Lili Dong, Deyong Yang, Jianping Hu, Qizhi Yang, Y. Hu
{"title":"Compact optimization method of sample data and its application to axial fans on-line condition monitoring and fault diagnosis","authors":"Lili Dong, Deyong Yang, Jianping Hu, Qizhi Yang, Y. Hu","doi":"10.1109/ICITEC.2014.7105587","DOIUrl":null,"url":null,"abstract":"A compact optimization method with neural network fault diagnosis samples is presented by combining with grey correlation analysis theory, so as to resolve on-line fault diagnosis issues on massive amounts of samples affecting the neural network diagnostic performances and its application in engineering. This method is utilized to enhance the network performances of neural network, and speed up the convergent velocity, so as to reduce the time and misjudgment of the condition monitoring in the neural network and fault diagnosis, while its application steps in fault diagnosis are designed to be applied for the sample compact optimization of coal mine ventilator fault diagnosis. The simulation result shows that this method in this paper can be effective. Compared with the rough set neural network method, it has the advantage of simplified computation that is convenient for engineering applications.","PeriodicalId":293382,"journal":{"name":"Proceedings of 2nd International Conference on Information Technology and Electronic Commerce","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2014-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of 2nd International Conference on Information Technology and Electronic Commerce","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICITEC.2014.7105587","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
A compact optimization method with neural network fault diagnosis samples is presented by combining with grey correlation analysis theory, so as to resolve on-line fault diagnosis issues on massive amounts of samples affecting the neural network diagnostic performances and its application in engineering. This method is utilized to enhance the network performances of neural network, and speed up the convergent velocity, so as to reduce the time and misjudgment of the condition monitoring in the neural network and fault diagnosis, while its application steps in fault diagnosis are designed to be applied for the sample compact optimization of coal mine ventilator fault diagnosis. The simulation result shows that this method in this paper can be effective. Compared with the rough set neural network method, it has the advantage of simplified computation that is convenient for engineering applications.