反向传播神经网络在精制板模型损伤检测中的应用研究

IF 0.6 4区 工程技术 Q4 MECHANICS
Teng Wenxiang, Qian Cheng, Yan Leilei, Shen Gang, Liu Pengyu, He Jipeng, Wang Cheng
{"title":"反向传播神经网络在精制板模型损伤检测中的应用研究","authors":"Teng Wenxiang,&nbsp;Qian Cheng,&nbsp;Yan Leilei,&nbsp;Shen Gang,&nbsp;Liu Pengyu,&nbsp;He Jipeng,&nbsp;Wang Cheng","doi":"10.1134/S0025654424603392","DOIUrl":null,"url":null,"abstract":"<p>Artificial intelligence has been widely used in engineering. In this paper, we propose to combine the backpropagation neural network (BPNN) with the refined plate model based on Carrera Unified Formula (CUF) to advance the development of damage detection. The prediction model is built by utilizing the error back propagation function of the neural network. In addition, MATLAB uses Taylor’s interpolation algorithm and lower degrees of freedom yet achieves the same accuracy as ANSYS, and the improved plate model accurately reproduces the mechanical properties of the metal plate. A database is then built based on the mechanical model to detect the location of damaged elements and node displacements. The nodal displacements were used as inputs while the locations of damaged elements were used as training outputs for the neural network. The effectiveness of the proposed method was verified through various damage scenarios. The results show that the method can accurately predict individual damage locations based on node displacements alone. The neural network combined with the plate model achieved a detection accuracy of 91% with a regression coefficient of 0.95.</p>","PeriodicalId":697,"journal":{"name":"Mechanics of Solids","volume":"59 3","pages":"1672 - 1688"},"PeriodicalIF":0.6000,"publicationDate":"2024-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Research on Application of Backpropagation Neural Network in Damage Detection of the Refined Plate Model\",\"authors\":\"Teng Wenxiang,&nbsp;Qian Cheng,&nbsp;Yan Leilei,&nbsp;Shen Gang,&nbsp;Liu Pengyu,&nbsp;He Jipeng,&nbsp;Wang Cheng\",\"doi\":\"10.1134/S0025654424603392\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Artificial intelligence has been widely used in engineering. In this paper, we propose to combine the backpropagation neural network (BPNN) with the refined plate model based on Carrera Unified Formula (CUF) to advance the development of damage detection. The prediction model is built by utilizing the error back propagation function of the neural network. In addition, MATLAB uses Taylor’s interpolation algorithm and lower degrees of freedom yet achieves the same accuracy as ANSYS, and the improved plate model accurately reproduces the mechanical properties of the metal plate. A database is then built based on the mechanical model to detect the location of damaged elements and node displacements. The nodal displacements were used as inputs while the locations of damaged elements were used as training outputs for the neural network. The effectiveness of the proposed method was verified through various damage scenarios. The results show that the method can accurately predict individual damage locations based on node displacements alone. The neural network combined with the plate model achieved a detection accuracy of 91% with a regression coefficient of 0.95.</p>\",\"PeriodicalId\":697,\"journal\":{\"name\":\"Mechanics of Solids\",\"volume\":\"59 3\",\"pages\":\"1672 - 1688\"},\"PeriodicalIF\":0.6000,\"publicationDate\":\"2024-11-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Mechanics of Solids\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://link.springer.com/article/10.1134/S0025654424603392\",\"RegionNum\":4,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q4\",\"JCRName\":\"MECHANICS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Mechanics of Solids","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1134/S0025654424603392","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"MECHANICS","Score":null,"Total":0}
引用次数: 0

摘要

人工智能已广泛应用于工程领域。本文提出将反向传播神经网络(BPNN)与基于卡雷拉统一公式(CUF)的精炼板模型相结合,以推进损伤检测的发展。预测模型是利用神经网络的误差反向传播功能建立的。此外,MATLAB 使用泰勒插值算法和较低的自由度,却能达到与 ANSYS 相同的精度,改进后的板模型准确地再现了金属板的机械性能。然后根据力学模型建立数据库,以检测受损元素的位置和节点位移。节点位移用作输入,而受损元素的位置则用作神经网络的训练输出。通过各种损坏情况验证了所提方法的有效性。结果表明,仅根据节点位移,该方法就能准确预测单个损坏位置。神经网络与板模型相结合的检测准确率达到 91%,回归系数为 0.95。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

Research on Application of Backpropagation Neural Network in Damage Detection of the Refined Plate Model

Research on Application of Backpropagation Neural Network in Damage Detection of the Refined Plate Model

Artificial intelligence has been widely used in engineering. In this paper, we propose to combine the backpropagation neural network (BPNN) with the refined plate model based on Carrera Unified Formula (CUF) to advance the development of damage detection. The prediction model is built by utilizing the error back propagation function of the neural network. In addition, MATLAB uses Taylor’s interpolation algorithm and lower degrees of freedom yet achieves the same accuracy as ANSYS, and the improved plate model accurately reproduces the mechanical properties of the metal plate. A database is then built based on the mechanical model to detect the location of damaged elements and node displacements. The nodal displacements were used as inputs while the locations of damaged elements were used as training outputs for the neural network. The effectiveness of the proposed method was verified through various damage scenarios. The results show that the method can accurately predict individual damage locations based on node displacements alone. The neural network combined with the plate model achieved a detection accuracy of 91% with a regression coefficient of 0.95.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Mechanics of Solids
Mechanics of Solids 医学-力学
CiteScore
1.20
自引率
42.90%
发文量
112
审稿时长
6-12 weeks
期刊介绍: Mechanics of Solids publishes articles in the general areas of dynamics of particles and rigid bodies and the mechanics of deformable solids. The journal has a goal of being a comprehensive record of up-to-the-minute research results. The journal coverage is vibration of discrete and continuous systems; stability and optimization of mechanical systems; automatic control theory; dynamics of multiple body systems; elasticity, viscoelasticity and plasticity; mechanics of composite materials; theory of structures and structural stability; wave propagation and impact of solids; fracture mechanics; micromechanics of solids; mechanics of granular and geological materials; structure-fluid interaction; mechanical behavior of materials; gyroscopes and navigation systems; and nanomechanics. Most of the articles in the journal are theoretical and analytical. They present a blend of basic mechanics theory with analysis of contemporary technological problems.
×
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