Spatial-channel collaborative multi-scale graph interaction deep transfer learning for unsupervised rotating machinery fault diagnosis

Accurate machine fault diagnosis under unlabeled scenarios remains a major challenge in the intelligent transformation driven by Industry 4.0/5.0. To enable cross-domain diagnosis in unlabeled target scenarios, it is both urgent and essential to extract valuable and transferable knowledge from diverse historical source domains. Graph-based multi-source transfer learning offers a promising solution. However, current methods are often constrained by inaccurate feature extraction and insufficient feature interaction, which hinder diagnostic performance. Therefore, a spatial-channel collaborative multi-scale graph interaction deep transfer learning (SCMGIDTL) is proposed. Firstly, a spatial-channel collaborative prototype extraction module is built to refine features in both spatial and channel dimensions, obtaining precise multi-domain feature prototypes to construct a high-quality graph network. Secondly, a multi-scale graph interaction transfer network is creatively established to enable multi-scale feature interaction across the multi-source domain, guiding the graph network to fuse deeper neighborhood features that benefit target graph nodes, thus enabling more accurate fault diagnosis. Finally, a category constraint loss is designed to simultaneously constrain category feature relationships from both local and global perspectives, facilitating domain alignment at the category level and further improving unsupervised fault diagnosis performance. Ablation experiments demonstrate that, starting from the graph-based transfer baseline method, the three proposed components introduce cumulative performance gains of 5.41%, 8.35%, and 1.54%, respectively. The average diagnosis accuracy of multiple tasks in the two cases reaches 99.87% and 99.60%. These results indicate that SCMGIDTL achieves outstanding performance in unsupervised machine fault diagnosis.