{"title":"Virtual prototyping of a digital neural current controller","authors":"A. Dinu, M. Cirstea, M. McCormick","doi":"10.1109/IWRSP.1998.676688","DOIUrl":null,"url":null,"abstract":"The paper describes a significant case study of virtual prototyping in modern digital electronics. It outlines the design process of a neural predictive current controller for VSI-PWM inverters. MATLAB simulations of power system behaviour were initially performed to check the viability of the principles underlying the operation of the new controller. The controller was designed and tested using Viewlogic/Xilinx software for FPGA design/implementation. The intensive use of C++ programming to generate the required VHDL model of the neural networks considerably accelerated the design process.","PeriodicalId":310447,"journal":{"name":"Proceedings. Ninth International Workshop on Rapid System Prototyping (Cat. No.98TB100237)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"1998-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings. Ninth International Workshop on Rapid System Prototyping (Cat. No.98TB100237)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IWRSP.1998.676688","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 3
Abstract
The paper describes a significant case study of virtual prototyping in modern digital electronics. It outlines the design process of a neural predictive current controller for VSI-PWM inverters. MATLAB simulations of power system behaviour were initially performed to check the viability of the principles underlying the operation of the new controller. The controller was designed and tested using Viewlogic/Xilinx software for FPGA design/implementation. The intensive use of C++ programming to generate the required VHDL model of the neural networks considerably accelerated the design process.