A Novel Multisource-Domain Adaptation Framework for Bearing Fault Diagnosis Based on Adversarial Network and Feature Enhancement

Abstract

Data-driven fault diagnosis methods have received extensive attention, and the existing diagnostic methods usually require sufficient supervised data. However, developing effective diagnostic methods with insufficient training data remains challenging, which is highly demanding in real industrial scenarios since collecting high-quality fault data is often difficult and expensive. Considering the potential similarity of rotating machinery, collecting bearing fault data from different but related equipment may benefit the diagnostic performance of the target machinery. This article proposes a novel multisource-domain adaptation framework for bearing fault diagnosis methods based on adversarial network and feature enhancement. This method reduces the feature distribution discrepancy between the target domain and each source domain through domain adversarial training and transfers the fault diagnosis knowledge learned from multiple labeled source domains to a single unlabeled target domain. Considering the problem of scarce fault data, this method uses multilinear mapping to fuse the class information (Class Inf.) with high-level features and introduces AlignMixup to enhance the real fault signal features. To evaluate the model, experimental validation was performed on the Case Western Reserve University (CWRU) and KAT datasets. The results show that the proposed method is promising to address the bearing fault diagnosis tasks from different places of machines, further improving the applicability of data-driven methods in real industries.