Sep 2026
A semi-supervised learning framework for bearing fault recognition under strong noise
An improved dynamic pseudo-label learning strategy is developed, improving model generalization by involving more unlabeled data in training, and a noise reduction learning strategy based on self-supervised learning is proposed, extracting invariant features under noise conditions by a new optimization objective.
Ning Zhou, Lei Liu, Yao Cheng et al.
· Structural Health Monitoring · 3 citations