Bearing Compound Fault Diagnosis Based on Morphological Filtering and Independent Component Analysis

Abstract

The state monitoring and fault diagnosis of rolling bearings are of great significance. The fault signal of rolling bearing contains periodic impact components, and the impact frequency reflects the location information of bearing fault. In order to effectively diagnose the early and weak fault of rolling bearing, the method of morphological filtering was used to pretreat the fault signal of rolling bearing in this paper. Then, the independent component analysis (ICA) was applied to separate the signal after morphological filtering. The results of experimental study on the compound fault signals of rolling bearing inner and outer ring show that this method can effectively identify and separate the fault characteristics of rolling bearing.