About this Abstract |
Meeting |
2024 TMS Annual Meeting & Exhibition
|
Symposium
|
Algorithm Development in Materials Science and Engineering
|
Presentation Title |
Predicting and Designing the Thermo-elasto-plastic Response of Composites Using Deep Material Network |
Author(s) |
Remi Dingreville, Dongil Shin, Ryan Alberdi, Ricardo Lebensohn |
On-Site Speaker (Planned) |
Remi Dingreville |
Abstract Scope |
Recent developments integrating micromechanics and neural networks offer promising paths for rapid predictions of the response of heterogeneous materials with similar accuracy as direct numerical simulations. I will present recent extensions to the deep material network (DMN) to predict the thermo-elasto-plastic response of composite materials and compare these predictions to Fast Fourier transform direct numerical simulations. This approach is based on a microstructure-aware binary tree-type network with connected mechanistic building blocks. These building blocks use analytical homogenization solutions to describe the overall material thermo-mechanical response of the microstructure. In the offline training, the network is trained on coefficient of thermal extension and elastic stiffness data. In the online prediction, the network does not need to be retrained on data and is able to extrapolate to predict the thermo-elasto-plastic response of composites subjected to various thermal boundary conditions. SNL is managed and operated by NTESS under DOE NNSA contract DE-NA0003525. |
Proceedings Inclusion? |
Planned: |
Keywords |
Computational Materials Science & Engineering, Machine Learning, ICME |