About this Abstract |
Meeting |
2023 TMS Annual Meeting & Exhibition
|
Symposium
|
Additive Manufacturing of Metals: Applications of Solidification Fundamentals
|
Presentation Title |
A Machine Learning Approach to Fast Microstructure Predictions in Laser Powder Bed Fusion |
Author(s) |
Mason Jones, Jean-Pierre Delplanque, Theron Rodgers, Daniel Moser |
On-Site Speaker (Planned) |
Mason Jones |
Abstract Scope |
This work investigates the application of machine learning techniques developed for computer vision to the prediction of microstructures produced in additive manufacturing, with a goal of creating a model fast enough for effective optimization of process parameters. The approach taken is to couple a fast physics-based surrogate thermal model with a machine learning model to predict local and global grain size statistics produced during the laser powder bed fusion additive manufacturing process. The machine learning model is trained on ensemble data generated with the thermally coupled SPPARKS microstructure application. This work focuses specifically on the development of the machine learning model. |
Proceedings Inclusion? |
Planned: |
Keywords |
Additive Manufacturing, Machine Learning, Modeling and Simulation |