Pub Date : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942892
Yun Wang, Bo Jing, Yifeng Huang, Xiaoxuan Jiao, Shenglong Wang, Qinglin Liu
Aiming at the problems of poor real-time fault diagnosis and low efficiency in the complex equipment PHM engineering maturity, a fault diagnosis implementation scheme based on PHM high performance computing platform is proposed. The BP neural network algorithm is used as an example to verify. Firstly, the current technical status and urgent needs of the existing PHM operation platform are analyzed. The overall structure and software and hardware optimization configuration of PHM high performance computing platform with FPGA and DSP as the core are expounded. Then, by means of module division, HDL design, functional verification and package testing of the time domain feature extraction method and BP neural network, the implementation of the platform fault diagnosis algorithm is carried out. Finally, combined with the analysis of a certain type of on-board fuel pump fault data, comparative analysis was carried out with the CPU platform operation. The results show that the fault diagnosis implementation proposed in this paper has high real-time performance, low resource consumption and low power consumption, which can provide an important reference for complex equipment PHM engineering applications.
{"title":"Research of Equipment Fault Diagnosis Based on PHM High Performance Computing Platform","authors":"Yun Wang, Bo Jing, Yifeng Huang, Xiaoxuan Jiao, Shenglong Wang, Qinglin Liu","doi":"10.1109/phm-qingdao46334.2019.8942892","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942892","url":null,"abstract":"Aiming at the problems of poor real-time fault diagnosis and low efficiency in the complex equipment PHM engineering maturity, a fault diagnosis implementation scheme based on PHM high performance computing platform is proposed. The BP neural network algorithm is used as an example to verify. Firstly, the current technical status and urgent needs of the existing PHM operation platform are analyzed. The overall structure and software and hardware optimization configuration of PHM high performance computing platform with FPGA and DSP as the core are expounded. Then, by means of module division, HDL design, functional verification and package testing of the time domain feature extraction method and BP neural network, the implementation of the platform fault diagnosis algorithm is carried out. Finally, combined with the analysis of a certain type of on-board fuel pump fault data, comparative analysis was carried out with the CPU platform operation. The results show that the fault diagnosis implementation proposed in this paper has high real-time performance, low resource consumption and low power consumption, which can provide an important reference for complex equipment PHM engineering applications.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133681794","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}
Pub Date : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942982
Wenbo Wu, Liangzhi Men, Lu Zhang, Dequan Yu, Yang Wang, Hongyong Fu
In order to predict the reliability of semiconductor lasers, an accelerated degradation test (ADT) was proposed as an element of reliability testing. Temperature-stressed ADT was applied for 8 Semiconductor lasers which used in space missions, and the degradation characteristics of output power of semiconductor lasers were studied. Then, a reliability model based multi-output Gaussian process regression (MOGP) was proposed to evaluate the lifetime and reliability for laser diodes. The advantage of the proposed MOGP based method is that it utilizes the output correlation between multiple degradation traces to make the outputs utilize each other's information and provide more accurate prediction than single modeling. Thereby improving the prediction accuracy. Furthermore, verifying applications and cases studies are discussed to prove the generality and practicability of the proposed reliability prediction model. Results show that the accuracy of the proposed MOGP based method is twice that of the SVM method.
{"title":"Accelerated Degradation Testing and MOGP Method","authors":"Wenbo Wu, Liangzhi Men, Lu Zhang, Dequan Yu, Yang Wang, Hongyong Fu","doi":"10.1109/phm-qingdao46334.2019.8942982","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942982","url":null,"abstract":"In order to predict the reliability of semiconductor lasers, an accelerated degradation test (ADT) was proposed as an element of reliability testing. Temperature-stressed ADT was applied for 8 Semiconductor lasers which used in space missions, and the degradation characteristics of output power of semiconductor lasers were studied. Then, a reliability model based multi-output Gaussian process regression (MOGP) was proposed to evaluate the lifetime and reliability for laser diodes. The advantage of the proposed MOGP based method is that it utilizes the output correlation between multiple degradation traces to make the outputs utilize each other's information and provide more accurate prediction than single modeling. Thereby improving the prediction accuracy. Furthermore, verifying applications and cases studies are discussed to prove the generality and practicability of the proposed reliability prediction model. Results show that the accuracy of the proposed MOGP based method is twice that of the SVM method.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132098843","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}
Pub Date : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942983
Yanyan Wang, Xiaohui Wang, Bingxiu Guo, G. Zhang
GJB150 has been the main criterion for the environmental adaptability design in China since its publication. In 2009, GJB150A was released as an alternative criterion for GJB150. The method of salt fog test of GJB150A is different from GJB150. The spray method in GJB150A is alternate and the spray method in GJB150 is continuous. In order to compare the difference of the corrosion degree for typical non-metallic materials of the two test methods, the paper chose the material of typical and representative rubber of organic polymer and PCB specimens coated with different organic coatings and the test applied GJB150 and GJB150A respectively. The results of two tests were compared and analyzed and it demonstrated that salt fog test in GJB150A has higher corrosion degree when applied to rubber and PCB coated with organic coating. At the same time, rubber and acrylic coatings are less susceptible to salt spray corrosion.
{"title":"The Analysis for the Contrast of Salt Fog Test of Typical Nonmetallic Material with GJB150 and GJB50A","authors":"Yanyan Wang, Xiaohui Wang, Bingxiu Guo, G. Zhang","doi":"10.1109/phm-qingdao46334.2019.8942983","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942983","url":null,"abstract":"GJB150 has been the main criterion for the environmental adaptability design in China since its publication. In 2009, GJB150A was released as an alternative criterion for GJB150. The method of salt fog test of GJB150A is different from GJB150. The spray method in GJB150A is alternate and the spray method in GJB150 is continuous. In order to compare the difference of the corrosion degree for typical non-metallic materials of the two test methods, the paper chose the material of typical and representative rubber of organic polymer and PCB specimens coated with different organic coatings and the test applied GJB150 and GJB150A respectively. The results of two tests were compared and analyzed and it demonstrated that salt fog test in GJB150A has higher corrosion degree when applied to rubber and PCB coated with organic coating. At the same time, rubber and acrylic coatings are less susceptible to salt spray corrosion.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115192575","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}
Pub Date : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942811
Xinyuan Wang, Yuhua Cheng, J. Mi, L. Bai
Since the rotary machinery equipment is the fundamental and crucial part of mechanical equipment, the fault diagnosis of rotary machinery has become a particularly important issue in mechanical engineering. This paper adopted a genetic algorithm (GA) based on the cloud model (CM) to optimize traditional SVM for fault diagnosis of rotating machinery with dual optimization levels. The first optimization level is to use the CM to optimize crossover operators in GA (CM-GA), so as to obtain a faster search process and achieve more effective optimization results. The second optimization level is using CM-GA to optimize SVM. In addition, we have proposed an optimized framework of SVM model based on CM-GA for fault diagnosis of rotating machinery. In the end we used two kinds of rolling bearing fault database for experiments and the diagnosis results have proved the validity and feasibility of the proposed method.
{"title":"Dual-Optimized Support Vector Machine for Fault Diagnosis of Rotating Equipment Based on CM-GA","authors":"Xinyuan Wang, Yuhua Cheng, J. Mi, L. Bai","doi":"10.1109/phm-qingdao46334.2019.8942811","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942811","url":null,"abstract":"Since the rotary machinery equipment is the fundamental and crucial part of mechanical equipment, the fault diagnosis of rotary machinery has become a particularly important issue in mechanical engineering. This paper adopted a genetic algorithm (GA) based on the cloud model (CM) to optimize traditional SVM for fault diagnosis of rotating machinery with dual optimization levels. The first optimization level is to use the CM to optimize crossover operators in GA (CM-GA), so as to obtain a faster search process and achieve more effective optimization results. The second optimization level is using CM-GA to optimize SVM. In addition, we have proposed an optimized framework of SVM model based on CM-GA for fault diagnosis of rotating machinery. In the end we used two kinds of rolling bearing fault database for experiments and the diagnosis results have proved the validity and feasibility of the proposed method.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124371502","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}
Pub Date : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942956
Y. Li, Bohua Qiu, Muheng Wei, W. Sun, Xueliang Liu
Rolling bearings play an important part in rotating machinery. As they work in complex conditions, faults will occur sometimes. Therefore, it is necessary to detect the faults early. Traditional bearing fault diagnosis methods are often based on mechanism analysis and feature selection, and the process is relatively complicated. Deep learning methods, however, have the ability to extract and select features automatically, which greatly reduces the workload. In recent years, deep learning-based methods have been successfully used in many fields, such as computer vision, voice recognition, medical diagnosis. In this paper, the end-to-end fault methods based on deep learning are proposed. The Long Short-Term Memory (LSTM) network, Gated Recurrent Unit (GRU) network and One-Dimensional Convolutional Neural Network (1D CNN) are used to build the deep learning network architecture respectively. A methodology is proposed for rolling bearing fault diagnosis, including data preprocessing, network modeling, training, validation and testing. Test bench data is used for fault diagnosis and the results show that deep learning based end-to-end methods are effective for the fault diagnosis of rolling bearings and that the model based on 1D CNN has the best performance.
{"title":"Deep Learning based End-to-End Rolling Bearing Fault Diagnosis","authors":"Y. Li, Bohua Qiu, Muheng Wei, W. Sun, Xueliang Liu","doi":"10.1109/phm-qingdao46334.2019.8942956","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942956","url":null,"abstract":"Rolling bearings play an important part in rotating machinery. As they work in complex conditions, faults will occur sometimes. Therefore, it is necessary to detect the faults early. Traditional bearing fault diagnosis methods are often based on mechanism analysis and feature selection, and the process is relatively complicated. Deep learning methods, however, have the ability to extract and select features automatically, which greatly reduces the workload. In recent years, deep learning-based methods have been successfully used in many fields, such as computer vision, voice recognition, medical diagnosis. In this paper, the end-to-end fault methods based on deep learning are proposed. The Long Short-Term Memory (LSTM) network, Gated Recurrent Unit (GRU) network and One-Dimensional Convolutional Neural Network (1D CNN) are used to build the deep learning network architecture respectively. A methodology is proposed for rolling bearing fault diagnosis, including data preprocessing, network modeling, training, validation and testing. Test bench data is used for fault diagnosis and the results show that deep learning based end-to-end methods are effective for the fault diagnosis of rolling bearings and that the model based on 1D CNN has the best performance.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124544190","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}
Pub Date : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942910
Yongsheng Bai, Chiming Guo, Shuang-han Ling
For the devices with condition inspections, the method for joint optimization of inspection interval and spare parts inventory strategy was studied. Firstly, the periodic inspection policy was introduced, based on which the spare parts consumption and provisioning process was analyzed; secondly, the cost structure of maintenance support was decomposed, and the mathematical models for total maintenance support cost were established; thirdly, a simulation method was proposed, by which the periodic inspection interval, spare parts maximum stock level and ordering interval could be optimized jointly; lastly, a numerical example was given, which demonstrated the optimization method and models above.
{"title":"Research on Joint Optimization of Condition Inspection Interval and Spare Parts Inventory Strategy","authors":"Yongsheng Bai, Chiming Guo, Shuang-han Ling","doi":"10.1109/phm-qingdao46334.2019.8942910","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942910","url":null,"abstract":"For the devices with condition inspections, the method for joint optimization of inspection interval and spare parts inventory strategy was studied. Firstly, the periodic inspection policy was introduced, based on which the spare parts consumption and provisioning process was analyzed; secondly, the cost structure of maintenance support was decomposed, and the mathematical models for total maintenance support cost were established; thirdly, a simulation method was proposed, by which the periodic inspection interval, spare parts maximum stock level and ordering interval could be optimized jointly; lastly, a numerical example was given, which demonstrated the optimization method and models above.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"118 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114483994","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}
Pub Date : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942848
Yuemei Zhang, Shaojie Zhang, Li Wang
This paper presents a weighted method of residual useful life (RUL) prediction based on generalized Eyring model and support vector machine (SVM) under multiple stress. In the first step, the Weibull distribution model is developed and the Weibull parameters can be obtained through maximum likelihood estimation (MLE). Secondly, this paper uses the generalized Eyring model and SVM model to establish two RUL prediction model respectively. Thirdly, a weight coefficient is introduced to allocate the two models. By minimizing the sum of error between real lifetime and estimated prediction, the value of weight coefficient is determined and the final RUL prediction model can be established. An accelerated life testing (ALT) case study of oil paper for power transformer is implemented to illustrate the performance of the proposed method under temperature-voltage stress. And the result of the ALT shows that the prediction accuracy of the weighted model is higher compared with generalized Eyring model and SVM model individually.
{"title":"A Weighted Residual Useful Life Prediction Method for Weibull Distribution Model under Multiple Stress","authors":"Yuemei Zhang, Shaojie Zhang, Li Wang","doi":"10.1109/phm-qingdao46334.2019.8942848","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942848","url":null,"abstract":"This paper presents a weighted method of residual useful life (RUL) prediction based on generalized Eyring model and support vector machine (SVM) under multiple stress. In the first step, the Weibull distribution model is developed and the Weibull parameters can be obtained through maximum likelihood estimation (MLE). Secondly, this paper uses the generalized Eyring model and SVM model to establish two RUL prediction model respectively. Thirdly, a weight coefficient is introduced to allocate the two models. By minimizing the sum of error between real lifetime and estimated prediction, the value of weight coefficient is determined and the final RUL prediction model can be established. An accelerated life testing (ALT) case study of oil paper for power transformer is implemented to illustrate the performance of the proposed method under temperature-voltage stress. And the result of the ALT shows that the prediction accuracy of the weighted model is higher compared with generalized Eyring model and SVM model individually.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114493902","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}
Pub Date : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942847
He Liu, Wanqing Song
The paper presents one kind of filter based on fractional Fourier transform for one dimensional signal. Compared with other one-dimensional filters, this filter can improve the edge effect before and after filtering. Not only has high signal-to-noise ratio, but also there is no leak at signal of two terminals. When calculating the signal-to-noise ratio, I take four examples with low noise to high noise. Through MATLAB simulation, it shows that has excellent filter characteristics and is very suitable for signal processing.
{"title":"The Fractional Fourier Filtering without Edge Effect","authors":"He Liu, Wanqing Song","doi":"10.1109/phm-qingdao46334.2019.8942847","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942847","url":null,"abstract":"The paper presents one kind of filter based on fractional Fourier transform for one dimensional signal. Compared with other one-dimensional filters, this filter can improve the edge effect before and after filtering. Not only has high signal-to-noise ratio, but also there is no leak at signal of two terminals. When calculating the signal-to-noise ratio, I take four examples with low noise to high noise. Through MATLAB simulation, it shows that has excellent filter characteristics and is very suitable for signal processing.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"254 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117316631","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}
Pub Date : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942920
J. Zhang, B. Wu, M. Y. Zhang, T. Yip
The traditional risk analysis method attributes the accidents to the chain reaction of a single event, which highlights the importance of component errors for the accident consequences. With the increasing integration of social science and technology, information interaction becomes more prominent in system safety. Therefore, the Systems-Theoretic Accident Modelling and Processes (STAMP) is introduced to analysis the complex socio-technical system. It focuses on safety constraints, information interaction and process model, and deeply excavates the functions and impacts among components. The STAMP-based causal analysis is conducted in this paper for hazard identification of navigation safety during Beiwei routes in China. First, lessons are learned by analyzing the latest grounding accident of Beiyou25; Second, the problems existing in ships, wharfs, company and meteorology are thoroughly proposed based on the actual situation of the Beiwei routes to ensure the navigation safety.
{"title":"A STAMP-based Causal Analysis of the Beiyou25 Grounding Accident","authors":"J. Zhang, B. Wu, M. Y. Zhang, T. Yip","doi":"10.1109/phm-qingdao46334.2019.8942920","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942920","url":null,"abstract":"The traditional risk analysis method attributes the accidents to the chain reaction of a single event, which highlights the importance of component errors for the accident consequences. With the increasing integration of social science and technology, information interaction becomes more prominent in system safety. Therefore, the Systems-Theoretic Accident Modelling and Processes (STAMP) is introduced to analysis the complex socio-technical system. It focuses on safety constraints, information interaction and process model, and deeply excavates the functions and impacts among components. The STAMP-based causal analysis is conducted in this paper for hazard identification of navigation safety during Beiwei routes in China. First, lessons are learned by analyzing the latest grounding accident of Beiyou25; Second, the problems existing in ships, wharfs, company and meteorology are thoroughly proposed based on the actual situation of the Beiwei routes to ensure the navigation safety.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116294992","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}
Pub Date : 2019-10-01DOI: 10.1109/phm-qingdao46334.2019.8942846
Zhendong Yin, Li Wang, Yaojia Zhang, Yang Gao, Shanshui Yang
Compared with AC arc faults, there isn’t zero-crossing points in the current waveform when the DC arc faults occur. Dc arc fault brings great harm to the safe operation of power supply system. Wavelet transform (WT) is suitable for analyzing nonstationary signal, and multi-scale fuzzy entropy (MFE) is of excellent performance in detecting the uncertainty and complexity of the signal. The random fluctuation and uncertainty of current will be greatly enhanced when arc faults occur. This paper aims to elevate the property of detection of dc arc faults, WT and MFE are utilized to construct the fault features. Least squares support vector machine (LSSVM) is employed to be as the classifier to make the detection of dc arc faults. The result of the experiment shows the availability of the method this paper proposed.
{"title":"The DC Arc Fault Detection Method Taken Advantage of WT and MFE","authors":"Zhendong Yin, Li Wang, Yaojia Zhang, Yang Gao, Shanshui Yang","doi":"10.1109/phm-qingdao46334.2019.8942846","DOIUrl":"https://doi.org/10.1109/phm-qingdao46334.2019.8942846","url":null,"abstract":"Compared with AC arc faults, there isn’t zero-crossing points in the current waveform when the DC arc faults occur. Dc arc fault brings great harm to the safe operation of power supply system. Wavelet transform (WT) is suitable for analyzing nonstationary signal, and multi-scale fuzzy entropy (MFE) is of excellent performance in detecting the uncertainty and complexity of the signal. The random fluctuation and uncertainty of current will be greatly enhanced when arc faults occur. This paper aims to elevate the property of detection of dc arc faults, WT and MFE are utilized to construct the fault features. Least squares support vector machine (LSSVM) is employed to be as the classifier to make the detection of dc arc faults. The result of the experiment shows the availability of the method this paper proposed.","PeriodicalId":259179,"journal":{"name":"2019 Prognostics and System Health Management Conference (PHM-Qingdao)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124833356","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：