Abstract
Timely and accurate detection of bearing faults is critical to the reliability of rotating machinery, yet models trained under fixed conditions often fail in unseen domains owing to distribution shifts. To overcome this limitation, we develop DGNSCA—a domain generalization network that leverages similarity guidance, class-conditional feature alignment, and adversarial training to learn domain-agnostic, yet class-discriminative features. The architecture is built on a 1-D convolutional neural network and incorporates three key modules: global distribution alignment to extract domain-invariant features, class-conditional contrastive learning to enhance intraclass consistency across domains, and adversarial training to improve generalization. DGNSCA further introduces a domain-similarity-guided decision module that adaptively aggregates per-source predictions via similarity weights, enabling robust inference without access to target-domain data. Comprehensive evaluations on two widely recognized benchmark datasets show that DGNSCA consistently surpasses current leading methods regarding accuracy, precision, and F1-score. Ablation analyses further validate the distinct contribution of each module within the framework. These results indicate that DGNSCA provides a reliable and scalable solution for intelligent fault diagnosis under realistic, distribution-shifted operating conditions.
Funding Information
  • Joint Fund of the National Natural Science Foundation of China and Civil Aviation Administration of China (U2033202)
  • Joint Fund of the National Natural Science Foundation of China and Civil Aviation Administration of China (U1333119)
  • National Natural Science Foundation of China (52172387)
  • Fundamental Research Funds for the Central Universities (ILA22032-1A)
  • Aeronautical Science Foundation of China (2022Z071052001)

This publication has 51 references indexed in Scilit: