Multilayer neural networks-based direct adaptive control for switched nonlinear systems

This paper is concerned to present a direct adaptive neural control scheme for switched nonlinear systems with unknown constant control gain. Multilayer neural networks (MNNs) are used as a tool for modeling nonlinear functions up to a small error tolerance. The adaptive updated laws have been derived from the switched multiple Lyapunov function method, also an admissible switching signal with average dwell-time technique is given. It is proved that the resulting closed-loop system is asymptotically Lyapunov stable such that the output tracking error performance is well obtained. Finally, a simulation example of two Duffing forced-oscillation systems is given to illustrate the effectiveness of the proposed control scheme.