Adaptive output tracking of a class of unknown nonlinear systems using neural networks

In this paper, a neural network based adaptive control is presented to solve the output tracking problem for a class of nonlinear continuous-time feedback linearizable systems with unknown nonlinearities. The adaptive control adopted in this paper ingeniously combines the sliding control outputs and the outputs of the multilayered neural networks to perform approximate input-output linearization. The sliding control is used to compensate the network approximation errors and the neural network parameters are updated according to the Lyapunov principle. It is shown that the outputs of the closed-loop system asymptotically track the desired output trajectories while maintaining the boundedness of all signals within the system. The effectiveness of the proposed control scheme is demonstrated by simulation examples.