Adaptive NN tracking control of uncertain nonlinear pure-feedback systems via dynamic surface technique

In this paper, by incorporating the dynamic surface control technique into a neural network based adaptive control design framework, we have developed a backstepping based control design for a class of nonlinear systems in pure-feedback form with arbitrary uncertainty. Our development is able to eliminate the problem of “explosion of complexity” inherent in existing methods effectively. In addition, the circular design problem which exists in pure-feedback systems is overcome. Stability analysis shows that our control law can guarantee the uniform ultimate boundedness of the solution of the closed-loop system, and make the tracking error arbitrarily small. Simulation study is included to demonstrate the effectiveness of the proposed approach.