Seul‐Gi Kim
Papers
1
Total Citations
13
H-Index
1
About
Seul‐Gi Kim is a leading researcher in industrial fault detection and predictive maintenance, with a focus on advancing sensor-based monitoring for manufacturing, aerospace, and power systems. Her most-cited work, “Evaluation of One-Class Classifiers for Fault Detection: Mahalanobis Classifiers and the Mahalanobis–Taguchi System” (2021, 13 citations), provides a critical comparative analysis of one-class classification methods for diagnosing faults in rotating machinery, such as motors, industrial robots, and wind turbines. Kim’s contributions bridge the gap between statistical quality control and machine learning, offering robust frameworks for real-time anomaly detection in high-stakes environments. Her research is instrumental in enabling early fault diagnosis, reducing downtime, and improving system reliability across industries. By rigorously evaluating the Mahalanobis–Taguchi System against other classifiers, she has provided practitioners with actionable insights for deploying efficient, data-driven maintenance strategies. Kim’s work is widely cited by engineers and data scientists developing predictive maintenance solutions, underscoring her impact on both academic research and industrial application. Her dedication to practical, scalable fault detection methods continues to shape the future of smart manufacturing and infrastructure monitoring.
Research Focus
Key Achievements
Top Papers
- 1