Robust adaptive control of a class of uncertain nonlinear composite systems using neural networks

A novel robust adaptive controller is presented for a class of uncertain nonlinear composite systems using neural networks. This approach resolves the difficult questions of complex interconnected terms in large-scale systems, and the transient performance of the system is improved by updating the weights of neural networks online. It requires only little prior knowledge and guarantees the stability of closed-loop systems, and can be easily realized in engineering.