针对典型电液伺服控制系统非线性、参数时变的特点,常规PID控制无法满足控制性能要求.文中提出将小脑模型(CMAC)神经网络和PID相结合的控制策略.仿真结果表明,经过CMAC神经网络对常规PID控制器的输出不断在线学习,系统能够有效抑制扰动,并具有实时性好,输出误差小,鲁棒性强等优点.在系统参数变化,外界扰动的影响下,其控制性能得到明显提高.
Since the electro - hydraulic servo control system is nonlinear and its parameters vary with time, the demand of servo system is difficultly to meet by the general PID control. The method of Composite Cerebetlar Model Articulation Controller (CMAC) neural network with PID Control is proposed in this paper. The simulation results show that the output of general PID controller is unceasing on - line learning with CMAC neural network, and the servo system can effectively restrain the disturbance and it also has the advantages of good real time, little output error and strong robustness. The performance of servo system is obviously improved under the influence of parameter variation and external perturbation.