Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

A Physics Preserving Neural Network Based Approach for Constitutive Modeling of Isotropic Fibrous Materials (2403.13357v5)

Published 20 Mar 2024 in physics.bio-ph, cond-mat.soft, and cs.CE

Abstract: We develop a new neural network architecture that strictly enforces constitutive constraints such as polyconvexity, frame-indifference, and the symmetry of the stress and material stiffness. Additionally, we show that the accuracy of the stress and material stiffness predictions is significantly improved for this neural network by using a Sobolev minimization strategy that includes derivative terms. Using our neural network, we model the constitutive behavior of fibrous-type discrete network material. With Sobolev minimization, we obtain a normalized mean square error of 0.15% for the strain energy density, 0.815% averaged across the components of the stress, and 5.4% averaged across the components of the stiffness tensor. This machine-learned constitutive model was deployed in a finite element simulation of a facet capsular ligament. The displacement fields and stress-strain curves were compared to a multiscale simulation that required running on a GPU-based supercomputer. The new approach maintained upward of 85% accuracy in stress up to 70% strain while reducing the computation cost by orders of magnitude.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (32)
  1. Merson, J. S., Picu, C. R., and Shephard, M. S., 2024, “A New Open-Source Framework for Multiscale Modeling of Fibrous Materials on Heterogeneous Supercomputers,” https://doi.org/10.1007/s00366-023-01934-4Engineering with Computers.
  2. Mahutga, R. R., Barocas, V. H., and Alford, P. W., 2023, “The Non-Affine Fiber Network Solver: A Multiscale Fiber Network Material Model for Finite-Element Analysis,” https://doi.org/10.1016/j.jmbbm.2023.105967Journal of the Mechanical Behavior of Biomedical Materials, 144, p. 105967.
  3. Lai, V. K., Hadi, M. F., Tranquillo, R. T., and Barocas, V. H., 2013, “A Multiscale Approach to Modeling the Passive Mechanical Contribution of Cells in Tissues,” Journal of Biomechanical Engineering, 135(7), 071007.
  4. Holzapfel, G. A., Gasser, T. C., and Ogden, R. W., 2000, “A New Constitutive Framework for Arterial Wall Mechanics and a Comparative Study of Material Models,” https://doi.org/10.1023/A:1010835316564Journal of elasticity and the physical science of solids, 61(1), pp. 1–48.
  5. Picu, R. C., Deogekar, S., and Islam, M. R., 2018, “Poisson’s Contraction and Fiber Kinematics in Tissue: Insight from Collagen Network Simulations,” https://doi.org/10.1115/1.4038428Journal of Biomechanical Engineering, 140(2), 021002.
  6. Feyel, F., 1999, “Multiscale FE2 Elastoviscoplastic Analysis of Composite Structures,” https://doi.org/10.1016/S0927-0256(99)00077-4Computational Materials Science, 16(1), pp. 344–354.
  7. Merson, J. and Shephard, M. S., 2023, “Using Hierarchical Parallelism to Accelerate the Solution of Many Small Partial Differential Equations,” 10.48550/arXiv.2305.07030, 2305.07030
  8. Merson, J. and Picu, R., 2020, “Size Effects in Random Fiber Networks Controlled by the Use of Generalized Boundary Conditions,” https://doi.org/10.1016/j.ijsolstr.2020.09.033International Journal of Solids and Structures, 206, pp. 314–321.
  9. Hatami-Marbini, H. and Picu, R. C., 2009, “Effect of Fiber Orientation on the Non-Affine Deformation of Random Fiber Networks,” https://doi.org/10.1007/s00707-009-0170-7Acta Mechanica, 205(1), pp. 77–84.
  10. Broedersz, C. and MacKintosh, F., 2011, “Molecular Motors Stiffen Non-Affine Semiflexible Polymer Networks,” https://doi.org/10.1039/C0SM01004ASoft Matter, 7(7), pp. 3186–3191.
  11. Lake, S. P., Cortes, D. H., Kadlowec, J. A., Soslowsky, L. J., and Elliott, D. M., 2012, “Evaluation of Affine Fiber Kinematics in Human Supraspinatus Tendon Using Quantitative Projection Plot Analysis,” https://doi.org/10.1007/s10237-011-0303-5Biomechanics and Modeling in Mechanobiology, 11(1), pp. 197–205.
  12. Lee, C.-H., Zhang, W., Liao, J., Carruthers, C. A., Sacks, J. I., and Sacks, M. S., 2015, “On the Presence of Affine Fibril and Fiber Kinematics in the Mitral Valve Anterior Leaflet,” https://doi.org/10.1016/j.bpj.2015.03.019Biophysical Journal, 108(8), pp. 2074–2087.
  13. Thakolkaran, P., Joshi, A., Zheng, Y., Flaschel, M., De Lorenzis, L., and Kumar, S., 2022, “NN-EUCLID: Deep-Learning Hyperelasticity without Stress Data,” https://doi.org/10.1016/j.jmps.2022.105076Journal of the Mechanics and Physics of Solids, 169, p. 105076.
  14. Sacks, M. S., Motiwale, S., Goodbrake, C., and Zhang, W., “Neural Network Approaches for Soft Biological Tissue and Organ Simulations,” https://doi.org/10.1115/1.4055835Journal of Biomechanical Engineering, 144(121010).
  15. Kakaletsis, S., Lejeune, E., and Rausch, M. K., “Can Machine Learning Accelerate Soft Material Parameter Identification from Complex Mechanical Test Data?” https://doi.org/10.1007/s10237-022-01631-zBiomechanics and Modeling in Mechanobiology, 22(1), pp. 57–70.
  16. Gupta, A., Bhaduri, A., and Graham-Brady, L., 2023, “Accelerated Multiscale Mechanics Modeling in a Deep Learning Framework,” https://doi.org/10.1016/j.mechmat.2023.104709Mechanics of Materials, 184, p. 104709.
  17. Amos, B., Xu, L., and Kolter, J. Z., 2017, “Input Convex Neural Networks,” 1609.07152
  18. Glüge, R., 2013, “Generalized Boundary Conditions on Representative Volume Elements and Their Use in Determining the Effective Material Properties,” https://doi.org/10.1016/j.commatsci.2013.06.038Computational Materials Science, 79, pp. 408–416.
  19. Kouznetsova, V., Brekelmans, W. A. M., and Baaijens, F. P. T., 2001, “An Approach to Micro-Macro Modeling of Heterogeneous Materials,” https://doi.org/10.1007/s004660000212Computational Mechanics, 27(1), pp. 37–48.
  20. Parvez, N., Merson, J., and Picu, R. C., 2023, “Stiffening Mechanisms in Stochastic Athermal Fiber Networks,” https://doi.org/10.1103/PhysRevE.108.044502Physical Review E, 108(4), p. 044502.
  21. Picu, R. and Jin, S., 2023, “Toughness of Network Materials: Structural Parameters Controlling Damage Accumulation,” https://doi.org/10.1016/j.jmps.2022.105176Journal of the Mechanics and Physics of Solids, 172, p. 105176.
  22. Song, D., Oberai, A. A., and Janmey, P. A., 2022, “Hyperelastic Continuum Models for Isotropic Athermal Fibrous Networks,” https://doi.org/10.1098/rsfs.2022.0043Interface Focus, 12(6), p. 20220043.
  23. Tikenoğulları, O. Z., Açan, A. K., Kuhl, E., and Dal, H., 2023, “Data-Driven Hyperelasticity, Part II: A Canonical Framework for Anisotropic Soft Biological Tissues,” https://doi.org/10.1016/j.jmps.2023.105453Journal of the Mechanics and Physics of Solids, 181, p. 105453.
  24. Linden, L., Klein, D. K., Kalina, K. A., Brummund, J., Weeger, O., and Kästner, M., 2023, “Neural Networks Meet Hyperelasticity: A Guide to Enforcing Physics,” https://doi.org/10.1016/j.jmps.2023.105363Journal of the Mechanics and Physics of Solids, 179, p. 105363.
  25. Tac, V., Sree, V. D., Rausch, M. K., and Tepole, A. B., 2021, “Data-Driven Modeling of the Mechanical Behavior of Anisotropic Soft Biological Tissue,” 2107.05388
  26. Linka, K. and Kuhl, E., 2023, “A New Family of Constitutive Artificial Neural Networks towards Automated Model Discovery,” https://doi.org/10.1016/j.cma.2022.115731Computer Methods in Applied Mechanics and Engineering, 403, p. 115731.
  27. Kingma, D. P. and Ba, J., 2017, “Adam: A Method for Stochastic Optimization,” 10.48550/arXiv.1412.6980, 1412.6980
  28. He, K., Zhang, X., Ren, S., and Sun, J., 2015, “Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification,” Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034.
  29. Czarnecki, W. M., Osindero, S., Jaderberg, M., Swirszcz, G., and Pascanu, R., “Sobolev Training for Neural Networks,” .
  30. Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., Desmaison, A., Kopf, A., Yang, E., DeVito, Z., Raison, M., Tejani, A., Chilamkurthy, S., Steiner, B., Fang, L., Bai, J., and Chintala, S., 2019, “PyTorch: An Imperative Style, High-Performance Deep Learning Library,” Advances in Neural Information Processing Systems, Vol. 32, Curran Associates, Inc.
  31. Islam, M. R. and Picu, R. C., 2018, “Effect of Network Architecture on the Mechanical Behavior of Random Fiber Networks,” https://doi.org/10.1115/1.4040245Journal of Applied Mechanics, Transactions ASME, 85(8), pp. 1–8.
  32. Licup, A. J., Münster, S., Sharma, A., Sheinman, M., Jawerth, L. M., Fabry, B., Weitz, D. A., and MacKintosh, F. C., 2015, “Stress Controls the Mechanics of Collagen Networks,” https://doi.org/10.1073/pnas.1504258112Proceedings of the National Academy of Sciences of the United States of America, 112(31), pp. 9573–9578.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now