Attend the Smart Manufacturing Seminar Series event on Thursday, April 1, 2021, with Ruimin Chen from Pennsylvania University for a talk about AI in additive manufacturing.
AI-enabled Characterization of Design-quality Interactions and Causal Discovery in Additive Manufacturing
Presented by Ruimin Chen, Harold and Inge Marcus Department of Industrial and Manufacturing Engineering, Pennsylvania State University, University Park
Thursday, April 1, 2021
9–10 a.m.
Attend on Zoom
Abstract
Additive manufacturing, or AM, provides a great level of flexibility in the design-driven fabrication of metal builds. However, the more complex the design, the more difficult it becomes to control the quality. Advanced imaging is increasingly invested in AM processes to cope with the complexity and enhance information visibility, thereby leading to data-rich environments. Realizing full potentials of image data for quality assurance and quality control (QA/QC) depends to a great extent on the development of novel analytical methods that extract useful information (i.e., process-structure-property relationship identification and causal discovery).
In this talk, Chen will present two projects that leverage image data and AI to analyze and understand the design-quality interactions along with causal relationships in AM. In the first topic, Chen will present a novel generalized recurrence network approach to represent, model, and analyze the AM spatial image data. This proposed design-quality analysis shows great potential to optimize engineering design and enhance the quality of AM builds. In the second topic, Chen will present an ontology-driven Bayesian network model to infer causal relationships between AM design and process parameters and QA/QC requirements (e.g., structure and mechanical properties). The proposed causal discovery model enables engineering interpretations and can further advance AM process monitoring and control. In the end, Chen will talk about her future research plan.
About the speaker
Ruimin Chen is a doctoral candidate in the Harold and Inge Marcus Department of Industrial and Manufacturing Engineering at The Pennsylvania State University. She also received her dual-title master’s degree in Industrial Engineering and Operations Research from Penn State. Ruimin’s research focuses on sensor-based system informatics and AI-driven service optimization in advanced manufacturing systems. She was the recipient of NSF INTERN Scholarship and extended her academic training with IBM Thomas J. Watson Research. Ruimin has also been selected as a research scholar of NSF CHOT and NIST and has been actively collaborated with Suzan G. Komen and CIMP-3D. She is a member of ASME, IISE, INFORMS and IEEE.
