About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Additive Manufacturing Modeling, Simulation and Artificial Intelligence
|
| Presentation Title |
Optimizing Powder Spreading in LPBF: A DEM and Machine Learning Approach |
| Author(s) |
Khushahal Thool, Rohit Raj, Saurabh Pawar, Shi Hoon Choi |
| On-Site Speaker (Planned) |
Khushahal Thool |
| Abstract Scope |
Laser powder bed fusion (LPBF) is a leading additive manufacturing technique, where uniform powder spreading is critical to part quality. This study proposes a hybrid approach combining discrete element method (DEM) simulations and machine learning (ML) to optimize powder spreading. DEM was used to model particle-scale behavior, including morphology and packing density, and was calibrated using experiments conducted with an in-house spreading system and 316L stainless steel powder. Surface roughness was evaluated via laser confocal microscopy, while ML-based image analysis enabled automated, high-resolution assessment of powder bed uniformity. A statistical binning approach ensured reliable comparison between experiments and simulations. Key variables, including particle size, morphology, and spreader speed, were analyzed. Results show that optimizing spreading speed improves packing without compromising uniformity. The integration of DEM and ML provides a robust framework for powder bed quality control and process parameter optimization in LPBF, supporting more reliable and efficient additive manufacturing. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
Additive Manufacturing, Machine Learning, Other |