A method of fuzzy modeling for non-linear systems

A method of fuzzy identification based on a new objective function is proposed. There are two items in the new objective function, including the goal of fuzzy clustering and the goal of identification. It is testified that the method could simultaneously make the structure of the fuzzy model optimum and estimate parameters of fuzzy model through a theorem. The method makes the fuzzy modeling simple. Simulation results demonstrate that the method could identify non-linear systems and improve identification accuracy.