Adaptive NN Tracking Control for Stochastic Pure-Feedback Nonlinear Systems in Non-Strict-Feedback form

This work is dedicated to solving the neural network-based tracking control problem for stochastic pure-feedback nonlinear systems in non-strict-feedback form. In order to deal with the difficulty caused by the non-strict-feedback structure, the structural characteristics of neural networks is employed by a lemma. At the same time, the pure-feedback structure in the system is also dealt with by the mean-value theorem. Based on the backstepping technology and neural networks, the adaptive neural tracking controller has been successfully constructed. And it guarantees all signals of closed-loop stochastic nonlinear systems are bounded in probability.