Fault Diagnosis Based on FVMD Multi-scale Permutation Entropy and GK Fuzzy Clustering

Abstract

Aiming at the nonlinear and non-stationary characteristics of equipment fault signals, a fault diagnosis method based on the fast variational mode decomposition (FVMD), the parameter optimized multi-scale permutation entropy and the feature weighted GK fuzzy clustering is proposed. Firstly, to reduce the running time and the number of iterations, the idea of fast iteration is introduced on the basis of variational mode decomposition, and the fast variational mode decomposition method is proposed. Secondly, aiming at the problem of parameter determination of multi-scale permutation entropy and considering the interaction among parameters comprehensively, a method of parameters optimization based on multi force particle swarm optimization is proposed, then the parameter optimized multi-scale permutation entropy is combined with fast variational mode decomposition for fault feature extraction. Thirdly, considering the contribution of each feature in the feature vector to the clustering process, a new method of GK fuzzy clustering based on ReliefF feature weighting is proposed, the feature weighted GK fuzzy clustering is used to determine the standard clustering center, and the fault pattern recognition is realized by the principle of choosing the nearest. Finally, the fault data of rolling bearing collected on the machinery fault simulator is taken as the research object, and the proposed method is applied to the analysis. The results show that compared with the original variational mode decomposition, multi-scale permutation entropy and GK fuzzy clustering, the proposed method not only can extract the fault features effectively, but also can realize the classification and recognition of fault modes accurately, and the fault recognition rate is improved.