基于反馈更新策略训练的深度卷积网络在桥梁状态监测中的裂缝识别

J. Hua, Tong Tong, Jing Lin, Fei Gao, Han Zhang
{"title":"基于反馈更新策略训练的深度卷积网络在桥梁状态监测中的裂缝识别","authors":"J. Hua, Tong Tong, Jing Lin, Fei Gao, Han Zhang","doi":"10.21595/mrcm.2021.22032","DOIUrl":null,"url":null,"abstract":"Orthotropic steel bridge decks and steel box girders are key structures of long-span bridges. Fatigue cracks often occur in these structures due to coupled factors of initial material flaws and dynamic vehicle loads, which drives the need for automating crack identification for bridge condition monitoring. With the use of unmanned aerial vehicle (UAV), the acquirement of bridge surface pictures is convenient, which facilitates the development of vision-based bridge condition monitoring. In this study, a combination of convolutional neural network (CNN) with fully convolutional network (FCN) is designed for crack identification and bridge condition monitoring. Firstly, 120 images are cropped into small patches to create a basic dataset. Subsequently, CNN and FCN models are trained for patch classification and pixel-level crack segmentation, respectively. In patch classification, some non-crack patches that contain complicated disturbance information, such as handwriting and shadow, are often mistakenly identified as cracks by directly using the CNN model. To address this problem, we propose a feedback-update strategy for CNN training, in which mistaken classification results of non-crack data are selected to update the training set to generate a new CNN model. By that analogy, several different CNN models are obtained and the accuracy of patch classification could be improved by using all models together. Finally, 80 test images are processed by the feedback-update CNN models and FCN model with a sliding window technique to generate crack identification results. Intersection over union (IoU) is calculated as an index to quantificationally evaluate the accuracy of the proposed method.","PeriodicalId":285529,"journal":{"name":"Maintenance, Reliability and Condition Monitoring","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-08-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"2","resultStr":"{\"title\":\"Crack identification for bridge condition monitoring using deep convolutional networks trained with a feedback-update strategy\",\"authors\":\"J. Hua, Tong Tong, Jing Lin, Fei Gao, Han Zhang\",\"doi\":\"10.21595/mrcm.2021.22032\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Orthotropic steel bridge decks and steel box girders are key structures of long-span bridges. Fatigue cracks often occur in these structures due to coupled factors of initial material flaws and dynamic vehicle loads, which drives the need for automating crack identification for bridge condition monitoring. With the use of unmanned aerial vehicle (UAV), the acquirement of bridge surface pictures is convenient, which facilitates the development of vision-based bridge condition monitoring. In this study, a combination of convolutional neural network (CNN) with fully convolutional network (FCN) is designed for crack identification and bridge condition monitoring. Firstly, 120 images are cropped into small patches to create a basic dataset. Subsequently, CNN and FCN models are trained for patch classification and pixel-level crack segmentation, respectively. In patch classification, some non-crack patches that contain complicated disturbance information, such as handwriting and shadow, are often mistakenly identified as cracks by directly using the CNN model. To address this problem, we propose a feedback-update strategy for CNN training, in which mistaken classification results of non-crack data are selected to update the training set to generate a new CNN model. By that analogy, several different CNN models are obtained and the accuracy of patch classification could be improved by using all models together. Finally, 80 test images are processed by the feedback-update CNN models and FCN model with a sliding window technique to generate crack identification results. Intersection over union (IoU) is calculated as an index to quantificationally evaluate the accuracy of the proposed method.\",\"PeriodicalId\":285529,\"journal\":{\"name\":\"Maintenance, Reliability and Condition Monitoring\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-08-06\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"2\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Maintenance, Reliability and Condition Monitoring\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.21595/mrcm.2021.22032\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Maintenance, Reliability and Condition Monitoring","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.21595/mrcm.2021.22032","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 2

摘要

正交各向异性钢桥面和钢箱梁是大跨度桥梁的关键结构。由于初始材料缺陷和车辆动力载荷的耦合作用,这些结构经常出现疲劳裂纹,这就要求对桥梁状态监测中的裂纹进行自动化识别。无人机的使用方便了桥梁表面图像的获取,促进了基于视觉的桥梁状态监测的发展。本研究将卷积神经网络(CNN)与全卷积网络(FCN)相结合,设计用于裂缝识别和桥梁状态监测。首先,将120张图像裁剪成小块,创建基本数据集。随后,分别训练CNN和FCN模型进行patch分类和像素级裂缝分割。在patch分类中,一些包含复杂干扰信息的非裂纹patch,如手写、阴影等,经常被直接使用CNN模型错误地识别为裂纹。为了解决这个问题,我们提出了一种CNN训练的反馈更新策略,即选择非裂纹数据的错误分类结果来更新训练集,生成新的CNN模型。以此类推,可以得到几种不同的CNN模型,所有模型一起使用可以提高patch分类的精度。最后,采用反馈更新CNN模型和滑动窗口技术的FCN模型对80幅测试图像进行处理,得到裂纹识别结果。通过计算交联(Intersection over union, IoU)作为定量评价该方法准确性的指标。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Crack identification for bridge condition monitoring using deep convolutional networks trained with a feedback-update strategy
Orthotropic steel bridge decks and steel box girders are key structures of long-span bridges. Fatigue cracks often occur in these structures due to coupled factors of initial material flaws and dynamic vehicle loads, which drives the need for automating crack identification for bridge condition monitoring. With the use of unmanned aerial vehicle (UAV), the acquirement of bridge surface pictures is convenient, which facilitates the development of vision-based bridge condition monitoring. In this study, a combination of convolutional neural network (CNN) with fully convolutional network (FCN) is designed for crack identification and bridge condition monitoring. Firstly, 120 images are cropped into small patches to create a basic dataset. Subsequently, CNN and FCN models are trained for patch classification and pixel-level crack segmentation, respectively. In patch classification, some non-crack patches that contain complicated disturbance information, such as handwriting and shadow, are often mistakenly identified as cracks by directly using the CNN model. To address this problem, we propose a feedback-update strategy for CNN training, in which mistaken classification results of non-crack data are selected to update the training set to generate a new CNN model. By that analogy, several different CNN models are obtained and the accuracy of patch classification could be improved by using all models together. Finally, 80 test images are processed by the feedback-update CNN models and FCN model with a sliding window technique to generate crack identification results. Intersection over union (IoU) is calculated as an index to quantificationally evaluate the accuracy of the proposed method.
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
自引率
0.00%
发文量
0
×
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:604180095
Book学术官方微信