Incompressible rubber thermoelasticity: a neural network approach. (English) Zbl 1517.74028
Summary: The subject of investigation in this paper is the modeling of adiabatic thermally expanded hyperelasticity. Through the use of neural networks Cauchy stresses were predicted from logarithmic strains and the derivatives of the neural network outputs with respect to the strains were used to compute the material stiffness matrix. Firstly, a neural network based model for incompressible behaviour was developed, tested and compared with available literature to ensure the validity of the approach. Ogden’s model was used as a base with which results were compared to. Afterwards the model was expanded to accommodate thermoelastic behaviour and the results were compared to the expanded Ogden’s model for thermoelasticity.
MSC:
| 74F05 | Thermal effects in solid mechanics |
| 74B20 | Nonlinear elasticity |
| 74S99 | Numerical and other methods in solid mechanics |
| 68T05 | Learning and adaptive systems in artificial intelligence |
Keywords:
feed-forward neural network; thermally expanded Ogden hyperelasticity; Cauchy stress; deep learning; material stiffness matrixReferences:
| [1] | Abadi M, Agarwal A, Barham P et al (2015) TensorFlow: large-scale machine learning on heterogeneous systems. software available from tensorflow.org, http://tensorflow.org/ |
| [2] | As’ad, F.; Avery, P.; Farhat, C., A mechanics-informed artificial neural network approach in data-driven constitutive modeling, Int J Numer Methods Eng, 123, 12, 2738-2759 (2022) · Zbl 1528.74114 · doi:10.1002/nme.6957 |
| [3] | du Bos, ML; Balabdaoui, F.; Heidenreich, JN, Modeling stress-strain curves with neural networks: a scalable alternative to the return mapping algorithm, Comput Mater Sci, 178, 109, 629 (2020) · doi:10.1016/j.commatsci.2020.109629 |
| [4] | Cam, JBL, A review of volume changes in rubbers: the effect of stretching, Rubber Chem Technol, 83, 3, 247-269 (2010) · doi:10.5254/1.3525684 |
| [5] | Čanađija, M., Deep learning framework for carbon nanotubes: mechanical properties and modeling strategies, Carbon, 184, 891-901 (2021) · doi:10.1016/j.carbon.2021.08.091 |
| [6] | Capuano, G.; Rimoli, JJ, Smart finite elements: a novel machine learning application, Comput Methods Appl Mech Eng, 345, 363-381 (2019) · Zbl 1440.65190 · doi:10.1016/j.cma.2018.10.046 |
| [7] | Carrara, P.; Lorenzis, LD; Stainier, L., Data-driven fracture mechanics, Comput Methods Appl Mech Eng, 372, 113, 390 (2020) · Zbl 1506.74347 · doi:10.1016/j.cma.2020.113390 |
| [8] | Chadwick, P., Thermo-mechanics of rubberlike materials, Philos Trans R Soc Lond Ser A Math Phys Sci, 276, 1260, 371-403 (1974) · Zbl 0287.73005 · doi:10.1098/rsta.1974.0026 |
| [9] | Freitag, S.; Graf, W.; Kaliske, M., A material description based on recurrent neural networks for fuzzy data and its application within the finite element method, Comput Struct, 124, 29-37 (2013) · doi:10.1016/j.compstruc.2012.11.011 |
| [10] | Fuhg, JN; Bouklas, N., On physics-informed data-driven isotropic and anisotropic constitutive models through probabilistic machine learning and space-filling sampling, Comput Methods Appl Mech Eng, 394, 114, 915 (2022) · Zbl 1507.74551 · doi:10.1016/j.cma.2022.114915 |
| [11] | Glorot, X.; Bengio, Y., Understanding the difficulty of training deep feedforward neural networks, J Mach Learn Res Proc Track, 9, 249-256 (2010) |
| [12] | Géron, A., Hands-on machine learning with Scikit-Learn, Keras, and tensorflow (2019), Farnham: O’Reilly UK Ltd, Farnham |
| [13] | He K, Zhang X, Ren S et al (2015) Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification. In: 2015 IEEE International Conference on Computer Vision (ICCV). IEEE, 10.1109/iccv.2015.123 |
| [14] | Holzapfel, AG, Nonlinear solid mechanics (2000), New York: John Wiley & Sons, New York · Zbl 0980.74001 |
| [15] | Holzapfel, G.; Simo, J., Entropy elasticity of isotropic rubber-like solids at finite strains, Comput Methods Appl Mech Eng, 132, 1-2, 17-44 (1996) · Zbl 0890.73022 · doi:10.1016/0045-7825(96)01001-8 |
| [16] | Hornik, K.; Stinchcombe, M.; White, H., Multilayer feedforward networks are universal approximators, Neural Netw, 2, 5, 359-366 (1989) · Zbl 1383.92015 · doi:10.1016/0893-6080(89)90020-8 |
| [17] | Huang, D.; Fuhg, JN; Weißenfels, C., A machine learning based plasticity model using proper orthogonal decomposition, Comput Methods Appl Mech Eng, 365, 113, 008 (2020) · Zbl 1442.74042 · doi:10.1016/j.cma.2020.113008 |
| [18] | van Huyssteen, D.; Reddy, B., A virtual element method for isotropic hyperelasticity, Comput Methods Appl Mech Eng, 367, 113, 134 (2020) · Zbl 1442.74036 · doi:10.1016/j.cma.2020.113134 |
| [19] | Joshi, A.; Thakolkaran, P.; Zheng, Y., Bayesian-EUCLID: discovering hyperelastic material laws with uncertainties, Comput Methods Appl Mech Eng, 398, 115, 225 (2022) · Zbl 1507.74073 · doi:10.1016/j.cma.2022.115225 |
| [20] | Jung, J.; Yoon, K.; Lee, PS, Deep learned finite elements, Comput Methods Appl Mech Eng, 372, 113, 401 (2020) · Zbl 1506.65217 · doi:10.1016/j.cma.2020.113401 |
| [21] | Kalidindi, S.; Bronkhorst, C.; Anand, L., Crystallographic texture evolution in bulk deformation processing of FCC metals, J Mech Phys Solids, 40, 3, 537-569 (1992) · doi:10.1016/0022-5096(92)80003-9 |
| [22] | Kalina, KA; Linden, L.; Brummund, J., Automated constitutive modeling of isotropic hyperelasticity based on artificial neural networks, Comput Mech, 69, 1, 213-232 (2021) · Zbl 07492666 · doi:10.1007/s00466-021-02090-6 |
| [23] | Kalina KA, Linden L, Brummund J et al (2022) Feann—anefficient data-driven multiscale approach based on physics-constrained neural networks and automated datamining. arXiv:2207.01045 |
| [24] | Klein, DK; Fernández, M.; Martin, RJ, Polyconvex anisotropic hyperelasticity with neural networks, J Mech Phys Solids, 159, 104, 703 (2022) · doi:10.1016/j.jmps.2021.104703 |
| [25] | Klinkel, S.; Gruttmann, F.; Wagner, W., A mixed shell formulation accounting for thickness strains and finite strain 3d material models, Int J Numer Meth Eng, 74, 6, 945-970 (2008) · Zbl 1158.74491 · doi:10.1002/nme.2199 |
| [26] | Košmerl, V.; Štajduhar, I.; Čanađ ija, M., Predicting stress-strain behavior of carbon nanotubes using neural networks, Neural Comput Appl (2022) · doi:10.1007/s00521-022-07430-y |
| [27] | Lederer J (2021) Activation functions in artificial neural networks: A systematic overview arXiv:2101.09957 [cs.LG] |
| [28] | Liang, L.; Liu, M.; Martin, C., A deep learning approach to estimate stress distribution: a fast and accurate surrogate of finite-element analysis, J R Soc Interface, 15, 138, 20170 (2018) · doi:10.1098/rsif.2017.0844 |
| [29] | Linka, K.; Hillgärtner, M.; Abdolazizi, KP, Constitutive artificial neural networks: a fast and general approach to predictive data-driven constitutive modeling by deep learning, J Comput Phys, 429, 110, 010 (2021) · Zbl 07500745 · doi:10.1016/j.jcp.2020.110010 |
| [30] | Liu, Z.; Wu, C.; Koishi, M., A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials, Comput Methods Appl Mech Eng, 345, 1138-1168 (2019) · Zbl 1440.74340 · doi:10.1016/j.cma.2018.09.020 |
| [31] | Malik, A.; Abendroth, M.; Hütter, G., A hybrid approach employing neural networks to simulate the elasto-plastic deformation behavior of 3d-foam structures, Adv Eng Mater, 24, 2, 2100641 (2021) · doi:10.1002/adem.202100641 |
| [32] | Masi, F.; Stefanou, I.; Vannucci, P., Thermodynamics-based artificial neural networks for constitutive modeling, J Mech Phys Solids, 147, 104, 277 (2021) · doi:10.1016/j.jmps.2020.104277 |
| [33] | Mendizabal, A.; Márquez-Neila, P.; Cotin, S., Simulation of hyperelastic materials in real-time using deep learning, Med Image Anal, 59, 101, 569 (2020) · doi:10.1016/j.media.2019.101569 |
| [34] | Miehe, C., Entropic thermoelasticity at finite strains. aspects of the formulation and numerical implementation, Comput Methods Appl Mech Eng, 120, 3-4, 243-269 (1995) · Zbl 0851.73012 · doi:10.1016/0045-7825(94)00057-t |
| [35] | Ogden, R., Large deformation isotropic elasticity—on the correlation of theory and experiment for incompressible rubberlike solids, Proc R Soc Lond A Math Phys Sci, 326, 1567, 565-584 (1972) · Zbl 0257.73034 · doi:10.1098/rspa.1972.0026 |
| [36] | Ogden, R., Large deformation isotropic elasticity: on the correlation of theory and experiment for compressible rubberlike solids, Proc R Soc Lond A Math Phys Sci, 328, 1575, 567-583 (1972) · Zbl 0245.73032 · doi:10.1098/rspa.1972.0096 |
| [37] | Ogden, R., Volume changes associated with the deformation of rubber-like solids, J Mech Phys Solids, 24, 6, 323-338 (1976) · Zbl 0356.73041 · doi:10.1016/0022-5096(76)90007-7 |
| [38] | Ogden RW (1992) On the thermoelastic modeling of rubberlike solids. J Therm Stresses 15(4):533-557. doi:10.1080/01495739208946155 |
| [39] | Parisch, H., Efficient non-linear finite element shell formulation involving large strains, Eng Comput, 3, 2, 121-128 (1986) · doi:10.1108/eb023650 |
| [40] | Pascon, JP, Large deformation analysis of plane-stress hyperelastic problems via triangular membrane finite elements, Int J Adv Struct Eng, 11, 3, 331-350 (2019) · doi:10.1007/s40091-019-00234-w |
| [41] | Roux, NL; Bengio, Y., Deep belief networks are compact universal approximators, Neural Comput, 22, 8, 2192-2207 (2010) · Zbl 1195.68079 · doi:10.1162/neco.2010.08-09-1081 |
| [42] | Shen, Y.; Chandrashekhara, K.; Breig, WF, Neural network based constitutive model for rubber material, Rubber Chem Technol, 77, 2, 257-277 (2004) · doi:10.5254/1.3547822 |
| [43] | Treloar, LRG, Stress-strain data for vulcanised rubber under various types of deformation, Trans Faraday Soc, 40, 59 (1944) · doi:10.1039/tf9444000059 |
| [44] | Truesdell, C., The non-linear field theories of mechanics (2004), Berlin Heidelberg: Springer, Berlin Heidelberg · Zbl 1068.74002 · doi:10.1007/978-3-662-10388-3 |
| [45] | Vlassis, NN; Sun, W., Sobolev training of thermodynamic-informed neural networks for interpretable elasto-plasticity models with level set hardening, Comput Methods Appl Mech Eng, 377, 113, 695 (2021) · Zbl 1506.74449 · doi:10.1016/j.cma.2021.113695 |
| [46] | Vlassis, NN; Ma, R.; Sun, W., Geometric deep learning for computational mechanics part i: anisotropic hyperelasticity, Comput Methods Appl Mech Eng, 371, 113, 299 (2020) · Zbl 1506.74504 · doi:10.1016/j.cma.2020.113299 |
| [47] | Weber, P.; Geiger, J.; Wagner, W., Constrained neural network training and its application to hyperelastic material modeling, Comput Mech, 68, 5, 1179-1204 (2021) · Zbl 1478.74010 · doi:10.1007/s00466-021-02064-8 |
| [48] | Yagawa, G.; Okuda, H., Neural networks in computational mechanics, Arch Comput Methods Eng, 3, 4, 435-512 (1996) · doi:10.1007/bf02818935 |
| [49] | Zopf, C.; Kaliske, M., Numerical characterisation of uncured elastomers by a neural network based approach, Comput Struct, 182, 504-525 (2017) · doi:10.1016/j.compstruc.2016.12.012 |
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. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
