Bearing Fault Diagnosis Based on Feature Weighted FCM Cluster Analysis

A new method of fault diagnosis based on feature weighted FCM is presented. Feature-weight assigned to a feature indicates the importance of the feature. This paper shows that an appropriate assignment of feature-weight can improve the performance of fuzzy c-means clustering. Feature evaluation based on class separability criterion is discussed in this paper. Experiment shows that the algorithm is able to reliably recognize not only different fault categories but also fault severities. Therefore, it is a promising approach to fault diagnosis of rotating machinery.