Adaptive neural networks control for a class of nonlinear uncertain systems

In this paper, an adaptive dynamic surface control scheme is proposed for a class of nonlinear uncertain systems. By using RBF (radial basis function) neural networks to approximate the uncertainties of systems, the problem of singularity is avoided and the trouble caused by "explosion of complexity" in traditional backstepping methods is removed by taking advantage of DSC (dynamic surface control) technique. In addition, the input saturation constrains are taken into consideration in the control design. Finally, this scheme guarantees that the closed-loop system is uniformly ultimately bounded and the tracking error converges to a small neighborhood around zero. The simulations on aircraft are given to demonstrate the effectiveness of the proposed scheme.