An approach of nonlinear model multi-step-ahead predictive control based on SVM

Abstract

In this paper, a support vector machine (SVM) with polynomial kernel function based nonlinear model multi-step-ahead controller is presented. A SVM based multi-step-ahead predictive model is established by black-box identification. And control law is obtained by numerical and optimization methods respectively. The effect of controller is demonstrated on a recognized benchmark problem. Simulation results show that multi-step-ahead predictive controller can be well applied to nonlinear system with good performance. © Springer-Verlag Berlin Heidelberg 2005.