Engineering deep learning methods on automatic detection of damage in infrastructure due to extreme events

计算机科学 分割 稳健性(进化) 人工智能 深度学习 残余物 残差神经网络 模式识别(心理学) 管道(软件) 剥落 领域(数学) 数据挖掘 机器学习
作者
Bai, Yongsheng,Zha, Bing,Sezen, Halil,Yilmaz, Alper
出处
期刊:Structural Health Monitoring-an International Journal [SAGE Publishing]
卷期号:: 147592172210836-147592172210836
标识
DOI:10.1177/14759217221083649
摘要

This paper presents a few comprehensive experimental studies for automated Structural Damage Detection (SDD) in extreme events using deep learning methods for processing 2D images. In the first study, a 152-layer Residual network (ResNet) is utilized to classify multiple classes in eight SDD tasks, which include identification of scene levels, damage levels, material types, etc. The proposed ResNet achieved high accuracy for each task while the positions of the damage are not identifiable. In the second study, the existing ResNet and a segmentation network (U-Net) are combined into a new pipeline, cascaded networks, for categorizing and locating structural damage. The results show that the accuracy of damage detection is significantly improved compared to only using a segmentation network. In the third and fourth studies, end-to-end networks are developed and tested as a new solution to directly detect cracks and spalling in the image collections of recent large earthquakes. One of the proposed networks can achieve an accuracy above 67.6% for all tested images at various scales and resolutions, and shows its robustness for these human-free detection tasks. As a preliminary field study, we applied the proposed method to detect damage in a concrete structure that was tested to study its progressive collapse performance. The experiments indicate that these solutions for automatic detection of structural damage using deep learning methods are feasible and promising. The training datasets and codes will be made available for the public upon the publication of this paper.

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
AiQi发布了新的文献求助10
4秒前
我就想看看文献完成签到 ,获得积分10
7秒前
是大亨啊完成签到,获得积分10
12秒前
xu完成签到 ,获得积分10
12秒前
qianci2009完成签到,获得积分10
14秒前
林好人完成签到,获得积分10
19秒前
牛牛要当院士喽完成签到,获得积分10
19秒前
20秒前
恋暖发布了新的文献求助10
24秒前
牛牛要当院士喽完成签到,获得积分10
25秒前
Ding-Ding完成签到,获得积分10
28秒前
我和你完成签到 ,获得积分10
36秒前
NexusExplorer应助恋暖采纳,获得10
42秒前
月儿完成签到 ,获得积分10
46秒前
孔刚完成签到 ,获得积分10
49秒前
淞淞于我完成签到 ,获得积分10
50秒前
百宝完成签到,获得积分10
51秒前
陆上飞完成签到,获得积分10
1分钟前
旺大财完成签到 ,获得积分10
1分钟前
李大宝完成签到 ,获得积分10
1分钟前
三脸茫然完成签到 ,获得积分10
1分钟前
coolplex完成签到 ,获得积分10
1分钟前
1分钟前
红豆杉发布了新的文献求助20
1分钟前
cdercder应助科研通管家采纳,获得10
1分钟前
cdercder应助科研通管家采纳,获得10
1分钟前
科研通AI2S应助科研通管家采纳,获得10
1分钟前
润润润完成签到 ,获得积分10
1分钟前
刘丰完成签到 ,获得积分10
1分钟前
HY完成签到 ,获得积分10
2分钟前
曾泳钧完成签到,获得积分10
2分钟前
秋思冬念完成签到 ,获得积分10
2分钟前
叮叮当当完成签到,获得积分10
2分钟前
褚浩然完成签到,获得积分10
2分钟前
yuna_yqc完成签到 ,获得积分10
2分钟前
红豆杉完成签到,获得积分10
2分钟前
沉默的小耳朵完成签到 ,获得积分10
2分钟前
巫巫巫巫巫完成签到 ,获得积分0
2分钟前
ommphey完成签到 ,获得积分10
2分钟前
瞿霞完成签到 ,获得积分10
2分钟前
高分求助中
Introduction to Strong Mixing Conditions Volumes 1-3 500
Tip60 complex regulates eggshell formation and oviposition in the white-backed planthopper, providing effective targets for pest control 400
Optical and electric properties of monocrystalline synthetic diamond irradiated by neutrons 320
共融服務學習指南 300
Essentials of Pharmacoeconomics: Health Economics and Outcomes Research 3rd Edition. by Karen Rascati 300
Peking Blues // Liao San 300
Political Ideologies Their Origins and Impact 13 edition 240
热门求助领域 (近24小时)
化学 材料科学 医学 生物 工程类 有机化学 物理 生物化学 纳米技术 计算机科学 化学工程 内科学 复合材料 物理化学 电极 遗传学 量子力学 基因 冶金 催化作用
热门帖子
关注 科研通微信公众号,转发送积分 3800967
求助须知:如何正确求助?哪些是违规求助? 3346537
关于积分的说明 10329541
捐赠科研通 3063048
什么是DOI,文献DOI怎么找? 1681330
邀请新用户注册赠送积分活动 807474
科研通“疑难数据库(出版商)”最低求助积分说明 763721