{"title":"Neural network control of a chopper-fed DC motor","authors":"J. Bates, M. Elbuluk, D. Zinger","doi":"10.1109/PESC.1993.472027","DOIUrl":null,"url":null,"abstract":"Neural networks are finding their way into control of power electronics and electric machines. Neural network controllers (NCs) possess generalization and learning capabilities that makes them suitable for control of nonlinear, time-variant plants. Neural network control of a chopper-fed DC motor is studied. A dynamic NC is used in a direct adaptive control configuration. After proper training, the dynamic NC emulates the inverse plant dynamic mapping. Training requirements of a NC are investigated. Simulation results showing system performance are presented. Hardware implementation of the NC is discussed.<<ETX>>","PeriodicalId":358822,"journal":{"name":"Proceedings of IEEE Power Electronics Specialist Conference - PESC '93","volume":"32 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1993-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of IEEE Power Electronics Specialist Conference - PESC '93","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/PESC.1993.472027","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 10
Abstract
Neural networks are finding their way into control of power electronics and electric machines. Neural network controllers (NCs) possess generalization and learning capabilities that makes them suitable for control of nonlinear, time-variant plants. Neural network control of a chopper-fed DC motor is studied. A dynamic NC is used in a direct adaptive control configuration. After proper training, the dynamic NC emulates the inverse plant dynamic mapping. Training requirements of a NC are investigated. Simulation results showing system performance are presented. Hardware implementation of the NC is discussed.<>