DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Predictive modeling of dynamic fracture growth in brittle materials with machine learning

Abstract

We use simulation data from a high delity Finite-Discrete Element Model to build an e cient Machine Learning (ML) approach to predict fracture growth and coalescence. Our goal is for the ML approach to be used as an emulator in place of the computationally intensive high delity models in an uncertainty quanti cation framework where thousands of forward runs are required. The failure of materials with various fracture con gurations (size, orientation and the number of initial cracks) are explored and used as data to train our ML model. This novel approach has shown promise in predicting spatial (path to failure) and temporal (time to failure) aspects of brittle material failure. Predictions of where dominant fracture paths formed within a material were ~85% accurate and the time of material failure deviated from the actual failure time by an average of ~16%. Additionally, the ML model achieves a reduction in computational cost by multiple orders of magnitude.

Authors:
 [1];  [1];  [1];  [1];  [1];  [1]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1425767
Alternate Identifier(s):
OSTI ID: 1547147
Report Number(s):
LA-UR-17-30614
Journal ID: ISSN 0927-0256; TRN: US1802161
Grant/Contract Number:  
AC52-06NA25396; 20170103DR
Resource Type:
Accepted Manuscript
Journal Name:
Computational Materials Science
Additional Journal Information:
Journal Volume: 148; Journal Issue: C; Journal ID: ISSN 0927-0256
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE; Computer Science; Material Science; Machine Learning, Brittle Failure, Fracture Propagation

Citation Formats

Moore, Bryan A., Rougier, Esteban, O’Malley, Daniel, Srinivasan, Gowri, Hunter, Abigail, and Viswanathan, Hari. Predictive modeling of dynamic fracture growth in brittle materials with machine learning. United States: N. p., 2018. Web. doi:10.1016/j.commatsci.2018.01.056.
Moore, Bryan A., Rougier, Esteban, O’Malley, Daniel, Srinivasan, Gowri, Hunter, Abigail, & Viswanathan, Hari. Predictive modeling of dynamic fracture growth in brittle materials with machine learning. United States. https://doi.org/10.1016/j.commatsci.2018.01.056
Moore, Bryan A., Rougier, Esteban, O’Malley, Daniel, Srinivasan, Gowri, Hunter, Abigail, and Viswanathan, Hari. Thu . "Predictive modeling of dynamic fracture growth in brittle materials with machine learning". United States. https://doi.org/10.1016/j.commatsci.2018.01.056. https://www.osti.gov/servlets/purl/1425767.
@article{osti_1425767,
title = {Predictive modeling of dynamic fracture growth in brittle materials with machine learning},
author = {Moore, Bryan A. and Rougier, Esteban and O’Malley, Daniel and Srinivasan, Gowri and Hunter, Abigail and Viswanathan, Hari},
abstractNote = {We use simulation data from a high delity Finite-Discrete Element Model to build an e cient Machine Learning (ML) approach to predict fracture growth and coalescence. Our goal is for the ML approach to be used as an emulator in place of the computationally intensive high delity models in an uncertainty quanti cation framework where thousands of forward runs are required. The failure of materials with various fracture con gurations (size, orientation and the number of initial cracks) are explored and used as data to train our ML model. This novel approach has shown promise in predicting spatial (path to failure) and temporal (time to failure) aspects of brittle material failure. Predictions of where dominant fracture paths formed within a material were ~85% accurate and the time of material failure deviated from the actual failure time by an average of ~16%. Additionally, the ML model achieves a reduction in computational cost by multiple orders of magnitude.},
doi = {10.1016/j.commatsci.2018.01.056},
journal = {Computational Materials Science},
number = C,
volume = 148,
place = {United States},
year = {Thu Feb 22 00:00:00 EST 2018},
month = {Thu Feb 22 00:00:00 EST 2018}
}

Journal Article:

Citation Metrics:
Cited by: 47 works
Citation information provided by
Web of Science

Figures / Tables:

Figure 1 Figure 1: Visualization of the extraction of pair data from a 2D HOSS fracture simulation. In the feature vector, the Ls are lengths of initial fractures, the θs are fracture orientations, Dist is the distance between the two fractures and min DB is the minimum distance to the boundary frommore » either fracture. The simulation above has 20 initial fractures which yield 190 data points (with boundary-fracture pairs included).« less

Save / Share:

Works referenced in this record:

Development of intermetallic materials for aerospace systems
journal, April 1992

  • Dimiduk, D. M.; Miracle, D. B.; Ward, C. H.
  • Materials Science and Technology, Vol. 8, Issue 4
  • DOI: 10.1179/mst.1992.8.4.367

Where Does Water Go During Hydraulic Fracturing?: D. O'Malley et al. Groundwater xx, no. x: xx-xx
journal, October 2015

  • O'Malley, D.; Karra, S.; Currier, R. P.
  • Groundwater, Vol. 54, Issue 4
  • DOI: 10.1111/gwat.12380

Introduction to Fracture Mechanics
journal, January 1983

  • Ohji, K.
  • Journal of the Society of Materials Science, Japan, Vol. 32, Issue 359
  • DOI: 10.2472/jsms.32.935

The dynamics of rapid fracture: instabilities, nonlinearities and length scales
journal, March 2014


Computational modelling of impact damage in brittle materials
journal, August 1996


Experimental investigation and poroplastic modelling of saturated porous geomaterials
journal, December 2012


Computational materials: Multi-scale modeling and simulation of nanostructured materials
journal, December 2005


The Phenomena of Rupture and Flow in Solids
journal, January 1921

  • Griffith, A. A.
  • Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences, Vol. 221, Issue 582-593
  • DOI: 10.1098/rsta.1921.0006

A Critical Analysis of Crack Propagation Laws
journal, December 1963

  • Paris, P.; Erdogan, F.
  • Journal of Basic Engineering, Vol. 85, Issue 4
  • DOI: 10.1115/1.3656900

Modern topics and challenges in dynamic fracture
journal, March 2005

  • Cox, Brian N.; Gao, Huajian; Gross, Dietmar
  • Journal of the Mechanics and Physics of Solids, Vol. 53, Issue 3
  • DOI: 10.1016/j.jmps.2004.09.002

Particle methods in the study of fracture
journal, November 2015


Coupled-volume multi-scale modelling of quasi-brittle material
journal, May 2008


Microscale and mesoscale discrete models for dynamic fracture of structures built of brittle material
journal, May 2003


Effective Elastic Moduli of Two-Dimensional Brittle Solids With Interacting Microcracks, Part I: Basic Formulations
journal, June 1994

  • Ju, J. W.; Chen, Tsung-Muh
  • Journal of Applied Mechanics, Vol. 61, Issue 2
  • DOI: 10.1115/1.2901451

Elastic moduli of a cracked body
journal, May 1983

  • Margolin, L. G.
  • International Journal of Fracture, Vol. 22, Issue 1
  • DOI: 10.1007/BF00960099

Computational mechanics at the mesoscale
journal, January 2000


Analysis of crack formation and crack growth in concrete by means of fracture mechanics and finite elements
journal, November 1976


Foundations of statistical natural language processing
journal, September 2002


Machine learning in bioinformatics
journal, March 2006

  • Larrañaga, Pedro; Calvo, Borja; Santana, Roberto
  • Briefings in Bioinformatics, Vol. 7, Issue 1
  • DOI: 10.1093/bib/bbk007

Random Forests
journal, January 2001


Multilayer feedforward networks are universal approximators
journal, January 1989


A combined finite‐discrete element method in transient dynamics of fracturing solids
journal, February 1995


A generalized anisotropic deformation formulation for geomaterials
journal, October 2015


Validation of a three-dimensional Finite-Discrete Element Method using experimental results of the Split Hopkinson Pressure Bar test
journal, September 2014

  • Rougier, E.; Knight, E. E.; Broome, S. T.
  • International Journal of Rock Mechanics and Mining Sciences, Vol. 70
  • DOI: 10.1016/j.ijrmms.2014.03.011

Popular Ensemble Methods: An Empirical Study
journal, July 1999

  • Opitz, D.; Maclin, R.
  • Journal of Artificial Intelligence Research, Vol. 11
  • DOI: 10.1613/jair.614

Works referencing / citing this record:

Fourier amplitude sensitivity test applied to dynamic combined finite‐discrete element methods–based simulations
journal, August 2018

  • Godinez, Humberto C.; Rougier, Esteban; Osthus, Dave
  • International Journal for Numerical and Analytical Methods in Geomechanics, Vol. 43, Issue 1
  • DOI: 10.1002/nag.2852

Surrogate Models for Estimating Failure in Brittle and Quasi-Brittle Materials
journal, July 2019

  • Mudunuru, Maruti Kumar; Panda, Nishant; Karra, Satish
  • Applied Sciences, Vol. 9, Issue 13
  • DOI: 10.3390/app9132706

FSIS: a novel fluid–solid interaction solver for fracturing and fragmenting solids
journal, January 2020


A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics
journal, May 2019


A review of the application of machine learning and data mining approaches in continuum materials mechanics
text, January 2019

  • Bock, Frederic E.; Aydin, Roland C.; Cyron, Christian J.
  • TUHH Universitätsbibliothek
  • DOI: 10.15480/882.2309

Figures/Tables have been extracted from DOE-funded journal article accepted manuscripts.