About this Abstract |
Meeting |
2022 TMS Annual Meeting & Exhibition
|
Symposium
|
Additive Manufacturing: Advanced Characterization with Synchrotron, Neutron, and In Situ Laboratory-scale Techniques II
|
Presentation Title |
Sensor Enabled Material Response Prediction in Powder Bed Fusion Additive Manufacturing |
Author(s) |
Justin Gambone |
On-Site Speaker (Planned) |
Justin Gambone |
Abstract Scope |
PBFAM is becoming an increasingly utilized manufacturing technique for multiple industrial applications and with this machine consistency and robustness is an essential capability. Current systems use a variety of sensors to monitor the additive process throughout a build, but do not draw direct correlations to resulting material and part behavior. Through the use of robust experimental and sensor datasets, machine learning techniques can be applied to better associate in-process behavior to final material quality. The focus of this work is to leverage on-machine sensors, tied to post-build quality information regarding the meltpool and part, to identify system performance and resulting part quality. The results of which are used to further improve the understanding of the build process and provide input for improved local control of the additive system. |
Proceedings Inclusion? |
Planned: |
Keywords |
Additive Manufacturing, Machine Learning, |