About this Abstract |
Meeting |
2023 TMS Annual Meeting & Exhibition
|
Symposium
|
Frontiers in Solidification: An MPMD Symposium Honoring Jonathan A. Dantzig
|
Presentation Title |
N-16: Physics-embedded Graph Network for Accelerating Phase-field Simulation of Microstructure Evolution in Additive Manufacturing |
Author(s) |
Zhengtao Gan |
On-Site Speaker (Planned) |
Zhengtao Gan |
Abstract Scope |
The phase-field (PF) method is a physics-based computational approach for simulating interfacial morphology and phase transformation of materials.
However, traditional direct numerical simulation (DNS) of the PF method is computationally resource-intensive as sufficiently small mesh size and time step are necessary to capture the fine-scale interfacial evolution of grains or dendrites. Here, a physics-embedded graph network (PEGN) is proposed to leverage an elegant graph representation of the grain structure and embed the classic PF theory into the graph network. By reformulating the classic PF problem as an unsupervised machine learning task on a graph network, PEGN efficiently solves temperature field, liquid/solid phase fraction, and grain orientation variables to minimize a physics-based loss/energy function. The approach is at least 50 times faster than DNS in both CPU and GPU implementation while still capturing key physical features. |
Proceedings Inclusion? |
Planned: |
Keywords |
Additive Manufacturing, Phase Transformations, Machine Learning |