[en] Artificial Neural Networks (NNWs) are appealing functions to substitute high dimensional and non-linear history-dependent problems in computational mechanics since they offer the possibility to drastically reduce the computational time. This feature has recently been exploited in the context of multi-scale simulations, in which the NNWs serve as surrogate model of micro-scale nite element resolutions. Nevertheless, in the literature, mainly the macro-stress-macro-strain response of the meso-scale boundary value problem was considered and the micro-structure information could not be recovered in a so-called localization step. In this work, we develop Recurrent Neural Networks (RNNs) as surrogates of the RVE response while being able to recover the evolution of the local micro-structure state variables for complex loading scenarios. The main difficulty is the high dimensionality of the RNNs output which consists in the internal state variable distribution in the micro-structure. We thus propose and compare several surrogate models based on a dimensionality reduction: i) direct RNN modeling with implicit NNW dimensionality reduction, ii) RNN with PCA dimensionality reduction, and iii) RNN with PCA dimensionality reduction and dimension- ality break down, i.e. the use of several RNNs instead of a single one. Besides, we optimize the sequential training strategy of the latter surrogate for GPU usage in order to speed up the process. Finally, through RNN modeling of the principal components coefficients, the connection between the physical state variables and the hidden variables of the RNN is revealed, and exploited in order to select the hyper-parameters of the RNN-based surrogate models in their design stage.
H2020 - 862015 - MOAMMM - Multi-scale Optimisation for Additive Manufacturing of fatigue resistant shock-absorbing MetaMaterials
Name of the research project :
This project has received funding from the European Unions Horizon 2020 research and innovation programme under grant agreement No 862015 for the project \Multi-scale Optimisation for Additive Manufacturing of fatigue resistant shock-absorbing MetaMaterials (MOAMMM) of the H2020-EU.1.2.1. - FET Open Programme.
Funders :
EC - European Commission EU - European Union
Commentary :
Data can be downloaded on https://doi.org/10.5281/zenodo.5668390
Furukawa, T., Yagawa, G., Implicit constitutive modelling for viscoplasticity using neural networks. Internat. J. Numer. Methods Engrg. 43:2 (1998), 195–219.
Furukawa, T., Hoffman, M., Accurate cyclic plastic analysis using a neural network material model. Eng. Anal. Bound. Elem. 28:3 (2004), 195–204, 10.1016/S0955-7997(03)00050-X Inverse Problems URL http://www.sciencedirect.com/science/article/pii/S095579970300050X.
Wang, K., Sun, W., Meta-modeling game for deriving theory-consistent, microstructure-based traction–separation laws via deep reinforcement learning. Comput. Methods Appl. Mech. Engrg. 346 (2019), 216–241, 10.1016/j.cma.2018.11.026 URL http://www.sciencedirect.com/science/article/pii/S0045782518305851.
Fernández, M., Rezaei, S., Mianroodi, J.R., Fritzen, F., Reese, S., Application of artificial neural networks for the prediction of interface mechanics: a study on grain boundary constitutive behavior. Adv. Model. Simul. Eng. Sci. 7:1 (2020), 1–27.
Lefik, M., Schrefler, B., Artificial neural network as an incremental non-linear constitutive model for a finite element code. Comput. Methods Appl. Mech. Engrg. 192:28 (2003), 3265–3283, 10.1016/S0045-7825(03)00350-5 Multiscale Computational Mechanics for Materials and Structures URL http://www.sciencedirect.com/science/article/pii/S0045782503003505.
Hashash, Y.M.A., Jung, S., Ghaboussi, J., Numerical implementation of a neural network based material model in finite element analysis. Internat. J. Numer. Methods Engrg. 59:7 (2004), 989–1005, 10.1002/nme.905 arXiv:https://onlinelibrary.wiley.com/doi/pdf/10.1002/nme.905. URL https://onlinelibrary.wiley.com/doi/abs/10.1002/nme.905.
Zhang, A., Mohr, D., Using neural networks to represent von mises plasticity with isotropic hardening. Int. J. Plast., 2020, 102732, 10.1016/j.ijplas.2020.102732.
Wu, L., Zulueta, K., Major, Z., Arriaga, A., Noels, L., BayesIan inference of non-linear multiscale model parameters accelerated by a deep neural network. Comput. Methods Appl. Mech. Engrg., 360, 2020, 112693, 10.1016/j.cma.2019.112693 URL http://www.sciencedirect.com/science/article/pii/S004578251930578X.
Lefik, M., Schrefler, B., Artificial neural network for parameter identifications for an elasto-plastic model of superconducting cable under cyclic loading. Comput. Struct. 80:22 (2002), 1699–1713, 10.1016/S0045-7949(02)00162-1 URL http://www.sciencedirect.com/science/article/pii/S0045794902001621.
Hambli, R., Katerchi, H., Benhamou, C.-L., Multiscale methodology for bone remodelling simulation using coupled finite element and neural network computation. Biomech. Model. Mechanobiol. 10:1 (2011), 133–145.
Noels, L., Wu, L., Adam, L., Seyfarth, J., Soni, G., Segurado, J., Laschet, G., Chen, G., Lesueur, M., Lobos, M., Böhlke, T., Reiter, T., Oberpeilsteiner, S., Salaberger, D., Weichert, D., Broeckmann, C., Effective properties. Handbook of Software Solutions for ICME, 2016, Wiley-VCH Verlag GmbH & Co. KGaA, 433–485, 10.1002/9783527693566.ch6.
Yvonnet, J., Solid mechanics and its applications. Computational Homogenization of Heterogeneous Materials with Finite Elements, 2019, Springer International Publishing.
Miehe, C., Schotte, J., Schröder, J., Computational micro-macro transitions and overall moduli in the analysis of polycrystals at large strains. Comput. Mater. Sci. 16:1–4 (1999), 372–382 cited By 88.
Terada, K., Hori, M., Kyoya, T., Kikuchi, N., Simulation of the multi-scale convergence in computational homogenization approaches. Int. J. Solids Struct. 37:16 (2000), 2285–2311, 10.1016/S0020-7683(98)00341-2 URL http://www.sciencedirect.com/science/article/pii/S0020768398003412.
Kouznetsova, V., Brekelmans, W., Baaijens, F., An approach to micro-macro modeling of heterogeneous materials. Comput. Mech. 27:1 (2001), 37–48.
Le, B.A., Yvonnet, J., He, Q.C., Computational homogenization of nonlinear elastic materials using neural networks. Internat. J. Numer. Methods Engrg. 104:12 (2015), 1061–1084, 10.1002/nme.4953.
Bessa, M., Bostanabad, R., Liu, Z., Hu, A., Apley, D.W., Brinson, C., Chen, W., Liu, W.K., A framework for data-driven analysis of materials under uncertainty: Countering the curse of dimensionality. Comput. Methods Appl. Mech. Engrg. 320 (2017), 633–667, 10.1016/j.cma.2017.03.037 URL http://www.sciencedirect.com/science/article/pii/S0045782516314803.
Fritzen, F., Fernández, M., Larsson, F., On-the-fly adaptivity for nonlinear twoscale simulations using artificial neural networks and reduced order modeling. Front. Mater., 6, 2019, 75, 10.3389/fmats.2019.00075 URL https://www.frontiersin.org/article/10.3389/fmats.2019.00075.
Unger, J.F., Könke, C., Coupling of scales in a multiscale simulation using neural networks. Comput. Struct. 86:21 (2008), 1994–2003, 10.1016/j.compstruc.2008.05.004 URL http://www.sciencedirect.com/science/article/pii/S0045794908001430.
Settgast, C., Hütter, G., Kuna, M., Abendroth, M., A hybrid approach to simulate the homogenized irreversible elastic–plastic deformations and damage of foams by neural networks. Int. J. Plast., 126, 2020, 102624, 10.1016/j.ijplas.2019.11.003 URL http://www.sciencedirect.com/science/article/pii/S074964191930381X.
Masi, F., Stefanou, I., Vannucci, P., Maffi-Berthier, V., Thermodynamics-based artificial neural networks for constitutive modeling. J. Mech. Phys. Solids, 147, 2021, 104277, 10.1016/j.jmps.2020.104277 URL https://www.sciencedirect.com/science/article/pii/S0022509620304841.
Rocha, I., Kerfriden, P., van der Meer, F.P., Micromechanics-based surrogate models for the response of composites: A critical comparison between a classical mesoscale constitutive model, hyper-reduction and neural networks. Eur. J. Mech. A Solids, 82, 2020, 103995, 10.1016/j.euromechsol.2020.103995.
Lu, X., Yvonnet, J., Papadopoulos, L., Kalogeris, I., Papadopoulos, V., A stochastic FE2 data-driven method for nonlinear multiscale modeling. Materials, 14(11), 2021, 10.3390/ma14112875 URL https://www.mdpi.com/1996-1944/14/11/2875.
Ghavamian, F., Simone, A., Accelerating multiscale finite element simulations of history-dependent materials using a recurrent neural network. Comput. Methods Appl. Mech. Engrg., 357, 2019, 112594, 10.1016/j.cma.2019.112594 URL http://www.sciencedirect.com/science/article/pii/S0045782519304700.
Koeppe, A., Bamer, F., Markert, B., An intelligent nonlinear meta element for elastoplastic continua: deep learning using a new time-distributed residual U-net architecture. Comput. Methods Appl. Mech. Engrg., 366, 2020, 113088, 10.1016/j.cma.2020.113088.
Mozaffar, M., Bostanabad, R., Chen, W., Ehmann, K., Cao, J., Bessa, M.A., Deep learning predicts path-dependent plasticity. Proc. Natl. Acad. Sci. 116:52 (2019), 26414–26420, 10.1073/pnas.1911815116 arXiv:https://www.pnas.org/content/116/52/26414.full.pdf.
Gorji, M.B., Mozaffar, M., Heidenreich, J.N., Cao, J., Mohr, D., On the potential of recurrent neural networks for modeling path dependent plasticity. J. Mech. Phys. Solids, 143, 2020, 103972, 10.1016/j.jmps.2020.103972.
Wu, L., Nguyen, V.D., Kilingar, N.G., Noels, L., A recurrent neural network-accelerated multi-scale model for elasto-plastic heterogeneous materials subjected to random cyclic and non-proportional loading paths. Comput. Methods Appl. Mech. Engrg., 369, 2020, 113234, 10.1016/j.cma.2020.113234 URL https://www.sciencedirect.com/science/article/pii/S0045782520304199.
Janssen, R.P.M., de Kanter, D., Govaert, L.E., Meijer, H.E.H., Fatigue life predictions for glassy polymers: A constitutive approach. Macromolecules 41:7 (2008), 2520–2530, 10.1021/ma071273i.
Krairi, A., Doghri, I., Robert, G., Multiscale high cycle fatigue models for neat and short fiber reinforced thermoplastic polymers. Int. J. Fatigue 92 (2016), 179–192, 10.1016/j.ijfatigue.2016.06.029 URL https://www.sciencedirect.com/science/article/pii/S0142112316301736.
Berrehili, A., Nadot, Y., Castagnet, S., Grandidier, J., Dumas, C., Multiaxial fatigue criterion for polypropylene – automotive applications. Int. J. Fatigue 32:8 (2010), 1389–1392, 10.1016/j.ijfatigue.2010.01.008 URL https://www.sciencedirect.com/science/article/pii/S0142112310000216.
Jolliffe, I.T., Principal Component Analysis. 1986, Springer-Verlag, Berlin; New York.
Yvonnet, J., He, Q.-C., The reduced model multiscale method (R3M) for the non-linear homogenization of hyperelastic media at finite strains. J. Comput. Phys. 223:1 (2007), 341–368, 10.1016/j.jcp.2006.09.019 URL http://www.sciencedirect.com/science/article/pii/S0021999106004402.
Cao, B.-T., Freitag, S., Meschke, G., A hybrid RNN-GPOD surrogate model for real-time settlement predictions in mechanised tunnelling. Adv. Model. Simul. Eng. Sci., 3(1), 2016, 5, 10.1186/s40323-016-0057-9.
Bamer, F., Koeppe, A., Markert, B., An efficient Monte Carlo simulation strategy based on model order reduction and artificial neural networks. PAMM 17:1 (2017), 287–288, 10.1002/pamm.201710113 arXiv:https://onlinelibrary.wiley.com/doi/pdf/10.1002/pamm.201710113. URL https://onlinelibrary.wiley.com/doi/abs/10.1002/pamm.201710113.
Vijayaraghavan, S., Wu, L., Noels, L., Bordas, S., Natarajan, S., Beex, L., Neural-network acceleration of projection-based model-order-reduction for finite plasticity: Application to RVEs. Mech. Res. Commun., 2022 (Under revision).
Michel, J., Moulinec, H., Suquet, P., Effective properties of composite materials with periodic microstructure: a computational approach. Comput. Methods Appl. Mech. Engrg. 172:1 (1999), 109–143, 10.1016/S0045-7825(98)00227-8 URL https://www.sciencedirect.com/science/article/pii/S0045782598002278.
Nguyen, V.-D., Wu, L., Noels, L., Unified treatment of microscopic boundary conditions and efficient algorithms for estimating tangent operators of the homogenized behavior in the computational homogenization method. Comput. Mech. 59:3 (2017), 483–505, 10.1007/s00466-016-1358-z.
Wippler, J., Fünfschilling, S., Fritzen, F., B”ohlke, T., Hoffmann, M.J., Homogenization of the thermoelastic properties of silicon nitride. Acta Mater. 59:15 (2011), 6029–6038, 10.1016/j.actamat.2011.06.011 URL https://www.sciencedirect.com/science/article/pii/S1359645411004162.
Nguyen, V.-D., Béchet, E., Geuzaine, C., Noels, L., Imposing periodic boundary condition on arbitrary meshes by polynomial interpolation. Comput. Mater. Sci. 55 (2012), 390–406, 10.1016/j.commatsci.2011.10.017 URL http://www.sciencedirect.com/science/article/pii/S0927025611005866.
URL https://pytorch.org/. (Accessed 30 April 2020), 2020.
Hinton, G.E., Salakhutdinov, R.R., Reducing the dimensionality of data with neural networks. Science 313:5786 (2006), 504–507, 10.1126/science.1127647 arXiv:https://www.science.org/doi/pdf/10.1126/science.1127647. URL https://www.science.org/doi/abs/10.1126/science.1127647.
Cuitino, A., Ortiz, M., A material-independent method for extending stress update algorithms from small-strain plasticity to finite plasticity with multiplicative kinematics. Eng. Comput., 9, 1992, 437.
Nguyen, V.-D., Noels, L., Micromechanics-based material networks revisited from the interaction viewpoint; robust and efficient implementation for multi-phase composites. Eur. J. Mech. A Solids, 91, 2022, 104384, 10.1016/j.euromechsol.2021.104384.
Wu, L., Noels, L., Data of “Recurrent Neural Networks (RNNs) with Dimensionality Reduction and Break Down in Computational Mechanics; Application to Multi-Scale Localization Step”. 2021, Zenodo, 10.5281/zenodo.5668390.