Lidar","authors":"Zhaodong Li, Zhibao Su, Tingting Yang","doi":"10.1109/SDPC.2019.00118","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00118","url":null,"abstract":"The basic conditions for intelligent mobile robots to achieve the corresponding functions are positioning, composition and navigation. However, when the robot is in a completely unknown environment and cannot obtain its own position using GPS, it can only use its own laser radar, IMU and odometer to complete the positioning and map construction. IMU has low cost, low power consumption and light weight, but its accuracy is not high and its error is large. Odometer works stably, but it can't locate independently. Lidar has high precision, but it is easy to be disturbed by environment, resulting in position loss of the robot. This paper combines the fusion algorithm of IMU inertial sensor, odometer and lidar. Based on Kalman filtering algorithm, the odometer-assisted IMU system and lidar feature extraction matching system are combined to obtain the real-time position of the robot. The simulation results show that the algorithm can correct the error of IMU inertial navigation system in real time, improve the stability of lidar and improve the positioning accuracy of the navigation system.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130839791","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Due to the insufficient fault information of the tank fire control system and the complex fault characteristics, and the fault signal has the characteristics of high dimension, small sample and nonlinearity, the fault prediction of the fire control system is difficult and the reliability is low. In order to solve such problems, two intelligent predictive models for fire control systems for machine learning algorithms are proposed: multi-step prediction model of fire control system performance trend based on particle swarm improved support vector regression machine, and the fault state prediction model based on support vector classifier ,constructs a failure decision function and performs intelligent prediction combined with lateral prediction and longitudinal prediction to improve the reliability of fault prediction. The two models were verified by the power module of the fire control computer and sensor subsystem in a certain type of tank fire control system. The experimental results show that the proposed fire control system fault prediction model has high accuracy and practicability.
{"title":"Research on Comprehensive Fault Prediction Model of Tank Fire Control System Based on Machine Learning","authors":"Yingshun Li, Wei-Zhou Jia, X. Yi","doi":"10.1109/SDPC.2019.00170","DOIUrl":"https://doi.org/10.1109/SDPC.2019.00170","url":null,"abstract":"Due to the insufficient fault information of the tank fire control system and the complex fault characteristics, and the fault signal has the characteristics of high dimension, small sample and nonlinearity, the fault prediction of the fire control system is difficult and the reliability is low. In order to solve such problems, two intelligent predictive models for fire control systems for machine learning algorithms are proposed: multi-step prediction model of fire control system performance trend based on particle swarm improved support vector regression machine, and the fault state prediction model based on support vector classifier ,constructs a failure decision function and performs intelligent prediction combined with lateral prediction and longitudinal prediction to improve the reliability of fault prediction. The two models were verified by the power module of the fire control computer and sensor subsystem in a certain type of tank fire control system. The experimental results show that the proposed fire control system fault prediction model has high accuracy and practicability.","PeriodicalId":403595,"journal":{"name":"2019 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128004429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：