A Novel Fuzzy Identification Method Based on Ant Colony Optimization Algorithm

Abstract

In this paper, an identification problem for nonlinear models is explored and a novel fuzzy identification method based on the ant colony optimization algorithm is proposed. First, a modified cluster validity criterion with a fuzzy c-regression model is adopted to find appropriate rule numbers of the Takagi-Sugeno fuzzy model. Then, the ant colony optimization algorithm is adopted and the sifted initial membership function and the consequent parameters of the fuzzy model are obtained. Through an improved fuzzy c-regression model and the orthogonal least-squares method, the premise structure and the consequent parameters can be obtained to establish the Takagi-Sugeno fuzzy model. Some examples are illustrated to show that the proposed method provides better approximation results and robustness than those obtained using some of the existing methods.

Keywords

• Fuzzy system identification
• Takagi-Sugeno fuzzy model
• ant colony optimization algorithm (ACO)
• fuzzy c-regression model