H-infinity tracking of unknown nonlinear systems using neural network

A stable neural adaptive control scheme is proposed in this work to achieve H-infinity performance for a class of unknown nonlinear SISO systems with external disturbances. Ill the control design, The controller is com prised of a certainty equivalence control term and a H-infinity compensating term, Tile neural network are used to approximate the unknown nonlinear functions for the design of tile equivalence controller, and the Lyapunov method is used for the update of the parameters of tile neural network, the stability of the proposed control algorithm call be guaranteed. Tile performance crf tile proposed method is demonstrated through the control of the inverted pendulum system.