SIMULATION STUDY OF ADAPTIVE SPEED CONTROL OF VSI FED INDUCTION MOTOR DRIVE

Abstract

Multilayer Neural Networks have been used successfully in pattern recognition problems, and numerous applications have been suggested in the literature. Back propagation is one of the standard methods used in these cases to adjust the weights (parameters) of the neural networks. Multilayer neural networks are being used for the identification and control of nonlinear dynamical systems and back-propagation method is being used for such problems as dynamic back propagation method. In this dissertation work, a neural network based identification and control scheme is presented for control of VSI fed induction motor drive. A single artificial neural network is trained to capture the nonlinear dynamics of the induction motor. A control law is derived using the dynamics captured by the network and employed to force the stator currents and rotor speed to follow prescribed trajectories. The network architecture adapts and generalizes its learning to a wide variety of loads. Extensive simulations reveal that neural designs are effective means of system identification and control for time-varying nonlinear systems, in the presence of uncertainty