{"title":"Machine learning method with compensation distance technique for gear fault detection","authors":"Zhixin Yang, Jianhua Zhong, S. F. Wong","doi":"10.1109/WCICA.2011.5970591","DOIUrl":null,"url":null,"abstract":"In this paper, a condition monitoring and fault diagnosis method for rotating machineries using machine learning technologies including artificial neural network (ANNs) and support vector machine (SVMs) is described. The vibration signal is acquired from gearbox used in local power generation industry for analysis of potential defects. Wavelet packet transforms (WPT) and time domains statistical are used to extraction features, and the compensation distance evaluation technique (CDET) is applied to select optimal feature via sensitivities ranking. A comparative experiment study of the efficiency of ANN and SVM in predication of failure is carried out. The results reveal that the proposed feature selection and machine learning algorithms could be effectively used automatic diagnosis of gear faults.","PeriodicalId":211049,"journal":{"name":"2011 9th World Congress on Intelligent Control and Automation","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2011-06-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"7","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2011 9th World Congress on Intelligent Control and Automation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/WCICA.2011.5970591","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 7
Abstract
In this paper, a condition monitoring and fault diagnosis method for rotating machineries using machine learning technologies including artificial neural network (ANNs) and support vector machine (SVMs) is described. The vibration signal is acquired from gearbox used in local power generation industry for analysis of potential defects. Wavelet packet transforms (WPT) and time domains statistical are used to extraction features, and the compensation distance evaluation technique (CDET) is applied to select optimal feature via sensitivities ranking. A comparative experiment study of the efficiency of ANN and SVM in predication of failure is carried out. The results reveal that the proposed feature selection and machine learning algorithms could be effectively used automatic diagnosis of gear faults.