基于机器视觉的钢结构工程运维关键技术研究现状

陈飞圻; 薛江; 逯鹏; 王剑; 丁代伟

doi:10.3724/j.gyjzG25031702

基于机器视觉的钢结构工程运维关键技术研究现状

doi: 10.3724/j.gyjzG25031702

陈飞圻¹,
薛江¹,
逯鹏^2,3,,
王剑^1,,
丁代伟⁴

1. 天津城建大学, 天津 300384;
2. 中冶检测认证有限公司, 北京 100088;
3. 中冶建筑研究总院有限公司, 北京 100088;
4. 中国市政工程华北设计研究总院有限公司, 天津 300074

详细信息

作者简介:
陈飞圻，硕士研究生，主要从事钢结构损伤智能化检测与评价方面的研究。

通讯作者:
逯鹏，博士，正高级工程师，lupeng201501@126.com

王剑，博士，副教授，avonlea@163.com

计量
- 文章访问数: 54
- HTML全文浏览量: 10
- PDF下载量: 4
- 被引次数: 0
出版历程
- 收稿日期: 2025-03-17
- 网络出版日期: 2025-09-12

Advances in Key Technologies for Steel Structure Operation and Maintenance Based on Machine Vision

CHEN Feiqi¹,
XUE Jiang¹,
LU Peng^{2,3
,},
WANG Jian^1
,,
DING Daiwei⁴

1. Tianjin Chengjian University, Tianjin 300384, China;
2. Inspection and Certification Co., Ltd., MCC, Beijing 100088, China;
3. Central Research Institute of Building and Construction Co., Ltd., MCC Group, Beijing 100088, China;
4. North China Municipal Engineering Design & Research Institute Co., Ltd., Tianjin 300074, China

摘要

摘要: 系统梳理了机器视觉在螺栓松动与缺失检测、焊缝缺陷识别、局部变形监测与锈蚀位置及程度评估等方面的研究进展。针对传统方法依赖手工特征、环境适应性差的问题，深度学习与三维重建技术实现了特征自动提取、多尺度检测与空间形态量化，显著提升了检测的准确性与智能化水平。为应对复杂背景干扰和小目标漏检，研究中引入了注意力机制、特征金字塔、多模态数据融合与半监督迁移学习等方法，优化了模型性能与泛化能力。然而，现有技术仍面临数据集多样性不足、算法鲁棒性和实时部署能力受限等挑战。未来发展方向包括：强化多模态协同感知与三维重构融合、构建持续学习与自适应模型、实现云端实时分析与边缘轻量化部署，并推进智能检测与数字孪生体系的深度结合，推动钢结构运维检测向全自动化、智能化、系统化转型。
- 钢结构 /
- 结构健康检测 /
- 损伤检测 /
- 自动化检测系统 /
- 机器视觉
Abstract: This paper systematically reviews advancements in bolt loosening and loss detection， weld defect identification， local deformation monitoring， and corrosion localization and severity assessment. To address the limitations of traditional manual-feature-based methods—such as poor environmental adaptability—deep learning and 3D reconstruction techniques have been employed to enable automatic feature extraction， multi-scale detection， and spatial deformation quantification， greatly enhancing detection accuracy and intelligence. To overcome challenges such as complex background interference and small-target omission， researchers have introduced attention mechanisms， feature pyramid networks， multimodal data fusion， and semi-supervised transfer learning to improve model robustness and generalization. Nevertheless， current technologies still face challenges including insufficient dataset diversity， limited algorithm robustness， and difficulties in real-time deployment. Future development directions will include strengthening multimodal collaborative sensing and 3D reconstruction integration， building continuously adaptive learning models， enabling real-time cloud-edge collaborative analysis， and advancing intelligent inspection systems integrated with digital twin frameworks. These advancements will drive the maintenance of steel structures towards full automation， intelligence， and systematization.
- steel structures /
- structural health monitoring /
- damage detection /
- automated detection systems /
- machine vision

HTML全文

参考文献(51)

[1]	周红波，高文杰，黄誉. 钢结构事故案例统计分析［J］. 钢结构，2008，23（6）:28-31.
[2]	CHA Y J，YOU K，CHOI W. Vision-based detection of loosened bolts using the Hough transform and support vector machines［J］. Automation in Construction，2016，71:181-188.
[3]	NGUYEN T C，HUYNH T C，RYU J Y，et al. Bolt-loosening identification of bolt connections by vision image-based technique［C］// Nondestructive Characterization and Monitoring of Advanced Materials，Aerospace，and Civil Infrastructure 2016. Bellingham:SPIE，2016:227-243.
[4]	ZHAO X，ZHANG Y，WANG N. Bolt loosening angle detection technology using deep learning［J］. Structural Control and Health Monitoring，2019，26（1），e2292.
[5]	LAO W，CUI C，ZHANG D，et al. Computer vision‐based autonomous method for quantitative detection of loose bolts in bolted connections of steel structures［J］. Structural Control and Health Monitoring，2023，30（1），8817058.
[6]	周明涛，张永敬. 基于3D点云和深度学习的动车组螺栓松动智能检测研究［J］. 智慧轨道交通，2022，59（6 ）:62-66.
[7]	赵欣欣，钱胜胜，刘晓光. 基于卷积神经网络的铁路桥梁高强螺栓缺失图像识别方法［J］. 中国铁道科学，2018，39（4）:56-62.
[8]	卓德兵. 基于计算机听觉与视觉技术的钢桁架螺栓连接损伤检测研究［D］. 重庆:重庆大学，2021.
[9]	张洪，朱志伟，胡天宇，等. 基于改进YOLOv5s的桥梁螺栓缺陷识别方法［J］. 吉林大学学报（工学版），2024，54（3）:749-760.
[10]	LUO P，WANG B，WANG H，et al. An ultrasmall bolt defect detection method for transmission line inspection［J］. IEEE Transactions on Instrumentation and Measurement，2023，72:1-12.
[11]	崔闯，罗纯坤，邱师津，等. 基于数据深度增强的钢桥螺栓脱落智能检测方法研究［J］. 桥梁建设，2024，54（2）:39-47.
[12]	王域辰，冯海龙，刘伯奇. 基于YOLO算法的高速铁路客运车站钢结构雨棚螺栓缺失检测系统［J］. 铁道学报，2023，45（12）:1-10.
[13]	LIU B，ZHANG X，GAO Z，et al. Weld defect images classification with vgg16-based neural network［C］// International Forum on Digital TV and Wireless Multimedia Communications. Singapore:Springer Singapore，2017:215-223.
[14]	MA G，YU L，YUAN H，et al. A vision-based method for lap weld defects monitoring of galvanized steel sheets using convolutional neural network［J］. Journal of Manufacturing Processes，2021，64:130-139.
[15]	CHEN Y，WANG J，WANG G. Intelligent welding defect detection model on improved r-cnn［J］. IETE Journal of Research，2023，69（12）:9235-9244.
[16]	JI C，WANG H，LI H. Defects detection in weld joints based on visual attention and deep learning［J］. NDT& E International，2023，133，102764.
[17]	WANG J，MU C，MU S，et al. Welding seam detection and location:deep learning network-based approach［J］. International Journal of Pressure Vessels and Piping，2023，202，104893.
[18]	JI W，LUO Z，LUO K，et al. Computer vision-based surface defect identification method for weld images［J］. Materials Letters，2024，325，136972.
[19]	KUMAR D D，FANG C，ZHENG Y，et al. Semi-supervised transfer learning-based automatic weld defect detection and visual inspection［J］. Engineering Structures，2023，292，116580.
[20]	GUO W，LIU K，QU H. Welding defect detection of X-ray images based on Faster R-CNN model［J］. Journal of Beijing University of Posts and Telecommunications，2019，42（6）:20-29.
[21]	ROCA B F，DHIERRO P J，RIBES L F，et al. Development of an ultrasonic weld inspection system based on image processing and neural networks［J］. Nondestructive Testing and Evaluation，2017，32（7）:678-692.
[22]	BUONGIORNO D，PRUNELLA M，GROSSI S，et al. Inline defective laser weld identification by processing thermal image sequences with machine and deep learning techniques［J］. Applied Sciences，2022，12（12），6455.
[23]	HAN Y，FAN J，YANG X. A structured light vision sensor for on-line weld bead measurement and weld quality inspection［J］. International Journal of Advanced Manufacturing Technology，2019，102（9）:2055-2065.
[24]	赵亚波，王智. 基于三维激光点云的钢结构变形分析［J］. 测绘通报，2021，（5）:155-158.
[25]	LIU Y F，LIU X G，FAN J S，et al. Refined safety assessment of steel grid structures with crooked tubular members［J］. Automation in Construction，2019，99:249-264.
[26]	诸宏博，谢忠，傅林峰. 三维激光扫描技术在钢结构检测技术中的应用研究［J］. 建筑结构，2023，53（增刊2）:1739-1743.
[27]	WEI X C，FAN J S，LIU Y F，et al. Automated inspection and monitoring of member deformation in grid structures［J］. Computer-Aided Civil and Infrastructure Engineering，2022，37（10）:1277-1297.
[28]	XU M N，SUN L M，LIU Y F，et al. Member separation and deformation recognition of spatial grid structures in-service［J］. Engineering Structures，2024，304，117642.
[29]	WANG J T，LIU Y F，LIU X G，et al. Photogrammetry-based bending monitoring and load identification of steel truss structures［J］. Advances in Structural Engineering，2023，26（13）:2543-2561.
[30]	LYDON D，LYDON M，TAYLOR S，et al. Development and field testing of a vision-based displacement system using a low cost wireless action camera［J］. Mechanical Systems and Signal Processing，2019，121:343-358.
[31]	KROMANIS R，KRIPAKARAN P. A multiple camera position approach for accurate displacement measurement using computer vision［J］. Journal of Civil Structural Health Monitoring，2021，11（3）:661-678.
[32]	HAGIWARA T，SHIMAMOTO Y，SUZUKI T. Non-contact detection of degradation of in-service steel sheet piles due to buckling phenomena by using digital image analysis with Hough transform［J］. Frontiers in Built Environment，2022，8，948232.
[33]	KHAYATAZAD M，DE P L，DE W W. Detection of corrosion on steel structures using automated image processing［J］. Developments in the Built Environment，2020，3，100022.
[34]	VOROBEL R，IVASENKO I，BEREHULYAK O，et al. Segmentation of rust defects on painted steel surfaces by intelligent image analysis［J］. Automation in Construction，2021，123，103515.
[35]	FONDEVIK S K，STAHL A，TRANSETH A A，et al. Image segmentation of corrosion damages in industrial inspections［C］// 2020 IEEE 32nd International Conference on Tools with Artificial Intelligence（ICTAI）. Los Alamitos:IEEE Computer Society，2020:787-792.
[36]	TIAN Z，ZHANG G，LIAO Y，et al. Corrosion identification of fittings based on computer vision［C］// 2019 International Conference on Artificial Intelligence and Advanced Manufacturing（AIAM）. New York:IEEE，2019:592-597.
[37]	PAN F. Corrosion detection method of substation aboveground steel structure based on deep learning［C］// 2022 7th Asia Conference on Power and Electrical Engineering（ACPEE）. New York:IEEE，2022:2234-2238.
[38]	HUANG I F，CHEN P H. Automated steel bridge coating rust defect recognition method based on U-net fully convolutional networks［C］// 2020 IEEE 2nd International Conference on Architecture，Construction，Environment and Hydraulics（ICACEH）. New York:IEEE，2020:18-21.
[39]	CHEN Q，WEN X，LU S，et al. Corrosion detection for large steel structure base on uav integrated with image processing system［C］// IOP Conference Series:Materials Science and Engineering. Bristol:IOP Publishing，2019，608（1），012020.
[40]	HAN Q，ZHAO N，XU J. Recognition and location of steel structure surface corrosion based on unmanned aerial vehicle images［J］. Journal of Civil Structural Health Monitoring，2021，11（5）:1375-1392.
[41]	NASH W，ZHENG L，BIRBILIS N. Deep learning corrosion detection with confidence［J］. NPG Materials Degradation，2022，6（1），26.
[42]	KATSAMENIS I，PROTOPAPADAKIS E，DOULAMIS A，et al. Pixel-level corrosion detection on metal constructions by fusion of deep learning semantic and contour segmentation［C］// International Symposium on Visual Computing. Cham:Springer International Publishing，2020:160-169.
[43]	KHAYATAZAD M，HONHON M D W W. Detection of corrosion on steel structures using an artificial neural network［J］. Structure and Infrastructure Engineering，2023，19（12）:1860-1871.
[44]	DAS A，DORAFSHAN S，KAABOUCH N. Autonomous image-based corrosion detection in steel structures using deep learning［J］. Sensors，2024，24（11），3630.
[45]	HATHOUT I，CALLERY K，HATHOUT T，et al. Digital image expert system for corrosion analysis of steel transmission structures［C］// 2017 IEEE Power& Energy Society General Meeting. New York:IEEE，2017:1-5.
[46]	逯鹏，赵天淞，王剑，等. 基于计算机视觉的钢结构表面锈蚀程度检测方法［J］. 工业建筑，2024，54（8）:133-139.
[47]	WANG Y，SHEN X，WU K，et al. Corrosion grade recognition for weathering steel plate based on a convolutional neural network［J］. Measurement Science and Technology，2022，33（9），095014.
[48]	KATSAMENIS I，DOULAMIS N，DOULAMIS A，et al. Simultaneous precise localization and classification of metal rust defects for robotic-driven maintenance and prefabrication using residual attention U-Net［J］. Automation in Construction，2022，137，104182.
[49]	RAHMAN A，WU Z Y，KALFARISI R. Semantic deep learning integrated with RGB feature-based rule optimization for facility surface corrosion detection and evaluation［J］. Journal of Computing in Civil Engineering，2021，35（6），04021018.
[50]	ZHOU Q，DING S，FENG Y，et al. Corrosion inspection and evaluation of crane metal structure based on UAV vision［J］. Signal，Image and Video Processing，2022，16（6）:1701-1709.
[51]	AMELI Z，NESHELI S J，LANDIS E N. Deep learning-based steel bridge corrosion segmentation and condition rating using Mask RCNN and YOLOv8［J］. Infrastructures，2023，9（1），3.