Papers
2
Total Citations
32
H-Index
2
About
Ze Lin is a leading researcher at the intersection of federated learning, multimodal fusion, and intelligent robotic assembly. Their work addresses critical challenges in industrial automation, particularly in enabling robots to generalize across diverse contexts while preserving data privacy. Lin’s most influential contribution, the "Knowledge-based Clustering Federated Learning" framework (2024, 23 citations), pioneers a novel approach to fault diagnosis in robotic assembly by clustering decentralized knowledge, significantly improving diagnostic accuracy without sharing sensitive production data. Complementing this, their "Task attention-based multimodal fusion and curriculum residual learning" method (2024, 9 citations) introduces an innovative architecture that integrates visual and force-torque data with curriculum learning, allowing robots to adapt to novel assembly scenarios with minimal retraining. These works have garnered attention for their practical impact on manufacturing efficiency and robustness. Lin’s research not only advances theoretical understanding of context generalization and privacy-preserving machine learning but also offers scalable solutions for real-world industrial applications, marking them as a rising authority in intelligent manufacturing systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2