Papers
3
Total Citations
50
H-Index
2
About
Zuoyi Chen is a leading researcher in intelligent fault diagnosis, specializing in the detection of mechanical failures under extreme data scarcity. His work focuses on developing advanced deep learning methods—including relation networks, residual shrinkage transformers, and contrastive learning—to address the critical challenge of diagnosing faults when zero or very few faulty samples are available. Chen’s most impactful contribution is his 2023 paper on a residual shrinkage transformer relation network for industrial robot fault detection, which has garnered 32 citations and introduced a novel approach to zero-fault sample scenarios. He further advanced this field with a 2024 study on out-of-distribution data augmentation for zero-fault detection, accumulating 17 citations. His most recent 2025 work integrates physical information with contrastive learning to tackle extreme sample imbalance in rotating machinery, a cornerstone of ship operations. Chen’s research is pivotal for ensuring the reliability of industrial and maritime equipment, offering practical solutions where traditional methods fail. His innovative use of transformer architectures and data augmentation techniques marks him as a rising authority in machinery health monitoring and predictive maintenance.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3