Identification, modeling and control by means of Takagi-Sugeno fuzzy systems

This paper deals with the development of Takagi-Sugeno fuzzy models and controllers for monovariable nonlinear systems. An original method is presented to model specific nonlinear phenomena, like friction effects in mechanical systems, from experimental data. The identification of the fuzzy model is done by a new partitioning method where the state space is identified subspace by subspace separately. The identified fuzzy model is used for control especially to compensate nonlinear effects