Automatic generation of interpretable hyperelastic material models by symbolic regression. (English) Zbl 1532.74014
Summary: In this article, we present a new procedure to automatically generate interpretable hyperelastic material models. This approach is based on symbolic regression which represents an evolutionary algorithm searching for a mathematical model in the form of an algebraic expression. This results in a relatively simple model with good agreement to experimental data. By expressing the strain energy function in terms of its invariants or other parameters, it is possible to interpret the resulting algebraic formulation in a physical context. In addition, a direct implementation of the obtained algebraic equation for example into a finite element procedure is possible. For the validation of the proposed approach, benchmark tests on the basis of the generalized Mooney-Rivlin model are presented. In all these tests, the chosen ansatz can find the predefined models. Additionally, this method is applied to the multi-axial loading data set of vulcanized rubber. Finally, a data set for a temperature-dependent thermoplastic polyester elastomer is evaluated. In latter cases, good agreement with the experimental data is obtained.
{© 2023 The Authors. International Journal for Numerical Methods in Engineering published by John Wiley & Sons Ltd.}
{© 2023 The Authors. International Journal for Numerical Methods in Engineering published by John Wiley & Sons Ltd.}
MSC:
| 74B20 | Nonlinear elasticity |
| 74A20 | Theory of constitutive functions in solid mechanics |
| 74F05 | Thermal effects in solid mechanics |
| 74S99 | Numerical and other methods in solid mechanics |
| 68T05 | Learning and adaptive systems in artificial intelligence |
Keywords:
machine learning; multi-axial constitutive modeling; evolutionary algorithm; strain energy function; generalized Mooney-Rivlin model; vulcanized rubber; temperature-dependent elastomerReferences:
| [1] | EggersmannR, KirchdoerferT, ReeseS, StainierL, OrtizM. Model‐free data‐driven inelasticity. Comput Methods Appl Mech Eng. 2019;350:81‐99. doi:10.1016/j.cma.2019.02.016 · Zbl 1441.74048 |
| [2] | IbañezR, BorzacchielloD, AguadoJV, et al. Data‐driven non‐linear elasticity: constitutive manifold construction and problem discretization. Comput Mech. 2017;60(5):813‐826. doi:10.1007/s00466‐017‐1440‐1 · Zbl 1387.74015 |
| [3] | IbañezR, Abisset‐ChavanneE, AguadoJV, GonzálezD, CuetoE, ChinestaF. A manifold learning approach to data‐driven computational elasticity and inelasticity. Arch Comput Methods Eng. 2018;25(1):47‐57. doi:10.1007/s11831‐016‐9197‐9 · Zbl 1390.74195 |
| [4] | KirchdoerferT, OrtizM. Data‐driven computational mechanics. Comput Methods Appl Mech Eng. 2016;304:81‐101. doi:10.1016/j.cma.2016.02.001 · Zbl 1425.74503 |
| [5] | LeygueA, CoretM, RéthoréJ, StainierL, VerronE. Data‐based derivation of material response. Comput Methods Appl Mech Eng. 2018;331:184‐196. doi:10.1016/j.cma.2017.11.013 · Zbl 1439.74050 |
| [6] | HashashYMA, JungS, GhaboussiJ. Numerical implementation of a neural network based material model in finite element analysis. Int J Numer Methods Eng. 2004;59(7):989‐1005. doi:10.1002/nme.905 · Zbl 1065.74609 |
| [7] | LinkaK, HillgärtnerM, AbdolaziziKP, AydinRC, ItskovM, CyronCJ. Constitutive artificial neural networks: a fast and general approach to predictive data‐driven constitutive modeling by deep learning. J Comput Phys. 2021;429:110010. doi:10.1016/j.jcp.2020.110010 · Zbl 07500745 |
| [8] | ShenY, ChandrashekharaK, BreigWF, OliverLR. Neural network based constitutive model for rubber material. Rubber Chem Technol. 2004;77(2):257‐277. doi:10.5254/1.3547822 |
| [9] | LiangG, ChandrashekharaK. Neural network based constitutive model for elastomeric foams. Eng Struct. 2008;30(7):2002‐2011. doi:10.1016/j.engstruct.2007.12.021 |
| [10] | FritzenF, LeuschnerM. Reduced basis hybrid computational homogenization based on a mixed incremental formulation. Comput Methods Appl Mech Eng. 2013;260:143‐154. doi:10.1016/j.cma.2013.03.007 · Zbl 1286.74081 |
| [11] | MieheC, SchröderJ, SchotteJ. Computational homogenization analysis in finite plasticity simulation of texture development in polycrystalline materials. Comput Methods Appl Mech Eng. 1999;171(3‐4):387‐418. doi:10.1016/S0045‐7825(98)00218‐7 · Zbl 0982.74068 |
| [12] | LeBA, YvonnetJ, HeQC. Computational homogenization of nonlinear elastic materials using neural networks. Int J Numer Methods Eng. 2015;104(12):1061‐1084. doi:10.1002/nme.4953 · Zbl 1352.74266 |
| [13] | LiuZ, WuC, KoishiM. A deep material network for multiscale topology learning and accelerated nonlinear modeling of heterogeneous materials. Comput Methods Appl Mech Eng. 2019;345:1138‐1168. doi:10.1016/j.cma.2018.09.020 · Zbl 1440.74340 |
| [14] | ReimannD, NidadavoluK, Ul HassanH, et al. Modeling macroscopic material behavior with machine learning algorithms trained by micromechanical simulations. Front Mater. 2019;6:181. doi:10.3389/fmats.2019.00181 |
| [15] | TruesdellC, NollW. The Non‐Linear Field Theories of Mechanics. 3rd ed.Springer; 2004. · Zbl 1068.74002 |
| [16] | BomaritoG, TownsendT, StewartK, EshamK, EmeryJ, HochhalterJ. Development of interpretable, data‐driven plasticity models with symbolic regression. Comput Struct. 2021;252:106557. |
| [17] | KablimanE, KolodyAH, KronsteinerJ, KommendaM, KronbergerG. Application of symbolic regression for constitutive modeling of plastic deformation. Appl Eng Sci. 2020;2021(6):100052. doi:10.1016/j.apples.2021.100052 |
| [18] | KronbergerG, KablimanE, KronsteinerJ, KommendaM. Extending a physics‐based constitutive model using genetic programming. Appl Eng Sci. 2021;9:100080. doi:10.1016/j.apples.2021.100080 |
| [19] | KablimanE, KolodyAH, KommendaM, KronbergerG. Prediction of stress‐strain curves for aluminium alloys using symbolic regression. AIP Conference Proceedings; July 2019:2113. 10.1063/1.5112747 |
| [20] | GuselL, BrezocnikM. Application of genetic programming for modelling of material characteristics. Expert Syst Appl. 2011;38(12):15014‐15019. doi:10.1016/j.eswa.2011.05.045 |
| [21] | GuselL, BrezocnikM. Modeling of impact toughness of cold formed material by genetic programming. Comput Mater Sci. 2006;37(4):476‐482. doi:10.1016/j.commatsci.2005.11.007 |
| [22] | AsadzadehMZ, GänserHP, MückeM. Symbolic regression based hybrid semiparametric modelling of processes: an example case of a bending process. Appl Eng Sci. 2021;6:100049. doi:10.1016/j.apples.2021.100049 |
| [23] | WangM, ChenC, LiuW. Establish algebraic data‐driven constitutive models for elastic solids with a tensorial sparse symbolic regression method and a hybrid feature selection technique. J Mech Phys Solids. 2022;159:104742. doi:10.1016/j.jmps.2021.104742 |
| [24] | ChenZW, JoliP, FengZQ. Anisotropic hyperelastic behavior of soft biological tissues. Comput Methods Biomech Biomed Eng. 2015;18(13):1436‐1444. doi:10.1080/10255842.2014.915082 |
| [25] | GasserTC, OgdenRW, HolzapfelGA. Hyperelastic modelling of arterial layers with distributed collagen fibre orientations. J R Soc Interface. 2006;3(6):15‐35. doi:10.1098/rsif.2005.0073 |
| [26] | HillgärtnerM, LinkaK, ItskovM. A generalized inelastic modeling concept for soft fibrous tissues. GAMM‐Mitteilungen. 2019;42(4):e201900014. doi:10.1002/gamm.201900014 · Zbl 1541.92018 |
| [27] | LinkaK, HillgärtnerM, ItskovM. Fatigue of soft fibrous tissues: multi‐scale mechanics and constitutive modeling. Acta Biomater. 2018;71:398‐410. doi:10.1016/j.actbio.2018.03.010 |
| [28] | RynkevicR, FerreiraJ, MartinsP, ParenteM, FernandesAA. Linking hyperelastic theoretical models and experimental data of vaginal tissue through histological data. J Biomech. 2019;82:271‐279. doi:10.1016/j.jbiomech.2018.10.038 |
| [29] | ArrudaEM, BoyceMC. A three‐dimensional constitutive model for the large stretch behavior of rubber elastic materials. J Mech Phys Solids. 1993;41(2):389‐412. doi:10.1016/0022‐5096(93)90013‐6 · Zbl 1355.74020 |
| [30] | BoyceMC, ArrudaEM. Constitutive models of rubber elasticity: a review. Rubber Chem Technol. 2000;73(3):504‐523. doi:10.5254/1.3547602 |
| [31] | KaliskeM, HeinrichG. An extended tube‐model for rubber elasticity: statistical‐mechanical theory and finite element implementation. Rubber Chem Technol. 1999;72(4):602‐632. doi:10.5254/1.3538822 |
| [32] | PhamTT, WooC, ChoiS, MinJ, KimB. Development of hyperelastic model for butadiene rubber using a neural network. Elastomers Compos. 2021;56(2):79‐84. doi:10.7473/EC.2021.56.2.79 |
| [33] | EhretAE, ItskovM. A polyconvex hyperelastic model for fiber‐reinforced materials in application to soft tissues. J Mater Sci. 2007;42(21):8853‐8863. doi:10.1007/s10853‐007‐1812‐6 |
| [34] | ItskovM, AkselN. A class of orthotropic and transversely isotropic hyperelastic constitutive models based on a polyconvex strain energy function. Int J Solids Struct. 2004;41(14):3833‐3848. doi:10.1016/j.ijsolstr.2004.02.027 · Zbl 1079.74516 |
| [35] | FloryPJ. Thermodynamic relations for high elastic materials. Trans Faraday Soc. 1961;57:829. doi:10.1039/tf9615700829 |
| [36] | KozaJR. Genetic programming as a means for programming computers by natural selection. Stat Comput. 1994;4(2):87‐112. doi:10.1007/BF00175355 |
| [37] | KozaJR. Genetic Programming, Version 2. Encycl Comput Sci Technol. 1997;1989:1‐26. |
| [38] | WangY, WagnerN, RondinelliJM. Symbolic regression in materials science. MRS Commun. 2019;9(3):793‐805. doi:10.1557/mrc.2019.85 |
| [39] | AugustoD, BarbosaH. Symbolic regression via genetic programming. Proceedings of the Vol. 1. 6th Brazilian Symposium on Neural Networks; 2000: 173-178; IEEE Computer Society. |
| [40] | TreloarLRG. Stress‐strain data for vulcanised rubber under various types of deformation. Trans Faraday Soc. 1944;40:59. doi:10.1039/tf9444000059 |
| [41] | BowerAF. Applied Mechanics of Solids. CRC Press; 2010. |
| [42] | MooneyM. A theory of large elastic deformation. J Appl Phys. 1940;11(9):582‐592. doi:10.1063/1.1712836 · JFM 66.1021.04 |
| [43] | MarckmannG, VerronE. Comparison of hyperelastic models for rubber‐like materials. Rubber Chem Technol. 2006;79(5):835‐858. doi:10.5254/1.3547969 |
| [44] | Chemie Wirtschaftsförderungs‐GmbH. DuPont Engineering Polymers Hytrel 4556. Altair Engineering GmbH; 2022. https://www.campusplastics.com/campus/en/datasheet/Hytrel |
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.
