Multi-source alignment domain adaptation with similarity measurement for cross-domain bearing fault diagnosis

Abstract

Variations in bearing operating conditions may cause a shift in the feature distribution of fault signals, weakening the generalization ability of the fault diagnosis model. Traditional methods with domain adaptation (DA) extract invariant cross-domain fault features, but they are mostly applied to a single-source domain. In the case of multi-source cross-domain transfer, however, determining which source domain has a better transfer effect to the target domain is difficult. In this paper, we aim to combine the transferable knowledge contained in all available source domains to improve the transfer performance. Low-correlation features are often more prone to bias under variable working conditions. The contribution of high-correlation features to the model must be increased. Accordingly, a multi-source alignment DA network with similarity measurement (MADASM) is proposed for this issue. First, DA is performed for each combination of source and target domains, and similarity measurement is introduced to constrain the similarity between the input and the central features. Second, the learned features are inputted into the corresponding domain-specific classifiers, of which the classifier discrepancy loss is then introduced to minimize the difference between the outputs of each domain-specific classifier, resulting in consistent prediction results for classifiers on the target domain. Finally, the average of output probabilities from all the classifier is calculated as the diagnosis result. Experimental results show that MADASM can fully utilize fault category information in multiple source domains to extract fault features with high correlation even in challenging scenarios with unknown data labels and lacking of prior knowledge in target domain.