Search Menu
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information
Search Scholarly Publications

Title: A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning

Abstract

Many geological materials, such as shale, mudstone, carbonate rock, limestone and rock salt are multi-porosity porous media in which pores of different scales may co-exist in the host matrix. When fractures propagate in these multi-porosity materials, these pores may enlarge and coalesce and therefore change the magnitude and the principal directions of the effective permeability tensors. The pore-fluid inside the cracks and the pores of host matrix may interact and exchange fluid mass, but the difference in hydraulic properties of these pores often means that a single homogenized effective permeability tensor field is insufficient to characterize the evolving hydraulic properties of these materials at smaller time scale. Furthermore, the complexity of the hydro-mechanical coupling process and the induced mechanical and hydraulic anisotropy originated from the micro-fracture and plasticity at grain scale also makes it difficult to propose, implement and validate separated macroscopic constitutive laws for numerical simulations. Here this article presents a hybrid data-driven method designed to capture the multiscale hydro-mechanical coupling effect of porous media with pores of various different sizes. At each scale, data-driven models generated from supervised machine learning are hybridized with classical constitutive laws in a directed graph that represents the numerical models. By using sub-scalemore » simulations to generate database to train material models, an offline homogenization procedure is used to replace the up-scaling procedure to generate cohesive laws for localized physical discontinuities at both grain and specimen scales. Through a proper homogenization procedure that preserves spatial length scales, the proposed method enables field-scale simulations to gather insights from meso-scale and grain-scale micro-structural attributes. This method is proven to be much more computationally efficient than the classical DEM–FEM or FEM2 approach while at the same time more robust and flexible than the classical surrogate modeling approach. Due to the usage of bridging-scale technique, the proposed model may provide multiple opportunities to incorporate different types of simulations and experimental data across different length scales for machine learning. Numerical issues will also be discussed.« less

Authors:
 [1]; ORCiD logo [1]
+ Show Author Affiliations
  1. Columbia University, New York, NY (United States)
Publication Date:
Research Org.:
Columbia Univ., New York, NY (United States)
Sponsoring Org.:
USDOE Office of Nuclear Energy (NE), Nuclear Energy University Program (NEUP); Army Research Office (ARO); US Air Force Office of Scientific Research (AFOSR); USDOE
OSTI Identifier:
1538120
Alternate Identifier(s):
OSTI ID: 1548754
Grant/Contract Number:  
NE0008534; W911NF-15-1-0581; FA9550-17-1-0169
Resource Type:
Accepted Manuscript
Journal Name:
Computer Methods in Applied Mechanics and Engineering
Additional Journal Information:
Journal Volume: 334; Journal Issue: C; Journal ID: ISSN 0045-7825
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
42 ENGINEERING; dual-porosity; data-driven modeling; directed graph; embedded discontinuity; recurrent neural network; multiscale method

Citation Formats

Wang, Kun, and Sun, WaiChing. A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning. United States: N. p., 2018. Web. doi:10.1016/j.cma.2018.01.036.
Copy to clipboard
Wang, Kun, & Sun, WaiChing. A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning. United States. https://doi.org/10.1016/j.cma.2018.01.036
Copy to clipboard
Wang, Kun, and Sun, WaiChing. Sat . "A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning". United States. https://doi.org/10.1016/j.cma.2018.01.036. https://www.osti.gov/servlets/purl/1538120.
Copy to clipboard
@article{osti_1538120,
title = {A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning},
author = {Wang, Kun and Sun, WaiChing},
abstractNote = {Many geological materials, such as shale, mudstone, carbonate rock, limestone and rock salt are multi-porosity porous media in which pores of different scales may co-exist in the host matrix. When fractures propagate in these multi-porosity materials, these pores may enlarge and coalesce and therefore change the magnitude and the principal directions of the effective permeability tensors. The pore-fluid inside the cracks and the pores of host matrix may interact and exchange fluid mass, but the difference in hydraulic properties of these pores often means that a single homogenized effective permeability tensor field is insufficient to characterize the evolving hydraulic properties of these materials at smaller time scale. Furthermore, the complexity of the hydro-mechanical coupling process and the induced mechanical and hydraulic anisotropy originated from the micro-fracture and plasticity at grain scale also makes it difficult to propose, implement and validate separated macroscopic constitutive laws for numerical simulations. Here this article presents a hybrid data-driven method designed to capture the multiscale hydro-mechanical coupling effect of porous media with pores of various different sizes. At each scale, data-driven models generated from supervised machine learning are hybridized with classical constitutive laws in a directed graph that represents the numerical models. By using sub-scale simulations to generate database to train material models, an offline homogenization procedure is used to replace the up-scaling procedure to generate cohesive laws for localized physical discontinuities at both grain and specimen scales. Through a proper homogenization procedure that preserves spatial length scales, the proposed method enables field-scale simulations to gather insights from meso-scale and grain-scale micro-structural attributes. This method is proven to be much more computationally efficient than the classical DEM–FEM or FEM2 approach while at the same time more robust and flexible than the classical surrogate modeling approach. Due to the usage of bridging-scale technique, the proposed model may provide multiple opportunities to incorporate different types of simulations and experimental data across different length scales for machine learning. Numerical issues will also be discussed.},
doi = {10.1016/j.cma.2018.01.036},
journal = {Computer Methods in Applied Mechanics and Engineering},
number = C,
volume = 334,
place = {United States},
year = {Sat Feb 10 00:00:00 EST 2018},
month = {Sat Feb 10 00:00:00 EST 2018}
}
Copy to clipboard
Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1016/j.cma.2018.01.036
Copyright Statement
Other availability
Search WorldCat Search WorldCat to find libraries that may hold this journal
Citation Metrics:
Cited by: 178 works
Citation information provided by
Web of Science
Save / Share:
Export Metadata
Save to My Library
You must Sign In or Create an Account in order to save documents to your library.

Works referenced in this record:

Inverse Dual‐Permeability Modeling of Preferential Water Flow in a Soil Column and Implications for Field‐Scale Solute Transport
journal, January 2006

  • Köhne, J. Maximilian; Mohanty, Binayak P.; Šimůnek, Jirka
  • Vadose Zone Journal, Vol. 5, Issue 1
  • DOI: 10.2136/vzj2005.0008

The reduced model multiscale method (R3M) for the non-linear homogenization of hyperelastic media at finite strains
journal, April 2007

Identification of elastoplastic microscopic material parameters within a homogenization scheme
journal, June 2015

  • Schmidt, U.; Mergheim, J.; Steinmann, P.
  • International Journal for Numerical Methods in Engineering, Vol. 104, Issue 6
  • DOI: 10.1002/nme.4933

Advances in modelling hysteretic water retention curve in deformable soils
journal, November 2008

Flow‐Deformation Response of Dual‐Porosity Media
journal, January 1992

Homogenization and two-scale simulations of granular materials for different microstructural constraints
journal, August 2010

  • Miehe, C.; Dettmar, J.; Zäh, D.
  • International Journal for Numerical Methods in Engineering, Vol. 83, Issue 8-9
  • DOI: 10.1002/nme.2875

Time-dependent aspects of rock behavior as measured by a servocontrolled hydraulic testing machine
journal, May 1973

  • Peng, S. S.
  • International Journal of Rock Mechanics and Mining Sciences & Geomechanics Abstracts, Vol. 10, Issue 3
  • DOI: 10.1016/0148-9062(73)90033-8

Data Driven Computing with noisy material data sets
journal, November 2017

Multi-scale computational homogenization: Trends and challenges
journal, August 2010

  • Geers, M. G. D.; Kouznetsova, V. G.; Brekelmans, W. A. M.
  • Journal of Computational and Applied Mathematics, Vol. 234, Issue 7
  • DOI: 10.1016/j.cam.2009.08.077

A nonintrusive stochastic multiscale solver
journal, April 2011

  • Fish, Jacob; Wu, Wei
  • International Journal for Numerical Methods in Engineering, Vol. 88, Issue 9
  • DOI: 10.1002/nme.3201

Stabilized mixed finite elements for deformable porous media with double porosity
journal, August 2015

  • Choo, Jinhyun; Borja, Ronaldo I.
  • Computer Methods in Applied Mechanics and Engineering, Vol. 293
  • DOI: 10.1016/j.cma.2015.03.023

Albany: Using Component-Based Design to Develop a Flexible, Generic Multiphysics Analysis code
journal, January 2016

  • Salinger, Andrew G.; Bartlett, Roscoe A.; Bradley, Andrew M.
  • International Journal for Multiscale Computational Engineering, Vol. 14, Issue 4
  • DOI: 10.1615/IntJMultCompEng.2016017040

Network model evaluation of permeability and spatial correlation in a real random sphere packing
journal, April 1993

  • Bryant, Steven L.; King, Peter R.; Mellor, David W.
  • Transport in Porous Media, Vol. 11, Issue 1
  • DOI: 10.1007/BF00614635

A two-scale model of granular materials
journal, January 2012

  • Wellmann, Christian; Wriggers, Peter
  • Computer Methods in Applied Mechanics and Engineering, Vol. 205-208
  • DOI: 10.1016/j.cma.2010.12.023

Finite element methods for the analysis of strong discontinuities in coupled poro-plastic media
journal, August 2002

Modeling of soil behavior with a recurrent neural network
journal, October 1998

  • Zhu, Jian-Hua; Zaman, Musharraf M.; Anderson, Scott A.
  • Canadian Geotechnical Journal, Vol. 35, Issue 5
  • DOI: 10.1139/t98-042

Data driven modeling of plastic deformation
journal, May 2017

  • Versino, Daniele; Tonda, Alberto; Bronkhorst, Curt A.
  • Computer Methods in Applied Mechanics and Engineering, Vol. 318
  • DOI: 10.1016/j.cma.2017.02.016

Artificial neural network as an incremental non-linear constitutive model for a finite element code
journal, July 2003

Cam-Clay plasticity part III: Extension of the infinitesimal model to include finite strains
journal, March 1998

  • Borja, Ronaldo I.; Tamagnini, Claudio
  • Computer Methods in Applied Mechanics and Engineering, Vol. 155, Issue 1-2
  • DOI: 10.1016/S0045-7825(97)00141-2

Comparisons of the Size of the Representative Volume Element in Elastic, Plastic, Thermoelastic, and Permeable Random Microstructures
journal, January 2007

  • Ostoja-Starzewski, M.; Du, X.; Khisaeva, Z. F.
  • International Journal for Multiscale Computational Engineering, Vol. 5, Issue 2
  • DOI: 10.1615/IntJMultCompEng.v5.i2.10

On multiscale FE analyses of heterogeneous structures: from homogenization to multigrid solvers
journal, January 2007

  • Miehe, C.; Bayreuther, C. G.
  • International Journal for Numerical Methods in Engineering, Vol. 71, Issue 10
  • DOI: 10.1002/nme.1972

The use of artificial neural networks in decision support in cancer: A systematic review
journal, May 2006

A multilevel projection-based model order reduction framework for nonlinear dynamic multiscale problems in structural and solid mechanics: MULTILEVEL MODEL ORDER REDUCTION FOR MULTISCALE PROBLEMS
journal, May 2017

  • Zahr, Matthew J.; Avery, Philip; Farhat, Charbel
  • International Journal for Numerical Methods in Engineering, Vol. 112, Issue 8
  • DOI: 10.1002/nme.5535

Artificial neural networks in renewable energy systems applications: a review
journal, December 2001

Long Short-Term Memory
journal, November 1997

Hydromechanical Modeling of Unsaturated Flow in Double Porosity Media
journal, December 2016

A finite element model for strain localization analysis of strongly discontinuous fields based on standard Galerkin approximation
journal, December 2000

Recurrent Neural Networks for Uncertain Time-Dependent Structural Behavior: Recurrent neural networks for uncertain time-dependent structural behavior
journal, February 2010

Identifying Material Parameters for a Micro-Polar Plasticity Model via X-Ray Micro-Computed Tomographic (ct) Images: Lessons Learned from the Curve-Fitting Exercises
journal, January 2016

Multiscale modeling in computational biomechanics
journal, May 2009

  • Tawhai, M.; Bischoff, J.; Einstein, D.
  • IEEE Engineering in Medicine and Biology Magazine, Vol. 28, Issue 3
  • DOI: 10.1109/MEMB.2009.932489

Multiporosity/multipermeability approach to the simulation of naturally fractured reservoirs
journal, June 1993

  • Bai, Mao; Elsworth, Derek; Roegiers, Jean‐Claude
  • Water Resources Research, Vol. 29, Issue 6
  • DOI: 10.1029/92WR02746

Knowledge‐Based Modeling of Material Behavior with Neural Networks
journal, January 1991

FEM validation of a double porosity elastic model for consolidation of structurally complex clayey soils
journal, April 2000

Fabric evolution within shear bands of granular materials and its relation to critical state theory
journal, November 2010

  • Fu, Pengcheng; Dafalias, Yannis F.
  • International Journal for Numerical and Analytical Methods in Geomechanics, Vol. 35, Issue 18
  • DOI: 10.1002/nag.988

Multi-scale crystal plasticity finite element model approach to modeling nickel-based superalloys
journal, October 2013

A semi-implicit discrete-continuum coupling method for porous media based on the effective stress principle at finite strain
journal, June 2016

The transition from brittle faulting to cataclastic flow: Permeability evolution
journal, February 1997

  • Zhu, Wenlu; Wong, Teng-fong
  • Journal of Geophysical Research: Solid Earth, Vol. 102, Issue B2
  • DOI: 10.1029/96JB03282

Multiscale method for characterization of porous microstructures and their impact on macroscopic effective permeability
journal, May 2011

  • Sun, W. C.; Andrade, J. E.; Rudnicki, J. W.
  • International Journal for Numerical Methods in Engineering, Vol. 88, Issue 12
  • DOI: 10.1002/nme.3220

Neural network constitutive model for rate-dependent materials
journal, June 2006

A numerical dual-porosity model with semianalytical treatment of fracture/matrix flow
journal, July 1993

  • Zimmerman, Robert W.; Chen, Gang; Hadgu, Teklu
  • Water Resources Research, Vol. 29, Issue 7
  • DOI: 10.1029/93WR00749

Prediction of Soil–Water Characteristic Curve Using Genetic Programming
journal, May 2006

A stabilized finite element formulation for monolithic thermo-hydro-mechanical simulations at finite strain: STABILIZED FEM FOR THERMO-HYDRO-MECHANICS AT FINITE STRAIN
journal, April 2015

  • Sun, WaiChing
  • International Journal for Numerical Methods in Engineering, Vol. 103, Issue 11
  • DOI: 10.1002/nme.4910

Artificial neural networks (the multilayer perceptron)—a review of applications in the atmospheric sciences
journal, August 1998

Stress-induced anisotropy in granular materials: fabric, stiffness, and permeability
journal, June 2015

Using Support Vector Machines to Develop Pedotransfer Functions for Water Retention of Soils in Poland
journal, January 2008

  • Lamorski, K.; Pachepsky, Y.; Sławiński, C.
  • Soil Science Society of America Journal, Vol. 72, Issue 5
  • DOI: 10.2136/sssaj2007.0280N

Damage Evolution in Composites with a Homogenization-based Continuum Damage Mechanics Model
journal, September 2008

  • Jain, Jayesh R.; Ghosh, Somnath
  • International Journal of Damage Mechanics, Vol. 18, Issue 6
  • DOI: 10.1177/1056789508091563

Simple Plasticity Sand Model Accounting for Fabric Change Effects
journal, June 2004

Multiporosity flow in fractured low-permeability rocks
journal, February 2015

  • Kuhlman, Kristopher L.; Malama, Bwalya; Heath, Jason E.
  • Water Resources Research, Vol. 51, Issue 2
  • DOI: 10.1002/2014WR016502

A stabilized assumed deformation gradient finite element formulation for strongly coupled poromechanical simulations at finite strain: STABILIZED F-BAR FINITE ELEMENT FORMULATION FOR POROMECHANICS
journal, January 2013

  • Sun, WaiChing; Ostien, Jakob T.; Salinger, Andrew G.
  • International Journal for Numerical and Analytical Methods in Geomechanics
  • DOI: 10.1002/nag.2161

General Theory of Three‐Dimensional Consolidation
journal, February 1941

  • Biot, Maurice A.
  • Journal of Applied Physics, Vol. 12, Issue 2
  • DOI: 10.1063/1.1712886

Reservoir computing approaches to recurrent neural network training
journal, August 2009

Determining Material Parameters for Critical State Plasticity Models Based on Multilevel Extended Digital Database
journal, October 2015

  • Liu, Yang; Sun, WaiChing; Fish, Jacob
  • Journal of Applied Mechanics, Vol. 83, Issue 1
  • DOI: 10.1115/1.4031619

Cam-Clay plasticity, Part VIII: A constitutive framework for porous materials with evolving internal structure
journal, September 2016

  • Borja, Ronaldo I.; Choo, Jinhyun
  • Computer Methods in Applied Mechanics and Engineering, Vol. 309
  • DOI: 10.1016/j.cma.2016.06.016

The signature of shear-induced anisotropy in granular media
journal, January 2013

Two-scale modeling of granular materials: a DEM-FEM approach
journal, March 2011

A Semi-Implicit Microplar Discrete-To-Continuum Method for Granular Materials
conference, January 2016

  • Wang, Kun; Sun, Waiching
  • Proceedings of the VII European Congress on Computational Methods in Applied Sciences and Engineering (ECCOMAS Congress 2016)
  • DOI: 10.7712/100016.1958.5465

Artificial Neural Networks in numerical modelling of composites
journal, May 2009

  • Lefik, M.; Boso, D. P.; Schrefler, B. A.
  • Computer Methods in Applied Mechanics and Engineering, Vol. 198, Issue 21-26
  • DOI: 10.1016/j.cma.2008.12.036

Explicit Newmark/Verlet algorithm for time integration of the rotational dynamics of rigid bodies
journal, January 2005

  • Krysl, P.; Endres, L.
  • International Journal for Numerical Methods in Engineering, Vol. 62, Issue 15
  • DOI: 10.1002/nme.1272

Computational thermo-hydro-mechanics for multiphase freezing and thawing porous media in the finite deformation range
journal, May 2017

Characterization of pore structure and strain localization in Majella limestone by X-ray computed tomography and digital image correlation
journal, December 2014

  • Ji, Yuntao; Hall, Stephen A.; Baud, Patrick
  • Geophysical Journal International, Vol. 200, Issue 2
  • DOI: 10.1093/gji/ggu414

Implicit numerical integration of a three-invariant, isotropic/kinematic hardening cap plasticity model for geomaterials
journal, December 2005

  • Foster, C. D.; Regueiro, R. A.; Fossum, A. F.
  • Computer Methods in Applied Mechanics and Engineering, Vol. 194, Issue 50-52
  • DOI: 10.1016/j.cma.2005.01.001

A coupled FEM/DEM approach for hierarchical multiscale modelling of granular media: HIERARCHICAL MULTISCALE MODELLING OF GRANULAR MEDIA
journal, June 2014

  • Guo, Ning; Zhao, Jidong
  • International Journal for Numerical Methods in Engineering, Vol. 99, Issue 11
  • DOI: 10.1002/nme.4702

Evaluation of variation of permeability in liquefiable soil under earthquake loading
journal, March 2012

3D modelling of strong discontinuities in elastoplastic solids: fixed and rotating localization formulations
journal, January 2003

  • Mosler, J.; Meschke, G.
  • International Journal for Numerical Methods in Engineering, Vol. 57, Issue 11
  • DOI: 10.1002/nme.731

Hybrid Micro‐Macro‐Modeling of Evolving Anisotropies and Length Scales in Finite Plasticity of Polycrystals
journal, December 2011

Incremental topological flipping works for regular triangulations
journal, March 1996

Stabilized low-order finite elements for coupled solid-deformation/fluid-diffusion and their application to fault zone transients
journal, September 2008

  • White, Joshua A.; Borja, Ronaldo I.
  • Computer Methods in Applied Mechanics and Engineering, Vol. 197, Issue 49-50
  • DOI: 10.1016/j.cma.2008.05.015

FE2 multiscale approach for modelling the elastoviscoplastic behaviour of long fibre SiC/Ti composite materials
journal, March 2000

  • Feyel, Frédéric; Chaboche, Jean-Louis
  • Computer Methods in Applied Mechanics and Engineering, Vol. 183, Issue 3-4
  • DOI: 10.1016/S0045-7825(99)00224-8

Strong discontinuities in partially saturated poroplastic solids
journal, April 2010

  • Callari, C.; Armero, F.; Abati, A.
  • Computer Methods in Applied Mechanics and Engineering, Vol. 199, Issue 23-24
  • DOI: 10.1016/j.cma.2010.01.002

Pore-Scale Modeling of Viscous Flow and Induced Forces in Dense Sphere Packings
journal, July 2012

  • Chareyre, Bruno; Cortis, Andrea; Catalano, Emanuele
  • Transport in Porous Media, Vol. 94, Issue 2
  • DOI: 10.1007/s11242-012-0057-2

Cohesive Zone Models: A Critical Review of Traction-Separation Relationships Across Fracture Surfaces
journal, November 2011

  • Park, Kyoungsoo; Paulino, Glaucio H.
  • Applied Mechanics Reviews, Vol. 64, Issue 6
  • DOI: 10.1115/1.4023110

A novel finite element double porosity model for multiphase flow through deformable fractured porous media
journal, November 1997

Implicit constitutive modelling for viscoplasticity using neural networks
journal, September 1998

Data-driven computational mechanics
journal, June 2016

    Sort by:
    [ × clear filter / sort ]

    Similar Records in DOE PAGES and OSTI.GOV collections: