A novel excitation controller using support vector machines and approximate models

摘要

This paper proposes a novel excitation controller using support vector machines (SVM) and approximate models. The nonlinear control law is derived directly based on an input-output approximation method via Taylor expansion,which not only avoids complex control development and intensive computation,but also avoids online learning or adjust-ment. Only a general SVM modelling technique is involved in both model identification and controller implementation. The robustness of the stability is rigorously established using the Lyapunov method. Several simulations demonstrate the effectiveness of the proposed excitation controller.