Fuzzy modeling for a multi-input and multi-output complex process

A method is presented for obtaining a fuzzy model for the complex MIMO (multi-input and multi-output) process using experiment data. The discourse domain of each input variable is divided equally to determine the premise parameters and the total number of fuzzy rules. The consequent parameters of the fuzzy rules are then obtained by a learning algorithm. The theoretical analysis shows that the learning algorithm can converge to any arbitrary need and the characteristics of the fuzzy rules model which can approximate the experiment data with accuracy. The effectiveness of the fuzzy modeling method and the generalization ability of the fuzzy rules model are also demonstrated by a simulation example.