In response to the challenges of sparsely labeled samples and complex feature distribution in bearing fault diagnosis, a novel few-shot bearing fault diagnosis method is proposed by integrating spatio-temporal feature fusion with a Siamese-based learnable metric framework. A multi-scale residual network-Convolutional Block Attention Module network is adopted as the feature extractor, where channel-space attention enhancement and multi-level feature fusion are employed to improve the effective representation of spatio-temporal information in the time–frequency diagrams. To overcome the limitations of fixed distance metrics, a Siamese learnable metric network is introduced to enable adaptive similarity modeling. In addition, a local-global dual-branch fusion mechanism is designed to combine local similarity metrics with global context matching information, thereby enhancing the model’s robustness and generalization performance in few-shot scenarios. Experiments conducted on the Case Western Reserve University and Intelligent Maintenance Systems bearing datasets show that the proposed method achieves superior diagnostic performance under few-shot conditions compared with other approaches. The visualization results using confusion matrices and t-SNE further confirm the method’s strong interclass separability.
Xinyu Mo, Deqiang He, Haiyuan Zhao et al.· Engineering Research Express· 0 citations
In order to address common challenges in industrial environments, including limited labeled samples, variable operating conditions, and cross-machine fault diagnosis, this study proposes a novel vibration–acoustic multimodal contrastive learning framework. First, a multi-level constrained contrastive learning method is designed to jointly regularize vibration–acoustic features at the levels of sample distribution, feature statistics, and feature structure. This enhances multi modal consistency, feature discriminability, and information diversity, enabling the learning of robust joint representations. Second, a dynamic frequency domain collaborative enhancement module is introduced during the fine-tuning stage, which progressively integrates frequency domain features into vibration time series features while adaptively adjusting feature weights, thereby improving discriminative capability and representation stability. Finally, the proposed framework is validated on two motors with significant differences in structure and operating conditions, as well as on a series of variable condition and cross-machine fault diagnosis tasks. Experimental results demonstrate that, with only 10 labeled samples per class, the method achieves over 99.57% diagnostic accuracy in cross-machine tasks, highlighting its adaptability to distribution shifts and structural differences and confirming its robust generalization performance in cross-machine and cross condition fault diagnosis.
Yuan Zhuang, Deqiang He, Zhenzhen Jin et al.· Measurement science and tech...· 0 citations