An evolving T–S fuzzy model identification approach based on a special membership function and its application on pump-turbine governing system

Abstract

Hyper-plane-shaped clustering (HPSC) has been proved to be more effective in Takagi–Sugeno (T–S) fuzzy model identification compared with hyper-sphere-shaped clustering (HSSC). However, there is no special membership function matching HPSC in fuzzy modeling, and the commonly used bell-shaped Gaussian function is more suitable for HSSC. In this paper, a novel T–S fuzzy model identification method is adopted, in which a new fuzzy membership function designed for HSPC is designed. In this approach, a fuzzy c-regression model based clustering method is used to partition the fuzzy space firstly; and then a new HPSC fuzzy membership function is designed to identify the antecedent membership function (MF) parameters; finally the gravitational search algorithm is applied to optimize the MF parameters further. Experimental results on several benchmark problems show that modeling accuracies have been promoted significantly. The proposed approach has been applied in fuzzy modeling of pump-turbine governing system (PTGS). The comparative experimental results reveal that the proposed approach could achieve high accuracy and would be an effective modeling tool for complicated nonlinear system in engineering applications.