A new family of Constitutive Artificial Neural Networks towards automated model discovery
Open accessThe DOI matches its Crossref record; 47 of the 47 references it cites were found in a registry or an index.
Abstract
For more than 100 years, chemical, physical, and material scientists have proposed competing constitutive models to best characterize the behavior of natural and man-made materials in response to mechanical loading. Now, computer science offers a universal solution: Neural Networks. Neural Networks are powerful function approximators that can learn constitutive relations from large data without any knowledge of the underlying physics. However, classical Neural Networks entirely ignore a century of research in constitutive modeling, violate thermodynamic considerations, and fail to predict the behavior outside the training regime. Here we design a new family of Constitutive Artificial Neural Networks that inherently satisfy common kinematical, thermodynamical, and physical constraints and, at the same time, constrain the design space of admissible functions to create robust approximators, even in the presence of sparse data. Towards this goal we revisit the non-linear field theories of mechanics and reverse-engineer the network input to account for material objectivity, material symmetry and incompressibility; the network output to enforce thermodynamic consistency; the activation functions to implement physically reasonable restrictions; and the network architecture to ensure polyconvexity. We demonstrate that this new class of models is a generalization of the classical neo Hooke, Blatz Ko, Mooney Rivlin, Yeoh, and Demiray models and that the network weights have a clear physical interpretation in the form of shear moduli, stiffness-like parameters, and exponential coefficients. When trained with classical benchmark data for rubber under uniaxial tension, biaxial extension, and pure shear, our network autonomously selects the best constitutive model and learns its set of parameters. Our findings suggest that Constitutive Artificial Neural Networks have the potential to induce a paradigm shift in constitutive modeling, from user-defined model selection to automated model discovery. Our source code, data, and examples is available at https://github.com/LivingMatterLab/CANN.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Raissi, M., Perdikaris, P., & Karniadakis, G. E. (2019) · Journal of Computational Physics · doi:10.1016/j.jcp.2018.10.045 · Cited by 20,384
A logical calculus of the ideas immanent in nervous activity
McCulloch, W. S., & Pitts, W. (1943) · The Bulletin of Mathematical Biophysics · doi:10.1007/bf02478259 · Cited by 18,566
Physics-informed machine learning
Karniadakis, G. E., Kevrekidis, I. G., Lu, L., Perdikaris, P., Wang, S., & Yang, L. (2021) · Nature Reviews Physics · doi:10.1038/s42254-021-00314-5 · Cited by 8,718
A Theory of Large Elastic Deformation
Mooney, M. (1940) · Journal of Applied Physics · doi:10.1063/1.1712836 · Cited by 3,580
A new constitutive framework for arterial wall mechanics and a comparative study of material models
Holzapfel, G. A., Gasser, T. C., & Ogden, R. W. (2000) · Journal of Elasticity · doi:10.1023/a:1010835316564 · Cited by 3,071
Ogden, R. W. (1972) · Proceedings of the Royal Society of London. A. Mathematical and Physical Sciences · doi:10.1098/rspa.1972.0026 · Cited by 2,979
Nonlinear Solid Mechanics: A Continuum Approach for Engineering
Holzapfel, G. A. (2000) · Cited by 2,700
Convexity conditions and existence theorems in nonlinear elasticity
Ball, J. M. (1976) · Archive for Rational Mechanics and Analysis · doi:10.1007/bf00279992 · Cited by 2,436
Large elastic deformations of isotropic materials IV. further developments of the general theory
Rivlin, R. S. (1948) · Philosophical Transactions of the Royal Society of London. Series A, Mathematical and Physical Sciences · doi:10.1098/rsta.1948.0024 · Cited by 1,882
A New Constitutive Relation for Rubber
Gent, A. N. (1996) · Rubber Chemistry and Technology · doi:10.5254/1.3538357 · Cited by 1,850
Nonlinear Problems of Elasticity
(2005) · Applied Mathematical Sciences · doi:10.1007/0-387-27649-1 · Cited by 1,670
Some Forms of the Strain Energy Function for Rubber
Yeoh, O. H. (1993) · Rubber Chemistry and Technology · doi:10.5254/1.3538343 · Cited by 1,621
Large elastic deformations of isotropic materials VII. Experiments on the deformation of rubber
Rivlin, R. S., & Saunders, D. W. (1951) · Philosophical Transactions of the Royal Society of London Series A Mathematical and Physical Sciences · doi:10.1098/rsta.1951.0004 · Cited by 1,427
Theory of the elastic properties of rubber
James, H. M., & Guth, E. (1943) · The Journal of Chemical Physics · doi:10.1063/1.1723785 · Cited by 1,230 · cited 1×
“lastic response of rubber under large deformations [6, 23, 36, 38, 52].”
BackgroundLarge inelastic deformation of glassy polymers. part I: rate dependent constitutive model
Boyce, M. C., Parks, D. M., & Argon, A. S. (1988) · Mechanics of Materials · doi:10.1016/0167-6636(88)90003-8 · Cited by 1,110
Thermodynamic relations for high elastic materials
Flory, P. J. (1961) · Transactions of the Faraday Society · doi:10.1039/tf9615700829 · Cited by 946
Data-driven computational mechanics
Kirchdoerfer, T., & Ortíz, M. (2016) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2016.02.001 · Cited by 913
Stress-strain data for vulcanised rubber under various types of deformation
Treloar, L. R. G. (1944) · Transactions of the Faraday Society · doi:10.1039/tf9444000059 · Cited by 818
A theory of finite viscoelasticity and numerical aspects
Reese, S., & Govindjee, S. (1998) · International Journal of Solids and Structures · doi:10.1016/s0020-7683(97)00217-5 · Cited by 804
Knowledge‐Based Modeling of Material Behavior with Neural Networks
Ghaboussi, J., Garrett, J. H., & Wu, X. (1991) · Journal of Engineering Mechanics · doi:10.1061/(asce)0733-9399(1991)117:1(132 · Cited by 775
Application of Finite Elastic Theory to the Deformation of Rubbery Materials
Blatz, P. J., & Ko, W. L. (1962) · Transactions of the Society of Rheology · doi:10.1122/1.548937 · Cited by 689
Mechanical characterization of human brain tissue
Budday, S., Sommer, G., Birkl, C., Langkammer, C., Haybaeck, J., Kohnert, J., Bauer, M., Paulsen, F., Steinmann, P., Kuhl, E., et al. (2017) · Acta Biomaterialia · doi:10.1016/j.actbio.2016.10.036 · Cited by 656
Self-citationAlber, M., Buganza Tepole, A., Cannon, W. R., De, S., Dura-Bernal, S., Garikipati, K., Karniadakis, G., Lytton, W. W., Perdikaris, P., Petzold, L., et al. (2019) · npj Digital Medicine · doi:10.1038/s41746-019-0193-y · Cited by 639
Self-citationMIEHE, C. (2004) · Journal of the Mechanics and Physics of Solids · doi:10.1016/j.jmps.2004.03.011 · Cited by 556
Steinmann, P., Hossain, M., & Possart, G. (2012) · Archive of Applied Mechanics · doi:10.1007/s00419-012-0610-z · Cited by 432
Thermodynamics-based Artificial Neural Networks for constitutive modeling
Masi, F., Stefanou, I., Vannucci, P., & Maffi-Berthier, V. (2021) · Journal of the Mechanics and Physics of Solids · doi:10.1016/j.jmps.2020.104277 · Cited by 417
A note on the elasticity of soft biological tissues
Demiray, H. (1972) · Journal of Biomechanics · doi:10.1016/0021-9290(72)90047-4 · Cited by 416
Multiscale Modeling Meets Machine Learning: What Can We Learn?
Peng, G. C. Y., Alber, M., Buganza Tepole, A., Cannon, W. R., De, S., Dura-Bernal, S., Garikipati, K., Karniadakis, G., Lytton, W. W., Perdikaris, P., et al. (2021) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-020-09405-5 · Cited by 353
Self-citationPhysical biology of human brain development
Budday, S., Steinmann, P., & Kuhl, E. (2015) · Frontiers in Cellular Neuroscience · doi:10.3389/fncel.2015.00257 · Cited by 309
Self-citationPolyconvex anisotropic hyperelasticity with neural networks
Klein, D. K., Fernández, M., Martin, R. J., Neff, P., & Weeger, O. (2022) · Journal of the Mechanics and Physics of Solids · doi:10.1016/j.jmps.2021.104703 · Cited by 236
NN-EUCLID: Deep-learning hyperelasticity without stress data
Thakolkaran, P., Joshi, A. P., Zheng, Y., Flaschel, M., Lorenzis, L. D., & Kumar, S. (2022) · Journal of the Mechanics and Physics of Solids · doi:10.1016/j.jmps.2022.105076 · Cited by 216
Masi, F., & Stefanou, I. (2022) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2022.115190 · Cited by 197
PySINDy: A comprehensive Python package for robust sparse system identification
Kaptanoglu, A., de Silva, B., Fasel, U., Kaheman, K., Goldschmidt, A., Callaham, J., Delahunt, C., Nicolaou, Z., Champion, K., Loiseau, J.-C., et al. (2022) · Journal of Open Source Software · doi:10.21105/joss.03994 · Cited by 191
Bayesian Physics Informed Neural Networks for real-world nonlinear dynamical systems
Linka, K., Schäfer, A., Meng, X., Zou, Z., Karniadakis, G. E., & Kuhl, E. (2022) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2022.115346 · Cited by 186
Self-citationEntropy elasticity of isotropic rubber-like solids at finite strains
Holzapfel, G. A., & Simo, J. C. (1996) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/0045-7825(96)01001-8 · Cited by 171
Stresses and Birefringence in Rubber subjected to General Homogeneous Strain
Treloar, L. R. G. (1948) · Proceedings of the Physical Society · doi:10.1088/0959-5309/60/2/303 · Cited by 145
Data-driven tissue mechanics with polyconvex neural ordinary differential equations
Taç, V., Costabal, F. S., & Tepole, A. B. (2022) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2022.115248 · Cited by 137
Data-Driven Problems in Elasticity
Conti, S., Müller, S., & Ortíz, M. (2018) · Archive for Rational Mechanics and Analysis · doi:10.1007/s00205-017-1214-0 · Cited by 124
Large inelastic deformation of glassy polymers
Boyce, M. C. (1986) · DSpace@MIT (Massachusetts Institute of Technology) · Cited by 123
Dal, H., & Kaliske, M. (2009) · Journal of the Mechanics and Physics of Solids · doi:10.1016/j.jmps.2009.04.007 · Cited by 91
Numerical characterisation of uncured elastomers by a neural network based approach
Zopf, C., & Kaliske, M. (2017) · Computers & Structures · doi:10.1016/j.compstruc.2016.12.012 · Cited by 83
Wang, Z., Huan, X., & Garikipati, K. (2019) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2019.07.007 · Cited by 77
Ghaderi, A., Morovati, V., & Dargazany, R. (2020) · Polymers · doi:10.3390/polym12112628 · Cited by 76
Wang, Z., Estrada, J. B., Arruda, E. M., & Garikipati, K. (2020) · Journal of the Mechanics and Physics of Solids · doi:10.1016/j.jmps.2021.104474 · Cited by 67
COVID-19 dynamics across the US: A deep learning study of human mobility and social behavior
Bhouri, M. A., Costabal, F. S., Wang, H., Linka, K., Peirlinck, M., Kuhl, E., & Perdikaris, P. G. (2020) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2021.113891 · Cited by 63
Self-citationLinka, K., Cavinato, C., Humphrey, J. D., & Cyron, C. J. (2022) · Acta Biomaterialia · doi:10.1016/j.actbio.2022.05.039 · Cited by 26
Self-citationPolindara, C., Waffenschmidt, T., & Menzel, A. (2016) · Journal of Biomechanics · doi:10.1016/j.jbiomech.2016.01.037 · Cited by 24
Cited by
Deep learning in computational mechanics: a review
Herrmann, L., & Kollmannsberger, S. (2024) · Computational Mechanics · doi:10.1007/s00466-023-02434-4 · Cited by 162
“A similar effort was recently carried out by [403, 404], where NNs are designed to retain interpretability.”
AI for food: Accelerating and democratizing discovery and innovation
Kuhl, E. (2025) · npj Science of Food · doi:10.1038/s41538-025-00441-8 · Cited by 76
Metadata
- Authors
- Linka, K., & Kuhl, E.
- Venue
- Computer Methods in Applied Mechanics and Engineering
- Publisher
- Elsevier BV
- Published
- 2023-01
- Volume
- 403
- Pages
- 115731
- ISSN
- 0045-7825 (ISSN-L)
- OpenAlex
- W4309079827
- Cited by
- 281
- References
- 47
- FWCI
- 14.51
- Type
- journal article
- Language
- en
- Open access
- hybrid
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.