Multiple models adaptive control based on RBF neural network dynamic compensation

Abstract

A novel multiple models adaptive control method is proposed to improve the dynamic performance of complex nonlinear systems under different operating modes. Multiple linearized models are established at each equilibrium point of the system. Each local linearized model is valid within a neighborhood of the point, and then an improved RBF algorithm is applied to compensate for modeling error. Simulation results are presented to demonstrate the validity of the proposed method. © Springer-Verlag Berlin Heidelberg 2005.