Dr. Du’s Research Group focuses on an interdisciplinary framework: Fusion of Domain Knowledge, Data Science, Optimization, Control, and Computational Science.Table of Contents
The rapid advancement in sensing and computing technologies has resulted in unprecedented data-rich environments in smart manufacturing systems, which brings great opportunities for quality, productivity, and efficiency improvements. However, the collected sensing data are usually high-dimensional, heterogeneous, noisy, and high volume. Our research focuses on developing advanced data analytics methodologies to effectively extract important knowledge and information from these sensing data to advance real-time monitoring of manufacturing system operations, accurate change detection, prognostics of system status, automatic quality inspection, anomaly detection, root cause diagnosis, predictive control, and error compensation.
Profile data or functional curve analytics for change point detection, process monitoring, quality inspection, prognostics, and fault diagnosis.
High-density 3D point cloud data modeling and analytics for anomaly detection, classification, quality inspection, and efficient sampling.
This research is motivated by the fact that many advanced manufacturing systems, such as fuselage and ship assembly, have limited and expensive data collection. High-fidelity simulations like Finite Element Analysis (FEA) are used to simulate real manufacturing systems for process optimization and control. Our group focuses on developing methodologies to calibrate simulation platforms, establish surrogate models, and achieve optimal control strategy and process optimization.