基于BP神经网络的开关磁阻电机建模及仿真

Modeling and Simulation of Switched Reluctance Motor Based on BP Neural Network

为了改善开关磁阻电机的性能分析和控制效果,建立精确的开关磁阻电机模型是极其重要的。在获得准确的电机电磁特性基础上,利用神经网络所具有的非线性映射能力,建立开关磁阻电机非线性模型。本文采用基于附加动量法的BP神经网络建立开关磁阻电机磁链模型和转矩模型,同时在Matlab/Simulink平台上搭建电机控制系统模型。实验表明,该建模方法能满足开关磁阻电机驱动系统的高性能要求。

In order to improve the performance analysis and control effect of switched reluctance motor, it is very important to establish accurate switched reluctance motor model. Based on the accurate electromagnetic properties of the motor ,the non-linear model of the switched reluctance motor is established by using the nonlinear mapping ability of the neural network. In this paper, the flux linkage model and torque model of switched reluctance motor are established by BP neural network based on additional momentum method. At the same time, the model of motor control system is built on Matlab/Simulink platform. Experiments show that the modeling method can meet the high performance requirements of the switched reluctance motor drive system.