Maschinelles Lernen für die numerische Homogenisierung von Beton

Research output: Contribution to specialist publicationContribution in non-scientific journalTransfer

View graph of relations

Details

Translated title of the contributionMachine Learning for the Numerical Homogenization of Concrete
Original languageGerman
Pages354-360
Number of pages7
Volume98
Issue number11
JournalBauingenieur
Publication statusPublished - 2023

Abstract

Material modeling of concrete using modern numerical methods significantly accelerates the design process of structures. However, for multiscale modeling of such a heterogeneous material, the established homogenization methods are still very computationally intensive, especially for high accuracy requirements. In this paper, we propose a machine learning approach that provides a computationally efficient solution method while delivering a high degree of accuracy. The dataset used for the training and testing process consists of artificial and real microstructural images (input), while the result data (output) are the homogenized stresses of a given representative volume element (RVE). The performance of the model is demonstrated by examples and compared with classical homogenization methods. The developed ML model achieves higher accuracy in determining the homogenized stresses and significantly reduces the computation time.

ASJC Scopus subject areas

Cite this

Maschinelles Lernen für die numerische Homogenisierung von Beton. / Aldakheel, Fadi; Haist, Michael; Lohaus, Ludger et al.
In: Bauingenieur, Vol. 98, No. 11, 2023, p. 354-360.

Research output: Contribution to specialist publicationContribution in non-scientific journalTransfer

Aldakheel F, Haist M, Lohaus L, Wriggers P. Maschinelles Lernen für die numerische Homogenisierung von Beton. Bauingenieur. 2023;98(11):354-360. doi: 10.37544/0005-6650-2023-11-42
Aldakheel, Fadi ; Haist, Michael ; Lohaus, Ludger et al. / Maschinelles Lernen für die numerische Homogenisierung von Beton. In: Bauingenieur. 2023 ; Vol. 98, No. 11. pp. 354-360.
Download
@misc{eb1ac9ff2b2e488b89ca5b6d23159700,
title = "Maschinelles Lernen f{\"u}r die numerische Homogenisierung von Beton",
abstract = "Material modeling of concrete using modern numerical methods significantly accelerates the design process of structures. However, for multiscale modeling of such a heterogeneous material, the established homogenization methods are still very computationally intensive, especially for high accuracy requirements. In this paper, we propose a machine learning approach that provides a computationally efficient solution method while delivering a high degree of accuracy. The dataset used for the training and testing process consists of artificial and real microstructural images (input), while the result data (output) are the homogenized stresses of a given representative volume element (RVE). The performance of the model is demonstrated by examples and compared with classical homogenization methods. The developed ML model achieves higher accuracy in determining the homogenized stresses and significantly reduces the computation time.",
author = "Fadi Aldakheel and Michael Haist and Ludger Lohaus and Peter Wriggers",
year = "2023",
doi = "10.37544/0005-6650-2023-11-42",
language = "Deutsch",
volume = "98",
pages = "354--360",
journal = "Bauingenieur",
issn = "0005-6650",
publisher = "Springer-VDI Verlag GmbH und Co. KG",

}

Download

TY - GEN

T1 - Maschinelles Lernen für die numerische Homogenisierung von Beton

AU - Aldakheel, Fadi

AU - Haist, Michael

AU - Lohaus, Ludger

AU - Wriggers, Peter

PY - 2023

Y1 - 2023

N2 - Material modeling of concrete using modern numerical methods significantly accelerates the design process of structures. However, for multiscale modeling of such a heterogeneous material, the established homogenization methods are still very computationally intensive, especially for high accuracy requirements. In this paper, we propose a machine learning approach that provides a computationally efficient solution method while delivering a high degree of accuracy. The dataset used for the training and testing process consists of artificial and real microstructural images (input), while the result data (output) are the homogenized stresses of a given representative volume element (RVE). The performance of the model is demonstrated by examples and compared with classical homogenization methods. The developed ML model achieves higher accuracy in determining the homogenized stresses and significantly reduces the computation time.

AB - Material modeling of concrete using modern numerical methods significantly accelerates the design process of structures. However, for multiscale modeling of such a heterogeneous material, the established homogenization methods are still very computationally intensive, especially for high accuracy requirements. In this paper, we propose a machine learning approach that provides a computationally efficient solution method while delivering a high degree of accuracy. The dataset used for the training and testing process consists of artificial and real microstructural images (input), while the result data (output) are the homogenized stresses of a given representative volume element (RVE). The performance of the model is demonstrated by examples and compared with classical homogenization methods. The developed ML model achieves higher accuracy in determining the homogenized stresses and significantly reduces the computation time.

UR - http://www.scopus.com/inward/record.url?scp=85181461786&partnerID=8YFLogxK

U2 - 10.37544/0005-6650-2023-11-42

DO - 10.37544/0005-6650-2023-11-42

M3 - Beitrag in Publikumszeitung/-zeitschrift

AN - SCOPUS:85181461786

VL - 98

SP - 354

EP - 360

JO - Bauingenieur

JF - Bauingenieur

SN - 0005-6650

ER -

By the same author(s)