Seung-Soo Han

About

Seung-Soo Han is a leading researcher in predictive maintenance and condition-based monitoring for semiconductor manufacturing, with a focused expertise on wafer transfer robots (WTRs). His work addresses the critical challenge of minimizing economic losses from unexpected equipment failures in highly automated fabrication processes. Han pioneered the use of clustering algorithms—including K-Means, Gaussian Mixture Models, and Mean-Shift—combined with neural networks to predict maintenance timing and detect anomalies from acceleration sensor data. His 2022 paper on a predictive maintenance system using K-Means and neural networks has garnered 20 citations, establishing a foundational approach in the field. More recently, Han has advanced the state of the art by integrating explainable artificial intelligence (XAI) into failure detection and cause identification, as demonstrated in his 2024 study. With a cumulative citation count approaching 40 across his most-cited works, Han’s research directly enhances equipment reliability and yield in semiconductor manufacturing, offering practical, data-driven solutions for industry and academia alike.

Research Focus

Key Achievements

Top Papers

1. 1
   Predictive Maintenance System for Wafer Transport Robot Using K-Means Algorithm and Neural Network Model

   20 citations · 2022
2. 2
   Development of Predictive Maintenance Technology for Wafer Transfer Robot using Clustering Algorithm

   11 citations · 2019
3. 3
   Predictive Maintenance System for Wafer Transfer Robot Using Gaussian Mixture Model and Mean-Shift Clustering

   6 citations · 2024
4. 4
   Condition-Based Monitoring for Failure Detection and Cause Identification in Wafer Transfer Robot Using Machine Learning and Explainable Artificial Intelligence Algorithms

   2 citations · 2024

Key Collaborators

Contact & Links