Defeng Wu
Papers
1
Total Citations
1
H-Index
1
About
Defeng Wu is an emerging researcher specializing in intelligent fault diagnosis, rotating machinery health monitoring, and machine learning applications in mechanical engineering. His work sits at the intersection of deep learning and industrial condition monitoring, with a particular focus on addressing real-world challenges such as extreme sample imbalance — a persistent obstacle in practical fault detection scenarios where faulty samples are inherently scarce. Wu's most notable contribution, published in 2025, introduces a novel fault diagnosis framework that synergizes physical domain knowledge with contrastive learning, enabling robust and accurate fault identification even when training data is severely limited. This approach is especially significant for maritime engineering contexts, where rotating machinery forms the operational backbone of ship systems and undetected faults can carry serious safety consequences. By embedding physical priors into a data-driven learning paradigm, Wu's methodology bridges the gap between theoretical machine learning and deployable industrial solutions. Though Wu's publication record is still developing, his research addresses critically relevant problems in smart manufacturing and intelligent transportation. His work reflects a growing trend toward physics-informed neural networks and self-supervised learning techniques, positioning him as a promising contributor to the future of predictive maintenance and autonomous ship systems.
Research Focus
Key Achievements
Top Papers
- 1