Papers
1
Total Citations
15
H-Index
1
About
Hojin Lee is a researcher specializing in intelligent fault diagnosis and prognostics for industrial systems, with a particular focus on early-stage anomaly detection in critical electromechanical components. His work centers on developing deep learning architectures that integrate attention mechanisms and recurrent neural networks to enhance the sensitivity and accuracy of predictive maintenance. Lee’s most cited paper, “Attention Recurrent Neural Network-Based Severity Estimation Method for Early-Stage Fault Diagnosis in Robot Harness Cable” (2023, 15 citations), addresses the challenge of detecting “soft fault states” in robot harness cables—transient, incipient conditions that precede catastrophic failure. By modeling these subtle signal patterns, his method enables proactive intervention to prevent system downtime and maximize productivity. This contribution is especially significant in automated manufacturing and robotics, where cable integrity is vital for control and instrumentation. Lee’s research bridges the gap between theoretical deep learning and practical industrial reliability, offering scalable solutions for real-time monitoring. His work has been recognized for its potential to transform maintenance strategies from reactive to predictive, reducing costs and improving operational safety in smart factories.
Research Focus
Key Achievements
Top Papers
- 1