Physics-informed neural networks for solving elasticity problems

Bibliographic Details
Main Author: Almeida, Estevão Fuzaro [UNESP]
Publication Date: 2023
Other Authors: Silva, Samuel da [UNESP], Cunha Júnior, Americo
Format: Conference object
Language: eng
Source: Repositório Institucional da UNESP
Download full: https://hdl.handle.net/11449/253634
Summary: The first author would like to thank São Paulo Research Foundation (FAPESP) for providing financial support under grant number 2022/16156-9.
id UNSP_17f2df7c79fb469829b5ebc2c6c630e4
oai_identifier_str oai:repositorio.unesp.br:11449/253634
network_acronym_str UNSP
network_name_str Repositório Institucional da UNESP
repository_id_str 2946
spelling Physics-informed neural networks for solving elasticity problemsSolid mechanicsPhysics-informed neural networksStress distributionData-free modelingThe first author would like to thank São Paulo Research Foundation (FAPESP) for providing financial support under grant number 2022/16156-9.Computational mechanics has seen remarkable progress in recent years due to the integration of machine learning techniques, particularly neural networks. Traditional approaches in solid mechanics, such as the finite element method (FEM), often require extensive manual labor in discretization and mesh generation, making them time-consuming and challenging for complex geometries. Moreover, these methods heavily rely on accurate and complete data, which may not always be readily available or prone to measurement errors. On the other hand, Physics-Informed Neural Networks (PINNs) are a machine learning technique that can learn from data and physics equations, allowing accurate and physically consistent predictions. Through this study, we aim to demonstrate the effectiveness of PINNs in accurately predicting the stress distribution in a triangular plate, showcasing their potential as a valuable tool in solving real-world solid mechanics problems. Combining the elasticity conservation laws and boundary conditions into the neural network architecture creates a PINN and is trained on a coarse mesh of points over the plate domain and evaluated on a fine mesh using a data-free approach, compared with the Airy analytical solution.Associação Brasileira de Engenharia e Ciências Mecânicas (ABCM)São Paulo Research Foundation (FAPESP) Grant No 2022/16156-9Almeida, Estevão Fuzaro [UNESP]Silva, Samuel da [UNESP]Cunha Júnior, Americo2024-03-11T19:09:18Z2024-03-11T19:09:18Z2023-12-08info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/conferenceObjectapplication/pdfALMEIDA, E. F.; SILVA, S.; CUNHA JR, A. Physics-informed neural networks for solving elasticity problems. In: BRAZILIAN CONGRESS OF THERMAL SCIENCES AND ENGINEERING, 27th, 2023, Florianópolis. Proceedings [...] Rio de Janeiro: ABCM, 2023. v. 1. p. 1-8.https://hdl.handle.net/11449/25363410.26678/ABCM.COBEM2023.COB2023-0310157791846593546868075538006078030000-0001-7406-86980000-0001-6430-3746enginfo:eu-repo/semantics/openAccessreponame:Repositório Institucional da UNESPinstname:Universidade Estadual Paulista (UNESP)instacron:UNESP2024-07-04T20:06:26Zoai:repositorio.unesp.br:11449/253634Repositório InstitucionalPUBhttp://repositorio.unesp.br/oai/requestrepositoriounesp@unesp.bropendoar:29462024-07-04T20:06:26Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)false
dc.title.none.fl_str_mv Physics-informed neural networks for solving elasticity problems
title Physics-informed neural networks for solving elasticity problems
spellingShingle Physics-informed neural networks for solving elasticity problems
Almeida, Estevão Fuzaro [UNESP]
Solid mechanics
Physics-informed neural networks
Stress distribution
Data-free modeling
title_short Physics-informed neural networks for solving elasticity problems
title_full Physics-informed neural networks for solving elasticity problems
title_fullStr Physics-informed neural networks for solving elasticity problems
title_full_unstemmed Physics-informed neural networks for solving elasticity problems
title_sort Physics-informed neural networks for solving elasticity problems
author Almeida, Estevão Fuzaro [UNESP]
author_facet Almeida, Estevão Fuzaro [UNESP]
Silva, Samuel da [UNESP]
Cunha Júnior, Americo
author_role author
author2 Silva, Samuel da [UNESP]
Cunha Júnior, Americo
author2_role author
author
dc.contributor.none.fl_str_mv São Paulo Research Foundation (FAPESP) Grant No 2022/16156-9
dc.contributor.author.fl_str_mv Almeida, Estevão Fuzaro [UNESP]
Silva, Samuel da [UNESP]
Cunha Júnior, Americo
dc.subject.por.fl_str_mv Solid mechanics
Physics-informed neural networks
Stress distribution
Data-free modeling
topic Solid mechanics
Physics-informed neural networks
Stress distribution
Data-free modeling
description The first author would like to thank São Paulo Research Foundation (FAPESP) for providing financial support under grant number 2022/16156-9.
publishDate 2023
dc.date.none.fl_str_mv 2023-12-08
2024-03-11T19:09:18Z
2024-03-11T19:09:18Z
dc.type.status.fl_str_mv info:eu-repo/semantics/publishedVersion
dc.type.driver.fl_str_mv info:eu-repo/semantics/conferenceObject
format conferenceObject
status_str publishedVersion
dc.identifier.uri.fl_str_mv ALMEIDA, E. F.; SILVA, S.; CUNHA JR, A. Physics-informed neural networks for solving elasticity problems. In: BRAZILIAN CONGRESS OF THERMAL SCIENCES AND ENGINEERING, 27th, 2023, Florianópolis. Proceedings [...] Rio de Janeiro: ABCM, 2023. v. 1. p. 1-8.
https://hdl.handle.net/11449/253634
10.26678/ABCM.COBEM2023.COB2023-0310
1577918465935468
6807553800607803
0000-0001-7406-8698
0000-0001-6430-3746
identifier_str_mv ALMEIDA, E. F.; SILVA, S.; CUNHA JR, A. Physics-informed neural networks for solving elasticity problems. In: BRAZILIAN CONGRESS OF THERMAL SCIENCES AND ENGINEERING, 27th, 2023, Florianópolis. Proceedings [...] Rio de Janeiro: ABCM, 2023. v. 1. p. 1-8.
10.26678/ABCM.COBEM2023.COB2023-0310
1577918465935468
6807553800607803
0000-0001-7406-8698
0000-0001-6430-3746
url https://hdl.handle.net/11449/253634
dc.language.iso.fl_str_mv eng
language eng
dc.rights.driver.fl_str_mv info:eu-repo/semantics/openAccess
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Associação Brasileira de Engenharia e Ciências Mecânicas (ABCM)
publisher.none.fl_str_mv Associação Brasileira de Engenharia e Ciências Mecânicas (ABCM)
dc.source.none.fl_str_mv reponame:Repositório Institucional da UNESP
instname:Universidade Estadual Paulista (UNESP)
instacron:UNESP
instname_str Universidade Estadual Paulista (UNESP)
instacron_str UNESP
institution UNESP
reponame_str Repositório Institucional da UNESP
collection Repositório Institucional da UNESP
repository.name.fl_str_mv Repositório Institucional da UNESP - Universidade Estadual Paulista (UNESP)
repository.mail.fl_str_mv repositoriounesp@unesp.br
_version_ 1834484524719800320

Similar Items