Accelerating phase-field-based microstructure evolution predictions via surrogate models trained by machine learning methods

Abstract The phase-field method is a powerful and versatile computational approach for modeling the evolution of microstructures and associated properties for a wide variety of physical, chemical, and biological systems. However, existing high-fidelity phase-field models are inherently computational...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	David Montes de Oca Zapiain, James A. Stewart, Rémi Dingreville
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/5364a3d9c8394b509924926f4946716f
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5364a3d9c8394b509924926f4946716f
record_format	dspace
spelling	oai:doaj.org-article:5364a3d9c8394b509924926f4946716f2021-12-02T15:13:05ZAccelerating phase-field-based microstructure evolution predictions via surrogate models trained by machine learning methods10.1038/s41524-020-00471-82057-3960https://doaj.org/article/5364a3d9c8394b509924926f4946716f2021-01-01T00:00:00Zhttps://doi.org/10.1038/s41524-020-00471-8https://doaj.org/toc/2057-3960Abstract The phase-field method is a powerful and versatile computational approach for modeling the evolution of microstructures and associated properties for a wide variety of physical, chemical, and biological systems. However, existing high-fidelity phase-field models are inherently computationally expensive, requiring high-performance computing resources and sophisticated numerical integration schemes to achieve a useful degree of accuracy. In this paper, we present a computationally inexpensive, accurate, data-driven surrogate model that directly learns the microstructural evolution of targeted systems by combining phase-field and history-dependent machine-learning techniques. We integrate a statistically representative, low-dimensional description of the microstructure, obtained directly from phase-field simulations, with either a time-series multivariate adaptive regression splines autoregressive algorithm or a long short-term memory neural network. The neural-network-trained surrogate model shows the best performance and accurately predicts the nonlinear microstructure evolution of a two-phase mixture during spinodal decomposition in seconds, without the need for “on-the-fly” solutions of the phase-field equations of motion. We also show that the predictions from our machine-learned surrogate model can be fed directly as an input into a classical high-fidelity phase-field model in order to accelerate the high-fidelity phase-field simulations by leaping in time. Such machine-learned phase-field framework opens a promising path forward to use accelerated phase-field simulations for discovering, understanding, and predicting processing–microstructure–performance relationships.David Montes de Oca ZapiainJames A. StewartRémi DingrevilleNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 7, Iss 1, Pp 1-11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765
spellingShingle	Materials of engineering and construction. Mechanics of materials TA401-492 Computer software QA76.75-76.765 David Montes de Oca Zapiain James A. Stewart Rémi Dingreville Accelerating phase-field-based microstructure evolution predictions via surrogate models trained by machine learning methods
description	Abstract The phase-field method is a powerful and versatile computational approach for modeling the evolution of microstructures and associated properties for a wide variety of physical, chemical, and biological systems. However, existing high-fidelity phase-field models are inherently computationally expensive, requiring high-performance computing resources and sophisticated numerical integration schemes to achieve a useful degree of accuracy. In this paper, we present a computationally inexpensive, accurate, data-driven surrogate model that directly learns the microstructural evolution of targeted systems by combining phase-field and history-dependent machine-learning techniques. We integrate a statistically representative, low-dimensional description of the microstructure, obtained directly from phase-field simulations, with either a time-series multivariate adaptive regression splines autoregressive algorithm or a long short-term memory neural network. The neural-network-trained surrogate model shows the best performance and accurately predicts the nonlinear microstructure evolution of a two-phase mixture during spinodal decomposition in seconds, without the need for “on-the-fly” solutions of the phase-field equations of motion. We also show that the predictions from our machine-learned surrogate model can be fed directly as an input into a classical high-fidelity phase-field model in order to accelerate the high-fidelity phase-field simulations by leaping in time. Such machine-learned phase-field framework opens a promising path forward to use accelerated phase-field simulations for discovering, understanding, and predicting processing–microstructure–performance relationships.
format	article
author	David Montes de Oca Zapiain James A. Stewart Rémi Dingreville
author_facet	David Montes de Oca Zapiain James A. Stewart Rémi Dingreville
author_sort	David Montes de Oca Zapiain
title	Accelerating phase-field-based microstructure evolution predictions via surrogate models trained by machine learning methods
title_short	Accelerating phase-field-based microstructure evolution predictions via surrogate models trained by machine learning methods
title_full	Accelerating phase-field-based microstructure evolution predictions via surrogate models trained by machine learning methods
title_fullStr	Accelerating phase-field-based microstructure evolution predictions via surrogate models trained by machine learning methods
title_full_unstemmed	Accelerating phase-field-based microstructure evolution predictions via surrogate models trained by machine learning methods
title_sort	accelerating phase-field-based microstructure evolution predictions via surrogate models trained by machine learning methods
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/5364a3d9c8394b509924926f4946716f
work_keys_str_mv	AT davidmontesdeocazapiain acceleratingphasefieldbasedmicrostructureevolutionpredictionsviasurrogatemodelstrainedbymachinelearningmethods AT jamesastewart acceleratingphasefieldbasedmicrostructureevolutionpredictionsviasurrogatemodelstrainedbymachinelearningmethods AT remidingreville acceleratingphasefieldbasedmicrostructureevolutionpredictionsviasurrogatemodelstrainedbymachinelearningmethods
_version_	1718387569270456320

Accelerating phase-field-based microstructure evolution predictions via surrogate models trained by machine learning methods

Ejemplares similares