Identification of nonlinear systems using robust stable recurrent high order neural networks
Qian Ji-xing · Journal of Zhejiang University(Engineering Science) · 2001
For identification of nonlinear systems using recurrent high order neural networks, a set of available robust stable learning rules and the corresponding structures based on the Lyapunov stability method are presented. It ensures that the identification error and parameters of the neural networks are stable in the sense of uniform ultimate boundedness when a nonlinear system is identified, even in the case there exists modeling error. The simulation shows that the proposed learning rules are effective.