T-S fuzzy modeling and model-based fuzzy control for nonlinear systems using a RCGA technique

This paper presents a technique for designing a model-based fuzzy controller for a class of nonlinear systems. A Takagi-Sugeno fuzzy model, described by IF-THEN rules which locally represent linear input-output relations of a nonlinear system, is obtained and both the membership functions and model parameters in the consequents are simultaneously adjusted using a Real-coded genetic algorithm (RCGA). Then model-based local controllers are designed by another RCGA such that the given performance index is minimized. The overall fuzzy controller is derived through a fuzzy blending of the local controllers. The design methodology is illustrated by an application to the stabilization problem of an inverted pendulum on a cart.