Fuzzy identification of nonlinear dynamic system based on selection of important input variables

Input variables selection (IVS) is proved to be pivotal in nonlinear dynamic system modeling. In order optimize the model of system, a fuzzy modeling method for determining premise structure by selecting important inputs studied. Firstly, simplified two stage curves proposed, which employed sort all possible their relevance with outputs, select input and identify structure. Secondly, reduce complexity model, standard c-means clustering algorithm recursive least squares are used parameters conclusion parameters, respectively. Then, effectiveness IVS verified well-known issues. Finally, proposed identification applied realistic variable load pneumatic system. The simulation experiments indi cate that this paper has positive influence on approximation performance Takagi-Sugeno (T-S)