Neural cellular automata for solidification microstructure modelling

Neural cellular automata for solidification microstructure modelling

Tang, Jian (ETH Zürich; Swiss Federal Laboratories for Materials Science and Technology (Empa))
Kumar, Siddhant (TU Delft Team Sid Kumar)
De Lorenzis, Laura (ETH Zürich)
Hosseini, Ehsan (Swiss Federal Laboratories for Materials Science and Technology (Empa))

2023

We propose Neural Cellular Automata (NCA) to simulate the microstructure development during the solidification process in metals. Based on convolutional neural networks, NCA can learn essential solidification features, such as preferred growth direction and competitive grain growth, and are up to six orders of magnitude faster than the conventional Cellular Automata (CA). Notably, NCA deliver reliable predictions also outside their training range, e.g. for larger domains, longer solidification duration, and different temperature fields and nucleation settings, which indicates that they learn the physics of the solidification process. While in this study we employ data produced by CA for training, NCA can be trained based on any microstructural simulation data, e.g. from phase-field models.

Cellular automata
Computational speed
Convolutional neural networks
Microstructure modelling

http://resolver.tudelft.nl/uuid:9a7b6b66-d240-435d-9d0a-c940c3a5e5cd

https://doi.org/10.1016/j.cma.2023.116197

0045-7825

Computer Methods in Applied Mechanics and Engineering, 414

Institutional Repository

journal article

© 2023 Jian Tang, Siddhant Kumar, Laura De Lorenzis, Ehsan Hosseini