Learning data-driven reduced elastic and inelastic models of spot-welded patches
Solving mechanical problems in large structures with rich localized behaviors remains a challenging issue despite the enormous advances in numerical procedures and computational performance. In particular, these localized behaviors need for extremely fine descriptions, and this has an associated imp...
Main Authors: | , , , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
EDP Sciences
2021-01-01
|
Series: | Mechanics & Industry |
Subjects: | |
Online Access: | https://www.mechanics-industry.org/articles/meca/full_html/2021/01/mi210009/mi210009.html |
id |
doaj-76a0cf28c57e4b4ea3509772873ec577 |
---|---|
record_format |
Article |
spelling |
doaj-76a0cf28c57e4b4ea3509772873ec5772021-10-07T12:00:38ZengEDP SciencesMechanics & Industry2257-77772257-77502021-01-01223210.1051/meca/2021031mi210009Learning data-driven reduced elastic and inelastic models of spot-welded patchesReille AgatheChampaney Victor0Daim Fatima1Tourbier Yves2https://orcid.org/0000-0002-0639-5854Hascoet Nicolas3Gonzalez David4Cueto Elias5https://orcid.org/0000-0003-1017-4381Duval Jean Louis6Chinesta FranciscoESI Group Chair & PIMM Laboratory, Arts et Métiers Institute of TechnologyESI Group, Batiment SevilleRenaultESI Group Chair & PIMM Laboratory, Arts et Métiers Institute of TechnologyAragon Institute of Engineering Research, Universidad de ZaragozaAragon Institute of Engineering Research, Universidad de ZaragozaESI Group, Batiment SevilleSolving mechanical problems in large structures with rich localized behaviors remains a challenging issue despite the enormous advances in numerical procedures and computational performance. In particular, these localized behaviors need for extremely fine descriptions, and this has an associated impact in the number of degrees of freedom from one side, and the decrease of the time step employed in usual explicit time integrations, whose stability scales with the size of the smallest element involved in the mesh. In the present work we propose a data-driven technique for learning the rich behavior of a local patch and integrate it into a standard coarser description at the structure level. Thus, localized behaviors impact the global structural response without needing an explicit description of that fine scale behaviors.https://www.mechanics-industry.org/articles/meca/full_html/2021/01/mi210009/mi210009.htmlmodel order reductionspot-weldsmachine learningartificial intelligencedata-driven mechanics |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Reille Agathe Champaney Victor Daim Fatima Tourbier Yves Hascoet Nicolas Gonzalez David Cueto Elias Duval Jean Louis Chinesta Francisco |
spellingShingle |
Reille Agathe Champaney Victor Daim Fatima Tourbier Yves Hascoet Nicolas Gonzalez David Cueto Elias Duval Jean Louis Chinesta Francisco Learning data-driven reduced elastic and inelastic models of spot-welded patches Mechanics & Industry model order reduction spot-welds machine learning artificial intelligence data-driven mechanics |
author_facet |
Reille Agathe Champaney Victor Daim Fatima Tourbier Yves Hascoet Nicolas Gonzalez David Cueto Elias Duval Jean Louis Chinesta Francisco |
author_sort |
Reille Agathe |
title |
Learning data-driven reduced elastic and inelastic models of spot-welded patches |
title_short |
Learning data-driven reduced elastic and inelastic models of spot-welded patches |
title_full |
Learning data-driven reduced elastic and inelastic models of spot-welded patches |
title_fullStr |
Learning data-driven reduced elastic and inelastic models of spot-welded patches |
title_full_unstemmed |
Learning data-driven reduced elastic and inelastic models of spot-welded patches |
title_sort |
learning data-driven reduced elastic and inelastic models of spot-welded patches |
publisher |
EDP Sciences |
series |
Mechanics & Industry |
issn |
2257-7777 2257-7750 |
publishDate |
2021-01-01 |
description |
Solving mechanical problems in large structures with rich localized behaviors remains a challenging issue despite the enormous advances in numerical procedures and computational performance. In particular, these localized behaviors need for extremely fine descriptions, and this has an associated impact in the number of degrees of freedom from one side, and the decrease of the time step employed in usual explicit time integrations, whose stability scales with the size of the smallest element involved in the mesh. In the present work we propose a data-driven technique for learning the rich behavior of a local patch and integrate it into a standard coarser description at the structure level. Thus, localized behaviors impact the global structural response without needing an explicit description of that fine scale behaviors. |
topic |
model order reduction spot-welds machine learning artificial intelligence data-driven mechanics |
url |
https://www.mechanics-industry.org/articles/meca/full_html/2021/01/mi210009/mi210009.html |
work_keys_str_mv |
AT reilleagathe learningdatadrivenreducedelasticandinelasticmodelsofspotweldedpatches AT champaneyvictor learningdatadrivenreducedelasticandinelasticmodelsofspotweldedpatches AT daimfatima learningdatadrivenreducedelasticandinelasticmodelsofspotweldedpatches AT tourbieryves learningdatadrivenreducedelasticandinelasticmodelsofspotweldedpatches AT hascoetnicolas learningdatadrivenreducedelasticandinelasticmodelsofspotweldedpatches AT gonzalezdavid learningdatadrivenreducedelasticandinelasticmodelsofspotweldedpatches AT cuetoelias learningdatadrivenreducedelasticandinelasticmodelsofspotweldedpatches AT duvaljeanlouis learningdatadrivenreducedelasticandinelasticmodelsofspotweldedpatches AT chinestafrancisco learningdatadrivenreducedelasticandinelasticmodelsofspotweldedpatches |
_version_ |
1716839408405053440 |