版权说明 操作指南
首页 > 成果 > 详情

Interpretability Analysis of Convolutional Neural Networks for Crack Detection

认领
导出
Link by DOI
反馈
分享
QQ微信 微博
成果类型:
期刊论文
作者:
Wu, Jie;He, Yongjin;Xu, Chengyu;Jia, Xiaoping;Huang, Yule;...
通讯作者:
Huang, SP;Chen, QR
作者机构:
[Huang, Chuyue; Wu, Jie] Wuhan Polytech Univ, Sch Civil Engn & Architecture, Wuhan 430023, Peoples R China.
[Huang, Yule; Huang, Shiping; He, Yongjin; Eslamlou, Armin Dadras; Huang, SP] South China Univ Technol, Sch Civil Engn & Transportat, Guangzhou 510640, Peoples R China.
[Xu, Chengyu; Jia, Xiaoping] China Railway 17th Bur Grp Guangzhou Co Ltd, Guangzhou 510799, Peoples R China.
[Chen, Qianru] South China Normal Univ, Sch Elect & Informat Engn, Foshan 528225, Peoples R China.
通讯机构:
[Chen, QR ; Huang, SP ] S
South China Univ Technol, Sch Civil Engn & Transportat, Guangzhou 510640, Peoples R China.
South China Normal Univ, Sch Elect & Informat Engn, Foshan 528225, Peoples R China.
语种:
英文
关键词:
structural health monitoring;crack detection;interpretability analysis;convolutional neural network
期刊:
Buildings
ISSN:
2075-5309
年:
2023
卷:
13
期:
12
页码:
3095-
基金类别:
Conceptualization, S.H.; methodology, S.H.; software, Y.H. (Yongjin He); validation, C.X. and X.J.; data curation, Y.H. (Yongjin He), Y.H. (Yule Huang) and C.H.; writing—original draft preparation, Y.H. (Yongjin He); writing—review and editing, J.W., A.D.E., S.H. and Q.C.; supervision, S.H.; funding acquisition, J.W. and A.D.E. All authors have read and agreed to the published version of the manuscript. This work is supported by the Hubei Provincial Department of Education Program (No. Q20221606), the Department of Housing and Urban-Rural Development of Hubei Province (Urban and rural construction and development-202001), the Scientific research project of Wuhan Polytechnic University Grant 2021Y047, the Fundamental Research Funds for the Central Universities (2023ZYGXZR089), the Science and Technology Planning Project of Guangdong Province (Foreign Experts Program of the Department of Science and Technology of Guangdong Province, China), and the Special Construction Fund of the Faculty of Engineering (No. 46201503).
机构署名:
本校为第一机构
院系归属:
土木工程与建筑学院
摘要:
Crack detection is an important task in bridge health monitoring, and related detection methods have gradually shifted from traditional manual methods to intelligent approaches with convolutional neural networks (CNNs) in recent years. Due to the opaque process of training and operating CNNs, if the learned features for identifying cracks in the network are not evaluated, it may lead to safety risks. In this study, to evaluate the recognition basis of different crack detection networks; several crack detection CNNs are trained using the same training conditions. Afterwards, several crack image...

反馈

验证码:
看不清楚,换一个
确定
取消

成果认领

标题:
用户 作者 通讯作者
请选择
请选择
确定
取消

提示

该栏目需要登录且有访问权限才可以访问

如果您有访问权限,请直接 登录访问

如果您没有访问权限,请联系管理员申请开通

管理员联系邮箱:yun@hnwdkj.com