摘要
永磁同步电机控制系统是多变量和非线性的。针对传统PI控制方法的不足,提出了一种基于RBF神经网络的永磁同步电机在线辨识与模型参考自适应控制方法。该方法利用RBF神经网络极强的非线性映射能力,通过对神经网络的离线和在线训练,实现了电机速度的自适应控制。仿真结果表明该方法控制精度高,动、静态特性好。
The control system of the permanent magnet synchronous motor is multi-variable and non-linear. To solve the defects of the traditional PI control method, a RBF neural network based on-line discrimination and model reference self-adaptive control method for permanent magnet synchronous motors is proposed which achieves the adaptive control of the motor speed by using the outstanding non-linear mapping ability of RBF neural network and the off-line and on-line training of the neural network. Simulations show that the method has high control accuracy and good dynamic and static characteristics.
出处
《华东电力》
北大核心
2008年第2期108-112,共5页
East China Electric Power
关键词
永磁同步电机
自适应控制
RBF神经网络
矢量控制
在线辨识
permanent magnet synchronous motor
self-adaptive control
RBF neural network
vector control
on-line discrimination
