| About this Abstract |
| Meeting |
2024 TMS Annual Meeting & Exhibition
|
| Symposium
|
Additive Manufacturing Modeling, Simulation and Machine Learning
|
| Presentation Title |
F-17: Coupling In-situ Monitoring and Machine Learning Towards Faster Laser-based Powder Bed Fusion Process Qualification |
| Author(s) |
Giuseppe Del Guercio, Chinmay Phutela, Jide Oyebanji, Federico Bosio, Nesma Aboulkhair |
| On-Site Speaker (Planned) |
Giuseppe Del Guercio |
| Abstract Scope |
Laser-based powder bed fusion (PBF-LB) is rapidly developing owing to the introduction of tailored materials and in-situ monitoring peripherical devices. Although many approaches have been proposed to quickly design new materials, the identification of pore-free processing windows still requires extensive experimental campaigns due to the limited understanding of the laser-matter interaction. The present work couples well-known thermal models describing PBF-LB and in-situ measured pyrometer data with machine learning (ML) algorithms, aiming at refining the evaluation of the laser-matter interaction and correctly identifying pore-free processing regimes. The methodology is then experimentally validated by 3D printing samples and the results demonstrated the effectiveness of in-situ monitoring coupled with ML for faster development of new materials, leading to shorter qualification time and improved efficiency in the AM process. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Additive Manufacturing, Machine Learning, Modeling and Simulation |