Papers
1
Total Citations
9
H-Index
1
About
Han Te is a leading researcher in intelligent fault diagnosis and industrial robot health monitoring, with a focus on the critical components of robotic systems. His most influential work introduces a semi-supervised fault diagnosis method for RV reducers—key parts of industrial robots—that addresses the practical challenge of limited labeled data. By combining graph label propagation with discriminative feature enhancement, Han’s approach effectively assigns pseudo-labels to unlabeled samples, evaluates their confidence via information entropy to reduce mislabeling interference, and optimizes metric learning in deep feature space to improve feature discrimination. This work, published in 2022 and already cited 9 times, demonstrates significant impact in advancing data-driven diagnostics under real-world constraints. Han’s contributions are vital for reducing costly manual labeling while maintaining high diagnostic accuracy, directly supporting the reliability and precision of industrial robots. His research bridges machine learning and mechanical engineering, offering scalable solutions for smart manufacturing and predictive maintenance.
Research Focus
Key Achievements
Top Papers
- 1