D. Sawitri, D. A. Asfani, M. Purnomo, I. Purnama, M. Ashari
{"title":"Early detection of unbalance voltage in three phase induction motor based on SVM","authors":"D. Sawitri, D. A. Asfani, M. Purnomo, I. Purnama, M. Ashari","doi":"10.1109/DEMPED.2013.6645772","DOIUrl":null,"url":null,"abstract":"Unbalance voltage supply in induction motor is a crucial problem. This paper proposes an original system to detect an unbalance voltage condition in induction motor using Support Vector Machine (SVM). Induction motor current, as a signal due to the unbalance voltage supply in three-phase induction motor, is recorded in lab bench. The features of recorded signals are extracted by wavelet transform and Principal Component Analysis algorithm. Then, the quality of detection is classified by SVM, and the average result of detection is 86%.","PeriodicalId":425644,"journal":{"name":"2013 9th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives (SDEMPED)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2013-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2013 9th IEEE International Symposium on Diagnostics for Electric Machines, Power Electronics and Drives (SDEMPED)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/DEMPED.2013.6645772","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6
Abstract
Unbalance voltage supply in induction motor is a crucial problem. This paper proposes an original system to detect an unbalance voltage condition in induction motor using Support Vector Machine (SVM). Induction motor current, as a signal due to the unbalance voltage supply in three-phase induction motor, is recorded in lab bench. The features of recorded signals are extracted by wavelet transform and Principal Component Analysis algorithm. Then, the quality of detection is classified by SVM, and the average result of detection is 86%.