Unknown fault detection of rolling bearings guided by global–local feature coupling

Fault diagnosis technology can effectively prevent the occurrence of faults and reduce safety hazards, which is of great significance in nuclear power, aerospace, manufacturing, and other fields. Given the stringent demands of safe and reliable equipment operation in practical production environments, acquiring a comprehensive set of fault samples becomes challenging. At present, many deep learning-based methods have been researched on this problem. However, these methods do not account for the identification of novel faults that may emerge. In this paper, we propose a novel global and local feature joint learning method for unknown fault detection, which addresses this problem by applying the knowledge learned by the supervised feature extraction process to the unsupervised clustering process. In particular, we propose a dual-branch framework for detecting unknown faults, which is based on multi-scale coupled feature extraction. This framework establishes correlations between features at different scales and employs the coupling of global and local features to facilitate the detection of unknown faults. Additionally, we propose a causal modeling method for global and local features, aiming to uncover the true causal relationship among global and local features and fault categories. Moreover, we propose a consistent prediction method to ensure the coherence of prediction results between the global and local branches. We evaluate the performance of our model using the CWRU, PU, and RB datasets, and the results demonstrate its superiority over state-of-the-art methods in terms of clustering accuracy and normalized mutual information.