Multi-fault diagnosis of rolling bearingusing fuzzy entropy of empirical modedecomposition, principal componentanalysis, and SOM neural network

Abstract

The condition monitoring and multi-fault diagnosis of rolling bearing is a very important research content in the field ofthe rotating machinery health management. Most researches widely used empirical mode decomposition in tandem withprincipal component analysis which is applied for feature extraction. But this method may lead to imprecise classification.In this paper, we propose a new method of rolling bearing multi-fault diagnosis, by combining the fuzzy entropy ofempirical mode decomposition, principal component analysis, and self-organizing map neural network. The empiricalmode decomposition process allows the vibration signal to be decomposed into a series of intrinsic mode functions. Foreach intrinsic mode function, we obtained the fault feature information. The proposed approach combines the fuzzyfunction and sample entropy to obtain fuzzy entropy. By this combination, we can reflect the complexity and theirregularity in each intrinsic mode function component. The fuzzy entropy of empirical mode decomposition used toconstruct the vectors is defined as the input of the principal component analysis. This principal component analysis isused to reduce the dimension of the feature vectors. Finally, the reduced feature vectors are chosen as input of self-organizing map network for automatic fault diagnosis and fault classification. The obtained results show that theproposed approach makes it possible to correctly assess the degradation of rolling bearing and to obtain recognitionof high-sensitivity defects for different types of bearing faults