开关磁阻电机自适应RBF神经网络控制方法研究

摘要

Switched reluctance motor doubly salient structure and magnetic circuit of the motor flux is highly saturated highly nonlinear, leading to classical PID control can not get higher control precision. Designing of feed-forward and feedback controller based on self-adaptive RBF neural network for SRM, the simulation results show that, this method can improve the precision of motor speed, torque pulsation, thereby optimizing the motor operat-ing performance.%开关磁阻电机(switched reluctance motor,SRM)双凸极结构和磁路高度饱和使得电机磁链呈高度非线性,导致经典PID控制不能得到较高的控制精度.设计了基于自适应RBF(radial basis function)神经网络的SRM前馈+反馈控制器,对电机实行自适应控制.仿真结果表明,该方法能提高电机转速精度,降低转矩脉动,从而优化电机的运行性能.