Data-Driven Modeling for Smart Manufacturing

During my research internship at AISC Lab, AIM-HI Institute, National Chung Cheng University, I worked on smart sensing technology for smart manufacturing, particularly data-driven modeling for cutting force prediction in milling.

This project introduced me to the role of machine learning and system identification in manufacturing processes. Instead of relying only on traditional analytical models, data-driven approaches can learn complex relationships from experimental datasets and support better prediction of machining behavior.

My current work continues in this direction by exploring machine learning models such as Random Forest and XGBoost, as well as sparse identification methods, to improve cutting force prediction accuracy using large-scale experimental datasets.