Modeling, Identification and Control of a Class of Nonlinear System

A new hyperbolic model is proposed for the complex nonlinear system. The hyperbolic model can be easily derived from a set of fuzzy rules. Also it can be seen as a neural network model, so we can learn the model parameter by back propagation (BP) algorithm. Also this model can be seen as the extension of linear model, so many results of linear system theory can be applied to analyze stability of closed loop system. At last we propose a method of designing the H ∞ controller for the hyperbolic model. The results of simulation prove its feasibility.