Intelligent control of nonlinear systems with application to chemical reactor recycle

The dynamic surface control technique can simplify the backstepping design for the control of nonlinear systems by overcoming the problem of explosion of complexity. In this paper, we incorporate this design technique into a neural network-based adaptive control design framework for a class of nonlinear stochastic systems. The time delays exist in the gain of the stochastic disturbance in the systems, and the neural networks are employed to compensate for all unknown nonlinear terms depending on the delayed output. The proposed approach is able to eliminate the problem of explosion of complexity inherent in the existing method. It can be proven that all the signals are semi-globally uniformly ultimately bounded in probability, and the system output tracks the reference signal to a bounded compact set. A simulation example is given to verify the effectiveness of the proposed approach.