Adaptive vector control of a three-phase induction motor using neural networks

This work presents nonlinear techniques applied to the speed control of a three-phase squirrel-cage induction motor. Artificial neural networks are used to develop adaptive control strategies based on nonlinear dynamic system identification and nonlinear parameter estimation. The principal results include a nonlinear rotor flux observer based on recurrent neural networks, and a nonlinear rotor time constant estimator based on nonrecurrent neural networks. Computer simulation results are obtained and the performance of the resulting adaptive field-oriented controller is analyzed.<>