| Computer & Information Science |
|
|
|
|
| Nonlinear decoupling controller design based on least squares support vector regression |
| Wen Xiang-jun, Zhang Yu-nong, Yan Wei-wu, Xu Xiao-ming |
| Department of Automatic Control, Shanghai Jiao Tong University, Shanghai 200030, China; Department of Electronic and Electrical Engineering, University of Strathclyde, Glasgow G1 1QE, UK |
|
|
|
Abstract 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 unknown or state variables are difficult or impossible to measure. Simulation results showed the efficacy of the method.
|
|
Received: 06 April 2005
|
|
|
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
| |
Shared |
|
|
|
|
| |
Discussed |
|
|
|
|
