Torque Ripple Minimization in Switched Reluctance Motor by Using Artificial Neural Network

This article presents switched reluctance motor (SRM) with an artificial neural network (ANN). The SRM motor is an electronically controlled motor like a BLDC motor. The motor required a power electronic converter for controlling stator poles. The main advantages of SRM motor are low cost, a low-temperature effect due to no winding on the rotor, easy manufacturing design, it operates at high speed, and high efficiency. The main disadvantage of the SRM motor is torque ripple and noise. This paper ANN-based SRM implemented for torque ripple minimization. The simulation results are verified in MATLAB /Simulink software. The verified results are motor speed, torque, current, and flux. The performance of SRM compared with Hysteresis Current Controller (HCC) and ANN controller. ANN-based SRM results are the best performance during motor starting and running conditions. The main outcomes of this paper are reducing starting torque and torque ripple minimization and reducing starting current and running current.