About this Abstract |
Meeting |
2023 TMS Annual Meeting & Exhibition
|
Symposium
|
Additive Manufacturing of Metals: Applications of Solidification Fundamentals
|
Presentation Title |
Layer-wise Optimization of Powder-bed Fusion Parameters Using Machine Learning Models in Metal Additive Manufacturing |
Author(s) |
Najmeh Samadiani, Dayalan Gunasegaram |
On-Site Speaker (Planned) |
Najmeh Samadiani |
Abstract Scope |
The ability to control the formation of defects and anomalies in metal parts during their building using powder bed fusion (PBF) additive manufacturing (AM) processes is a critical strength that can make these technologies more attractive to the industry. The required knowledge is presently generated through dozens of trial and error experiments; these inform the selection of the initial values of process parameters and their change during the build process. Machine learning (ML) models present an alternative to the time-consuming and expensive trial and error process. By analyzing vast amounts of data efficiently, they uncover critical relationships between process parameters that may be hidden from human analysis. Significantly, these models can be used for new parts that have not been made before. We discuss the various ML models that may help optimize process parameters to mitigate defects and anomalies in both laser-beam and electron-beam processes. |
Proceedings Inclusion? |
Planned: |
Keywords |
Machine Learning, Additive Manufacturing, |