Fuzzy Identification of Non-uniformly Sampled Data Nonlinear Systems Based on Clustering Method

This paper is motivated by the practical control considerations that non-uniformly sampled nonlinear systems are abundant in industrial process. The corresponding input-output relationship of non-uniformly sampled nonlinear systems is obtained by using the weighted combination of the multiple local lifted linear models acquired from non-uniformly sampled measurements. Further, fuzzy model is derived by constructing the fuzzy membership degree functions as the weighted combination representation. On this basis, we propose a fuzzy identification algorithm using GK fuzzy clustering and recursive least squared method. Finally, the simulation example is studied to demonstrate the effectiveness of the proposed method..