Neural network-based adaptive tracking control for a class of uncertain stochastic nonlinear pure-feedback systems

In this paper, based on the wellknown back-stepping method, a novel adaptive neural network (NN) control scheme is introduced to achieve a desired tracking performance for a class of uncertain stochastic nonlinear pure-feedback systems. The neural networks are utilized to approximate unknown functions in analysis procedure. Based on the key assumption, the adaptive NN controller only needs to adjust less adaptive parameters, therefore, it is clear that the proposed approach can reduce on-line computation burden. It is proven that all the signals in the closed-loop system are uniformly ultimately bounded (UUB) and the tracking error can converge to a small neighborhood of zero by choosing the appropriate design parameters. A simulation example is used to verify the effectiveness of the proposed approach.