| About this Abstract |
| Meeting |
2020 TMS Annual Meeting & Exhibition
|
| Symposium
|
Additive Manufacturing: Processing Effects on Microstructure and Material Performance
|
| Presentation Title |
A-120: Machine Learning Approach for Process Optimization of Pure Cu in a Powder Bed Fusion Additive Manufacturing with Electron Beam |
| Author(s) |
Kenta Aoyagi, Tadashi Kii, Nobuyuki Sasaki, Hirofumi Watanabe, Yoshitaka Shibuya, Kenji Sato, Akihiko Chiba |
| On-Site Speaker (Planned) |
Kenta Aoyagi |
| Abstract Scope |
Additively manufactured pure Cu parts have attracted much attention because Cu has a high thermal conductivity and additive manufacturing can provide complex-shaped parts, enabling a high-efficient heat radiator. However, it is difficult to obtain additively manufactured pure Cu parts with high density because a process window for pure Cu is narrow. Absorptivity of Cu for electron beam is higher than that for laser, and then, electron beam melting (EBM), one of a powder bed fusion additive manufacturing with electron beam, allows pure Cu parts with higher density than selective laser melting. In this study, therefore, we optimized process condition by a machine learning approach in order to determine a robust process condition, and evaluate density, microstructure, and physical properties of pure-Cu parts fabricated under a predicted condition. In addition, cuboid blocks with flow channels were also fabricated under the predicted condition. |
| Proceedings Inclusion? |
Planned: Supplemental Proceedings volume |