Self-tuning control of switched reluctance motors for optimized torque per ampere at all operating points

Abstract

Online self-tuning of control angles of a switched reluctance motor (SRM) is essential to optimize its performance in the presence of manufacturing imperfections. This paper reports an adaptive control scheme to optimize the torque per ampere at low and high speeds using artificial neural networks (ANN). An heuristic optimization technique has been introduced to find the changes in control angles. Using these results, the ANN will update its synaptic weights. Computer simulation has been employed to show the feasibility of this approach. Experimental results are provided to demonstrate the working of the self-tuning control.