Design of robust optimal controller using neural network

In this paper, a sliding mode controller with neural network sliding surface is proposed. This sliding surface uses the estimation of the relationship between the nominal states by using neural network. In the conventional sliding mode control, the dynamic of sliding surface is not as same as nominal dynamic of original system. To overcome this problem, some research papers with additional dynamic states have been proposed. However this makes the order of a controller become higher. This paper proposes a new design method of a sliding surface without defining any additional dynamic state by using neural network. With this new sliding surface, a robust optimal controller is designed.