# zbMATH — the first resource for mathematics

A SVM internal model control approach for unknown nonlinear discrete systems. (Chinese. English summary) Zbl 1212.93145
Summary: This paper presents an approximate internal model control approach for unknown nonlinear discrete SISO systems based on the support vector machine (SVM). The control law consists of a nominal controller and a robust controller. The nominal controller is derived from the SVM-NARMA approximate internal model by optimizing a quadratic performance index. The robust controller reduces the effects of the uncertainties. The stability and robustness of the closed-loop system are proved using the Lyapunov method. The results show that the method can be applied not only to systems with ill-defined relative degrees but also to non-minimum phase systems. Extensive simulations demonstrate the effectiveness of this control approach.
##### MSC:
 93C10 Nonlinear systems in control theory 93B35 Sensitivity (robustness) 93D05 Lyapunov and other classical stabilities (Lagrange, Poisson, $$L^p, l^p$$, etc.) in control theory