Fulei Chu

Semantics-guided contrastive pre-training with cluster-aware decision making for zero-shot bearing fault diagnosis

Fault diagnosis contrastive language-signal pre-training (FD-CLSP) is proposed, a zero-shot cross-domain framework for bearing fault diagnosis under unseen operating conditions that leverages the noise-robustness and domain-invariance of high-level semantics to guide the extraction of elusive physical features.

A federated class-incremental learning framework with dynamic client participation and evolution for machine fault diagnosis