About this Abstract |
Meeting |
2025 TMS Annual Meeting & Exhibition
|
Symposium
|
Additive Manufacturing Modeling, Simulation and Machine Learning
|
Presentation Title |
Anomaly Detection Via In-Situ Monitoring and Machine Learning
|
Author(s) |
Annika E. Bauman, Michael Heiden, Dan Bolintineanu, Anthony Garland |
On-Site Speaker (Planned) |
Annika E. Bauman |
Abstract Scope |
In situ monitoring of Laser Powder Bed Fusion (LPBF) additive manufacturing (AM) enables the utilization of various sensors, including acoustic, optical, and thermal to swiftly identify anomalous process behavior. The stochastic nature of LPBF necessitates faster qualification pathways to determine parts quality without significant time investment, thereby promoting less risky adoption of AM. Identifying pore formation through a combination of in-situ sensors without the need for computed tomography (CT) scanning would expediate the identification of defective parts. This presentation highlights using a variety of sensors to capture defect and process signatures for a full build plate of tensile bars. Discussion will cover how sensor outputs were linked to final mechanical properties and CT-determined ground truth porosity.
SNL is managed and operated by NTESS under DOE NNSA contract DE-NA0003525 |
Proceedings Inclusion? |
Planned: |
Keywords |
Other, Other, |