A publicly available PyTorch-$\mathrm{ABAQUS}$ $\mathrm{UMAT}$ deep-learning framework for level-set plasticity

Suh, Hyoung Suk; Kweon, Chulmin; Lester, Brian T.; Kramer, Sharlotte; Sun, WaiChing

doi:10.1016/j.mechmat.2023.104682

A publicly available PyTorch-$$\mathrm{ABAQUS}$$ $$\mathrm{UMAT}$$ deep-learning framework for level-set plasticity

Journal Article · Tue May 23 00:00:00 EDT 2023 · Mechanics of Materials

DOI:https://doi.org/10.1016/j.mechmat.2023.104682· OSTI ID:2311677

^[1]; Kweon, Chulmin ^[1]; ^[2]; ^[2]; ^[1]

Columbia University, New York, NY (United States)
Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)

Here this paper introduces a publicly available PyTorch-ABAQUS deep-learning framework of a family of plasticity models where the yield surface is implicitly represented by a scalar-valued function. In particular, our focus is to introduce a practical framework that can be deployed for engineering analysis that employs a user-defined material subroutine (UMAT/VUMAT) for ABAQUS, which is written in FORTRAN. To accomplish this task while leveraging the back-propagation learning algorithm to speed up the neural-network training, we introduce an interface code where the weights and biases of the trained neural networks obtained via the PyTorch library can be automatically converted into a generic FORTRAN code that can be a part of the UMAT/VUMAT algorithm. To enable third-party validation, we purposely make all the data sets, source code used to train the neural-network-based constitutive models, and the trained models available in a public repository. Furthermore, the practicality of the workflow is then further tested on a dataset for anisotropic yield function to showcase the extensibility of the proposed framework. A number of representative numerical experiments are used to examine the accuracy, robustness and reproducibility of the results generated by the neural network models.

View Accepted Manuscript (DOE)

Research Organization:: Sandia National Laboratories (SNL-NM), Albuquerque, NM (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA); USDOE Laboratory Directed Research and Development (LDRD) Program; National Science Foundation (NSF)

Grant/Contract Number:: NA0003525

OSTI ID:: 2311677

Report Number(s):: SAND--2023-08639J

Journal Information:: Mechanics of Materials, Journal Name: Mechanics of Materials Journal Issue: None Vol. 184; ISSN 0167-6636

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (47)

Studies in anisotropic plasticity with reference to the Hill criterion De Borst, René; Feenstra, Peter H. International Journal for Numerical Methods in Engineering, Vol. 29, Issue 2 https://doi.org/10.1002/nme.1620290208	journal	February 1990
Multiscale method for characterization of porous microstructures and their impact on macroscopic effective permeability Sun, W. C.; Andrade, J. E.; Rudnicki, J. W. International Journal for Numerical Methods in Engineering, Vol. 88, Issue 12 https://doi.org/10.1002/nme.3220	journal	May 2011
Generalized radial-return mapping algorithm for anisotropic von Mises plasticity framed in material eigenspace: Generalized radial-return mapping algorithm Versino, Daniele; Bennett, Kane C. International Journal for Numerical Methods in Engineering, Vol. 116, Issue 3 https://doi.org/10.1002/nme.5921	journal	August 2018
A mechanics‐informed artificial neural network approach in data‐driven constitutive modeling As'ad, Faisal; Avery, Philip; Farhat, Charbel International Journal for Numerical Methods in Engineering, Vol. 123, Issue 12 https://doi.org/10.1002/nme.6957	journal	March 2022
Numerical implementation of a neural network based material model in finite element analysis: NEURAL NETWORK BASED MATERIAL MODEL Hashash, Y. M. A.; Jung, S.; Ghaboussi, J. International Journal for Numerical Methods in Engineering, Vol. 59, Issue 7 https://doi.org/10.1002/nme.905	journal	January 2004
A Fast Level Set Method for Propagating Interfaces Adalsteinsson, David; Sethian, James A. Journal of Computational Physics, Vol. 118, Issue 2 https://doi.org/10.1006/jcph.1995.1098	journal	May 1995
Data-driven discovery of interpretable causal relations for deep learning material laws with uncertainty propagation Sun, Xiao; Bahmani, Bahador; Vlassis, Nikolaos N. Granular Matter, Vol. 24, Issue 1 https://doi.org/10.1007/s10035-021-01137-y	journal	November 2021
A kernel method for learning constitutive relation in data-driven computational elasticity Kanno, Yoshihiro Japan Journal of Industrial and Applied Mathematics, Vol. 38, Issue 1 https://doi.org/10.1007/s13160-020-00423-1	journal	May 2020
Recent developments in the finite element analysis of prestressed concrete reactor vessels Argyris, J. H.; Faust, G.; Szimmat, J. Nuclear Engineering and Design, Vol. 28, Issue 1 https://doi.org/10.1016/0029-5493(74)90088-0	journal	July 1974
Consistent tangent operators for rate-independent elastoplasticity Simo, J. C.; Taylor, R. L. Computer Methods in Applied Mechanics and Engineering, Vol. 48, Issue 1 https://doi.org/10.1016/0045-7825(85)90070-2	journal	February 1985
An efficient flood-filling algorithm Burtsev, S. V.; Kuzmin, Ye. P. Computers & Graphics, Vol. 17, Issue 5 https://doi.org/10.1016/0097-8493(93)90006-U	journal	September 1993
Cam-Clay plasticity, Part IV: Implicit integration of anisotropic bounding surface model with nonlinear hyperelasticity and ellipsoidal loading function Borja, Ronaldo I.; Lin, Chao-Hua; Montáns, Francisco J. Computer Methods in Applied Mechanics and Engineering, Vol. 190, Issue 26-27 https://doi.org/10.1016/S0045-7825(00)00301-7	journal	March 2001
Artificial neural network as an incremental non-linear constitutive model for a finite element code Lefik, M.; Schrefler, B. A. Computer Methods in Applied Mechanics and Engineering, Vol. 192, Issue 28-30 https://doi.org/10.1016/S0045-7825(03)00350-5	journal	July 2003
A non-associated viscoplastic model for the behaviour of granite in triaxial compression Maranini, Enrico; Yamaguchi, Tsutomu Mechanics of Materials, Vol. 33, Issue 5 https://doi.org/10.1016/S0167-6636(01)00052-7	journal	May 2001
Data-driven computational mechanics Kirchdoerfer, T.; Ortiz, M. Computer Methods in Applied Mechanics and Engineering, Vol. 304 https://doi.org/10.1016/j.cma.2016.02.001	journal	June 2016
A framework for data-driven analysis of materials under uncertainty: Countering the curse of dimensionality Bessa, M. A.; Bostanabad, R.; Liu, Z. Computer Methods in Applied Mechanics and Engineering, Vol. 320 https://doi.org/10.1016/j.cma.2017.03.037	journal	June 2017
A multiscale multi-permeability poroplasticity model linked by recursive homogenizations and deep learning Wang, Kun; Sun, WaiChing Computer Methods in Applied Mechanics and Engineering, Vol. 334 https://doi.org/10.1016/j.cma.2018.01.036	journal	June 2018
A physics-constrained data-driven approach based on locally convex reconstruction for noisy database He, Qizhi; Chen, Jiun-Shyan Computer Methods in Applied Mechanics and Engineering, Vol. 363 https://doi.org/10.1016/j.cma.2019.112791	journal	May 2020
Geometric deep learning for computational mechanics Part I: anisotropic hyperelasticity Vlassis, Nikolaos N.; Ma, Ran; Sun, WaiChing Computer Methods in Applied Mechanics and Engineering, Vol. 371 https://doi.org/10.1016/j.cma.2020.113299	journal	November 2020
Machine learning materials physics: Multi-resolution neural networks learn the free energy and nonlinear elastic response of evolving microstructures Zhang, Xiaoxuan; Garikipati, Krishna Computer Methods in Applied Mechanics and Engineering, Vol. 372 https://doi.org/10.1016/j.cma.2020.113362	journal	December 2020
Model-free data-driven computational mechanics enhanced by tensor voting Eggersmann, Robert; Stainier, Laurent; Ortiz, Michael Computer Methods in Applied Mechanics and Engineering, Vol. 373 https://doi.org/10.1016/j.cma.2020.113499	journal	January 2021
SciANN: A Keras/TensorFlow wrapper for scientific computations and physics-informed deep learning using artificial neural networks Haghighat, Ehsan; Juanes, Ruben Computer Methods in Applied Mechanics and Engineering, Vol. 373 https://doi.org/10.1016/j.cma.2020.113552	journal	January 2021
Sobolev training of thermodynamic-informed neural networks for interpretable elasto-plasticity models with level set hardening Vlassis, Nikolaos N.; Sun, WaiChing Computer Methods in Applied Mechanics and Engineering, Vol. 377 https://doi.org/10.1016/j.cma.2021.113695	journal	April 2021
A kd-tree-accelerated hybrid data-driven/model-based approach for poroelasticity problems with multi-fidelity multi-physics data Bahmani, Bahador; Sun, WaiChing Computer Methods in Applied Mechanics and Engineering, Vol. 382 https://doi.org/10.1016/j.cma.2021.113868	journal	August 2021
Geometric prior of multi-resolution yielding manifolds and the local closest point projection for nearly non-smooth plasticity Xiao, Mian; Sun, WaiChing Computer Methods in Applied Mechanics and Engineering, Vol. 400 https://doi.org/10.1016/j.cma.2022.115469	journal	October 2022
Model-free Data-Driven inference in computational mechanics Prume, E.; Reese, S.; Ortiz, M. Computer Methods in Applied Mechanics and Engineering, Vol. 403 https://doi.org/10.1016/j.cma.2022.115704	journal	January 2023
Distance-preserving manifold denoising for data-driven mechanics Bahmani, Bahador; Sun, WaiChing Computer Methods in Applied Mechanics and Engineering, Vol. 405 https://doi.org/10.1016/j.cma.2022.115857	journal	February 2023
Mechanical MNIST: A benchmark dataset for mechanical metamodels Lejeune, Emma Extreme Mechanics Letters, Vol. 36 https://doi.org/10.1016/j.eml.2020.100659	journal	April 2020
Gradient-enhanced statistical analysis of cleavage fracture Martínez-Pañeda, Emilio; Fuentes-Alonso, Sandra; Betegón, Covadonga European Journal of Mechanics - A/Solids, Vol. 77 https://doi.org/10.1016/j.euromechsol.2019.05.002	journal	September 2019
Linear transfomation-based anisotropic yield functions Barlat, F.; Aretz, H.; Yoon, J. W. International Journal of Plasticity, Vol. 21, Issue 5 https://doi.org/10.1016/j.ijplas.2004.06.004	journal	May 2005
A review of some plasticity and viscoplasticity constitutive theories Chaboche, J. L. International Journal of Plasticity, Vol. 24, Issue 10 https://doi.org/10.1016/j.ijplas.2008.03.009	journal	October 2008
Implicit stress-update algorithm for isotropic Cam-clay model based on the subloading surface concept at finite strains Yamakawa, Yuki; Hashiguchi, Koichi; Ikeda, Kiyohiro International Journal of Plasticity, Vol. 26, Issue 5 https://doi.org/10.1016/j.ijplas.2009.09.007	journal	May 2010
Extracting dislocation microstructures by deep learning Zhang, Yuqi; Ngan, Alfonso H. W. International Journal of Plasticity, Vol. 115 https://doi.org/10.1016/j.ijplas.2018.11.008	journal	April 2019
Machine learning-based constitutive model for J2- plasticity Jang, Dong Phill; Fazily, Piemaan; Yoon, Jeong Whan International Journal of Plasticity, Vol. 138 https://doi.org/10.1016/j.ijplas.2020.102919	journal	March 2021
Anisotropic plasticity model forms for extruded Al 7079: Part I, calibration Corona, E.; Kramer, S. L. B.; Scherzinger, W. M. International Journal of Solids and Structures, Vol. 213 https://doi.org/10.1016/j.ijsolstr.2020.11.030	journal	March 2021
Anisotropic plasticity model forms for extruded Al 7079: Part II, validation Jones, E. M. C.; Corona, E.; Jones, A. R. International Journal of Solids and Structures, Vol. 213 https://doi.org/10.1016/j.ijsolstr.2020.11.031	journal	March 2021
Data-Driven multiscale modeling in mechanics Karapiperis, K.; Stainier, L.; Ortiz, M. Journal of the Mechanics and Physics of Solids, Vol. 147 https://doi.org/10.1016/j.jmps.2020.104239	journal	February 2021
Manifold embedding data-driven mechanics Bahmani, Bahador; Sun, WaiChing Journal of the Mechanics and Physics of Solids, Vol. 166 https://doi.org/10.1016/j.jmps.2022.104927	journal	September 2022
Investigating the plastic anisotropy and hardening behavior of a commercial Zn–Cu–Ti alloy: Experimental & modeling approach Cauvin, Ludovic; Raghavan, Balaji; Jin, Jianqiang Mechanics of Materials, Vol. 164 https://doi.org/10.1016/j.mechmat.2021.104103	journal	January 2022
Machine-learning convex and texture-dependent macroscopic yield from crystal plasticity simulations Fuhg, Jan N.; van Wees, Lloyd; Obstalecki, Mark Materialia, Vol. 23 https://doi.org/10.1016/j.mtla.2022.101446	journal	June 2022
Multitask Learning Caruana, Rich Machine Learning, Vol. 28, Issue 1, p. 41-75 https://doi.org/10.1023/A:1007379606734	journal	January 1997
Reproducibility standards for machine learning in the life sciences Heil, Benjamin J.; Hoffman, Michael M.; Markowetz, Florian Nature Methods, Vol. 18, Issue 10 https://doi.org/10.1038/s41592-021-01256-7	journal	August 2021
Knowledge‐Based Modeling of Material Behavior with Neural Networks Ghaboussi, J.; Garrett, J. H.; Wu, X. Journal of Engineering Mechanics, Vol. 117, Issue 1 https://doi.org/10.1061/(ASCE)0733-9399(1991)117:1(132)	journal	January 1991
Deep learning predicts path-dependent plasticity Mozaffar, M.; Bostanabad, R.; Chen, W. Proceedings of the National Academy of Sciences, Vol. 116, Issue 52 https://doi.org/10.1073/pnas.1911815116	journal	December 2019
An overview of multi-task learning Zhang, Yu; Yang, Qiang National Science Review, Vol. 5, Issue 1 https://doi.org/10.1093/nsr/nwx105	journal	September 2017
Trustworthy AI Wing, Jeannette M. Communications of the ACM, Vol. 64, Issue 10 https://doi.org/10.1145/3448248	journal	September 2021
State of the Art: Reproducibility in Artificial Intelligence Gundersen, Odd Erik; Kjensmo, Sigbjørn Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 32, Issue 1 https://doi.org/10.1609/aaai.v32i1.11503	journal	April 2018

Similar Records

LCA-PyTorch

Software · Thu Jun 22 20:00:00 EDT 2023 · OSTI ID:code-110613

PyTorch Implementation of Log-Additive Convolutional Neural Networks

Software · Wed May 15 20:00:00 EDT 2024 · OSTI ID:code-140120

Granular Flow Constitutive Model Add-ons For Abaqus

Software · Sun Jan 03 19:00:00 EST 2021 · OSTI ID:code-51074

Related Subjects

36 MATERIALS SCIENCE
ABAQUS subroutine
neural-network-based constitutive models
public availability
reproducibility

A publicly available PyTorch-$$\mathrm{ABAQUS}$$ $$\mathrm{UMAT}$$ deep-learning framework for level-set plasticity

Citation Formats

References (47)

Similar Records

Related Subjects