Title :
Study on SVM based model predictive control
Author :
Zhong, Weimin ; Pi, Daoying ; Sun, Youxian
Author_Institution :
Inst. of Modern Control Eng., Zhejiang Univ., Hangzhou, China
Abstract :
A SVM with linear kernel based single-step predictive model and algorithm are developed after simple discussion of model predictive control. A predictive model is established by non-linear system identification with SVM. An explicit control law is gotten through the predictive control mechanism. Simulation results show that SVM based predictive control can be applied for non-linear system, and the SVM based single-step predictive of non-linear system has good performance in keeping reference trace and interference-free.
Keywords :
identification; nonlinear control systems; predictive control; support vector machines; SVM based model predictive control; nonlinear system identification; single step predictive algorithm; single step predictive model; Control engineering; Electronic mail; Industrial control; Laboratories; Modems; Predictive control; Predictive models; Sun; Support vector machines; System identification;
Conference_Titel :
Intelligent Control and Automation, 2004. WCICA 2004. Fifth World Congress on
Print_ISBN :
0-7803-8273-0
DOI :
10.1109/WCICA.2004.1340648