Based on high order dyna mi c neural network,this paper presents the tracking problem for uncertain nonlinear composite system,which contain s external disturbance,whose nonlinear ities are assumed to be unknown.A smooth contr oller is designed to guarantee a uniform ultimate boundedness property for the tracking error and a ll other signals in the closed loop.Certain meas ures are utilized to test its performance.No a priori knowledge of an upper bound on the “ optimal" weight and modeling error is required;the weights of neural networks are updated on-line.N umerical simulations performed on a simple example i llustrate and clarify the approach.
展开▼