A crack identification scheme based on neural network surrogate model and XFEM

IF 2.6 3区 物理与天体物理 Q2 PHYSICS, MULTIDISCIPLINARY Physica Scripta Pub Date : 2024-09-15 DOI:10.1088/1402-4896/ad7706
Yudong Zhong, Xue Zeng, Junjian Hou, Ruolan Wang, Liangwen Wang, Dengfeng Zhao, Wenbin He and Yinan Zheng
{"title":"A crack identification scheme based on neural network surrogate model and XFEM","authors":"Yudong Zhong, Xue Zeng, Junjian Hou, Ruolan Wang, Liangwen Wang, Dengfeng Zhao, Wenbin He and Yinan Zheng","doi":"10.1088/1402-4896/ad7706","DOIUrl":null,"url":null,"abstract":"Crack detection and identification is of great significance to the safety issues of engineering structures. In this paper, an intelligent crack identification scheme based on extended finite element and neural network surrogate model is proposed to realize the accurate identification of crack parameters. The method firstly employs extended finite element forward analysis to obtain the displacement data of measurement points on geometric models with different crack lengths, and inputs them as sample data to train the agent model, establishes a neural network-based inverse analysis model for crack identification, and automatically updates the threshold and weight of the neural network by using the Gray Wolf optimization algorithm to finally compute the globally optimal results. In the screening of the surrogate model, this paper verifies the advantages of the neural network surrogate model in data fitting and crack information extraction by comparing and analyzing the characteristics of neural network, support vector machine and other surrogate models, and optimizing the neural network surrogate model by adopting the Gray Wolf optimization algorithm. Finally, several numerical examples of different types of cracks are given to verify the validity of the proposed method, and the results show that the proposed method can accurately invert the geometric information of cracks.","PeriodicalId":20067,"journal":{"name":"Physica Scripta","volume":"41 1","pages":""},"PeriodicalIF":2.6000,"publicationDate":"2024-09-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Physica Scripta","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1088/1402-4896/ad7706","RegionNum":3,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"PHYSICS, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

Abstract

Crack detection and identification is of great significance to the safety issues of engineering structures. In this paper, an intelligent crack identification scheme based on extended finite element and neural network surrogate model is proposed to realize the accurate identification of crack parameters. The method firstly employs extended finite element forward analysis to obtain the displacement data of measurement points on geometric models with different crack lengths, and inputs them as sample data to train the agent model, establishes a neural network-based inverse analysis model for crack identification, and automatically updates the threshold and weight of the neural network by using the Gray Wolf optimization algorithm to finally compute the globally optimal results. In the screening of the surrogate model, this paper verifies the advantages of the neural network surrogate model in data fitting and crack information extraction by comparing and analyzing the characteristics of neural network, support vector machine and other surrogate models, and optimizing the neural network surrogate model by adopting the Gray Wolf optimization algorithm. Finally, several numerical examples of different types of cracks are given to verify the validity of the proposed method, and the results show that the proposed method can accurately invert the geometric information of cracks.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于神经网络代用模型和 XFEM 的裂纹识别方案
裂缝检测与识别对工程结构的安全问题具有重要意义。本文提出了一种基于扩展有限元和神经网络代理模型的智能裂缝识别方案,以实现裂缝参数的精确识别。该方法首先采用扩展有限元正演分析法获取不同裂缝长度几何模型上测点的位移数据,并将其作为样本数据输入代型模型训练,建立基于神经网络的裂缝识别逆分析模型,利用灰狼优化算法自动更新神经网络的阈值和权值,最终计算出全局最优结果。在代用模型的筛选方面,本文通过对比分析神经网络、支持向量机和其他代用模型的特点,验证了神经网络代用模型在数据拟合和裂纹信息提取方面的优势,并采用灰狼优化算法对神经网络代用模型进行了优化。最后,给出了几个不同类型裂纹的数值实例来验证所提方法的有效性,结果表明所提方法能准确反演裂纹的几何信息。
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 去求助
来源期刊
Physica Scripta
Physica Scripta 物理-物理:综合
CiteScore
3.70
自引率
3.40%
发文量
782
审稿时长
4.5 months
期刊介绍: Physica Scripta is an international journal for original research in any branch of experimental and theoretical physics. Articles will be considered in any of the following topics, and interdisciplinary topics involving physics are also welcomed: -Atomic, molecular and optical physics- Plasma physics- Condensed matter physics- Mathematical physics- Astrophysics- High energy physics- Nuclear physics- Nonlinear physics. The journal aims to increase the visibility and accessibility of research to the wider physical sciences community. Articles on topics of broad interest are encouraged and submissions in more specialist fields should endeavour to include reference to the wider context of their research in the introduction.
期刊最新文献
Psychometric Properties of Scores on the Mental Distress Response Scale among First-Generation College Students: Implications for Retention. Exceptional anisotropic superhydrophobicity of sword-lily striated leaf surface and soft lithographic biomimicking using polystyrene replica Improving bidirectional controlled remote preparation of arbitrary number of qudits in noisy environment A study on the synthesis of superheavy element Mc (Z = 115) using lead, bismuth and actinide targets Comparative study of structural, opto-electronic properties of Cs2TiX6-based single halide double perovskite solar cells: computational and experimental approach
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1