About this Abstract |
| Meeting |
2026 TMS Annual Meeting & Exhibition
|
| Symposium
|
Verification, Calibration, and Validation Approaches in Modeling the Mechanical Performance of Metallic Materials
|
| Presentation Title |
A proposed framework for the development of microstructurally informed material models for engineering applications: the case study of a deformation model for pure copper |
| Author(s) |
Cory Jason Hamelin, Pratheek Shanthraj, Adam Plowman, Michael Atkinson, Mike White, Samuel Engel, Daniella Heristchian, Allan Harte |
| On-Site Speaker (Planned) |
Cory Jason Hamelin |
| Abstract Scope |
Conventional approaches to develop practical engineering models based on microstructurally informed phenomena typically require the use of several software packages, and manual transfer of data across those packages. These approaches are thus highly demanding in terms of the skilled, multidisciplinary personnel required during each stage of development. The present work implements the open-source matflow framework to automate several data manipulation and transfer processes through such model development, including iterative calibration runs of physics-based models and their subsequent use as training data for a recurrent neural network. The result is a streamlined model development pipeline that can take statistical distributions of relevant microstructural features, along with the desired macroscopic material response, as input data and output a practical engineering model with minimal need for user intervention through development. A case study on the production of a microstructurally informed deformation model for pure copper is used to demonstrate this technology. |
| Proceedings Inclusion? |
Planned: |
| Keywords |
ICME, Copper / Nickel / Cobalt, Machine Learning |