基于改进型Volterra基函数网络的直接自适应逆控制方法  

Direct Adaptive Inverse Control Strategy Based on Modified VPBF Neural Networks

作　　者：党映农[1] 韩崇昭[1] 

机构地区：[1]西安交通大学电子与信息工程学院,陕西西安710049

出　　处：《控制与决策》2001年第5期633-636,共4页Control and Decision

摘　　要：构造一种改进型 Volterra基函数网络 ,其特点是结构简单 ,容易离线确定最佳网络结构和初始权值。通过利用该网络在线学习非线性系统的逆 ,构造出一种非线性系统的直接自适应逆控制策略 ,并从理论上证明了闭环系统跟踪误差一致最终有界。A modified Volterra polynomial basis function (VPBF) neural network with simple structure is constructed. The structure and the initial parameters are easily determined. A direct adaptive inverse control strategy is proposed by on line learning the inverse of the controller plant directly by using modified VPBF neural networks. The closed loop control system is proved to be uniformly ultimately bounded (UUB). A simulation result shows that the strategy has good robustness.

关 键 词：自适应逆控制 改进型Volterra基函数网络 神经网络 PID控制器 

分 类 号：TP273.2[自动化与计算机技术—检测技术与自动化装置] TP183[自动化与计算机技术—控制科学与工程]