Neural network based torque control of switched reluctance motor for hybrid electric vehicle propulsion at high speeds

This paper presents a neural network (NN) based solution to optimize the efficiency of a switched reluctance motor (SRM) for hybrid electric vehicle propulsion at high speeds. Based on the high learning ability of NN, the NN controller learns off-line the relationship between switching angles (turn-on and turn-off angles) corresponding to maximum motor efficiency and SRM operating points (torque, speed and battery voltage), and finds a pair of appropriate switching angles in real-time to control the SRM to track the command change. Simulation results are presented to demonstrate that the proposed controller provides good dynamic performance with respect to changes in operation points while optimizing the motor efficiency.