Qijun Liu
Papers
1
Total Citations
1
H-Index
1
About
Qijun Liu is a leading researcher in intelligent fault diagnosis and machinery health monitoring, with a focus on rotating machinery used in critical marine and industrial applications. His work bridges advanced machine learning and physical modeling to solve real-world reliability challenges. Liu’s most notable contribution is the development of a novel framework that integrates physical information and contrastive learning to achieve accurate fault diagnosis under extreme sample imbalance conditions—a persistent problem in real-world datasets where normal operating data vastly outnumbers fault data. His 2025 paper on this topic, already garnering early citations, demonstrates how combining domain knowledge with self-supervised learning can dramatically improve diagnostic robustness. Liu’s research addresses the fundamental need for timely, automated detection of potential faults in shipboard machinery, directly enhancing operational safety and reducing maintenance costs. By pioneering methods that work reliably even with scarce fault examples, he is advancing the frontier of practical intelligent maintenance systems. His work is essential reading for engineers and researchers developing next-generation condition monitoring solutions for critical rotating equipment.
Research Focus
Key Achievements
Top Papers
- 1