基于RBF神经网络在线辨识的永磁无刷直流电机单神经元PID模型参考自适应控制

Single Neuron PID Model Reference Adaptive Control for PM Rushless DC Motors Based on RBF Neural Network On-Line Identification

永磁无刷直流电机控制系统是多变量和非线性的。针对传统PID控制方法的不足,提出一种基于径向基函数神经网络在线辨识的单神经元PID模型参考自适应控制方法,并用于永磁无刷直流电机的控制中。该方法构造了一个径向基函数神经网络对系统进行在线辨识,建立其在线参考模型,由单神经元控制器完成控制器参数的自学习,并在数字信号处理器中实现控制参数的在线调节。系统较好地实现了给定速度参考模型的自适应跟踪,结构简单,能适应环境变化,具有较强的鲁棒性。

The PM brushless DC motor is a multi-variable and non-linear system. This paper presents a novel approach of single neuron PID model reference adaptive control for PM brushless DC motors based on radial basis function （RBF） neural network on-line identification in virtue of the disadvantage of conventional PID control. A RBF network is built to identify the system on-line.It constructs the on-line reference model. Self-learning of controller parameters is implemented by single neuron controller. And a digital signal processor is used to fully prove the flexibility of the control scheme in real time. Excellent flexibility and adaptability as well as high precision and good robustness are obtained by the proposed strategy.