电液伺服系统的神经网络在线学习补偿自适应控制

基于反馈误差学习法、小波分析理论并结合面向控制的辨识思想，提出了一种神经网络在线学习补偿自适应控制结构。基于被控过程的小波变换结果信息利用反馈误差学习法调整控制参数。利用“参征器”实行监督控制，避免控制器的输出产生振荡或进入饱和状态。工程应用表明，该方法将过程辨识和“参征器”引入神经网络的学习和控制中，可有效地提高了系统的控制品质。

A Neural Network On-line Self-learning Adaplive Control of Electro-hydraulic Servo System

In this paper,a neural network on line self learn adaptive control and OSC compensate control based on the feedback error learning and wavelet analytic theory combined with identification idea faced controlling is introduced.The control parameters can be regulated on line by using the measured input/output data with feedback error learning method,OSC get up of supervise control function,so as to prevent the output of the controller income oscillation and saturation.Application results show the control method can effectively enhance the control performances of the system by introducing process identification in neural network learning and controlling.