Use of machine learning in determining the parameters of viscoplastic models

IF 1.5 4区 工程技术 Q3 COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS
Jiří Halamka, Michal Bartošák
{"title":"Use of machine learning in determining the parameters of viscoplastic models","authors":"Jiří Halamka, Michal Bartošák","doi":"10.1108/ec-02-2024-0166","DOIUrl":null,"url":null,"abstract":"<h3>Purpose</h3>\n<p>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.</p><!--/ Abstract__block -->\n<h3>Design/methodology/approach</h3>\n<p>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.</p><!--/ Abstract__block -->\n<h3>Findings</h3>\n<p>A reasonable correlation between experimental and numerical data was achieved using the determined material parameters.</p><!--/ Abstract__block -->\n<h3>Originality/value</h3>\n<p>This paper fulfils a need to research alternative methods of identifying material parameters.</p><!--/ Abstract__block -->","PeriodicalId":50522,"journal":{"name":"Engineering Computations","volume":null,"pages":null},"PeriodicalIF":1.5000,"publicationDate":"2024-07-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Engineering Computations","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1108/ec-02-2024-0166","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"COMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
引用次数: 0

Abstract

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.

利用机器学习确定粘性模型参数
目的构成模型根据模型参数确定对确定加载的机械响应。本文研究的是逆问题,即根据加载和材料响应确定模型参数。确定构成模型参数的传统方法通常需要大量的计算时间或丰富的模型知识来进行手动校准。本文旨在介绍一种基于人工神经网络的替代方法,用于确定粘塑性模型的参数。设计/方法/途径利用三个半衰期滞后环的数据,提出了一种人工神经网络,用于确定粘塑性模型的九个材料参数。根据铝合金在高温和三种不同机械应变速率下获得的单轴低循环疲劳实验数据,利用提出的网络确定材料参数。研究结果利用确定的材料参数实现了实验数据和数值数据之间的合理相关性。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Engineering Computations
Engineering Computations 工程技术-工程:综合
CiteScore
3.40
自引率
6.20%
发文量
61
审稿时长
5 months
期刊介绍: The journal presents its readers with broad coverage across all branches of engineering and science of the latest development and application of new solution algorithms, innovative numerical methods and/or solution techniques directed at the utilization of computational methods in engineering analysis, engineering design and practice. For more information visit: http://www.emeraldgrouppublishing.com/ec.htm
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信