Linguistic fuzzy model identification

The paper presents an approach for identifying a fuzzy model composed of fuzzy-logic based linguistic rules for a multi-input/single-output system. The approach includes structure identification and parameter identification. We propose to utilise a fuzzy c-means clustering and genetic algorithm (GA) hybrid scheme to identify the structure and the parameters of a fuzzy model, respectively. To evaluate the advantages and the effectiveness of the suggested approach, we deal with numerical examples. Comparison shows that the proposed approach can produce the fuzzy model with higher accuracy and a smaller number of rules than previously achieved in other works. To show the global optimisation and local convergence of the GA hybrid scheme, we also consider an optimisation problem having a few local minima and maxima.