About this Abstract |
Meeting |
2020 TMS Annual Meeting & Exhibition
|
Symposium
|
Additive Manufacturing: Advanced Characterization with Synchrotron, Neutron, and In Situ Laboratory-scale Techniques
|
Presentation Title |
Unsupervised Learning of Dislocation Motion |
Author(s) |
Darren C. Pagan, Thien Q. Phan, Jordan S. Weaver, Austin R. Benson, Armand J. Beaudoin |
On-Site Speaker (Planned) |
Darren C. Pagan |
Abstract Scope |
The application of machine learning to materials characterization data from engineering alloys has been primarily limited to classification of microstructural features and correlation to observed properties. Instead we propose the application of the unsupervised learning technique, locally linear embedding (LLE), to analyze in-situ diffraction data and find lower-dimensional embeddings that characterize microstructural transients. We apply the approach to diffraction data gathered during uniaxial deformation of additively manufactured Inconel 625. With the aid of a physics-based material model, we find that the lower-dimensional coordinates determined using LLE appear to reflect the evolution of the defect densities that dictate strength and plastic flow behavior. The implications of the findings for future constitutive model development and wider applicability to the study of in-situ materials processing, including additive manufacturing will be presented. |
Proceedings Inclusion? |
Planned: Supplemental Proceedings volume |