Quality control and authentication for additive manufacturing in cyber-physical systems: an integrated knowledge-driven approach

Advanced sensing technologies provide high-volume data for additive manufacturing (AM) quality improvement. Various engineering knowledge, such as kinematics information and physical process models, can be incorporated to guide the statistical learning for enhanced modeling accuracy and interpretability. In this talk, the presenter will introduce examples of the ongoing research of her lab on the integration of process knowledge into statistical modeling, monitoring, and process authentication for AM processes. Real-world case studies are used to demonstrate the effectiveness of the proposed approaches. Finally, several challenges and research opportunities are discussed for AM quality control in cyber-physical systems.