JEE_V3_N2_RP3 V. Jamuna S. Rama Reddy Journal on Electrical Engineering 2230 – 7176 3 2 17 25 Pulse Width Modulation, Induction Motor Modeling, Total Harmonic Distortion, Neural Network Controller In this paper, the speed control of induction motor drives using neural networks is presented. A new simulink model for a neural network-controlled bidirectional chopper fed single phase induction motor is developed. The single phase induction motor is modeled using double field revolving theory. The parameters of the controller corresponding to various drive parameter sets are found off-line and stored as the training patterns. Under normal operation, the true drive parameters are real-time identified and they are converted into the controller parameter through multilayer forward computation by neural networks, in which, the connection weights of the multilayer feed forward network are estimated by back propagation learning algorithm. A comparative study has been made between the conventional and neural network controllers. It is observed that the neural network controlled drive system has better dynamic performance, reduced overshoot and faster transient response than the PI controlled system. Here the stator voltage is varied using the neural network controller, according to the non-linear load conditions, and the speed is maintained at the required level. October - December 2009 Copyright © 2009 i-manager publications. All rights reserved. i-manager Publications http://www.imanagerpublications.com/Article.aspx?ArticleId=1045