| About this Abstract |
| Meeting |
2024 TMS Annual Meeting & Exhibition
|
| Symposium
|
Frontiers of Materials Award Symposium: Physics-Informed Machine Learning for Modeling and Design of Materials and Manufacturing Processes
|
| Presentation Title |
Physics-Informed Machine Learning for Scan Path Optimization |
| Author(s) |
Benjamin Stump |
| On-Site Speaker (Planned) |
Benjamin Stump |
| Abstract Scope |
One of the key factors that directly impact the efficiency and quality of AM processes is the selection and optimization of scan paths. Well-optimized scan paths can significantly reduce build time, minimize material waste, and enhance mechanical properties of the final product. This talk details some of our recent advances in scan path optimization which harness Machine Learning (ML) alongside a rapid analytical heat transfer model to spatially match the desired input properties. These methods go beyond optimizing processing parameters along a generally prescribed path to broadly explore optimizing the path itself. |
| Proceedings Inclusion? |
Planned: None Selected |