Torque Characteristic Modeling of Switched Reluctance Motor Based on BP Neural Network Optimized by Improved Sparrow Search Algorithm

Abstract

Establishing an accurate model of switched reluctance motor (SRM) has an important impact on improving the performance and control effect of SRM. Aiming at the high saturation of the magnetic circuit and the serious nonlinearity of the magnetic circuit when SRM is running, a nonlinear SRM model based on BP (back propagation) neural network optimized by improved sparrow search algorithm based on Tent chaotic mapping disturbed by fireflies (FTCSSA-BP) is proposed. The four phase 8/6 pole SRM model is established by using Ansys Maxwell software and the finite element calculation is carried out. Through the comparison of simulation and experimental values, it is verified that the model has higher accuracy than the standard SSA optimized BP neural network (SSA-BP) model and the standard BP neural network model, can better reflect the torque characteristics of SRM during operation, and has better generalization ability.