Prediction of diffusional conductance in extracted pore network models using convolutional neural networks

Misaghian Niloo; Agnaou Mehrez; Sadeghi Mohammad AminFathiannasab HamedHadji IsmaRoberts EdwardGostick Jeff

首页> 外文期刊>Computers & geosciences >Prediction of diffusional conductance in extracted pore network models using convolutional neural networks

【24h】

Prediction of diffusional conductance in extracted pore network models using convolutional neural networks

机译：Prediction of diffusional conductance in extracted pore network models using convolutional neural networks

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相关主题

摘要

Pore network modeling (PNM) based on networks extracted from tomograms is a well-established tool for simulating pore-scale transport behavior in porous media. A key element of this approach is the accurate determination of pore-to-pore conductance values, which is a complex task that greatly affects the accuracy of flow and diffusive mass transport studies. Classic methods of conductance estimation based on analytical solu-tions and shape factors only apply to simple pore geometries, whereas real porous media contain irregular-shaped pores. Although direct numerical simulations (DNS) can accurately estimate conductance considering pores' real morphology, it has a high computational cost that becomes infeasible for large tomograms. The present work remedies this problem using a deep learning (DL) approach, with a specific focus on diffusional transport which has received less attention than hydraulic conductance. A convolutional neural network (CNN) model was trained to estimate diffusive conductance of PNM elements from volumetric images of porous media. The developed framework estimates the diffusive conductance by analyzing individual pore-to-pore 3D images isolated from the tomogram to fully capture the topology and shapes. A key outcome of the present work is that only images of the pore regions are used as input data, avoiding excessive preprocessing time for data prepa-ration. The results of the diffusive conductance prediction show good agreement with the test data obtained by DNS method, with 0.94 R-2 prediction accuracy and a speedup of 500x in prediction runtime.

著录项

来源
《Computers & geosciences》 |2022年第5期|105086.1-105086.12|共12页
作者
Misaghian Niloo; Agnaou Mehrez; Sadeghi Mohammad AminFathiannasab HamedHadji IsmaRoberts EdwardGostick Jeff;
展开▼
作者单位

Univ Waterloo, Dept Chem Engn, Waterloo, ON, Canada;

York Univ, Dept Elect Engn & Comp Sci, York, ON, Canada;

Univ Calgary, Dept Chem & Petr Engn, Calgary, AB, CanadaUniv Waterloo, Dept Chem Engn, Waterloo, ON, Canada|200 Univ Ave West, Waterloo, ON N2L 3G1, Canada;

展开▼
收录信息
原文格式 PDF
正文语种英语
中图分类
关键词
Pore network modeling; Diffusive conductance; Deep learning model; Convolutional neural network;

Prediction of diffusional conductance in extracted pore network models using convolutional neural networks

摘要

著录项

相关主题

期刊订阅