Adaptive Neural Decentralized Control for Nonlinear Large-Scale Systems

This paper presents an adaptive decentralized control method for a class of nonlinear large-scale systems with unknown nonlinear functions and bounded time varying state delays. The adaptive compensation controller is constructed by utilizing Neural Networks (NN) and a backstepping design method. With the help of NNs to approximate the unknown nonlinear functions, the novel adaptive control approach is developed by using the backstepping design method. The appropriate LyapunovKrasovskii type functionals are introduced to design new adaptive laws to compensate the unknown nonlinearities as well as uncertainties from unknown state delays. The proposed design method does not require a priori knowledge of the bounds of the unknown time delays. The boundedness of all the closed-loop signals is guaranteed and the tracking error is proved to converge to a small neighborhood of the origin. As an application, the proposed approach is employed for a two inverted pendulums. The simulation results show effectiveness of the proposed adaptive decentralized control approach