NN-Based Adaptive Backstepping Control for Uncertain System with a Dead Zone Input

Aiming at a class of mismatched uncertain nonlinear system with a dead zone input, an adaptive neural controller design scheme is presented by combining backstepping with variable structure control (VSC). By applying online approaching uncertainties with fully turned radial basis function (RBF) neural networks (NNs), the adaptive tuning rules are derived from the Lyapunov stability theory. To deal with the problem of extreme expanded operation quantity of backstepping method, a nonlinear tracking differentiator is introduced. The developed control scheme guarantees that all the signals of the closed loop system are uniformly ultimately bounded. Simulation results show the good tracking performance and robustness of the designed controller.