Decentralized adaptive neural network control for a large-scale nonlinear systems with unmodeled dynamic

Based on the approximation capability of the neural networks, a decentralized adaptive neural network control scheme is presented for a class of large-scale nonlinear systems in pure feedback form with unmodeled dynamics. A dynamic signal is introduced to dominate the unmodeled dynamics in the control process. The unknown nonaffine functions are separated by the mean value theorem, while the restrictions of disturbance and interconnections are relaxed by utilizing the separation technique. Decentralized control law and parameter adaptive law are designed by using variable structure technology. By theoretical analysis, the closed-loop control system is shown to be semi-globally uniformly ultimately bounded. The effectiveness of the proposed approach is illustrated by using simulation results.