A Novel Artificial Neural Network Based Space Vector Modulated DTC and Its Comparison with Other Artificial Intelligence (AI) Control Techniques

Abstract

On the basis of Artificial Neural Network (ANN) theory, this paper has put forth a new kind of controller for Space Vector Modulated (SVM) Direct Torque Control (DTC) system for Induction Motor. The controller has features like smooth operation, high dynamics, stable and robust performance. The training algorithm used is Resilient Back Propagation (RBP). The paper also presents the comparison of proposed ANN controller with other intelligent controllers (Fuzzy based control and Fuzzy_Sliding Mode Control) for the drive, based on various control performance criterion at transient state as well as steady state. It is observed that while working with comparatively less control efforts, proposed ANN improves the performance of SVM_DTC in all-round way. Simulation results confirm the superiority and feasibility of the proposed ANN controller. © Springer-Verlag Berlin Heidelberg 2013.