Rourou Li
Papers
2
Total Citations
18
H-Index
2
About
Rourou Li is pioneering the intersection of physics-informed deep learning and intelligent fault diagnosis for industrial robotics. Their research centers on developing interpretable, noise-robust diagnostic frameworks that bridge the gap between data-driven models and physical system understanding. Li’s most influential work introduces a hybrid physics-embedded recurrent neural network that leverages multivariate proprioceptive signals for fault diagnosis under time-varying conditions—a critical advancement for real-world manufacturing environments where operating conditions constantly shift. This paper has already garnered 15 citations since its 2024 publication, signaling strong community interest. More recently, Li has advanced the field with a deep complex wavelet denoising network designed to address two persistent challenges: strong noise interference that obscures fault signatures, and imbalanced data where scarce fault samples limit model training. This 2025 work further enhances interpretability—a key barrier to industrial adoption of deep learning diagnostics. By systematically tackling noise robustness, data scarcity, and physical interpretability, Li is laying the groundwork for next-generation predictive maintenance systems that manufacturers can trust and deploy.
Research Focus
Key Achievements
Top Papers
- 1
- 2