Model reference adaptive neural network control for a class of switched nonlinear singular systems

In this paper, we address the reference model adaptive neural network control problem for a class of switched nonlinear singular systems under the case of single input and multiple inputs. Based on RBF neural network, the state tracking controller and a switching strategy are designed so that switched nonlinear singular system can asymptotically track the desired reference model. It shows that RBF neural network are used to approximate the positive nonlinear unknown function. The approximation errors of the RBF neural networks are introduced to the adaptive law in order to improve the performance of the whole systems. A simulation example is performed in support of the proposed neural control scheme.