About this Abstract |
| Meeting |
2024 TMS Annual Meeting & Exhibition
|
| Symposium
|
Additive Manufacturing: Advanced Characterization with Synchrotron, Neutron, and In Situ Laboratory-scale Techniques III
|
| Presentation Title |
Machine Learning-driven In Situ Detection of Laser Powder Bed Fusion through Synchrotron and Lab-scale Techniques |
| Author(s) |
Zhongshu Ren, Tao Sun, Samuel Clark |
| On-Site Speaker (Planned) |
Zhongshu Ren |
| Abstract Scope |
Laser powder bed fusion is a mainstream 3D-printing technology widely used to manufacture complex parts in salient sectors including aerospace, biomedicine, and automobile. The unstable vapor depression (keyhole) during the printing process may cause a defect named keyhole pore, which is detrimental to the parts. In this work, we developed an effective approach to locally detect the generation of keyhole pore in real-time by leveraging machine learning. We collected high-fidelity ground truth through synchrotron x-ray imaging. We captured the acoustic and light emission of the printing process through lab-scale techniques. This proposed approach, especially working with the low-cost lab-scale sensors, provides a viable and practical way to improve the parts quality. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Additive Manufacturing, Machine Learning, Characterization |