알림
뒤로

Welcome to Data Intelligent PHM Lab.

  Data Intelligent PHM Lab. specializes in Prognostics and Health Management (PHM) of rotating machinery, based on AI. 

  

  Our research focuses on three key areas :
1. AI-based PHM for Rotating Machinery
2. Anomaly Detection in General Mechanical Systems
3. Deep Learning Model Compression for PHM


  We are currently engaged in advancing the field of mechanical system diagnostics by integrating cutting-edge AI and deep learning techniques to enhance the precision and efficiency of our PHM solutions.

Research

Anomaly Detection

  Enhancing manufacturing efficiency through advanced anomaly detection systems, enabling proactive identification and resolution of abnormalities. Real-time monitoring of data, enabling prompt intervention to minimize downtime and optimize productivity.


Deep Learning Model Compression

  Deep Learning Model Compression reduces neural network size to enhance computational efficiency. It includes quantization to lower numerical precision, pruning to remove non-essential connections, and knowledge distillation to train smaller models with similar accuracy to larger ones. These techniques facilitate deployment on devices with limited resources, speed up model inference, and decrease storage and transmission costs.  

Domain Adaptation

  The field of research focuses on developing domain-adaptive condition monitoring technology that takes into account variations in driving conditions, as the operating conditions of a system are not always constant. It considers various driving conditions such as system types, operating conditions, and load conditions.

RUL Predction

  The term "Remaining Useful Life" (RUL) refers to the remaining operating time or expected lifespan of a machine before it requires repair or replacement. The research field focuses on creating RUL prediction models by utilizing data acquired from the operational state of the target system. The goal is to predict the system's residual life, enabling proactive maintenance and decision-making

Location

Address

경기도 수원시 영통구 월드컵로 206

206 World cup-ro, Yeongtong-gu, Suwon-si, Gyeonggi-do, Republic of Korea (16499) 

Contact Information

Email: joonha at ajou.ac.kr