基于小波网络的非线性系统建模与控制

Modeling and Control of Nonlinear Systems\= Based on Wavelet Networks

提出一种基于小波网络的非线性系统的建模和控制方法。使用小波网络对未知控制系统建立一步预测模型，基于Ｄａｖｉｄｏｎ最小二乘法得到自适应控制律。小波网络的权值由广义递推最小二乘法来学习，尺度参数和平移参数通过稳定的Ｄａｖｉｄｏｎ最小二乘法来获得。仿真结果表明了该方法的有效性。

This paper presents a method of modeling and control for nonlinear systems based on wavelet networks. This method performs single-step modeling using wavelet network for unknown controlled systems and Davidon least squares algorithm optimizes the control law. The weights in wavelet network are learned by general recursive least squere method and dilation with translation parameters by Davidon least square algorithm. Simulation results shows that the controller can be successfully applied in nonlinear systems.