Using SVM to model and control nonlinear dynamical systems

This paper firstly provides an short introduction to least square support vector machine (LSSVM), a new class of kernel-based techniques introduced in statistical learning theory and structural risk minimization, then use it to model and control nonlinear systems, in which nonlinear predictive control framework is presented. The predictive control law is derived by a new stochastic search optimization algorithm. Simulation experiments are performed and indicate that the proposed method provides satisfactory performance with excellent generalization property.