Neural Network Based Speed Control for 6/4 Switched Reluctance Motor

Abstract

The switched reluctance motor has been widely used in many industry and consumer application owing its simple and low cost. But the existing speed controller performance is not satisfied under non linear conditions, so has to be develop the new speed controller. This paper presents artificial neural network based speed controller for a 6/4 switched reluctance motor. The neuro controller is trained by the back propagation algorithm considering the current reference as the output, the error and its derivative as the inputs. The proposed speed controller has been simulated in Matlab/Simulink environment and the performance of the proposed controller is compared with PI controller. The simulation results are presented to demonstrate remarkable performance of the proposed controller for the switched reluctances motor.