Weiyang Xu
Papers
1
Total Citations
3
H-Index
1
About
Dr. Weiyang Xu is a leading researcher in mechanical fault diagnosis and intelligent condition monitoring, with a particular focus on the complex dynamics of harmonic drives. His work addresses the critical challenge of extracting meaningful features from nonlinear, nonstationary operational data—a problem that traditional diagnostic methods struggle to solve. Dr. Xu’s major contribution lies in pioneering the application of graph neural networks (GNNs) to this domain, developing innovative frameworks that leverage dynamic graph data augmentation and adaptive knowledge distillation. His 2025 paper on this topic, which has already garnered 3 citations, introduces a novel methodology that significantly enhances the accuracy and robustness of fault detection in precision machinery. By transforming raw sensor data into graph structures, Dr. Xu enables GNNs to capture high-order dependencies and subtle degradation patterns that conventional techniques miss. His work is not only advancing the theoretical foundations of graph-based diagnostics but also offering practical, scalable solutions for predictive maintenance in robotics and aerospace applications. For students and researchers, Dr. Xu’s research represents a compelling intersection of deep learning and mechanical engineering, demonstrating how cutting-edge AI can solve real-world industrial problems.
Research Focus
Key Achievements
Top Papers
- 1