Neural cellular automata for solidification microstructure modelling

DOI10.1016/J.CMA.2023.116197MaRDI QIDQ6171252zbMATH OpenFDO

Authors Jian Tang, Siddhant Kumar, Laura De Lorenzis, Ehsan Hosseini

Publication date 11 August 2023

Published in Computer Methods in Applied Mechanics and Engineering (Search for Journal in Brave)

Copyright license Creative Commons Attribution 4.0 International

Full work available at URL https://arxiv.org/abs/2304.02354

zbMATH Keywords

cellular automatacomputational speedconvolutional neural networksmicrostructure modelling

Mathematics Subject Classification ID

Computer science (68-XX) Biology and other natural sciences (92-XX)

Abstract: 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 delivers reliable predictions also outside their training range, 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.

Recommendations

• scientific article; zbMATH DE number 5882264
• Review on cellular automata simulations of microstructure evolution during metal forming process: grain coarsening, recrystallization and phase transformation
• A modified cellular automaton method for the modeling of the dendritic morphology of binary alloys
• The development of a cellular automaton-finite volume model for dendritic growth

Cites work

• Accelerating phase-field predictions via recurrent neural networks learning the microstructure evolution in latent space
• Deep learning and crystal plasticity: a preconditioning approach for accurate orientation evolution prediction
• Free energy of a nonuniform system. I: Interfacial free energy
• Machine learning materials physics: multi-resolution neural networks learn the free energy and nonlinear elastic response of evolving microstructures
• Machine learning-enabled self-consistent parametrically-upscaled crystal plasticity model for Ni-based superalloys
• Quantitative phase-field modeling of dendritic growth in two and three dimensions

Cited in

(2)

• An efficient Poisson solver and a data-driven surrogate model for magnetic stray field calculations
• Grid anisotropy of propagation fronts in cellular automata and its reduction methods

This page was built for publication: Neural cellular automata for solidification microstructure modelling

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6171252)