Fault Diagnosis of Rolling Bearings Based on ALIFD Fuzzy Entropy and GK Clustering

Aiming at the non-stationary and nonlinear characteristics of rolling bearing fault vibration signals, a fault diagnosis method based on adaptive local iterative filter decomposition (ALIFD) fuzzy entropy and Gustafson-Kessel (GK) clustering was proposed. Firstly, the fault vibration signals of rolling bearings were decomposed with ALIFD into several intrinsic mode function (IMF) components. Secondly, the first three IMF componentscontaining the primary feature information were filtered out by the correlation analysis, and then the fuzzy entropy of the filtered IMF component was used as eigenvectors. Finally, the obtained eigenvectors were recognized and classified through the GK clustering. The proposed method was applied to the experimental data of rolling bearings, and the classification performance was evaluated by the classification coefficient and the average fuzzy entropy. The results show that the proposed method has better classification performance compared with the fault diagnosis method based on empirical mode decomposition fuzzy entropy and GK clustering.