SECURING INTERPRETABILITY OF FUZZY MODELS FOR MODELING NONLINEAR MIMO SYSTEMS USING A HYBRID OF EVOLUTIONARY ALGORITHMS

Abstract

In this study, a Multi-Objective Genetic Algorithm (MOGA) is <br />utilized to extract interpretable and compact fuzzy rule bases for modeling <br />nonlinear Multi-input Multi-output (MIMO) systems. In the process of non- <br />linear system identi cation, structure selection, parameter estimation, model <br />performance and model validation are important objectives. Furthermore, se- <br />curing low-level and high-level interpretability requirements of fuzzy models <br />is especially a complicated task in case of modeling nonlinear MIMO systems. <br />Due to these multiple and conicting objectives, MOGA is applied to yield a set <br />of candidates as compact, transparent and valid fuzzy models. Also, MOGA <br />is combined with a powerful search algorithm namely Di<br />erential Evolution <br />(DE). In the proposed algorithm, MOGA performs the task of membership <br />function tuning as well as rule base identi cation simultaneously while DE <br />is utilized only for linear parameter identi cation. Practical applicability of <br />the proposed algorithm is examined by two nonlinear system modeling prob- <br />lems used in the literature. The results obtained show the e<br />ectiveness of the <br />proposed method.