Application of symbolic regression for constitutive modeling of plastic deformation

In numerical process simulations, in-depth knowledge about material behavior during processing in the form of trustworthy material models is crucial. Among the different constitutive models used in the literature one can distinguish a physics-based approach (white-box model), which considers the evo...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Evgeniya Kabliman, Ana Helena Kolody, Johannes Kronsteiner, Michael Kommenda, Gabriel Kronberger
Formato: article
Lenguaje:EN
Publicado: Elsevier 2021
Materias:
Acceso en línea:https://doaj.org/article/b74db3cc9c924642a5f9f34beb989d4e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:b74db3cc9c924642a5f9f34beb989d4e
record_format dspace
spelling oai:doaj.org-article:b74db3cc9c924642a5f9f34beb989d4e2021-12-01T05:06:12ZApplication of symbolic regression for constitutive modeling of plastic deformation2666-496810.1016/j.apples.2021.100052https://doaj.org/article/b74db3cc9c924642a5f9f34beb989d4e2021-06-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2666496821000182https://doaj.org/toc/2666-4968In numerical process simulations, in-depth knowledge about material behavior during processing in the form of trustworthy material models is crucial. Among the different constitutive models used in the literature one can distinguish a physics-based approach (white-box model), which considers the evolution of material internal state variables, such as mean dislocation density, and data-driven models (grey or even black-box). Typically, parameters in physics-based models such as physical constants or material parameters, are interpretable and have a physical meaning. However, even physics-based models often contain calibration coefficients that are fitted to experimental data. In the present work, we investigate the applicability of symbolic regression for (1) predicting calibration coefficients of a physics-based model and (2) for deriving a constitutive model directly from measurement data. Our goal is to find mathematical expressions, which can be integrated into numerical simulation models. For this purpose, we have chosen symbolic regression to derive the constitutive equations based on data from compression testing with varying process parameters. To validate the derived constitutive models, we have implemented them into a FE solver (herein, LS-DYNA®), and calculated the force-displacement curves. The comparison with experiments shows a reasonable agreement for both data-driven and physics-based (with fitted and learned calibration parameters) models.Evgeniya KablimanAna Helena KolodyJohannes KronsteinerMichael KommendaGabriel KronbergerElsevierarticleMaterial constitutive equationsMachine learningSymbolic regressionData-driven modellingPhysics-based modellingFinite element analysisEngineering (General). Civil engineering (General)TA1-2040ENApplications in Engineering Science, Vol 6, Iss , Pp 100052- (2021)
institution DOAJ
collection DOAJ
language EN
topic Material constitutive equations
Machine learning
Symbolic regression
Data-driven modelling
Physics-based modelling
Finite element analysis
Engineering (General). Civil engineering (General)
TA1-2040
spellingShingle Material constitutive equations
Machine learning
Symbolic regression
Data-driven modelling
Physics-based modelling
Finite element analysis
Engineering (General). Civil engineering (General)
TA1-2040
Evgeniya Kabliman
Ana Helena Kolody
Johannes Kronsteiner
Michael Kommenda
Gabriel Kronberger
Application of symbolic regression for constitutive modeling of plastic deformation
description In numerical process simulations, in-depth knowledge about material behavior during processing in the form of trustworthy material models is crucial. Among the different constitutive models used in the literature one can distinguish a physics-based approach (white-box model), which considers the evolution of material internal state variables, such as mean dislocation density, and data-driven models (grey or even black-box). Typically, parameters in physics-based models such as physical constants or material parameters, are interpretable and have a physical meaning. However, even physics-based models often contain calibration coefficients that are fitted to experimental data. In the present work, we investigate the applicability of symbolic regression for (1) predicting calibration coefficients of a physics-based model and (2) for deriving a constitutive model directly from measurement data. Our goal is to find mathematical expressions, which can be integrated into numerical simulation models. For this purpose, we have chosen symbolic regression to derive the constitutive equations based on data from compression testing with varying process parameters. To validate the derived constitutive models, we have implemented them into a FE solver (herein, LS-DYNA®), and calculated the force-displacement curves. The comparison with experiments shows a reasonable agreement for both data-driven and physics-based (with fitted and learned calibration parameters) models.
format article
author Evgeniya Kabliman
Ana Helena Kolody
Johannes Kronsteiner
Michael Kommenda
Gabriel Kronberger
author_facet Evgeniya Kabliman
Ana Helena Kolody
Johannes Kronsteiner
Michael Kommenda
Gabriel Kronberger
author_sort Evgeniya Kabliman
title Application of symbolic regression for constitutive modeling of plastic deformation
title_short Application of symbolic regression for constitutive modeling of plastic deformation
title_full Application of symbolic regression for constitutive modeling of plastic deformation
title_fullStr Application of symbolic regression for constitutive modeling of plastic deformation
title_full_unstemmed Application of symbolic regression for constitutive modeling of plastic deformation
title_sort application of symbolic regression for constitutive modeling of plastic deformation
publisher Elsevier
publishDate 2021
url https://doaj.org/article/b74db3cc9c924642a5f9f34beb989d4e
work_keys_str_mv AT evgeniyakabliman applicationofsymbolicregressionforconstitutivemodelingofplasticdeformation
AT anahelenakolody applicationofsymbolicregressionforconstitutivemodelingofplasticdeformation
AT johanneskronsteiner applicationofsymbolicregressionforconstitutivemodelingofplasticdeformation
AT michaelkommenda applicationofsymbolicregressionforconstitutivemodelingofplasticdeformation
AT gabrielkronberger applicationofsymbolicregressionforconstitutivemodelingofplasticdeformation
_version_ 1718405566700716032