Accelerating discrete dislocation dynamics simulations with graph neural networks

Bertin, Nicolas; Zhou, Fei

doi:10.1016/j.jcp.2023.112180

Accelerating discrete dislocation dynamics simulations with graph neural networks

Journal Article · Tue Apr 25 00:00:00 EDT 2023 · Journal of Computational Physics

DOI:https://doi.org/10.1016/j.jcp.2023.112180· OSTI ID:2005099

^[1]; Zhou, Fei ^[1]

Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)

Discrete dislocation dynamics (DDD) is a widely employed computational method to study plasticity at the mesoscale that connects the motion of dislocation lines to the macroscopic response of crystalline materials. However, the computational cost of DDD simulations remains a bottleneck that limits its range of applicability. Here, we introduce a new DDD-GNN framework in which the expensive time-integration of dislocation motion is entirely substituted by a graph neural network (GNN) model trained on DDD trajectories. As a first application, we demonstrate the feasibility and potential of our method on a simple yet relevant model of a dislocation line gliding through an array of obstacles. We show that the DDD-GNN model is stable and reproduces very well unseen ground-truth DDD simulation responses for a range of straining rates and obstacle densities, without the need to explicitly compute nodal forces or dislocation mobilities during time-integration. Our approach opens new promising avenues to accelerate DDD simulations and to incorporate more complex dislocation motion behaviors.

View Accepted Manuscript (DOE)

Research Organization:: Lawrence Livermore National Laboratory (LLNL), Livermore, CA (United States)

Sponsoring Organization:: USDOE National Nuclear Security Administration (NNSA)

Grant/Contract Number:: AC52-07NA27344

OSTI ID:: 2005099

Report Number(s):: LLNL-JRNL--838407; 1058699

Journal Information:: Journal of Computational Physics, Journal Name: Journal of Computational Physics Journal Issue: N/A Vol. 487; ISSN 0021-9991

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (39)

Gaussian approximation potentials: A brief tutorial introduction Bartók, Albert P.; Csányi, Gábor International Journal of Quantum Chemistry, Vol. 115, Issue 16 https://doi.org/10.1002/qua.24927	journal	April 2015
Scaling of Dislocation Strengthening by Multiple Obstacle Types Dong, Y.; Nogaret, T.; Curtin, W. A. Metallurgical and Materials Transactions A, Vol. 41, Issue 8 https://doi.org/10.1007/s11661-010-0229-z	journal	June 2010
Analysis of Obstacle Hardening Models Using Dislocation Dynamics: Application to Irradiation-Induced Defects Sobie, Cameron; Bertin, Nicolas; Capolungo, Laurent Metallurgical and Materials Transactions A, Vol. 46, Issue 8 https://doi.org/10.1007/s11661-015-2935-z	journal	May 2015
Machine Learning of Dislocation-Induced Stress Fields and Interaction Forces Rafiei, Mohammad H.; Gu, Yejun; El-Awady, Jaafar A. JOM, Vol. 72, Issue 12 https://doi.org/10.1007/s11837-020-04389-w	journal	October 2020
The strengthening effect of voids Scattergood, R. O.; Bacon, D. J. Acta Metallurgica, Vol. 30, Issue 8 https://doi.org/10.1016/0001-6160(82)90188-2	journal	August 1982
Homogenization method for a discrete-continuum simulation of dislocation dynamics Lemarchand, C.; Devincre, B.; Kubin, L. P. Journal of the Mechanics and Physics of Solids, Vol. 49, Issue 9 https://doi.org/10.1016/S0022-5096(01)00026-6	journal	September 2001
Computer simulations of Orowan process controlled dislocation glide in particle arrangements of various randomness Mohles, V.; Fruhstorfer, B. Acta Materialia, Vol. 50, Issue 10 https://doi.org/10.1016/S1359-6454(02)00079-4	journal	June 2002
Chapter 88 Dislocation–Obstacle Interactions at the Atomic Level Bacon, D. J.; Osetsky, Y. N.; Rodney, D. Dislocations in Solids https://doi.org/10.1016/S1572-4859(09)01501-0	book	January 2009
Multiscale modelling of precipitation hardening in Al–Cu alloys: Dislocation dynamics simulations and experimental validation Santos-Güemes, R.; Bellón, B.; Esteban-Manzanares, G. Acta Materialia, Vol. 188 https://doi.org/10.1016/j.actamat.2020.02.019	journal	April 2020
Consistent formulation for the Discrete-Continuous Model: Improving complex dislocation dynamics simulations Jamond, O.; Gatti, R.; Roos, A. International Journal of Plasticity, Vol. 80 https://doi.org/10.1016/j.ijplas.2015.12.011	journal	May 2016
Connecting discrete and continuum dislocation mechanics: A non-singular spectral framework Bertin, Nicolas International Journal of Plasticity, Vol. 122 https://doi.org/10.1016/j.ijplas.2018.12.006	journal	November 2019
A FFT-based formulation for discrete dislocation dynamics in heterogeneous media Bertin, N.; Capolungo, L. Journal of Computational Physics, Vol. 355 https://doi.org/10.1016/j.jcp.2017.11.020	journal	February 2018
A non-singular continuum theory of dislocations Cai, W.; Arsenlis, A.; Weinberger, C. Journal of the Mechanics and Physics of Solids, Vol. 54, Issue 3 https://doi.org/10.1016/j.jmps.2005.09.005	journal	March 2006
Modelling crystal plasticity by 3D dislocation dynamics and the finite element method: The Discrete-Continuous Model revisited Vattré, A.; Devincre, B.; Feyel, F. Journal of the Mechanics and Physics of Solids, Vol. 63 https://doi.org/10.1016/j.jmps.2013.07.003	journal	February 2014
A statistical model of irradiation hardening induced by non-periodic irradiation defects Cui, Wei; Cui, Yinan; Liu, Wei Scripta Materialia, Vol. 201 https://doi.org/10.1016/j.scriptamat.2021.113959	journal	August 2021
Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals Chen, Chi; Ye, Weike; Zuo, Yunxing Chemistry of Materials, Vol. 31, Issue 9 https://doi.org/10.1021/acs.chemmater.9b01294	journal	April 2019
Four Generations of High-Dimensional Neural Network Potentials Behler, Jörg Chemical Reviews https://doi.org/10.1021/acs.chemrev.0c00868	journal	March 2021
Machine Learning Force Fields Unke, Oliver T.; Chmiela, Stefan; Sauceda, Huziel E. Chemical Reviews https://doi.org/10.1021/acs.chemrev.0c01111	journal	March 2021
The ReaxFF reactive force-field: development, applications and future directions Senftle, Thomas P.; Hong, Sungwook; Islam, Md Mahbubul npj Computational Materials, Vol. 2, Issue 1 https://doi.org/10.1038/npjcompumats.2015.11	journal	March 2016
Machine learning plastic deformation of crystals Salmenjoki, Henri; Alava, Mikko J.; Laurson, Lasse Nature Communications, Vol. 9, Issue 1 https://doi.org/10.1038/s41467-018-07737-2	journal	December 2018
E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials Batzner, Simon; Musaelian, Albert; Sun, Lixin Nature Communications, Vol. 13, Issue 1 https://doi.org/10.1038/s41467-022-29939-5	journal	May 2022
Accurate and scalable graph neural network force field and molecular dynamics with direct force architecture Park, Cheol Woo; Kornbluth, Mordechai; Vandermause, Jonathan npj Computational Materials, Vol. 7, Issue 1 https://doi.org/10.1038/s41524-021-00543-3	journal	May 2021
Machine learning for interatomic potential models Mueller, Tim; Hernandez, Alberto; Wang, Chuhong The Journal of Chemical Physics, Vol. 152, Issue 5 https://doi.org/10.1063/1.5126336	journal	February 2020
Dislocation glide through non-randomly distributed point obstacles de Vaucorbeil, A.; Sinclair, C. W.; Poole, W. J. Philosophical Magazine, Vol. 93, Issue 27 https://doi.org/10.1080/14786435.2013.820384	journal	September 2013
Dislocation movement through random arrays of obstacles Foreman, A. J. E.; Makin, M. J. Philosophical Magazine, Vol. 14, Issue 131 https://doi.org/10.1080/14786436608244762	journal	October 1966
Enabling strain hardening simulations with dislocation dynamics Arsenlis, A.; Cai, W.; Tang, M. Modelling and Simulation in Materials Science and Engineering, Vol. 15, Issue 6 https://doi.org/10.1088/0965-0393/15/6/001	journal	July 2007
Efficient time integration in dislocation dynamics Sills, Ryan B.; Cai, Wei Modelling and Simulation in Materials Science and Engineering, Vol. 22, Issue 2 https://doi.org/10.1088/0965-0393/22/2/025003	journal	January 2014
Implicit integration methods for dislocation dynamics Gardner, D. J.; Woodward, C. S.; Reynolds, D. R. Modelling and Simulation in Materials Science and Engineering, Vol. 23, Issue 2 https://doi.org/10.1088/0965-0393/23/2/025006	journal	January 2015
A FFT-based formulation for efficient mechanical fields computation in isotropic and anisotropic periodic discrete dislocation dynamics Bertin, N.; Upadhyay, M. V.; Pradalier, C. Modelling and Simulation in Materials Science and Engineering, Vol. 23, Issue 6 https://doi.org/10.1088/0965-0393/23/6/065009	journal	August 2015
Advanced time integration algorithms for dislocation dynamics simulations of work hardening Sills, Ryan B.; Aghaei, Amin; Cai, Wei Modelling and Simulation in Materials Science and Engineering, Vol. 24, Issue 4 https://doi.org/10.1088/0965-0393/24/4/045019	journal	April 2016
GPU-accelerated dislocation dynamics using subcycling time-integration Bertin, N.; Aubry, S.; Arsenlis, A. Modelling and Simulation in Materials Science and Engineering, Vol. 27, Issue 7 https://doi.org/10.1088/1361-651X/ab3a03	journal	August 2019
An efficient implicit time integration method for discrete dislocation dynamics Péterffy, Gábor; Ispánovity, Péter Dusán Modelling and Simulation in Materials Science and Engineering, Vol. 28, Issue 3 https://doi.org/10.1088/1361-651X/ab76b2	journal	March 2020
Dislocation precipitate bypass through elastically mismatched precipitates Szajewski, Benjamin A.; Crone, Joshua C.; Knap, Jaroslaw Modelling and Simulation in Materials Science and Engineering, Vol. 29, Issue 2 https://doi.org/10.1088/1361-651X/abd015	journal	February 2021
Multipole expansion of dislocation interactions: Application to discrete dislocations LeSar, R.; Rickman, J. M. Physical Review B, Vol. 65, Issue 14 https://doi.org/10.1103/PhysRevB.65.144110	journal	April 2002
Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties Xie, Tian; Grossman, Jeffrey C. Physical Review Letters, Vol. 120, Issue 14 https://doi.org/10.1103/PhysRevLett.120.145301	journal	April 2018
Frontiers in the Simulation of Dislocations Bertin, Nicolas; Sills, Ryan B.; Cai, Wei Annual Review of Materials Research, Vol. 50, Issue 1 https://doi.org/10.1146/annurev-matsci-091819-015500	journal	July 2020
Machine Learning for Molecular Simulation Noé, Frank; Tkatchenko, Alexandre; Müller, Klaus-Robert Annual Review of Physical Chemistry, Vol. 71, Issue 1 https://doi.org/10.1146/annurev-physchem-042018-052331	journal	April 2020
Effect of particle size distribution on strength of precipitation-hardened alloys Kulkarni, A. J.; Krishnamurthy, K.; Deshmukh, S. P. Journal of Materials Research, Vol. 19, Issue 9 https://doi.org/10.1557/JMR.2004.0364	journal	September 2004
Machine Learning-Based Classification of Dislocation Microstructures Steinberger, Dominik; Song, Hengxu; Sandfeld, Stefan Frontiers in Materials, Vol. 6 https://doi.org/10.3389/fmats.2019.00141	journal	June 2019

Similar Records

Geometrically projected discrete dislocation dynamics

Journal Article · Thu Jul 19 20:00:00 EDT 2018 · Modelling and Simulation in Materials Science and Engineering · OSTI ID:1464207

Enhanced mobility of dislocation network nodes and its effect on dislocation multiplication and strain hardening

Journal Article · Wed Apr 03 20:00:00 EDT 2024 · Acta Materialia · OSTI ID:2340984

Related Subjects

36 MATERIALS SCIENCE
Dislocation dynamics
Graph neural networks
Machine learning
Materials science
Time-integration

Accelerating discrete dislocation dynamics simulations with graph neural networks

Citation Formats

References (39)

Similar Records

Related Subjects