Accelerating high-strain continuum-scale brittle fracture simulations with machine learning

Fernandez, Maria Giselle; Panda, Nishant; O'Malley, Daniel; Larkin, Kevin; Hunter, Abigail; Haftka, Raphael T.; Srinivasan, Gowri

doi:10.1016/j.commatsci.2020.109959

Accelerating high-strain continuum-scale brittle fracture simulations with machine learning

Journal Article · Tue Sep 01 00:00:00 EDT 2020 · Computational Materials Science

DOI:https://doi.org/10.1016/j.commatsci.2020.109959· OSTI ID:1774441

^[1]; ^[1]; ^[1]; Larkin, Kevin ^[1]; ^[1]; Haftka, Raphael T. ^[2]; ^[1]

Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Univ. of Florida, Gainesville, FL (United States)

Failure in brittle materials under dynamic loading conditions is a result of the propagation and coalescence of microcracks. Simulating this discrete crack evolution at the continuum level is computationally expensive or, in some cases, intractable, resulting in the need to make broad assumptions or neglect key physics. In this work, we have developed an approach using machine learning that overcomes the current inability to represent meso-scale physics at the macro-scale. Our approach leverages damage and stress data from a computationally expensive high-fidelity model that explicitly resolves microcrack behavior to build an inexpensive machine learning emulator. Once trained, the machine learning emulator is used to predict the evolution of crack length statistics, which then informs a continuum-scale constitutive model. This results in a significant speed-up of the workflow by four orders of magnitude. Both the machine learning emulator and the continuum-scale model are validated against the high-fidelity model and experimental data, respectively, showing excellent agreement. There are two key findings. The first is that we can reduce the dimensionality of the problem, establishing that the machine learning emulator only needs the length of the longest crack and one of the maximum stress components to capture the necessary physics. Another compelling finding is that the emulator can be trained in one experimental setting and transferred successfully to predict behavior in a different setting.

View Accepted Manuscript (DOE)

Research Organization:: Los Alamos National Laboratory (LANL), Los Alamos, NM (United States)

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

Grant/Contract Number:: 89233218CNA000001

OSTI ID:: 1774441

Alternate ID(s):: OSTI ID: 1778360

Report Number(s):: LA-UR--20-22890

Journal Information:: Computational Materials Science, Journal Name: Computational Materials Science Vol. 186; ISSN 0927-0256

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (33)

Some fundamental issues of damage mechanics Krajcinovic, Dusan; Mastilovic, Sreten Mechanics of Materials, Vol. 21, Issue 3 https://doi.org/10.1016/0167-6636(95)00010-0	journal	October 1995
Numerical comparison of some explicit time integration schemes used in DEM, FEM/DEM and molecular dynamics Rougier, E.; Munjiza, A.; John, N. W. M. International Journal for Numerical Methods in Engineering, Vol. 61, Issue 6 https://doi.org/10.1002/nme.1092	journal	September 2004
The combined plastic and discrete fracture deformation framework for finite‐discrete element methods Rougier, Esteban; Munjiza, Antonio; Lei, Zhou International Journal for Numerical Methods in Engineering, Vol. 121, Issue 5 https://doi.org/10.1002/nme.6255	journal	December 2019
Effective elastic moduli of two-phase composites containing randomly dispersed spherical inhomogeneities Ju, J. W.; Chen, T. M. Acta Mechanica, Vol. 103, Issue 1-4 https://doi.org/10.1007/BF01180222	journal	March 1994
Simulation of Fracture Coalescence in Granite via the Combined Finite–Discrete Element Method Euser, Bryan; Rougier, E.; Lei, Z. Rock Mechanics and Rock Engineering, Vol. 52, Issue 9 https://doi.org/10.1007/s00603-019-01773-0	journal	March 2019
Power Law of Crack Length Distribution in the Multiple Damage Process Ignatovich, S. R.; Bouraou, N. I. Strength of Materials, Vol. 51, Issue 5 https://doi.org/10.1007/s11223-019-00122-4	journal	September 2019
Bridging machine learning and computer network research: a survey Cheng, Yang; Geng, Jinkun; Wang, Yanshu CCF Transactions on Networking, Vol. 1, Issue 1-4 https://doi.org/10.1007/s42045-018-0009-7	journal	November 2018
Predictive modeling of dynamic fracture growth in brittle materials with machine learning Moore, Bryan A.; Rougier, Esteban; O’Malley, Daniel Computational Materials Science, Vol. 148 https://doi.org/10.1016/j.commatsci.2018.01.056	journal	June 2018
Reduced-order modeling through machine learning and graph-theoretic approaches for brittle fracture applications Hunter, Abigail; Moore, Bryan A.; Mudunuru, Maruti Computational Materials Science, Vol. 157 https://doi.org/10.1016/j.commatsci.2018.10.036	journal	February 2019
Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networks Schwarzer, Max; Rogan, Bryce; Ruan, Yadong Computational Materials Science, Vol. 162 https://doi.org/10.1016/j.commatsci.2019.02.046	journal	May 2019
Ejecta source and transport modeling in the FLAG hydrocode Fung, J.; Harrison, A. K.; Chitanvis, S. Computers & Fluids, Vol. 83 https://doi.org/10.1016/j.compfluid.2012.08.011	journal	August 2013
A micromechanics based model to predict micro-crack coalescence in brittle materials under dynamic compression Huq, F.; Liu, J.; Tonge, A. L. Engineering Fracture Mechanics, Vol. 217 https://doi.org/10.1016/j.engfracmech.2019.106515	journal	August 2019
Validation of a three-dimensional Finite-Discrete Element Method using experimental results of the Split Hopkinson Pressure Bar test Rougier, E.; Knight, E. E.; Broome, S. T. International Journal of Rock Mechanics and Mining Sciences, Vol. 70 https://doi.org/10.1016/j.ijrmms.2014.03.011	journal	September 2014
Deep multiscale model learning Wang, Yating; Cheung, Siu Wun; Chung, Eric T. Journal of Computational Physics, Vol. 406 https://doi.org/10.1016/j.jcp.2019.109071	journal	April 2020
Mesoscale informed parameter estimation through machine learning: A case-study in fracture modeling Panda, Nishant; Osthus, Dave; Srinivasan, Gowri Journal of Computational Physics, Vol. 420 https://doi.org/10.1016/j.jcp.2020.109719	journal	November 2020
An interacting micro-crack damage model for failure of brittle materials under compression Paliwal, B.; Ramesh, K. T. Journal of the Mechanics and Physics of Solids, Vol. 56, Issue 3 https://doi.org/10.1016/j.jmps.2007.06.012	journal	March 2008
Fracture-permeability behavior of shale Carey, J. William; Lei, Zhou; Rougier, Esteban Journal of Unconventional Oil and Gas Resources, Vol. 11 https://doi.org/10.1016/j.juogr.2015.04.003	journal	September 2015
Surrogate-based analysis and optimization Queipo, Nestor V.; Haftka, Raphael T.; Shyy, Wei Progress in Aerospace Sciences, Vol. 41, Issue 1 https://doi.org/10.1016/j.paerosci.2005.02.001	journal	January 2005
Statistically informed upscaling of damage evolution in brittle materials Vaughn, N.; Kononov, A.; Moore, B. Theoretical and Applied Fracture Mechanics, Vol. 102 https://doi.org/10.1016/j.tafmec.2019.04.012	journal	August 2019
Scaling of fracture systems in geological media Bonnet, E.; Bour, O.; Odling, N. E. Reviews of Geophysics, Vol. 39, Issue 3 https://doi.org/10.1029/1999RG000074	journal	August 2001
Earthquake Damage Patterns Resolve Complex Rupture Processes Klinger, Yann; Okubo, Kurama; Vallage, Amaury Geophysical Research Letters, Vol. 45, Issue 19 https://doi.org/10.1029/2018GL078842	journal	October 2018
Digital selection and analogue amplification coexist in a cortex-inspired silicon circuit Hahnloser, Richard H. R.; Sarpeshkar, Rahul; Mahowald, Misha A. Nature, Vol. 405, Issue 6789 https://doi.org/10.1038/35016072	journal	June 2000
Recent advances and applications of machine learning in solid-state materials science Schmidt, Jonathan; Marques, Mário R. G.; Botti, Silvana npj Computational Materials, Vol. 5, Issue 1 https://doi.org/10.1038/s41524-019-0221-0	journal	August 2019
Quantifying Topological Uncertainty in Fractured Systems using Graph Theory and Machine Learning Srinivasan, Gowri; Hyman, Jeffrey D.; Osthus, David A. Scientific Reports, Vol. 8, Issue 1 https://doi.org/10.1038/s41598-018-30117-1	journal	August 2018
Characterization of shocked beryllium Cady, C. M.; Adams, C. D.; Hull, L. M. EPJ Web of Conferences, Vol. 26 https://doi.org/10.1051/epjconf/20122601009	journal	January 2012
A constitutive model for metals applicable at high‐strain rate Steinberg, D. J.; Cochran, S. G.; Guinan, M. W. Journal of Applied Physics, Vol. 51, Issue 3 https://doi.org/10.1063/1.327799	journal	March 1980
A combined finite‐discrete element method in transient dynamics of fracturing solids Munjiza, A.; Owen, D. R. J.; Bicanic, N. Engineering Computations, Vol. 12, Issue 2 https://doi.org/10.1108/02644409510799532	journal	February 1995
The Evolution of Computing: AlphaGo Chen, Jim X. Computing in Science & Engineering, Vol. 18, Issue 4 https://doi.org/10.1109/MCSE.2016.74	journal	July 2016
Evaporation Effects in Shock-Driven Multiphase Instabilities Black, Wolfgang J.; Denissen, Nicholas A.; McFarland, Jacob A. Journal of Fluids Engineering, Vol. 139, Issue 7 https://doi.org/10.1115/1.4036162	journal	April 2017
Big data classification: problems and challenges in network intrusion prediction with machine learning Suthaharan, Shan ACM SIGMETRICS Performance Evaluation Review, Vol. 41, Issue 4 https://doi.org/10.1145/2627534.2627557	journal	April 2014
Computational Methods for Fracture in Brittle and Quasi-Brittle Solids: State-of-the-Art Review and Future Perspectives Rabczuk, Timon ISRN Applied Mathematics, Vol. 2013 https://doi.org/10.1155/2013/849231	journal	January 2013
Issues in Deciding Whether to Use Multifidelity Surrogates Giselle Fernández-Godino, M.; Park, Chanyoung; Kim, Nam H. AIAA Journal, Vol. 57, Issue 5 https://doi.org/10.2514/1.J057750	journal	May 2019
Surrogate Models for Estimating Failure in Brittle and Quasi-Brittle Materials Mudunuru, Maruti Kumar; Panda, Nishant; Karra, Satish Applied Sciences, Vol. 9, Issue 13 https://doi.org/10.3390/app9132706	journal	July 2019

Similar Records

Scale bridging damage model for quasi-brittle metals informed with crack evolution statistics

Journal Article · Thu Feb 27 23:00:00 EST 2020 · Journal of the Mechanics and Physics of Solids · OSTI ID:1603990

Statistically informed upscaling of damage evolution in brittle materials

Journal Article · Fri May 03 00:00:00 EDT 2019 · Theoretical and Applied Fracture Mechanics · OSTI ID:1512769

Reduced-order modeling through machine learning and graph-theoretic approaches for brittle fracture applications

Journal Article · Tue Nov 06 23:00:00 EST 2018 · Computational Materials Science · OSTI ID:1603983

Related Subjects

36 MATERIALS SCIENCE
Machine learning
cost reduction
crack statistics
validation

Accelerating high-strain continuum-scale brittle fracture simulations with machine learning

Citation Formats

References (33)

Similar Records

Related Subjects