Inwoong Noh
Papers
5
Total Citations
103
H-Index
4
About
Inwoong Noh is a leading researcher in intelligent manufacturing, specializing in fault diagnosis and prognostics for industrial robotic systems. His work centers on developing robust, data-driven frameworks that leverage deep learning and transfer learning to ensure quality and reliability in complex processes like robotic spot-welding. Noh’s major contributions include pioneering multi-objective instance weighting for deep transfer learning networks, enabling accurate fault diagnosis even when industrial data is scarce or expensive to collect—a critical advancement for real-world manufacturing. He has also advanced explainable AI in fault diagnosis, creating methods that visualize sensor data as images to build operator trust and understanding. His real-time diagnostic frameworks for angular misalignment in welding robots have been cited over 28 times, demonstrating their practical impact. With papers accumulating more than 100 citations, Noh’s work addresses the industry’s need for situation-aware models that adapt to variable conditions, such as design changes, ensuring stable mass production. His research not only pushes the boundaries of AI-driven health management but also provides actionable solutions for the factory floor.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3
- 4
- 5