Multisource Unsupervised Subdomain Adaptation Network for Rotary Machine Fault Diagnosis

Domain adaptation-based methods have been widely developed for fault diagnosis. However, the existing approaches mainly focus on the global distribution alignment of single-to-single domain without considering multiple scenarios and overlooking the alignment of subdomains, which causes misclassification near the class boundaries. Thus, a multisource unsupervised subdomain adaptation network (MUSDAN) is proposed in this article to solve fault diagnosis of rotary machines under multiple and variable working conditions. Using data images as inputs, a domain feature extractor is constructed to extract the domain-invariant features and map each source-target pair into the advanced feature space. Multikernel local maximum mean discrepancy (MK-LMMD) is introduced to align subdomains. Moreover, the domain-specific classifiers are applied to diagnose fault category, and diagnosis result is jointly determined by multiple classifiers through weighted decision-making strategy. The experiment results on two sets of rotary machines achieve an average accuracy of 98.01% and 96.04%, respectively, which demonstrates the validity of the proposed method.