| About this Abstract |
| Meeting |
2021 TMS Annual Meeting & Exhibition
|
| Symposium
|
Advanced Real Time Imaging
|
| Presentation Title |
Quantifying Spatter in Powder Bed Fusion Processes with High-speed Video Observations and Machine Learning |
| Author(s) |
Christian Gobert, Evan Diewald, Jack Beuth |
| On-Site Speaker (Planned) |
Christian Gobert |
| Abstract Scope |
During laser powder bed fusion (L-PBF) additive manufacturing, spatter particles ejected from the melt pool region can be detrimental to material performance and powder recycling. Quantifying spatter generation with respect to processing conditions is a step towards mitigating spatter and better understanding the phenomenon. A high-speed camera was used to observe the L-PBF process at multiple laser power and velocities. A machine leaning network was trained to segment regions of spatter particles in the captured high-speed images. A separate machine learning network was used to generate affinity matrices between spatter particles of subsequent frames to aid object tracking. The detection and tracking tool were used to quantify spatter generation of multiple laser power and velocity settings for L-PBF. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Additive Manufacturing, Machine Learning, |