journal article·2026-01-10Open access

Machine-Learning-Based Multiscale Methods for 3D Modelling of Granular Materials by Incorporating History-Dependent State Variables

Mengqi Wang, Min Wang, Shaoheng Guan, Yuntian Feng

KONA Powder and Particle Journal· Volume 43· Issue 0

Abstract

Over the past decades, the prevalence of machine learning (ML) methods has made the development of ML-based constitutive models for granular materials undoubtedly a popular subject. Numerous studies have been made to feature the loading path or history-dependent stress-strain response of granular media using neural networks. In this work, a novel finite element method (FEM)–ML multiscale approach was developed by incorporating internal variables to improve the simulation accuracy of 3D history-dependent granular materials for the first time. To this end, a surrogate constitutive model based on the single-step-based multi-layer perceptron (MLP) neural network was used to replace representative volume element (RVE) simulations conducted by the discrete element method (DEM) in the multiscale FEM–DEM approach. Although the prediction principle of the MLP aligns with the FEM algorithm, artificially added internal variables are required to differentiate the loading history. To address this issue, history variables associated with the Frobenius norm are proposed to be fed into the MLP coupled with the strain tensor to extract the history-dependent behaviour of granular assemblies. The developed FEM–ML approach was demonstrated in 3D conventional triaxial compression (CTC) simulations. Compared to the multiscale FEM–DEM approach, the proposed FEM–ML method exhibits a significantly improved computational efficiency.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Rock Mechanics and Modeling · Grouting, Rheology, and Soil Mechanics · Soil and Unsaturated Flow

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Zienkiewicz Centre for Computational Engineering, Swansea University, UK

Fluid Dynamics and Solid Mechanics Group, Theoretical Division, Los Alamos National Laboratory, USA

Institute of Theoretical and Computational Physics, Graz University of Technology, Austria

References (32)

Show source-provided references
1. Andrade J.E., Avila C.F., Hall S.A., Lenoir N., Viggiani G., Multiscale modeling and characterization of granular matter: From grain kinematics to continuum mechanics, Journal of the Mechanics and Physics of Solids, 59 (2011) 237–250. https://doi.org/10.1016/j.jmps.2010.10.00910.1016/j.jmps.2010.10.009 ↗
2. Andrade J.E., Tu X., Multiscale framework for behavior prediction in granular media, Mechanics of Materials, 41 (2009) 652–669. https://doi.org/10.1016/j.mechmat.2008.12.00510.1016/j.mechmat.2008.12.005 ↗
3. Basheer I.A., Selection of methodology for neural network modeling of constitutive hystereses behavior of soils, Computer-Aided Civil and Infrastructure Engineering, 15 (2000) 445–463. https://doi.org/10.1111/0885-9507.0020610.1111/0885-9507.00206 ↗
4. Basheer I.A., Stress-strain behavior of geomaterials in loading reversal simulated by time-delay neural networks, Journal of Materials in Civil Engineering, 14 (2002) 270–273. https://doi.org/10.1061/(ASCE)0899-1561(2002)14:3(270)10.1061/(ASCE)0899-1561(2002)14:3(270) ↗
5. Desrues J., Andò E., Strain localisation in granular media, Comptes Rendus Physique, 16 (2015) 26–36. https://doi.org/10.1016/j.crhy.2015.01.00110.1016/j.crhy.2015.01.001 ↗
6. Drakos S., Pande G., On neural network constitutive models for geomaterials, Journal of Civil Engineering Research, 5 (2015) 106–113. https://doi.org/10.5923/j.jce.20150505.02
7. Geers M.G.D., Kouznetsova V.G., Brekelmans W.A.M., Multi-scale computational homogenization: trends and challenges, Journal of Computational and Applied Mathematics, 234 (2010) 2175–2182. https://doi.org/10.1016/j.cam.2009.08.07710.1016/j.cam.2009.08.077 ↗
8. Ghavamian F., Simone A., Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network, Computer Methods in Applied Mechanics and Engineering, 357 (2019) 112594. https://doi.org/10.1016/j.cma.2019.11259410.1016/j.cma.2019.112594 ↗
9. Gross L., Bourgouin L., Hale A.J., Mühlhaus H.B., Interface modeling in incompressible media using level sets in Escript, Physics of the Earth and Planetary Interiors, 163 (2007) 23–34. https://doi.org/10.1016/j.pepi.2007.04.00410.1016/j.pepi.2007.04.004 ↗
10. Guo N., Zhao J., A coupled FEM/DEM approach for hierarchical multiscale modelling of granular media, International Journal for Numerical Methods in Engineering, 99 (2014) 789–818. https://doi.org/10.1002/nme.470210.1002/nme.4702 ↗
11. Guo N., Zhao J., 3D multiscale modeling of strain localization in granular media, Computers and Geotechnics, 80 (2016) 360–372. https://doi.org/10.1016/j.compgeo.2016.01.02010.1016/j.compgeo.2016.01.020 ↗
12. Hashash Y.M.A., Jung S., Ghaboussi J., Numerical implementation of a neural network based material model in finite element analysis, International Journal for Numerical Methods in Engineering, 59 (2004) 989–1005. https://doi.org/10.1002/nme.90510.1002/nme.905 ↗
13. Hashash Y.M.A., Song H., The integration of numerical modeling and physical measurements through inverse analysis in geotechnical engineering, KSCE Journal of Civil Engineering, 12 (2008) 165–176. https://doi.org/10.1007/s12205-008-0165-210.1007/s12205-008-0165-2 ↗
14. Hu X., Zhang Y., Guo L., Wang J., Cai Y., Fu H., Cai Y., Cyclic behavior of saturated soft clay under stress path with bidirectional shear stresses, Soil Dynamics and Earthquake Engineering, 104 (2018) 319–328. https://doi.org/10.1016/j.soildyn.2017.10.01610.1016/j.soildyn.2017.10.016 ↗
15. Huang D., Fuhg J.N., Weißenfels C., Wriggers P., A machine learning based plasticity model using proper orthogonal decomposition, Computer Methods in Applied Mechanics and Engineering, 365 (2020) 113008. https://doi.org/10.1016/j.cma.2020.11300810.1016/j.cma.2020.113008 ↗
16. Kruyt N.P., Rothenburg L., Statistical theories for the elastic moduli of two-dimensional assemblies of granular materials, International Journal of Engineering Science, 36 (1998) 1127–1142. https://doi.org/10.1016/S0020-7225(98)00003-210.1016/S0020-7225(98)00003-2 ↗
17. Li X., Liu Q., Zhang J., A micro–macro homogenization approach for discrete particle assembly – Cosserat continuum modeling of granular materials, International Journal of Solids and Structures, 47 (2010) 291–303. https://doi.org/10.1016/j.ijsolstr.2009.09.03310.1016/j.ijsolstr.2009.09.033 ↗
18. Logarzo H.J., Capuano G., Rimoli J.J., Smart constitutive laws: inelastic homogenization through machine learning, Computer Methods in Applied Mechanics and Engineering, 373 (2021) 113482. https://doi.org/10.1016/j.cma.2020.11348210.1016/j.cma.2020.113482 ↗
19. Ma G., Guan S., Wang Q., Feng Y.T., Zhou W., A predictive deep learning framework for path-dependent mechanical behavior of granular materials, Acta Geotechnica, 17 (2022) 3463–3478. https://doi.org/10.1007/s11440-021-01419-y10.1007/s11440-021-01419-y ↗
20. Miehe C., Dettmar J., Zäh D., Homogenization and two-scale simulations of granular materials for different microstructural constraints, International Journal for Numerical Methods in Engineering, 83 (2010) 1206–1236. https://doi.org/10.1002/nme.287510.1002/nme.2875 ↗
21. Qu T., Di S., Feng Y.T., Wang M., Zhao T., Towards data-driven constitutive modelling for granular materials via micromechanics-informed deep learning, International Journal of Plasticity, 144 (2021) 103046. https://doi.org/10.1016/j.ijplas.2021.10304610.1016/j.ijplas.2021.103046 ↗
22. Qu T., Feng Y.T., Zhao J., A strain energy-based elastic parameter calibration method for lattice/bonded particle modelling of solid materials, Powder Technology, 410 (2022) 117860. https://doi.org/10.1016/j.powtec.2022.11786010.1016/j.powtec.2022.117860 ↗
23. Qu T., Guan S., Feng Y.T., Ma G., Zhou W., Zhao J., Deep active learning for constitutive modelling of granular materials: from representative volume elements to implicit finite element modelling, International Journal of Plasticity, 164 (2023) 103576. https://doi.org/10.1016/j.ijplas.2023.10357610.1016/j.ijplas.2023.103576 ↗
24. Sidarta D.E., Ghaboussi J., Constitutive modeling of geomaterials from non-uniform material tests, Computers and Geotechnics, 22 (1998) 53–71. https://doi.org/10.1016/S0266-352X(97)00035-910.1016/S0266-352X(97)00035-9 ↗
25. Smilauer V., Angelidakis V., Catalano E., Caulk R., Chareyre B., Chevremont W., Dorofeenko S., Duriez J., Dyck N., Elias J., et al.., Yade documentation, arXiv preprint, (2023) arXiv:2301.00611. https://doi.org/10.48550/arXiv.2301.00611
26. Thornton C., Numerical simulations of deviatoric shear deformation of granular media, Géotechnique, 50 (2000) 43–53. https://doi.org/10.1680/geot.2000.50.1.4310.1680/geot.2000.50.1.43 ↗
27. Tian Y., Yao Y.-P., Modelling the non-coaxiality of soils from the view of cross-anisotropy, Computers and Geotechnics, 86 (2017) 219–229. https://doi.org/10.1016/j.compgeo.2017.01.01310.1016/j.compgeo.2017.01.013 ↗
28. Wang M.Q., Feng Y.T., Guan S., Qu T., Multi-layer perceptron-based data-driven multiscale modelling of granular materials with a novel Frobenius norm-based internal variable, Journal of Rock Mechanics and Geotechnical Engineering, 16 (2024) 2198–2218. https://doi.org/10.1016/j.jrmge.2024.02.00310.1016/j.jrmge.2024.02.003 ↗
29. Wang M.Q., Qu T., Guan S., Zhao T., Liu B., Feng Y.T., Data-driven strain–stress modelling of granular materials via temporal convolution neural network, Computers and Geotechnics, 152 (2022) 105049. https://doi.org/10.1016/j.compgeo.2022.10504910.1016/j.compgeo.2022.105049 ↗
30. Wang M., Zhang D.Z., Deformation accommodating periodic computational domain for a uniform velocity gradient, Computer Methods in Applied Mechanics and Engineering, 374 (2021) 113607. https://doi.org/10.1016/j.cma.2020.11360710.1016/j.cma.2020.113607 ↗
31. Yin Z.-Y., Chang C.S., Karstunen M., Hicher P.-Y., An anisotropic elastic–viscoplastic model for soft clays, International Journal of Solids and Structures, 47 (2010) 665–677. https://doi.org/10.1016/j.ijsolstr.2009.11.00410.1016/j.ijsolstr.2009.11.004 ↗
32. Zhang P., Yang Y., Yin Z.-Y., BiLSTM-based soil–structure interface modeling, International Journal of Geomechanics, 21 (2021) 04021096. https://doi.org/10.1061/(ASCE)GM.1943-5622.000205810.1061/(ASCE)GM.1943-5622.0002058 ↗