Simulating fluid flow in complex porous materials by integrating the governing equations with deep-layered machines

Abstract Fluid flow in heterogeneous porous media arises in many systems, from biological tissues to composite materials, soil, wood, and paper. With advances in instrumentations, high-resolution images of porous media can be obtained and used directly in the simulation of fluid flow. The computatio...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Serveh Kamrava, Muhammad Sahimi, Pejman Tahmasebi
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/5bbe01e9e7a84ef4b4cb2a3785357e2a
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:5bbe01e9e7a84ef4b4cb2a3785357e2a
record_format	dspace
spelling	oai:doaj.org-article:5bbe01e9e7a84ef4b4cb2a3785357e2a2021-12-02T15:08:38ZSimulating fluid flow in complex porous materials by integrating the governing equations with deep-layered machines10.1038/s41524-021-00598-22057-3960https://doaj.org/article/5bbe01e9e7a84ef4b4cb2a3785357e2a2021-08-01T00:00:00Zhttps://doi.org/10.1038/s41524-021-00598-2https://doaj.org/toc/2057-3960Abstract Fluid flow in heterogeneous porous media arises in many systems, from biological tissues to composite materials, soil, wood, and paper. With advances in instrumentations, high-resolution images of porous media can be obtained and used directly in the simulation of fluid flow. The computations are, however, highly intensive. Although machine learning (ML) algorithms have been used for predicting flow properties of porous media, they lack a rigorous, physics-based foundation and rely on correlations. We introduce an ML approach that incorporates mass conservation and the Navier–Stokes equations in its learning process. By training the algorithm to relatively limited data obtained from the solutions of the equations over a time interval, we show that the approach provides highly accurate predictions for the flow properties of porous media at all other times and spatial locations, while reducing the computation time. We also show that when the network is used for a different porous medium, it again provides very accurate predictions.Serveh KamravaMuhammad SahimiPejman TahmasebiNature PortfolioarticleMaterials of engineering and construction. Mechanics of materialsTA401-492Computer softwareQA76.75-76.765ENnpj Computational Materials, Vol 7, Iss 1, Pp 1-9 (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 Serveh Kamrava Muhammad Sahimi Pejman Tahmasebi Simulating fluid flow in complex porous materials by integrating the governing equations with deep-layered machines
description	Abstract Fluid flow in heterogeneous porous media arises in many systems, from biological tissues to composite materials, soil, wood, and paper. With advances in instrumentations, high-resolution images of porous media can be obtained and used directly in the simulation of fluid flow. The computations are, however, highly intensive. Although machine learning (ML) algorithms have been used for predicting flow properties of porous media, they lack a rigorous, physics-based foundation and rely on correlations. We introduce an ML approach that incorporates mass conservation and the Navier–Stokes equations in its learning process. By training the algorithm to relatively limited data obtained from the solutions of the equations over a time interval, we show that the approach provides highly accurate predictions for the flow properties of porous media at all other times and spatial locations, while reducing the computation time. We also show that when the network is used for a different porous medium, it again provides very accurate predictions.
format	article
author	Serveh Kamrava Muhammad Sahimi Pejman Tahmasebi
author_facet	Serveh Kamrava Muhammad Sahimi Pejman Tahmasebi
author_sort	Serveh Kamrava
title	Simulating fluid flow in complex porous materials by integrating the governing equations with deep-layered machines
title_short	Simulating fluid flow in complex porous materials by integrating the governing equations with deep-layered machines
title_full	Simulating fluid flow in complex porous materials by integrating the governing equations with deep-layered machines
title_fullStr	Simulating fluid flow in complex porous materials by integrating the governing equations with deep-layered machines
title_full_unstemmed	Simulating fluid flow in complex porous materials by integrating the governing equations with deep-layered machines
title_sort	simulating fluid flow in complex porous materials by integrating the governing equations with deep-layered machines
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/5bbe01e9e7a84ef4b4cb2a3785357e2a
work_keys_str_mv	AT servehkamrava simulatingfluidflowincomplexporousmaterialsbyintegratingthegoverningequationswithdeeplayeredmachines AT muhammadsahimi simulatingfluidflowincomplexporousmaterialsbyintegratingthegoverningequationswithdeeplayeredmachines AT pejmantahmasebi simulatingfluidflowincomplexporousmaterialsbyintegratingthegoverningequationswithdeeplayeredmachines
_version_	1718388061155360768

Simulating fluid flow in complex porous materials by integrating the governing equations with deep-layered machines

Ejemplares similares