Details
Originalsprache | Englisch |
---|---|
Seiten (von - bis) | 889-910 |
Seitenumfang | 22 |
Fachzeitschrift | International Journal for Numerical and Analytical Methods in Geomechanics |
Jahrgang | 48 |
Ausgabenummer | 4 |
Publikationsstatus | Veröffentlicht - 13 Feb. 2024 |
Abstract
The purpose of this paper is to investigate the utilization of artificial neural networks (ANNs) in learning models that address the nonlinear anisotropic flow and hysteresis retention behavior of deformable porous materials. Herein, the micro-geometries of various networks of porous Bentheimer Sandstones subjected to several degrees of strain from the literature are considered. For the generation of the database required for the training, validation, and testing of the machine learning (ML) models, single-phase and biphasic lattice Boltzmann (LB) simulations are performed. The anisotropic nature of the intrinsic permeability is investigated for the single-phase LB simulations. Thereafter, the database contains the computed average fluid velocities versus the pressure gradients. In this database, the range of applied fluid pressure gradients includes Darcy as well as non-Darcy flows. The generated output from the single-phase flow simulations is implemented in a feed-forward neural network, representing a path-independent informed graph-based model. Concerning the two-phase LB simulations, the Shan-Chen multiphase LB model is used to generate the retention curves of the cyclic drying/wetting processes in the deformed porous networks. Consequently, two different ML path-dependent approaches, that is, 1D convolutional neural network and the recurrent neural network, are used to model the biphasic flow through the deformable porous materials. A comparison in terms of accuracy and speed of training between the two approaches is presented. Conclusively, the outcomes of the papers show the capability of the ML models in representing constitutive relations for permeability and hysteretic retention curves accurately and efficiently.
ASJC Scopus Sachgebiete
- Ingenieurwesen (insg.)
- Numerische Mechanik
- Werkstoffwissenschaften (insg.)
- Erdkunde und Planetologie (insg.)
- Geotechnik und Ingenieurgeologie
- Ingenieurwesen (insg.)
- Werkstoffmechanik
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
in: International Journal for Numerical and Analytical Methods in Geomechanics, Jahrgang 48, Nr. 4, 13.02.2024, S. 889-910.
Publikation: Beitrag in Fachzeitschrift › Artikel › Forschung › Peer-Review
}
TY - JOUR
T1 - A machine-learning supported multi-scale LBM-TPM model of unsaturated, anisotropic, and deformable porous materials
AU - Chaaban, Mohamad
AU - Heider, Yousef
AU - Sun, Wai Ching
AU - Markert, Bernd
N1 - Funding Information: The second author, Y. Heider, would like to gratefully thank the German Research Foundation (DFG) for the support of the project “Multi‐field continuum modeling of two‐fluid‐filled porous media fracture augmented by microscale‐based machine‐learning material laws”, grant number 458375627.
PY - 2024/2/13
Y1 - 2024/2/13
N2 - The purpose of this paper is to investigate the utilization of artificial neural networks (ANNs) in learning models that address the nonlinear anisotropic flow and hysteresis retention behavior of deformable porous materials. Herein, the micro-geometries of various networks of porous Bentheimer Sandstones subjected to several degrees of strain from the literature are considered. For the generation of the database required for the training, validation, and testing of the machine learning (ML) models, single-phase and biphasic lattice Boltzmann (LB) simulations are performed. The anisotropic nature of the intrinsic permeability is investigated for the single-phase LB simulations. Thereafter, the database contains the computed average fluid velocities versus the pressure gradients. In this database, the range of applied fluid pressure gradients includes Darcy as well as non-Darcy flows. The generated output from the single-phase flow simulations is implemented in a feed-forward neural network, representing a path-independent informed graph-based model. Concerning the two-phase LB simulations, the Shan-Chen multiphase LB model is used to generate the retention curves of the cyclic drying/wetting processes in the deformed porous networks. Consequently, two different ML path-dependent approaches, that is, 1D convolutional neural network and the recurrent neural network, are used to model the biphasic flow through the deformable porous materials. A comparison in terms of accuracy and speed of training between the two approaches is presented. Conclusively, the outcomes of the papers show the capability of the ML models in representing constitutive relations for permeability and hysteretic retention curves accurately and efficiently.
AB - The purpose of this paper is to investigate the utilization of artificial neural networks (ANNs) in learning models that address the nonlinear anisotropic flow and hysteresis retention behavior of deformable porous materials. Herein, the micro-geometries of various networks of porous Bentheimer Sandstones subjected to several degrees of strain from the literature are considered. For the generation of the database required for the training, validation, and testing of the machine learning (ML) models, single-phase and biphasic lattice Boltzmann (LB) simulations are performed. The anisotropic nature of the intrinsic permeability is investigated for the single-phase LB simulations. Thereafter, the database contains the computed average fluid velocities versus the pressure gradients. In this database, the range of applied fluid pressure gradients includes Darcy as well as non-Darcy flows. The generated output from the single-phase flow simulations is implemented in a feed-forward neural network, representing a path-independent informed graph-based model. Concerning the two-phase LB simulations, the Shan-Chen multiphase LB model is used to generate the retention curves of the cyclic drying/wetting processes in the deformed porous networks. Consequently, two different ML path-dependent approaches, that is, 1D convolutional neural network and the recurrent neural network, are used to model the biphasic flow through the deformable porous materials. A comparison in terms of accuracy and speed of training between the two approaches is presented. Conclusively, the outcomes of the papers show the capability of the ML models in representing constitutive relations for permeability and hysteretic retention curves accurately and efficiently.
KW - anisotropic permeability
KW - convolutional neural network
KW - hysteretic retention curve
KW - lattice Boltzmann method
KW - multiphase fluid flow
KW - recurrent neural network
UR - http://www.scopus.com/inward/record.url?scp=85178933061&partnerID=8YFLogxK
U2 - 10.1002/nag.3668
DO - 10.1002/nag.3668
M3 - Article
AN - SCOPUS:85178933061
VL - 48
SP - 889
EP - 910
JO - International Journal for Numerical and Analytical Methods in Geomechanics
JF - International Journal for Numerical and Analytical Methods in Geomechanics
SN - 0363-9061
IS - 4
ER -