skip to main content
DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

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

Abstract

Typically, thousands of computationally expensive micro-scale simulations of brittle crack propagation are needed to upscale lower length scale phenomena to the macro-continuum scale. Running such a large number of crack propagation simulations presents a significant computational challenge, making reduced-order models (ROMs) attractive for this task. Here, the ultimate goal of this research is to develop ROMs that have sufficient accuracy and low computational cost so that these upscaling simulations can be readily performed. However, constructing ROMs for these complex simulations presents its own challenge. Here, we present and compare four different approaches for reduced-order modeling of brittle crack propagation in geomaterials. These methods rely on machine learning (ML) and graph-theoretic algorithms to approximate key aspects of the brittle crack problem. These methods also incorporate different physics-based assumptions in order to reduce the training requirements while maintaining accurate physics as much as possible. Results from the ROMs are directly compared against a high-fidelity model of brittle crack propagation. Further, the strengths and weaknesses of the ROMs are discussed, and we conclude that combining smart physics-informed feature engineering with highly trainable ML models provides the best performance. The ROMs considered here have computational costs that are orders-of-magnitude less than the cost associatedmore » with high-fidelity physical models while maintaining good accuracy.« less

Authors:
ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1];  [2];  [3]; ORCiD logo [1]; ORCiD logo [4]; ORCiD logo [1]; ORCiD logo [1]; ORCiD logo [1]
  1. Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
  2. Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Univ. of Chicago, IL (United States)
  3. Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Brigham Young Univ., Provo, UT (United States)
  4. Los Alamos National Lab. (LANL), Los Alamos, NM (United States); Univ. of Maryland Baltimore County (UMBC), Baltimore, MD (United States)
Publication Date:
Research Org.:
Los Alamos National Lab. (LANL), Los Alamos, NM (United States)
Sponsoring Org.:
USDOE Laboratory Directed Research and Development (LDRD) Program
OSTI Identifier:
1603983
Report Number(s):
LA-UR-18-29900
Journal ID: ISSN 0927-0256
Grant/Contract Number:  
89233218CNA000001; 20170103DR; 20150693ECR
Resource Type:
Accepted Manuscript
Journal Name:
Computational Materials Science
Additional Journal Information:
Journal Volume: 157; Journal Issue: C; Journal ID: ISSN 0927-0256
Publisher:
Elsevier
Country of Publication:
United States
Language:
English
Subject:
36 MATERIALS SCIENCE; brittle crack; machine learning; crack interaction; reduced-order models; graph theory

Citation Formats

Hunter, Abigail, Moore, Bryan Alexander, Mudunuru, Maruti Kumar, Chau, Viet Tuan, Tchoua, Roselyne Barreto, Nyshadham, Chandramouli, Karra, Satish, O’Malley, Daniel, Rougier, Esteban, Viswanathan, Hari S., and Srinivasan, Gowri. Reduced-order modeling through machine learning and graph-theoretic approaches for brittle fracture applications. United States: N. p., 2018. Web. https://doi.org/10.1016/j.commatsci.2018.10.036.
Hunter, Abigail, Moore, Bryan Alexander, Mudunuru, Maruti Kumar, Chau, Viet Tuan, Tchoua, Roselyne Barreto, Nyshadham, Chandramouli, Karra, Satish, O’Malley, Daniel, Rougier, Esteban, Viswanathan, Hari S., & Srinivasan, Gowri. Reduced-order modeling through machine learning and graph-theoretic approaches for brittle fracture applications. United States. https://doi.org/10.1016/j.commatsci.2018.10.036
Hunter, Abigail, Moore, Bryan Alexander, Mudunuru, Maruti Kumar, Chau, Viet Tuan, Tchoua, Roselyne Barreto, Nyshadham, Chandramouli, Karra, Satish, O’Malley, Daniel, Rougier, Esteban, Viswanathan, Hari S., and Srinivasan, Gowri. Wed . "Reduced-order modeling through machine learning and graph-theoretic approaches for brittle fracture applications". United States. https://doi.org/10.1016/j.commatsci.2018.10.036. https://www.osti.gov/servlets/purl/1603983.
@article{osti_1603983,
title = {Reduced-order modeling through machine learning and graph-theoretic approaches for brittle fracture applications},
author = {Hunter, Abigail and Moore, Bryan Alexander and Mudunuru, Maruti Kumar and Chau, Viet Tuan and Tchoua, Roselyne Barreto and Nyshadham, Chandramouli and Karra, Satish and O’Malley, Daniel and Rougier, Esteban and Viswanathan, Hari S. and Srinivasan, Gowri},
abstractNote = {Typically, thousands of computationally expensive micro-scale simulations of brittle crack propagation are needed to upscale lower length scale phenomena to the macro-continuum scale. Running such a large number of crack propagation simulations presents a significant computational challenge, making reduced-order models (ROMs) attractive for this task. Here, the ultimate goal of this research is to develop ROMs that have sufficient accuracy and low computational cost so that these upscaling simulations can be readily performed. However, constructing ROMs for these complex simulations presents its own challenge. Here, we present and compare four different approaches for reduced-order modeling of brittle crack propagation in geomaterials. These methods rely on machine learning (ML) and graph-theoretic algorithms to approximate key aspects of the brittle crack problem. These methods also incorporate different physics-based assumptions in order to reduce the training requirements while maintaining accurate physics as much as possible. Results from the ROMs are directly compared against a high-fidelity model of brittle crack propagation. Further, the strengths and weaknesses of the ROMs are discussed, and we conclude that combining smart physics-informed feature engineering with highly trainable ML models provides the best performance. The ROMs considered here have computational costs that are orders-of-magnitude less than the cost associated with high-fidelity physical models while maintaining good accuracy.},
doi = {10.1016/j.commatsci.2018.10.036},
journal = {Computational Materials Science},
number = C,
volume = 157,
place = {United States},
year = {2018},
month = {11}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record

Citation Metrics:
Cited by: 7 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Reduced-order modeling: new approaches for computational physics
journal, February 2004


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

Support-vector networks
journal, September 1995

  • Cortes, Corinna; Vapnik, Vladimir
  • Machine Learning, Vol. 20, Issue 3
  • DOI: 10.1007/BF00994018

A logical calculus of the ideas immanent in nervous activity
journal, December 1943

  • McCulloch, Warren S.; Pitts, Walter
  • The Bulletin of Mathematical Biophysics, Vol. 5, Issue 4
  • DOI: 10.1007/BF02478259

Materials informatics
journal, October 2005


Materials informatics: a journey towards material design and synthesis
journal, January 2016

  • Takahashi, Keisuke; Tanaka, Yuzuru
  • Dalton Transactions, Vol. 45, Issue 26
  • DOI: 10.1039/C6DT01501H

Commentary: The Materials Project: A materials genome approach to accelerating materials innovation
journal, July 2013

  • Jain, Anubhav; Ong, Shyue Ping; Hautier, Geoffroy
  • APL Materials, Vol. 1, Issue 1
  • DOI: 10.1063/1.4812323

Alloy Negative Electrodes for High Energy Density Metal-Ion Cells
journal, January 2011

  • Tran, Tuan T.; Obrovac, M. N.
  • Journal of The Electrochemical Society, Vol. 158, Issue 12
  • DOI: 10.1149/2.083112jes

Computational screening of perovskite metal oxides for optimal solar light capture
journal, January 2012

  • Castelli, Ivano E.; Olsen, Thomas; Datta, Soumendu
  • Energy Environ. Sci., Vol. 5, Issue 2
  • DOI: 10.1039/C1EE02717D

Phase stability of chromium based compensated ferrimagnets with inverse Heusler structure
journal, September 2013


Compressive sensing as a paradigm for building physics models
journal, January 2013


Role of descriptors in predicting the dissolution energy of embedded oxides and the bulk modulus of oxide-embedded iron
journal, January 2017


Quantifying Topological Uncertainty in Fractured Systems using Graph Theory and Machine Learning
journal, August 2018


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

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


Numerical comparison of some explicit time integration schemes used in DEM, FEM/DEM and molecular dynamics
journal, September 2004

  • Rougier, E.; Munjiza, A.; John, N. W. M.
  • International Journal for Numerical Methods in Engineering, Vol. 61, Issue 6
  • DOI: 10.1002/nme.1092

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

Predictive modeling of dynamic fracture growth in brittle materials with machine learning
journal, June 2018


Fracture energy and fracture process zone
journal, July 1992

  • Hu, X. -Z.; Wittmann, F. H.
  • Materials and Structures, Vol. 25, Issue 6
  • DOI: 10.1007/BF02472590

Crack Interaction, Coalescence and Mixed mode Fracture Mechanics
journal, April 1996


A few useful things to know about machine learning
journal, October 2012


    Works referencing / citing this record:

    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