Feed-forward neural networks for failure mechanics problems

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autoren

Organisationseinheiten

Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Aufsatznummer6483
Seitenumfang22
FachzeitschriftApplied Sciences
Jahrgang11
Ausgabenummer14
PublikationsstatusVeröffentlicht - 14 Juli 2021

Abstract

This work addresses an efficient neural network (NN) representation for the phase-field modeling of isotropic brittle fracture. In recent years, data-driven approaches, such as neural networks, have become an active research field in mechanics. In this contribution, deep neural networks—in particular, the feed-forward neural network (FFNN)—are utilized directly for the development of the failure model. The verification and generalization of the trained models for elasticity as well as fracture behavior are investigated by several representative numerical examples under different loading conditions. As an outcome, promising results close to the exact solutions are produced.

ASJC Scopus Sachgebiete

Zitieren

Feed-forward neural networks for failure mechanics problems. / Aldakheel, Fadi; Satari, Ramish; Wriggers, Peter.
in: Applied Sciences, Jahrgang 11, Nr. 14, 6483, 14.07.2021.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Aldakheel F, Satari R, Wriggers P. Feed-forward neural networks for failure mechanics problems. Applied Sciences. 2021 Jul 14;11(14):6483. doi: 10.3390/app11146483
Aldakheel, Fadi ; Satari, Ramish ; Wriggers, Peter. / Feed-forward neural networks for failure mechanics problems. in: Applied Sciences. 2021 ; Jahrgang 11, Nr. 14.
Download
@article{ea21ed8cb04d4bc18033ebd313ee4cfb,
title = "Feed-forward neural networks for failure mechanics problems",
abstract = "This work addresses an efficient neural network (NN) representation for the phase-field modeling of isotropic brittle fracture. In recent years, data-driven approaches, such as neural networks, have become an active research field in mechanics. In this contribution, deep neural networks—in particular, the feed-forward neural network (FFNN)—are utilized directly for the development of the failure model. The verification and generalization of the trained models for elasticity as well as fracture behavior are investigated by several representative numerical examples under different loading conditions. As an outcome, promising results close to the exact solutions are produced.",
keywords = "Elasticity, Failure mechanics, Neural networks (NNs), Phase-field modeling",
author = "Fadi Aldakheel and Ramish Satari and Peter Wriggers",
note = "Funding Information: Funding: The publication of this article was funded by the Open Access Fund of the Leibniz Universit{\"a}t Hannover (LUH-TIB).",
year = "2021",
month = jul,
day = "14",
doi = "10.3390/app11146483",
language = "English",
volume = "11",
journal = "Applied Sciences",
issn = "2076-3417",
publisher = "Multidisciplinary Digital Publishing Institute",
number = "14",

}

Download

TY - JOUR

T1 - Feed-forward neural networks for failure mechanics problems

AU - Aldakheel, Fadi

AU - Satari, Ramish

AU - Wriggers, Peter

N1 - Funding Information: Funding: The publication of this article was funded by the Open Access Fund of the Leibniz Universität Hannover (LUH-TIB).

PY - 2021/7/14

Y1 - 2021/7/14

N2 - This work addresses an efficient neural network (NN) representation for the phase-field modeling of isotropic brittle fracture. In recent years, data-driven approaches, such as neural networks, have become an active research field in mechanics. In this contribution, deep neural networks—in particular, the feed-forward neural network (FFNN)—are utilized directly for the development of the failure model. The verification and generalization of the trained models for elasticity as well as fracture behavior are investigated by several representative numerical examples under different loading conditions. As an outcome, promising results close to the exact solutions are produced.

AB - This work addresses an efficient neural network (NN) representation for the phase-field modeling of isotropic brittle fracture. In recent years, data-driven approaches, such as neural networks, have become an active research field in mechanics. In this contribution, deep neural networks—in particular, the feed-forward neural network (FFNN)—are utilized directly for the development of the failure model. The verification and generalization of the trained models for elasticity as well as fracture behavior are investigated by several representative numerical examples under different loading conditions. As an outcome, promising results close to the exact solutions are produced.

KW - Elasticity

KW - Failure mechanics

KW - Neural networks (NNs)

KW - Phase-field modeling

UR - http://www.scopus.com/inward/record.url?scp=85111146427&partnerID=8YFLogxK

U2 - 10.3390/app11146483

DO - 10.3390/app11146483

M3 - Article

AN - SCOPUS:85111146427

VL - 11

JO - Applied Sciences

JF - Applied Sciences

SN - 2076-3417

IS - 14

M1 - 6483

ER -

Von denselben Autoren