\(\mathrm{SO}(3)\)-invariance of informed-graph-based deep neural network for anisotropic elastoplastic materials. (English) Zbl 1436.74012

Summary: This paper examines the frame-invariance (and the lack thereof) exhibited in simulated anisotropic elasto-plastic responses generated from supervised machine learning of classical multi-layer and informed-graph-based neural networks, and proposes different remedies to fix this drawback. The inherent hierarchical relations among physical quantities and state variables in an elasto-plasticity model are first represented as informed, directed graphs, where three variations of the graph are tested. While feed-forward neural networks are used to train path-independent constitutive relations (e.g., elasticity), recurrent neural networks are used to replicate responses that depends on the deformation history, i.e. or path dependent. In dealing with the objectivity deficiency, we use the spectral form to represent tensors and, subsequently, three metrics, the Euclidean distance between the Euler Angles, the distance from the identity matrix, and geodesic on the unit sphere in Lie algebra, can be employed to constitute objective functions for the supervised machine learning. In this, the aim is to minimize the measured distance between the true and the predicted 3D rotation entities. Following this, we conduct numerical experiments on how these metrics, which are theoretically equivalent, may lead to differences in the efficiency of the supervised machine learning as well as the accuracy and robustness of the resultant models. Neural network models trained with tensors represented in component form for a given Cartesian coordinate system are used as a benchmark. Our numerical tests show that, even given the same amount of information and data, the quality of the anisotropic elasto-plasticity model is highly sensitive to the way tensors are represented and measured. The results reveal that using a loss function based on geodesic on the unit sphere in Lie algebra together with an informed, directed graph yield significantly more accurate rotation prediction than the other tested approaches.


74C05 Small-strain, rate-independent theories of plasticity (including rigid-plastic and elasto-plastic materials)
74E10 Anisotropy in solid mechanics
Full Text: DOI


[1] Kirchdoerfer, Trenton; Ortiz, Michael, Data-driven computational mechanics, Comput. Methods Appl. Mech. Engrg., 304, 81-101 (2016) · Zbl 1425.74503
[2] Eggersmann, Robert; Kirchdoerfer, Trenton; Reese, Stefanie; Stainier, Laurent; Ortiz, Michael, Model-free data-driven inelasticity, Comput. Methods Appl. Mech. Engrg., 350, 81-99 (2019)
[3] Wang, Kun; Sun, WaiChing; Du, Qiang, A cooperative game for automated learning of elasto-plasticity knowledge graphs and models with AI-guided experimentation, Comput. Mech., 1-33 (2019) · Zbl 1464.74034
[4] Liu, Zeliang; Wu, C. T., Exploring the 3D architectures of deep material network in data-driven multiscale mechanics, J. Mech. Phys. Solids, 127, 20-46 (2019)
[5] Yang, Hang; Guo, Xu; Tang, Shan; Liu, Wing Kam, Derivation of heterogeneous material laws via data-driven principal component expansions, Comput. Mech., 1-15 (2019) · Zbl 1467.74013
[6] Drucker, Daniel Charles, Some implications of work hardening and ideal plasticity, Quart. Appl. Math., 7, 4, 411-418 (1950) · Zbl 0035.41203
[7] Green, R. J., A plasticity theory for porous solids, Int. J. Mech. Sci., 14, 4, 215-224 (1972) · Zbl 0247.73038
[8] Schofield, Andrew; Wroth, Peter, Critical State Soil Mechanics, volume 310 (1968), McGraw-Hill London
[9] Sun, WaiChing, A unified method to predict diffuse and localized instabilities in sands, Geomech. Geoengin., 8, 2, 65-75 (2013)
[10] Na, SeonHong; Sun, WaiChing, Computational thermo-hydro-mechanics for multiphase freezing and thawing porous media in the finite deformation range, Comput. Methods Appl. Mech. Engrg., 318, 667-700 (2017)
[11] Bryant, Eric C.; Sun, WaiChing, A micromorphically regularized cam-clay model for capturing size-dependent anisotropy of geomaterials, Comput. Methods Appl. Mech. Engrg., 354, 56-95 (2019)
[12] Ghaboussi, J.; Garrett Jr, J. H.; Wu, Xiping, Knowledge-based modeling of material behavior with neural networks, J. Eng. Mech., 117, 1, 132-153 (1991)
[13] Lefik, M.; Schrefler, B. A., Artificial neural network as an incremental non-linear constitutive model for a finite element code, Comput. Methods Appl. Mech. Engrg., 192, 28-30, 3265-3283 (2003) · Zbl 1054.74731
[14] Wang, Kun; Sun, WaiChing, A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning, Comput. Methods Appl. Mech. Engrg., 334, 337-380 (2018)
[15] Stoffel, Marcus; Bamer, Franz; Markert, Bernd, Neural network based constitutive modeling of nonlinear viscoplastic structural response, Mech. Res. Commun., 95, 85-88 (2019)
[16] Borja, Ronaldo I.; Rahmani, Helia, Discrete micromechanics of elastoplastic crystals in the finite deformation range, Comput. Methods Appl. Mech. Engrg., 275, 234-263 (2014) · Zbl 1296.74075
[17] Kuhn, Matthew R.; Sun, WaiChing; Wang, Qi, Stress-induced anisotropy in granular materials: fabric, stiffness, and permeability, Acta Geotech., 10, 4, 399-419 (2015)
[18] Wang, Kun; Sun, WaiChing, A semi-implicit discrete-continuum coupling method for porous media based on the effective stress principle at finite strain, Comput. Methods Appl. Mech. Engrg., 304, 546-583 (2016) · Zbl 1423.76286
[19] Wang, Kun; Sun, WaiChing, An updated lagrangian LBM-DEM-FEM coupling model for dual-permeability fissured porous media with embedded discontinuities, Comput. Methods Appl. Mech. Engrg., 344, 276-305 (2019)
[20] Wang, Kun; Sun, WaiChing, Meta-modeling game for deriving theory-consistent, microstructure-based traction-separation laws via deep reinforcement learning, Comput. Methods Appl. Mech. Engrg., 346, 216-241 (2019)
[21] Liu, Zeliang; Wu, C. T.; Koishi, M., A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials, Comput. Methods Appl. Mech. Engrg., 345, 1138-1168 (2019)
[22] Myers, Raymond H.; Montgomery, Douglas C.; Anderson-Cook, Christine M., Response Surface Methodology: Process and Product Optimization using Designed Experiments (2016), John Wiley & Sons · Zbl 1332.62004
[23] Chang, Chih-Chung; Lin, Chih-Jen, LIBSVM: A library for support vector machines, ACM Trans. Intell. Syst. Technol., 2, 3, 27 (2011)
[24] Soize, Christian; Ghanem, Roger; Safta, Cosmin; Huan, Xun; Vane, Zachary P.; Oefelein, Joseph C.; Lacaze, Guilhem; Najm, Habib N., Enhancing model predictability for a scramjet using probabilistic learning on manifolds, AIAA J., 57, 1, 365-378 (2018)
[25] Furukawa, Tomonari; Yagawa, Genki, Implicit constitutive modelling for viscoplasticity using neural networks, Internat. J. Numer. Methods Engrg., 43, 2, 195-219 (1998) · Zbl 0926.74020
[26] Ghaboussi, Jamshid; Pecknold, David A.; Zhang, Mingfu; Haj-Ali, Rami M., Autoprogressive training of neural network constitutive models, Internat. J. Numer. Methods Engrg., 42, 1, 105-126 (1998) · Zbl 0915.73075
[27] Huang, D. Z.; Xu, K.; Farhat, C.; Darve, E., Predictive modeling with learned constitutive laws from indirect observations (2019), arXiv preprint arXiv:1905.12530
[28] Battaglia, Peter W.; Hamrick, Jessica B.; Bapst, Victor; Sanchez-Gonzalez, Alvaro; Zambaldi, Vinicius; Malinowski, Mateusz; Tacchetti, Andrea; Raposo, David; Santoro, Adam; Faulkner, Ryan, Relational inductive biases, deep learning, and graph networks (2018), arXiv preprint arXiv:1806.01261
[29] Banerjee, R.; Sagiyama, K.; Teichert, G. H.; Garikipati, K., A graph theoretic framework for representation, exploration and analysis on computed states of physical systems, Comput. Methods Appl. Mech. Engrg., 351, 501-530 (2019)
[30] Zhou, Jie; Cui, Ganqu; Zhang, Zhengyan; Yang, Cheng; Liu, Zhiyuan; Sun, Maosong, Graph neural networks: A review of methods and applications, CoRR, abs/1812.08434 (2018), URL http://arxiv.org/abs/1812.08434
[31] Li, Xiang Song; Dafalias, Yannis F., Anisotropic critical state theory: role of fabric, J. Eng. Mech., 138, 3, 263-275 (2011)
[32] Asaro, Robert J., Crystal plasticity, J. Appl. Mech., 50, 4b, 921-934 (1983) · Zbl 0557.73033
[33] Na, SeonHong; Sun, WaiChing, Computational thermomechanics of crystalline rock, Part I: A combined multi-phase-field/crystal plasticity approach for single crystal simulations, Comput. Methods Appl. Mech. Engrg., 338, 657-691 (2018)
[34] Koeppe, Arnd; Bamer, Franz; Markert, Bernd, An efficient Monte Carlo strategy for elasto-plastic structures based on recurrent neural networks, Acta Mech., 230, 9, 3279-3293 (2019)
[35] Frankel, Ari L.; Jones, Reese E.; Alleman, Coleman; Templeton, Jeremy A., Predicting the mechanical response of oligocrystals with deep learning (2019), arXiv preprint arXiv:1901.10669
[36] Yang, Yibo; Perdikaris, Paris, Adversarial uncertainty quantification in physics-informed neural networks, J. Comput. Phys., 394, 136-152 (2019)
[37] Raissi, M.; Perdikaris, P.; Karniadakis, G. E., Physics informed deep learning (Part I): Data-driven solutions of nonlinear partial differential equations (2017), arXiv:1711.10561
[38] Dabrowski, Robert; Stencel, Krzysztof; Timoszuk, Grzegorz, Software is a directed multigraph, (European Conference on Software Architecture (2011), Springer), 360-369
[39] Simo, J. C.; Hughes, T. J.R., Computational Inelasticity (1998), Springer-Verlag New York · Zbl 0934.74003
[40] Borja, R. I., Plasticity: Modeling & Computation (2013), Springer Science & Business Media · Zbl 1279.74003
[41] Schröder, J., Theoretische und algorithmische Konzepte zur phänomenologischen Beschreibung anisotropen materialverhaltens (1996), Institut of Mechanics (CE), Chair I, University of Stuttgart, Report Nr.: I-1
[42] Schröder, J.; Neff, P., Invariant formulation of hyperelastic transverse isotropy based on polyconvex free energy functions, Int. J. Solids Struct., 40, 2, 401-445 (2003) · Zbl 1033.74005
[43] Boehler, Jean-Paul, A simple derivation of representations for non-polynomial constitutive equations in some cases of anisotropy, ZAMM Z. Angew. Math. Mech., 59, 4, 157-167 (1979) · Zbl 0416.73002
[44] Park, F. C.; Ravani, B., Smooth invariant interpolation of rotations, ACM Trans. Graph., 16, 3, 277-295 (1997)
[45] Huynh, Du Q., Metrics for 3D rotations: Comparison and analysis, J. Math. Imaging Vision, 35, 2, 155-164 (2009)
[46] Larochelle, Pierre M.; Murray, Andrew P.; Angeles, Jorge, A distance metric for finite sets of rigid-body displacements via the polar decomposition, J. Mech. Des., 129, 8, 883-886 (2007)
[47] Mota, Alejandro; Sun, WaiChing; Ostien, Jakob T.; Foulk Iii, James W.; Long, Kevin N., Lie-group interpolation and variational recovery for internal variables, Comput. Mech., 52, 6, 1281-1299 (2013) · Zbl 1398.74372
[48] Ortiz, M.; Radovitzky, R. A.; Repetto, E. A., The computation of the exponential and logarithmic mappings and their first and second linearizations, Internat. J. Numer. Methods Engrg., 52, 12, 1431-1441 (2001) · Zbl 0995.65053
[49] Noll, W., n the continuity of the fluid and solid states, J. Ration. Mech. Anal., 4, 3-81 (1955) · Zbl 0064.42001
[50] Chollet, François, Keras (2015)
[51] Abadi, Martín; Agarwal, Ashish; Barham, Paul; Brevdo, Eugene; Chen, Zhifeng; Citro, Craig; Corrado, Greg S.; Davis, Andy; Dean, Jeffrey; Devin, Matthieu, Tensorflow: Large-scale machine learning on heterogeneous distributed systems (2016), arXiv preprint arXiv:1603.04467
[52] Wes McKinney, et al. Data structures for statistical computing in python, in: PROC. of the 9th PYTHON in SCIENCE CONF., SCIPY 2010, 2010.
[53] Pedregosa, Fabian; Varoquaux, Gaël; Gramfort, Alexandre; Michel, Vincent; Thirion, Bertrand; Grisel, Olivier; Blondel, Mathieu; Prettenhofer, Peter; Weiss, Ron; Dubourg, Vincent, Scikit-learn: Machine learning in Python, J. Mach. Learn. Res., 12, Oct, 2825-2830 (2011) · Zbl 1280.68189
[54] Hochreiter, Sepp; Schmidhuber, Jürgen, Long short-term memory, Neural Comput., 9, 8, 1735-1780 (1997)
[55] Lukoševičius, Mantas; Jaeger, Herbert, Reservoir computing approaches to recurrent neural network training, Comp. Sci. Rev., 3, 3, 127-149 (2009) · Zbl 1302.68235
[56] Zhu, Jian-Hua; Zaman, Musharraf M.; Anderson, Scott A., Modeling of soil behavior with a recurrent neural network, Can. Geotech. J., 35, 5, 858-872 (1998) · Zbl 0967.74558
[57] Greff, K.; Srivastava, R. K.; Koutník, J.; Steunebrink, B. R.; Schmidhuber, J., LSTM: A search space odyssey, IEEE Trans. Neural Netw. Learn. Syst., 28, 10, 2222-2232 (2017)
[58] F.A. Gers, J. Schmidhuber, F. Cummins, Learning to forget: continual prediction with LSTM, in: 1999 Ninth International Conference on Artificial Neural Networks ICANN 99. (Conf. Publ. No. 470), vol. 2, 1999, pp. 850-855.
[59] Kendall, Maurice George, The Advanced Theory of Statistics (1946), Charles Griffin and Co., Ltd.: Charles Griffin and Co., Ltd. London · Zbl 0063.03217
[60] Gentle, J. E., Computational Statistics (2009), Springer · Zbl 1179.62001
[61] Schröder, J.; Miehe, C., Aspects of computational rate-independent crystal plasticity, Comput. Mater. Sci., 9, 1, 168-176 (1997)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. It attempts to reflect the references listed in the original paper as accurately as possible without claiming the completeness or perfect precision of the matching.