Design of neural network controller for a class of nonlinear systems with input saturation

In actual systems, actuator saturation is a common phenomenon, which often severely restricts system dynamic performance and gives rise to instability. In order to reduce the effects of saturation, this paper presents an adaptive control method based on neural networks (NN) for a class of uncertain nonlinear systems with Brunovsky canonical form and input saturation. This controller is composed of a tracking controller and a saturation compensator. The saturation compensator is designed by RBF neural networks. The adaptation laws are derived in the sense of Lyapunov function and Barbalat's lemma. The closed-loop system is uniformly ultimately bounded, which is proved by Lyapunov theory. The simulation example is given to illustrate the effectiveness of this method.