A Direct Adaptive Vector Neural Control of a Three-Phase Induction Motor

The paper proposes a complete neural solution to the direct vector control of three phase induction motor including realtime trained neural controllers for velocity, flux and torque, which permitted the speed up reaction to the variable load. The basic equations and elements of the direct field orie...

ver descrição completa

Detalhes bibliográficos
Autores: Ieroham S. Baruch, Irving Pavel de-la-Cruz
Tipo de documento: artigo
Estado:Versão publicada
Data de publicação:2009
País:México
Recursos:Instituto Politécnico Nacional
Repositório:Redalyc-IPN
OAI Identifier:oai:redalyc.org:61412466005
Acesso em linha:https://www.redalyc.org/articulo.oa?id=61412466005
Access Level:Acceso aberto
Palavra-chave:Ingeniería
Levenberg
Induction Motor
Neural Networks
Backpropagation
Marquardt Learning
Descrição
Resumo:The paper proposes a complete neural solution to the direct vector control of three phase induction motor including realtime trained neural controllers for velocity, flux and torque, which permitted the speed up reaction to the variable load. The basic equations and elements of the direct field oriented control scheme are given. The control scheme is realized by nine feedforward neural networks learned by real-time Backpropagation or off-line Levenberg-Marquardt algorithms with data taken by PI-control simulations. The graphical results of modelling show a better performance of the neural control system with respect to the PI controlled system realizing the same general control scheme.