Yan‐Fu Li
Papers
1
Total Citations
9
H-Index
1
About
Yan‐Fu Li is a leading researcher in intelligent fault diagnosis and machinery health monitoring, with a focus on critical industrial components. His work centers on developing semi-supervised and data-driven methods that reduce the reliance on expensive, labeled fault data—a major bottleneck in real-world industrial applications. In his most cited paper (2022, 9 citations), Li introduced a novel semi-supervised fault diagnosis method for RV reducers in industrial robots, combining graph label propagation with discriminative feature enhancement. This approach assigns pseudo-labels to unlabeled data, uses information entropy to filter low-confidence labels, and optimizes metric learning in deep feature space to improve diagnostic accuracy. Li’s contributions are vital for advancing predictive maintenance in smart manufacturing, enabling reliable health monitoring with minimal human annotation effort. His work has been recognized for bridging the gap between academic deep learning models and practical engineering constraints, particularly in robotics and rotating machinery. With growing citation impact, Li continues to shape the field of intelligent fault diagnosis, making his research essential for students and engineers working on industrial AI and condition-based maintenance.
Research Focus
Key Achievements
Top Papers
- 1