Fuzzy systems identification

A general identification approach for discrete-time multi-input/single-output fuzzy systems is presented, which includes structure identification, parameter (fuzzy relation) estimation, and the associated self-learning algorithm. Zadeh´s possibility distribution plays an important role in identification and the use of fuzzy models thus constructed. Numerical examples are provided which show the advantages of the proposed identification algorithm and the effectiveness of the self-learning algorithm. Comparison shows that the proposed method can produce the fuzzy model with higher accuracy than previously achieved in other work. In the application example, the proposed identification approach has been used to construct fuzzy models for a fluidised catalytic cracking unit in a big refinery. The resultant fuzzy models are accurate enough for industrial application purpose.