Neural network modulation for a Direct Torque controlled Induction Motor Drive

SIMULINK implementation of an artificial neural network (ANN) based Direct Torque Control (DTC) of Induction Motor Drive is presented in this paper. DTC is one of the most advanced control methods. Using DTC, an induction motor is driven by an inverter whose switching pattern is determined by the errors in the reference and estimated values of the machine flux and torque. To optimize the performance of the DTC scheme, a neural network based DTC scheme has been presented. Neural network is employed to determine the switching pattern for the inverter. The neural network employed uses the Levenberg-Marquardt back propagation algorithm for the adjustment of weights. The main advantage of the scheme is the parallel computation which decreases the computation time of the existing DTC scheme.