Rotary Machinery Fault Diagnosis Based on Split Attention Mechanism and Graph Convolutional Domain Adaptive Adversarial Network

In recent years, the unsupervised domain adaptation (UDA) technique has achieved remarkable success in cross-domain fault diagnosis of rotating machinery. In UDA, three pivotal pieces of information—namely, class labels, domain labels, and data structures, play a critical role in establishing a connection between labeled samples of the source domain and unlabeled samples of the target domain. Most research methods use only one or two of these types of information, ignoring the importance of data structure. In addition, global domain adaptive techniques are typically used, ignoring the relationships between subdomains. The conventional convolutional neural network (CNN) exhibits limited capability in extracting essential fault-related information, thereby significantly affecting the accuracy of fault identification. To address this problem, we propose the Graph Convolutional Domain Adaptive Adversarial Network (SPGCAN) as a novel approach for the intelligent diagnosis of faults in rotating machinery. A classifier and a domain discriminator are used to extract the first two types of information. Using residual networks with a multichannel split attention mechanism, graph CNNs for the modeling of data structures. We use a combination of local maximum mean discrepancy (LMMD) and adversarial domain adaptation methods to align the subdomain distributions and reduce the distributional differences between the relevant subdomains and the global. Case Western Reserve University (CWRU) bearing dataset and planetary gearbox dataset are used for cross-domain fault diagnosis and are compared with current mainstream UDA methods. Ultimately, SPGCAN demonstrates better fault identification accuracy across 24 cross-domain fault diagnosis tasks on both datasets, thus substantiating the method's effectiveness and superiority.