Use of machine learning in determining the parameters of viscoplastic models

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21220%2F25%3A00376594" target="_blank" >RIV/68407700:21220/25:00376594 - isvavai.cz</a>

Výsledek na webu

<a href="https://doi.org/10.1108/EC-02-2024-0166" target="_blank" >https://doi.org/10.1108/EC-02-2024-0166</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1108/EC-02-2024-0166" target="_blank" >10.1108/EC-02-2024-0166</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Use of machine learning in determining the parameters of viscoplastic models

Popis výsledku v původním jazyce

Purpose The constitutive models determine the mechanical response to the defined loading based on model parameters. In this paper, the inverse problem is researched, i.e. the identification of the model parameters based on the loading and responses of the material. The conventional methods for determining the parameters of constitutive models often demand significant computational time or extensive model knowledge for manual calibration. The aim of this paper is to introduce an alternative method, based on artificial neural networks, for determining the parameters of a viscoplastic model. Design/methodology/approach An artificial neural network was proposed to determine nine material parameters of a viscoplastic model using data from three half-life hysteresis loops. The proposed network was used to determine the material parameters from uniaxial low-cycle fatigue experimental data of an aluminium alloy obtained at elevated temperatures and three different mechanical strain rates. Findings A reasonable correlation between experimental and numerical data was achieved using the determined material parameters. Originality/value This paper fulfils a need to research alternative methods of identifying material parameters.

Název v anglickém jazyce

Use of machine learning in determining the parameters of viscoplastic models

Popis výsledku anglicky

Purpose The constitutive models determine the mechanical response to the defined loading based on model parameters. In this paper, the inverse problem is researched, i.e. the identification of the model parameters based on the loading and responses of the material. The conventional methods for determining the parameters of constitutive models often demand significant computational time or extensive model knowledge for manual calibration. The aim of this paper is to introduce an alternative method, based on artificial neural networks, for determining the parameters of a viscoplastic model. Design/methodology/approach An artificial neural network was proposed to determine nine material parameters of a viscoplastic model using data from three half-life hysteresis loops. The proposed network was used to determine the material parameters from uniaxial low-cycle fatigue experimental data of an aluminium alloy obtained at elevated temperatures and three different mechanical strain rates. Findings A reasonable correlation between experimental and numerical data was achieved using the determined material parameters. Originality/value This paper fulfils a need to research alternative methods of identifying material parameters.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

20302 - Applied mechanics

Projekt

<a href="/cs/project/GA21-06645S" target="_blank" >GA21-06645S: Výzkum životnosti strojních součástí při víceosém teplotně-mechanickém zatěžování s proměnnou amplitudou</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Engineering Computations

ISSN

0264-4401

e-ISSN

1758-7077

Svazek periodika

42

Číslo periodika v rámci svazku

6

Stát vydavatele periodika

GB - Spojené království Velké Británie a Severního Irska

Počet stran výsledku

15

Strana od-do

1927-1941

Kód UT WoS článku

001275338500001

EID výsledku v databázi Scopus

2-s2.0-85199360412