Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Machine Learning Applied to Prediction of Brittle Fracture Processes
share announcement

Machine Learning Applied to Prediction of Brittle Fracture Processes

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Materials Science and Engineering".

Deadline for manuscript submissions: closed (31 October 2019) | Viewed by 3019

Special Issue Editors

Dr. Esteban Rougier

E-Mail Website
Guest Editor
Earth and Environmental Sciences Division, Los Alamos National Laboratory, Los Alamos, NM 87545, USA
Interests: combined finite–discrete element simulations; finite element modeling; high strain rate processes; material modeling; fracture and fragmentation processes; shock wave propagation in solids and fluids
Special Issues, Collections and Topics in MDPI journals
Dr. Abigail Hunter

E-Mail Website
Guest Editor
Computational Physics Division, Los Alamos National Laboratory, USA
Interests: fracture and fragmentation processes; brittle materials; reduced-order models; multiscale modeling; constitutive models; mesoscale models; crack interaction and propagation; impact loading; shock physics; phase-field models
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

In recent decades, simulation of brittle fracture and fragmentation processes have been addressed with the help of high-fidelity first-principle physics-based numerical models which rely on different solution methodologies (e.g., finite elements). Similarly, the emergence of experimental capabilities now allows for detailed and in situ material characterization. As a consequence, the evolution of individual cracks and crack networks inside a brittle medium can be studied with a high level of fidelity at a microscale level. However, high-fidelity models can be quite expensive from the point of view of the CPU resources and the time needed to obtain a solution, to a point in which they can seriously constrain the simulation scale addressable. Furthermore, the sensitivity of the chosen numerical model with respect to the input parameters and the boundary conditions of the systems is not always clear to the user, which can have serious consequences when trying to establish error bounds for the obtained solutions. From an experimental standpoint, these techniques result in very large, multi-dimensional datasets that take time to process and study. An alternative approach is to develop machine learning techniques to learn from experimental datasets and/or from numerical results obtained from high fidelity numerical simulations, in order to obtain reasonable answers in a fraction of the time and resources needed with the other alternatives, thus accelerating the discovery and optimization of new/current material systems.

This Special Issue concentrates on gathering the latest and greatest advances in the application of machine learning techniques to the resolution, study, and classification of fracture processes (initiation, propagation, arrest, interaction, etc.) in brittle materials. Original contributions from engineers, mechanical materials scientists, computer scientists, physicists, chemists, and mathematicians are encouraged. Both experimental and theoretical papers are welcome.

Dr. Esteban Rougier
Dr. Abigail Hunter
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Fracture
  • Fragmentation
  • Machine learning
  • Data assimilation
  • Parameter sensitivity
  • Brittle materials
  • Reduced-order models

Published Papers (1 paper)

Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

21 pages, 1502 KiB  
Article
Surrogate Models for Estimating Failure in Brittle and Quasi-Brittle Materials
by Maruti Kumar Mudunuru, Nishant Panda, Satish Karra, Gowri Srinivasan, Viet T. Chau, Esteban Rougier, Abigail Hunter and Hari S. Viswanathan
Appl. Sci. 2019, 9(13), 2706; https://doi.org/10.3390/app9132706 - 03 Jul 2019
Cited by 14 | Viewed by 2778
Abstract
In brittle fracture applications, failure paths, regions where the failure occurs and damage statistics, are some of the key quantities of interest (QoI). High-fidelity models for brittle failure that accurately predict these QoI exist but are highly computationally intensive, making them infeasible to [...] Read more.
In brittle fracture applications, failure paths, regions where the failure occurs and damage statistics, are some of the key quantities of interest (QoI). High-fidelity models for brittle failure that accurately predict these QoI exist but are highly computationally intensive, making them infeasible to incorporate in upscaling and uncertainty quantification frameworks. The goal of this paper is to provide a fast heuristic to reasonably estimate quantities such as failure path and damage in the process of brittle failure. Towards this goal, we first present a method to predict failure paths under tensile loading conditions and low-strain rates. The method uses a k-nearest neighbors algorithm built on fracture process zone theory, and identifies the set of all possible pre-existing cracks that are likely to join early to form a large crack. The method then identifies zone of failure and failure paths using weighted graphs algorithms. We compare these failure paths to those computed with a high-fidelity fracture mechanics model called the Hybrid Optimization Software Simulation Suite (HOSS). A probabilistic evolution model for average damage in a system is also developed that is trained using 150 HOSS simulations and tested on 40 simulations. A non-parametric approach based on confidence intervals is used to determine the damage evolution over time along the dominant failure path. For upscaling, damage is the key QoI needed as an input by the continuum models. This needs to be informed accurately by the surrogate models for calculating effective moduli at continuum-scale. We show that for the proposed average damage evolution model, the prediction accuracy on the test data is more than 90%. In terms of the computational time, the proposed models are ≈ O ( 10 6 ) times faster compared to high-fidelity fracture simulations by HOSS. These aspects make the proposed surrogate model attractive for upscaling damage from micro-scale models to continuum models. We would like to emphasize that the surrogate models are not a replacement of physical understanding of fracture propagation. The proposed method in this paper is limited to tensile loading conditions at low-strain rates. This loading condition corresponds to a dominant fracture perpendicular to tensile direction. The proposed method is not applicable for in-plane shear, out-of-plane shear, and higher strain rate loading conditions. Full article
(This article belongs to the Special Issue Machine Learning Applied to Prediction of Brittle Fracture Processes)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-1
Back to TopTop