[an error occurred while processing this directive]
 
       首 页  |  期刊介绍  |  编委会  |  投稿指南  |  期刊订阅  |  广告合作  |  留言板  |  联系我们 |  English
现代隧道技术 2022, Vol. 59 Issue (6) :24-34    DOI:
绿色智能建造 最新目录 | 下期目录 | 过刊浏览 | 高级检索 << [an error occurred while processing this directive] | [an error occurred while processing this directive] >>
基于神经网络与边缘修正的隧道衬砌裂缝识别
(1.上海同岩土木工程科技股份有限公司,上海 200092;2.上海地下基础设施安全检测与养护装备工程技术研究中心,上海 200092;3.济南轨道交通集团有限公司,济南 250014;4.山东省智慧轨道交通信息化与装备重点实验室,济南 250014)
Crack Identification of Tunnel Lining Based on Neural Network and Edge Correction
(1. Shanghai Tongyan Civil Engineering Science & Technology Co., Ltd., Shanghai 200092; 2. Shanghai Research Center for Underground Infrastructure Safety Inspection and Maintenance Equipment Engineering Technology, Shanghai 200092; 3. Jinan Rail Transit Group Co., Ltd., Jinan 250014; 4. Shandong Provincial Key Laboratory of Intelligent Rail Transit Informatization and Equipment, Jinan 250014)
Download: PDF (5263KB)   HTML (1KB)   Export: BibTeX or EndNote (RIS)      Supporting Info
摘要 针对隧道衬砌图像背景复杂的问题,提出基于卷积神经网络的图像快速筛查与裂缝区域定位,并针对裂缝多存在网状形态以及毛刺形分叉区域的特点,提出基于二叉树与曲线拟合的隧道衬砌裂缝识别方法。首先通过网格化区域划分与卷积神经网络进行区域类别判断,实现海量图片快速筛查与裂缝区域大致定位。对检出的裂缝区域通过Zhang-Suen细化算法获得裂缝原始骨架。根据裂缝点间的关联信息构建裂缝骨架二叉树,采用最大距离化的节点筛查规则修正裂缝骨架,并根据修正结果进行裂缝边缘修正,保留裂缝网状形态的同时,实现裂缝短小分叉和结节等不合理区域的剔除。最后基于最小二乘法曲线拟合修正裂缝轨迹,结合二叉树节点信息对裂缝轨迹断裂部分进行连接从而获取完整轨迹。试验结果表明,提出的方法可准确筛除98.73%不包含裂缝的衬砌图像;采用基于二叉树的边缘修正提高了裂缝的分割精度,并通过轨迹修正确保了裂缝轨迹的完整性。
Service
把本文推荐给朋友
加入我的书架
加入引用管理器
Email Alert
RSS
作者相关文章
陈莹莹 1
2 刘新根 1
2 黄永亮 3
4 李明东 1
关键词隧道衬砌   裂缝识别   卷积神经网络   二叉树   曲线拟合   Zhang-Suen算法     
Abstract: To address the problem of complex imaging background of tunnel lining, this paper proposes a fast image screening and crack region localization based on convolutional neural network, as well as a tunnel lining crack identification method based on binary tree and curve fitting, in view of the feature that cracks mostly exist in reticular form and burr-shaped bifurcation areas. First, the rapid screening of massive amounts of pictures and locating of approximate position of crack areas are conducted by gridding the area segmentation and using convolutional neural networks to judge the category of the areas. Then the original crack skeleton is obtained by the Zhang-Suen refinement algorithm for the detected crack areas. The skeleton binary tree of the cracks is constructed based on the correlation information between crack points and the crack skeleton is corrected by using the node screening rule of maximum distance. Based on the correction results, the crack edges are further corrected to retain the crack mesh pattern while realizing the elimination of unreasonable areas such as areas with short bifurcations and joints Finally, the crack trajectory is corrected based on least-square curve fitting and the broken parts of the crack trajectory are connected based on the binary tree node information to obtain the complete trajectory. The test results show that the proposed method can accurately screen out 98.73% of the lining images that do not contain cracks; the use of binary tree-based edge correction has improved the segmentation accuracy of the cracks and ensured the integrity of the crack trajectory by trajectory correction.
KeywordsTunnel lining,   Crack identification,   Convolutional neural network,   Binary tree,   Curve fitting,   ZhangSuen algorithm     
基金资助:山东省重点研发计划(2019JZZY010428)
作者简介: 陈莹莹(1990-),女,硕士,工程师,主要从事隧道检测装备研发与机器视觉方面的工作,E-mail: joy543@live.com. 通讯作者:刘新根(1981-),男,硕士,高级工程师,主要从事隧道检测装备研发与数值分析软件开发方面的工作,E-mail: xuezhongfei2000@163.com.
引用本文:   
陈莹莹 1, 2 刘新根 1, 2 黄永亮 3等 .基于神经网络与边缘修正的隧道衬砌裂缝识别[J]  现代隧道技术, 2022,V59(6): 24-34
CHEN Yingying1, 2 LIU Xingen1, 2 HUANG Yongliang3 etc .Crack Identification of Tunnel Lining Based on Neural Network and Edge Correction[J]  MODERN TUNNELLING TECHNOLOGY, 2022,V59(6): 24-34
链接本文:  
http://www.xdsdjs.com/CN/      或     http://www.xdsdjs.com/CN/Y2022/V59/I6/24
 
没有本文参考文献
[1] 刘文建 1 张国才 2 吕建兵 3 刘 锋 3 吴维俊 3 陈贡发 3.排水孔结晶淤堵图像的语义分割识别技术及APP研究[J]. 现代隧道技术, 2022,59(4): 100-107
[2] 秦尚友 1 陈佳耀 2 张东明 2 杨同军 1 黄宏伟 2 赵 帅 2.基于深度学习的隧道工作面岩石结构自动化判别[J]. 现代隧道技术, 2021,58(4): 29-36
[3] 李鹏举 1 郑方坤 2 吕建兵 3 吴维俊 3 刘 锋 3 陈贡发 3.基于大数据迁移学习的灰岩地区排水孔淤堵自动识别技术[J]. 现代隧道技术, 2021,58(4): 37-47
[4] 江 桁 1 刘学增 2 朱合华 1.基于隧道快速检测车数据的公路隧道衬砌开裂识别模型研究[J]. 现代隧道技术, 2020,57(5): 61-65
[5] 谭 文.隧道衬砌防脱空预警监控新技术研究与应用[J]. 现代隧道技术, 2020,57(3): 199-203
[6] 刘 明 胡 谦 王志喜 缴鑫璐.油气管道隧道衬砌台车设计、制造与应用[J]. 现代隧道技术, 2020,57(3): 204-208
[7] 刘 劼 1 董 武 2 龚成明 3.衬砌缺陷防治技术在运营铁路隧道中的应用研究[J]. 现代隧道技术, 2019,56(6): 157-161
[8] 崔光耀 1 孙凌云 2 左奎现 1 王明年 3 荆鸿飞 4.纤维混凝土隧道衬砌力学性能研究综述[J]. 现代隧道技术, 2019,56(3): 1-7
[9] 王亚琼 1 张 雷 1,2 王志丰 1 孙铁军 3.在役隧道衬砌渗漏水引排技术[J]. 现代隧道技术, 2019,56(2): 24-29
[10] 张姣龙1 柳献1 袁勇1 Herbert MANG1, 2.考虑接头真实性能的盾构隧道衬砌结构计算模型与混合分析方法[J]. 现代隧道技术, 2018,55(5): 72-78
[11] 龚渠洪.浅谈铁路隧道衬砌常见施工质量问题及预防措施[J]. 现代隧道技术, 2018,55(2): 208-211
[12] 李德武 1, 2 杨进京 1.双层模筑混凝土隧道衬砌受力检算的叠合梁模型及其应用[J]. 现代隧道技术, 2016,53(5): 108-113
[13] 张文新.既有隧道衬砌结构在引水洞爆破施工中的安全性分析[J]. 现代隧道技术, 2016,53(4): 154-158
[14] 王建宇.对隧道衬砌结构计算问题的思考[J]. 现代隧道技术, 2014,51(2): 1-4
[15] 牛泽林1, 2, 张松涛2, 吴焕通2, 代亚雷2, 韩伟辉2.基于荷载-结构模型的隧道衬砌结构可靠性设计与研究 [J]. 现代隧道技术, 2014,51(2): 90-94
Copyright 2010 by 现代隧道技术