About this Abstract |
Meeting |
2025 TMS Annual Meeting & Exhibition
|
Symposium
|
Additive Manufacturing Modeling, Simulation and Machine Learning
|
Presentation Title |
A Resource-Effective In-situ Process Monitoring Framework for Defect Detection and Quality Assurance |
Author(s) |
Michael Heiden, Dan Bolintineanu, Anthony Garland, Annika Bauman, David Saiz, Tyler LeBrun, Ben Brown |
On-Site Speaker (Planned) |
Michael Heiden |
Abstract Scope |
Metal additive manufacturing (AM) is slowly improving complex component production across multiple industries. However, ensuring quality and reliability of AM-produced parts remains a critical challenge. In-situ monitoring has shown promise in detecting abnormal build events and detrimental defects. Yet, the slow and resource-intensive nature associated with acquiring & analyzing large datasets with complex outputs hinders the burdensome testing and inspection required for reducing uncertainty during qualification. This presentation highlights an ongoing multi-year effort within the DOE labs to develop a resource-effective in-situ instrumentation framework to benefit AM production. Leveraging machine learning and sensor fusion, the team aims to establish a data-resource effective, common data processing pathway. Discussion will focus on how this framework assists AM process development, ensure process consistency, and contributes to metal AM part acceptance.
SNL is managed and operated by NTESS under DOE NNSA contract DE-NA0003525. |
Proceedings Inclusion? |
Planned: |
Keywords |
Additive Manufacturing, Machine Learning, Process Technology |