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

Journal Article · · Computational Materials Science

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.

Research Organization:
Los Alamos National Laboratory (LANL)
Sponsoring Organization:
USDOE
Grant/Contract Number:
AC52-06NA25396
OSTI ID:
1425767
Alternate ID(s):
OSTI ID: 1547147
Report Number(s):
LA-UR-17-30614
Journal Information:
Computational Materials Science, Journal Name: Computational Materials Science Journal Issue: C Vol. 148; ISSN 0927-0256
Publisher:
ElsevierCopyright Statement
Country of Publication:
United States
Language:
English

References (25)

Random Forests journal January 2001
Coupled-volume multi-scale modelling of quasi-brittle material journal May 2008
Analysis of crack formation and crack growth in concrete by means of fracture mechanics and finite elements journal November 1976
Machine learning in bioinformatics journal March 2006
Introduction to Fracture Mechanics journal January 1983
Particle methods in the study of fracture journal November 2015
Computational materials: Multi-scale modeling and simulation of nanostructured materials journal December 2005
A Critical Analysis of Crack Propagation Laws journal December 1963
A combined finite‐discrete element method in transient dynamics of fracturing solids journal February 1995
The Phenomena of Rupture and Flow in Solids journal January 1921
Development of intermetallic materials for aerospace systems journal April 1992
The dynamics of rapid fracture: instabilities, nonlinearities and length scales journal March 2014
Computational modelling of impact damage in brittle materials journal August 1996
Microscale and mesoscale discrete models for dynamic fracture of structures built of brittle material journal May 2003
Experimental investigation and poroplastic modelling of saturated porous geomaterials journal December 2012
A generalized anisotropic deformation formulation for geomaterials journal October 2015
Modern topics and challenges in dynamic fracture journal March 2005
Popular Ensemble Methods: An Empirical Study journal July 1999
Elastic moduli of a cracked body journal May 1983
Computational mechanics at the mesoscale journal January 2000
Validation of a three-dimensional Finite-Discrete Element Method using experimental results of the Split Hopkinson Pressure Bar test journal September 2014
Where Does Water Go During Hydraulic Fracturing?: D. O'Malley et al. Groundwater xx, no. x: xx-xx journal October 2015
Foundations of statistical natural language processing journal September 2002
Effective Elastic Moduli of Two-Dimensional Brittle Solids With Interacting Microcracks, Part I: Basic Formulations journal June 1994
Multilayer feedforward networks are universal approximators journal January 1989

Cited By (6)

A Review of the Application of Machine Learning and Data Mining Approaches in Continuum Materials Mechanics journal May 2019
FSIS: a novel fluid–solid interaction solver for fracturing and fragmenting solids journal January 2020
A predictive failure framework for brittle porous materials via machine learning and geometric matching methods journal January 2020
Fourier amplitude sensitivity test applied to dynamic combined finite‐discrete element methods–based simulations
  • Godinez, Humberto C.; Rougier, Esteban; Osthus, Dave
  • International Journal for Numerical and Analytical Methods in Geomechanics, Vol. 43, Issue 1 https://doi.org/10.1002/nag.2852
journal August 2018
Surrogate Models for Estimating Failure in Brittle and Quasi-Brittle Materials journal July 2019
A review of the application of machine learning and data mining approaches in continuum materials mechanics text January 2019