Xue-Yi Li

Wind turbine drivetrain fault diagnosis and intelligent O&M: a review

As wind turbines evolve toward larger capacities, fleet-level clustering, and operation under complex conditions, fault mechanisms in key drivetrain components show multi-physics coupling and complex evolution, creating a major bottleneck in condition monitoring: models are often constructible but hard to generalize. A...

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.

Industrial Internet-Oriented Unsupervised Hydro-Turbine Bearing Fault Diagnosis via Prototype-Disentangled Conditional Wasserstein Domain Adaptation

Results indicate that the proposed method can effectively transfer diagnostic knowledge acquired from labeled historical operating conditions to unlabeled online monitoring data and can serve as an offline-trained diagnostic module for Industrial Internet of Things-based condition-monitoring platforms in hydropower sys...

Fault Diagnosis of Gearbox Bearings Under Extreme Class Imbalance Based on Multi-Resolution Windows and Density-Aware Cross-Modal Fusion

A dual-branch architecture with spatial density-weighted kernels is proposed to decouple high-frequency transients from low-frequency periodic trends and an imbalance-aware strategy integrating Focal Loss and composite augmentation is developed to mitigate model bias.

MAML-S3M: Selective state space meta-learning for cross-condition few-shot bearing fault diagnosis

A novel model-agnostic meta-learning framework based on a selective state space model (MAML-S3M) to address the challenge of cross-condition few-shot bearing fault diagnosis and achieves superior diagnostic accuracy, outperforming state-of-the-art methods by at least 1.1%.

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