评估 RC 剪力墙的强度和刚度退化:综合图像处理和深度学习方法

IF 4.3 2区 工程技术 Q1 ENGINEERING, CIVIL Earthquake Engineering & Structural Dynamics Pub Date : 2024-04-30 DOI:10.1002/eqe.4134
Xiaodong Ji, Yue Yu, Xiang Gao, Yuncheng Zhuang, Shaohui Zhang
{"title":"评估 RC 剪力墙的强度和刚度退化:综合图像处理和深度学习方法","authors":"Xiaodong Ji,&nbsp;Yue Yu,&nbsp;Xiang Gao,&nbsp;Yuncheng Zhuang,&nbsp;Shaohui Zhang","doi":"10.1002/eqe.4134","DOIUrl":null,"url":null,"abstract":"<p>In the aftermath of an earthquake, damage detection and performance evaluation of structural components are imperative for assessing the residual seismic capacity of a building. In this study, an integrated image processing and deep learning approach was developed to evaluate the degradation in strength and stiffness (i.e., strength reduction and stiffness reduction) of reinforced concrete (RC) shear walls. The approach comprised two main tasks: detecting and localizing visible seismic damage from photographs and evaluating strength and stiffness degradation based on this information. The semantic segmentation network, Damage-Net, was used for damage detection and localization. A novel crack morphological processing layer and a patch feature extraction layer were developed for damage feature extraction and compression. A lightweight deep convolutional neural network named DegradeEval-Net_v2, featuring the upgraded dilated and separable convolution block and multi-layer perception, was developed to link the damage feature with strength and stiffness degradation. A database comprising test data and photographs of 14 RC shear wall specimens with a flexural-dominated behavior mode and high to intermediate ductility was constructed to train and test the DegradeEval-Net_v2 network. The results indicate that DegradeEval-Net_v2 substantially improved the performance assessment accuracy of damaged RC shear walls, with a 35% smaller root mean square error (RMSE) for stiffness degradation evaluation and 75% smaller RMSE for strength degradation evaluation, compared with the provisions specified in JBDPA and FEMA guidelines. Moreover, evaluation results on test sets demonstrate that introducing the damage feature extraction and compression layers effectively preserved local crack information and improved the accuracy with which stiffness reduction was evaluated. In addition, DegradeEval-Net_v2 outperformed ResNet18 and MobileNet V3 in terms of balanced efficiency and accuracy. Interpretability analysis demonstrates that the model learned the distinct contribution patterns of various visible damage indexes to stiffness and strength degradation across different loading levels.</p>","PeriodicalId":11390,"journal":{"name":"Earthquake Engineering & Structural Dynamics","volume":"53 9","pages":"2827-2849"},"PeriodicalIF":4.3000,"publicationDate":"2024-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Evaluation of strength and stiffness degradation of RC shear walls: An integrated image processing and deep learning approach\",\"authors\":\"Xiaodong Ji,&nbsp;Yue Yu,&nbsp;Xiang Gao,&nbsp;Yuncheng Zhuang,&nbsp;Shaohui Zhang\",\"doi\":\"10.1002/eqe.4134\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>In the aftermath of an earthquake, damage detection and performance evaluation of structural components are imperative for assessing the residual seismic capacity of a building. In this study, an integrated image processing and deep learning approach was developed to evaluate the degradation in strength and stiffness (i.e., strength reduction and stiffness reduction) of reinforced concrete (RC) shear walls. The approach comprised two main tasks: detecting and localizing visible seismic damage from photographs and evaluating strength and stiffness degradation based on this information. The semantic segmentation network, Damage-Net, was used for damage detection and localization. A novel crack morphological processing layer and a patch feature extraction layer were developed for damage feature extraction and compression. A lightweight deep convolutional neural network named DegradeEval-Net_v2, featuring the upgraded dilated and separable convolution block and multi-layer perception, was developed to link the damage feature with strength and stiffness degradation. A database comprising test data and photographs of 14 RC shear wall specimens with a flexural-dominated behavior mode and high to intermediate ductility was constructed to train and test the DegradeEval-Net_v2 network. The results indicate that DegradeEval-Net_v2 substantially improved the performance assessment accuracy of damaged RC shear walls, with a 35% smaller root mean square error (RMSE) for stiffness degradation evaluation and 75% smaller RMSE for strength degradation evaluation, compared with the provisions specified in JBDPA and FEMA guidelines. Moreover, evaluation results on test sets demonstrate that introducing the damage feature extraction and compression layers effectively preserved local crack information and improved the accuracy with which stiffness reduction was evaluated. In addition, DegradeEval-Net_v2 outperformed ResNet18 and MobileNet V3 in terms of balanced efficiency and accuracy. Interpretability analysis demonstrates that the model learned the distinct contribution patterns of various visible damage indexes to stiffness and strength degradation across different loading levels.</p>\",\"PeriodicalId\":11390,\"journal\":{\"name\":\"Earthquake Engineering & Structural Dynamics\",\"volume\":\"53 9\",\"pages\":\"2827-2849\"},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2024-04-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Earthquake Engineering & Structural Dynamics\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1002/eqe.4134\",\"RegionNum\":2,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ENGINEERING, CIVIL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Earthquake Engineering & Structural Dynamics","FirstCategoryId":"5","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1002/eqe.4134","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, CIVIL","Score":null,"Total":0}
引用次数: 0

摘要

地震发生后,结构部件的损坏检测和性能评估对于评估建筑物的剩余抗震能力至关重要。本研究开发了一种集成图像处理和深度学习的方法,用于评估钢筋混凝土(RC)剪力墙的强度和刚度退化(即强度降低和刚度降低)。该方法包括两项主要任务:从照片中检测和定位可见的地震破坏,并根据这些信息评估强度和刚度的退化情况。语义分割网络 Damage-Net 用于损伤检测和定位。为提取和压缩损伤特征,开发了一个新颖的裂缝形态学处理层和一个补丁特征提取层。开发了一个名为 DegradeEval-Net_v2 的轻量级深度卷积神经网络,该网络具有升级的扩张和可分离卷积块以及多层感知,可将损伤特征与强度和刚度退化联系起来。为训练和测试 DegradeEval-Net_v2 网络,建立了一个数据库,其中包括 14 个具有弯曲主导行为模式和中高延性的钢筋混凝土剪力墙试件的测试数据和照片。结果表明,与 JBDPA 和 FEMA 指南中的规定相比,DegradeEval-Net_v2 大幅提高了受损钢筋混凝土剪力墙的性能评估准确性,刚度退化评估的均方根误差 (RMSE) 减小了 35%,强度退化评估的均方根误差 (RMSE) 减小了 75%。此外,测试集的评估结果表明,引入损伤特征提取和压缩层可有效保留局部裂缝信息,并提高刚度降低评估的准确性。此外,DegradeEval-Net_v2 在平衡效率和准确性方面优于 ResNet18 和 MobileNet V3。可解释性分析表明,该模型了解了各种可见损伤指标在不同加载水平下对刚度和强度降低的不同贡献模式。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
Evaluation of strength and stiffness degradation of RC shear walls: An integrated image processing and deep learning approach

In the aftermath of an earthquake, damage detection and performance evaluation of structural components are imperative for assessing the residual seismic capacity of a building. In this study, an integrated image processing and deep learning approach was developed to evaluate the degradation in strength and stiffness (i.e., strength reduction and stiffness reduction) of reinforced concrete (RC) shear walls. The approach comprised two main tasks: detecting and localizing visible seismic damage from photographs and evaluating strength and stiffness degradation based on this information. The semantic segmentation network, Damage-Net, was used for damage detection and localization. A novel crack morphological processing layer and a patch feature extraction layer were developed for damage feature extraction and compression. A lightweight deep convolutional neural network named DegradeEval-Net_v2, featuring the upgraded dilated and separable convolution block and multi-layer perception, was developed to link the damage feature with strength and stiffness degradation. A database comprising test data and photographs of 14 RC shear wall specimens with a flexural-dominated behavior mode and high to intermediate ductility was constructed to train and test the DegradeEval-Net_v2 network. The results indicate that DegradeEval-Net_v2 substantially improved the performance assessment accuracy of damaged RC shear walls, with a 35% smaller root mean square error (RMSE) for stiffness degradation evaluation and 75% smaller RMSE for strength degradation evaluation, compared with the provisions specified in JBDPA and FEMA guidelines. Moreover, evaluation results on test sets demonstrate that introducing the damage feature extraction and compression layers effectively preserved local crack information and improved the accuracy with which stiffness reduction was evaluated. In addition, DegradeEval-Net_v2 outperformed ResNet18 and MobileNet V3 in terms of balanced efficiency and accuracy. Interpretability analysis demonstrates that the model learned the distinct contribution patterns of various visible damage indexes to stiffness and strength degradation across different loading levels.

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
Earthquake Engineering & Structural Dynamics
Earthquake Engineering & Structural Dynamics 工程技术-工程:地质
CiteScore
7.20
自引率
13.30%
发文量
180
审稿时长
4.8 months
期刊介绍: Earthquake Engineering and Structural Dynamics provides a forum for the publication of papers on several aspects of engineering related to earthquakes. The problems in this field, and their solutions, are international in character and require knowledge of several traditional disciplines; the Journal will reflect this. Papers that may be relevant but do not emphasize earthquake engineering and related structural dynamics are not suitable for the Journal. Relevant topics include the following: ground motions for analysis and design geotechnical earthquake engineering probabilistic and deterministic methods of dynamic analysis experimental behaviour of structures seismic protective systems system identification risk assessment seismic code requirements methods for earthquake-resistant design and retrofit of structures.
期刊最新文献
Issue information Issue information SSI-induced seismic earth pressures on an integral abutment bridge model: Experimental measurements versus numerical simulations and code provisions Estimation of inelastic displacement ratio spectrum for existing RC structures via displacement response spectrum Linear equivalence for motion amplification devices in earthquake engineering
×
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