Field oriented control of induction motors using neural networks decouplers

This paper presents a novel approach to field oriented control (FOC) of induction motor drives. It discusses the introduction of artificial neural networks (ANN) in the area of decoupling control of induction motors using field oriented control principles. Two ANNs are presented for direct and indirect FOC applications. The first performs estimation of the stator flux and the second is trained to realize the decoupling control of the motor. The two ANNs use the backpropagation learning process to update their weights. A decoupling controller and a flux estimator are realized upon these ANNs using the MATLAB/SIMULINK Neural Network Toolbox. The data for training are obtained from a computer simulation of the system and from experimental measurements. The methodology used to train the network is presented and the results show very interesting features and good potential as an alternative to the conventional field oriented decoupling control of induction motors.