Yunhan Kim
Papers
2
Total Citations
115
H-Index
2
About
Yunhan Kim is a leading researcher in industrial robotics and intelligent fault diagnostics, specializing in vibration analysis and deep learning for predictive maintenance. His most influential work introduces the Phase-based Time Domain Averaging (PTDA) method, a novel signal processing technique that significantly enhances fault detection in gearboxes of industrial robots using vibration signals. This paper has garnered 84 citations, underscoring its impact on condition monitoring and reliability engineering. Building on this foundation, Kim developed a deep transferable motion-adaptive fault detection framework employing a residual–convolutional neural network, which achieves robust performance across varying robotic motions with minimal labeled data. This work, cited 31 times, demonstrates his ability to bridge traditional signal processing with modern deep learning to solve real-world industrial challenges. Kim’s contributions are vital for advancing autonomous manufacturing, enabling early fault diagnosis to reduce downtime and maintenance costs. His research is widely recognized for its practical applicability and methodological innovation, making him a key figure in the evolution of smart industrial systems.
Research Focus
Key Achievements
Top Papers
- 1
- 2