Xuyun Fu
Papers
1
Total Citations
84
H-Index
1
About
Xuyun Fu is a leading researcher in intelligent fault diagnosis and industrial artificial intelligence, with a focus on addressing data imbalance challenges in safety-critical systems. His most-cited work, "Feature-level SMOTE: Augmenting fault samples in learnable feature space for imbalanced fault diagnosis of gas turbines" (2023, 84 citations), introduces a novel augmentation strategy that synthesizes fault samples directly within a learnable feature space, significantly improving diagnostic accuracy for gas turbines where failure data is scarce. This contribution bridges the gap between traditional oversampling methods and deep learning, offering a robust solution for real-world industrial monitoring. Fu’s research has been widely recognized for its practical impact, with his work accumulating over 80 citations and influencing subsequent studies in imbalanced learning and predictive maintenance. By advancing methods that enhance model performance under severe class imbalance, he has helped pave the way for more reliable, data-efficient fault detection systems in aerospace and energy sectors. His ongoing work continues to push the boundaries of how deep learning can be adapted to the constraints of industrial data.
Research Focus
Key Achievements
Top Papers
- 1