Grain learning: Bayesian calibration of DEM models and validation against elastic wave propagation

Hongyang Cheng, Takayuki Shuku, Klaus Thoeni, Pamela Tempone, Stefan Luding, Vanessa Magnanimo

Research output: Contribution to journalConference article

Abstract

The estimation of micromechanical parameters of discrete element method (DEM) models is a nonlinear history-dependent inverse problem. In order to reproduce the experimental measurements with high accuracy, this work aims to develop a machine learning-based calibration toolbox named “Grain learning”, which can extract grains from X-ray computed tomography (CT) images and perform Bayesian parameter estimation for DEM models of dry granular materials.

Original languageEnglish
Pages (from-to)132-135
Number of pages4
JournalSpringer Series in Geomechanics and Geoengineering
Issue number216849
DOIs
Publication statusPublished - Jan 1 2018
EventChina-Europe Conference on Geotechnical Engineering, 2016 - Vienna, Austria
Duration: Aug 13 2016Aug 16 2016

Fingerprint

discrete element method
Elastic waves
elastic wave
Finite difference method
Wave propagation
wave propagation
learning
Calibration
calibration
Granular materials
inverse problem
Inverse problems
Parameter estimation
tomography
Tomography
Learning systems
X rays
history
machine learning
parameter estimation

ASJC Scopus subject areas

  • Geotechnical Engineering and Engineering Geology
  • Mechanics of Materials

Cite this

Grain learning : Bayesian calibration of DEM models and validation against elastic wave propagation. / Cheng, Hongyang; Shuku, Takayuki; Thoeni, Klaus; Tempone, Pamela; Luding, Stefan; Magnanimo, Vanessa.

In: Springer Series in Geomechanics and Geoengineering, No. 216849, 01.01.2018, p. 132-135.

Research output: Contribution to journalConference article

Cheng, Hongyang ; Shuku, Takayuki ; Thoeni, Klaus ; Tempone, Pamela ; Luding, Stefan ; Magnanimo, Vanessa. / Grain learning : Bayesian calibration of DEM models and validation against elastic wave propagation. In: Springer Series in Geomechanics and Geoengineering. 2018 ; No. 216849. pp. 132-135.
@article{e66adb954994452eac21aeb9c9a7bd98,
title = "Grain learning: Bayesian calibration of DEM models and validation against elastic wave propagation",
abstract = "The estimation of micromechanical parameters of discrete element method (DEM) models is a nonlinear history-dependent inverse problem. In order to reproduce the experimental measurements with high accuracy, this work aims to develop a machine learning-based calibration toolbox named “Grain learning”, which can extract grains from X-ray computed tomography (CT) images and perform Bayesian parameter estimation for DEM models of dry granular materials.",
author = "Hongyang Cheng and Takayuki Shuku and Klaus Thoeni and Pamela Tempone and Stefan Luding and Vanessa Magnanimo",
year = "2018",
month = "1",
day = "1",
doi = "10.1007/978-3-319-97112-4_29",
language = "English",
pages = "132--135",
journal = "Springer Series in Geomechanics and Geoengineering",
issn = "1866-8755",
publisher = "Springer Verlag",
number = "216849",

}

TY - JOUR

T1 - Grain learning

T2 - Bayesian calibration of DEM models and validation against elastic wave propagation

AU - Cheng, Hongyang

AU - Shuku, Takayuki

AU - Thoeni, Klaus

AU - Tempone, Pamela

AU - Luding, Stefan

AU - Magnanimo, Vanessa

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The estimation of micromechanical parameters of discrete element method (DEM) models is a nonlinear history-dependent inverse problem. In order to reproduce the experimental measurements with high accuracy, this work aims to develop a machine learning-based calibration toolbox named “Grain learning”, which can extract grains from X-ray computed tomography (CT) images and perform Bayesian parameter estimation for DEM models of dry granular materials.

AB - The estimation of micromechanical parameters of discrete element method (DEM) models is a nonlinear history-dependent inverse problem. In order to reproduce the experimental measurements with high accuracy, this work aims to develop a machine learning-based calibration toolbox named “Grain learning”, which can extract grains from X-ray computed tomography (CT) images and perform Bayesian parameter estimation for DEM models of dry granular materials.

UR - http://www.scopus.com/inward/record.url?scp=85060483898&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060483898&partnerID=8YFLogxK

U2 - 10.1007/978-3-319-97112-4_29

DO - 10.1007/978-3-319-97112-4_29

M3 - Conference article

AN - SCOPUS:85060483898

SP - 132

EP - 135

JO - Springer Series in Geomechanics and Geoengineering

JF - Springer Series in Geomechanics and Geoengineering

SN - 1866-8755

IS - 216849

ER -