Induction Motor Control Based On Artificial Neural Networks Inverse System Method

Supported by Doctoral Fund of Ministry of Education of China, the paper focuses on decoupling control of the AC induction motors. Artificial neural networks (ANN) inverse system method is applied on decoupling control and speed estimation of the induction motor based on dSPACE system. Also, a strategy of the connection value amended on-line is proposed.Firstly, on the basis of theoretic analysis of the ANN inverse system, the methods, the steps, the design principles and the cautions are proposed to fabricate the ANN inverse system of original system. And then the ANN inverse system of the induction motor is constructed. Cascading the ANN inverse system with the induction motor system, a pseudo-linear system is completed. So the multivariable, nonlinear and coupling induction motor system is decoupled into two independent linear subsystems-speed subsystem and flux subsystem, and then a linear close-loop adjustor is designed to control each of the subsystems, and the method of the connection value amended on-line and simulation results are given.Secondly, an ANN left-inversion rotator speed estimation model of the induction motor is obtained based on theory of ANN and technology of left-inversion observation. The methods and the steps are given to construct the model, also the simulation results are given.Finally, the decoupling control based on ANN right-inversion system which connection value can be amended on-line and the speed estimation based on ANN left-inversion system are validated on the dSPACE platform. The control and estimate performance are satisfactory by experiment, and which shows ANN inverse system method is an effective and applied method for the control and speed estimation of induction motor.