About this Abstract |
| Meeting |
2025 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2025)
|
| Symposium
|
2025 Annual International Solid Freeform Fabrication Symposium (SFF Symp 2025)
|
| Presentation Title |
In-Situ Prediction of Flaw Formation and Microstructure in
Laser Powder Bed Fusion Using Physics and Data-Driven Machine Learning
|
| Author(s) |
Antonio Carrington, Prahalada K. Rao, Zhenyu (James) Kong, Reagan Orth, Kamden Shephard, Kaustubh Deshmukh, Kyle Snyder, John Sions, Yuri Plotnikov |
| On-Site Speaker (Planned) |
Prahalada K. Rao |
| Abstract Scope |
This work concerns the prediction of flaw formation and microstructure in 316L stainless steel parts made using LPBF. Flaws, such as porosity invalidate the integrity of LPBF parts, while microstructure aspects, e.g., primary dendritic arm spacing and microhardness, govern mechanical characteristics. To predict the aforementioned multi-scale quality metrics in LPBF of 316L parts, we developed and implemented a physics and sensor data integrated machine learning approach. In this work, we manufactured 16 parts of varying geometry and processing parameters on an EOS M290 system. Real-time process data was acquired via a heterogeneous sensor suite consisting of a long-wave infrared camera, optical tomography, acoustic emission, and powder bed imaging camera. This sensor data was used along with thermal history predictions from a computational model as inputs to a machine learning model trained to predict flaw formation and microstructure. This work takes the first step toward in-situ qualification of LPBF part quality. |
| Proceedings Inclusion? |
Planned: Post-meeting proceedings |