Umar Saleem, Weinjie Liu, Weilin Li, M. U. Sardar, Muhammad Mobeen Aslam, Saleem Riaz
{"title":"利用机器学习驱动的故障分类改进飞机发电机 PHM 系统","authors":"Umar Saleem, Weinjie Liu, Weilin Li, M. U. Sardar, Muhammad Mobeen Aslam, Saleem Riaz","doi":"10.1109/ICETSIS61505.2024.10459418","DOIUrl":null,"url":null,"abstract":"Prognostic and Health Management (PHM) played a vital role in the industrial revolution. An efficient PHM system improves reliability and safety by detecting whether an industrial component has deviated from its normal operating condition, predicting when a fault will occur, and classifying the type of fault. Due to the rapid development of more electric aircraft in recent years, the electric power system of aircraft has become more critical in ensuring safe flying. This research mainly focuses on classifying aircraft generator faults using the Support Vector Machine (SVM). To use the SVM for fault classification, firstly, create a data set of 1112 records containing all possible types of short circuit faults and normal states using the MATLAB Simulink model. Extract features from these records by decomposing them with Wavelet Transform. The principal component analysis (PCA) optimization technique is used on detail coefficients for trained SVM that will correctly classify generator faults. Then, train the SVM at each type of fault and normal state using 70% of the data and test it on the remaining 30%. It has been observed that if the system works under normal working conditions, all SVM output will be zero. In the faulty condition, the SVM output that belongs to the type or class of fault will be one and will display the type of fault. The suggested technique has been extensively evaluated for several fault types under various operating conditions. The SVM results demonstrate impressive accuracy in fault classification and significantly improve aviation generators' PHM systems.","PeriodicalId":518932,"journal":{"name":"2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Enhancing PHM System of Aircraft Generator with Machine Learning-Driven Faults Classification\",\"authors\":\"Umar Saleem, Weinjie Liu, Weilin Li, M. U. Sardar, Muhammad Mobeen Aslam, Saleem Riaz\",\"doi\":\"10.1109/ICETSIS61505.2024.10459418\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Prognostic and Health Management (PHM) played a vital role in the industrial revolution. An efficient PHM system improves reliability and safety by detecting whether an industrial component has deviated from its normal operating condition, predicting when a fault will occur, and classifying the type of fault. Due to the rapid development of more electric aircraft in recent years, the electric power system of aircraft has become more critical in ensuring safe flying. This research mainly focuses on classifying aircraft generator faults using the Support Vector Machine (SVM). To use the SVM for fault classification, firstly, create a data set of 1112 records containing all possible types of short circuit faults and normal states using the MATLAB Simulink model. Extract features from these records by decomposing them with Wavelet Transform. The principal component analysis (PCA) optimization technique is used on detail coefficients for trained SVM that will correctly classify generator faults. Then, train the SVM at each type of fault and normal state using 70% of the data and test it on the remaining 30%. It has been observed that if the system works under normal working conditions, all SVM output will be zero. In the faulty condition, the SVM output that belongs to the type or class of fault will be one and will display the type of fault. The suggested technique has been extensively evaluated for several fault types under various operating conditions. The SVM results demonstrate impressive accuracy in fault classification and significantly improve aviation generators' PHM systems.\",\"PeriodicalId\":518932,\"journal\":{\"name\":\"2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-01-28\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICETSIS61505.2024.10459418\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2024 ASU International Conference in Emerging Technologies for Sustainability and Intelligent Systems (ICETSIS)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICETSIS61505.2024.10459418","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Enhancing PHM System of Aircraft Generator with Machine Learning-Driven Faults Classification
Prognostic and Health Management (PHM) played a vital role in the industrial revolution. An efficient PHM system improves reliability and safety by detecting whether an industrial component has deviated from its normal operating condition, predicting when a fault will occur, and classifying the type of fault. Due to the rapid development of more electric aircraft in recent years, the electric power system of aircraft has become more critical in ensuring safe flying. This research mainly focuses on classifying aircraft generator faults using the Support Vector Machine (SVM). To use the SVM for fault classification, firstly, create a data set of 1112 records containing all possible types of short circuit faults and normal states using the MATLAB Simulink model. Extract features from these records by decomposing them with Wavelet Transform. The principal component analysis (PCA) optimization technique is used on detail coefficients for trained SVM that will correctly classify generator faults. Then, train the SVM at each type of fault and normal state using 70% of the data and test it on the remaining 30%. It has been observed that if the system works under normal working conditions, all SVM output will be zero. In the faulty condition, the SVM output that belongs to the type or class of fault will be one and will display the type of fault. The suggested technique has been extensively evaluated for several fault types under various operating conditions. The SVM results demonstrate impressive accuracy in fault classification and significantly improve aviation generators' PHM systems.