A dynamic collaborative adversarial domain adaptation network for unsupervised rotating machinery fault diagnosis

Abstract

Acquiring sufficient fault data labels for new tasks in rotating machinery fault diagnosis is tricky. Accurately identifying faults in unlabeled scenarios is a critical and urgent practical need. Unsupervised domain adaptation (UDA) is a mainstream method to address this issue. However, most existing UDA models are static and struggle to dynamically adjust according to changes in the target task, resulting in limited diagnostic performance. To address this limitation, a dynamic collaborative adversarial domain adaptation network (DCADAN) is proposed for unsupervised rotating machinery fault diagnosis. Firstly, a multi-objective dynamic collaborative generator is designed to endow with dynamic characteristics for adjusting its own architecture, enhancing the capture capability of key domain adaptation features. Secondly, a dual-system dynamic collaborative adversarial mode is established to dynamically adjust the network training architecture, forming task-oriented refined diagnostic decision edges to steadily improve domain adaptation diagnostic capability. Finally, a multi-source domain dynamic collaborative loss is developed to match the force of multiple source domains, forming an efficient collaborative diagnostic pattern with dynamic adjustment across multi-source domains. Two case studies indicate that DCADAN demonstrates superior diagnostic performance when executing cross-domain diagnosis tasks without target labels.