Nonlinear decoupling controller design based on least squares support vector regression

被引：3

作者：

文香军 ^{[1
]}

张雨浓 ^{[2
]}

阎威武 ^{[1
]}

许晓鸣 ^{[1
]}

机构：

[1] Department of Automatic Control, Shanghai Jiao Tong University, Shanghai 200030, China

[2] Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1QE, UK

来源：

Journal of Zhejiang University Science A(Science in Engineering) | 2006年 / 02期

关键词：

Support Vector Machine (SVM); Decoupling control; Nonlinear system; Generalized inverse system;

D O I：

暂无

中图分类号：

TM571.6 [特殊控制器];

学科分类号：

0811 ; 081101 ;

摘要：

Support Vector Machines (SVMs) have been widely used in pattern recognition and have also drawn considerable interest in control areas. Based on a method of least squares SVM (LS-SVM) for multivariate function estimation, a generalized inverse system is developed for the linearization and decoupling control of a general nonlinear continuous system. The approach of inverse modelling via LS-SVM and parameters optimization using the Bayesian evidence framework is discussed in detail. In this paper, complex high-order nonlinear system is decoupled into a number of pseudo-linear Single Input Single Output (SISO) subsystems with linear dynamic components. The poles of pseudo-linear subsystems can be configured to desired positions. The proposed method provides an effective alternative to the controller design of plants whose accurate mathematical model is un- known or state variables are difficult or impossible to measure. Simulation results showed the efficacy of the method.

引用

页码：275 / 284

页数：10