基于无人机图像和机器学习技术的钢结构表面腐蚀智能识别方法研究
左吉寅 , 周学军 , 王振 , 刘哲 , 孙继祥
建筑钢结构进展 ›› 2026, Vol. 28 ›› Issue (9) : 109 -118.
基于无人机图像和机器学习技术的钢结构表面腐蚀智能识别方法研究
Research on Intelligent Identification Method for Steel Structure Surface Corrosion Based on UAV Images and Machine Learning Technology
随着以机器学习为核心的人工智能技术与无人机(unmanned aerial vehicle,UAV)图像技术不断发展,为高空在役钢结构表面腐蚀的快速识别提供了新的思路。文中利用UAV采集既有钢结构建筑的腐蚀图像并建立数据集;在现有机器学习方法的基础上,提出了一种基于分层注意力的FasterViT与YOLOv8网络结构相结合的机器学习新算法,实现了钢结构表面腐蚀区域的精准定位与腐蚀程度的快速智能识别。该算法识别准确率高于YOLO系列、FasterViT单独使用情况下的准确率,准确率达到92.6%。文中所提方法可为在役钢结构服役性能的量化评估提供技术支撑。
With the development of artificial intelligence technology centered on machine learning and unmanned aerial vehicle (UAV) imaging technology,new approaches are provided for the rapid identification of surface corrosion in high-altitude in-service steel structures.In this paper,UAV imaging technology was used to photograph existing steel structure buildings to obtain corrosion images and establish a dataset,and on the basis of existing machine learning methods,a new machine learning algorithm combining hierarchical-attention-based FasterViT and YOLOv8 network structure was proposed,which enabled the rapid and intelligent identification of corrosion severity and corrosion locations on the surface of steel structures.The recognition accuracy of this method was higher than those of the YOLO series and FasterViT alone,with an accuracy of 92.6%.The proposed method can provide technical support for the quantitative assessment of the service performance of in-service steel structures.
| [1] |
李霄,梁中红,曹廷义.超声波C扫描技术在涉硫设备及管道腐蚀检测中的应用[J].当代化工研究,2021(9):136-137.DOI:10.3969/j.issn.1672-8114.2021.09.063. |
| [2] |
LI Xiao,LIANG Zhonghong,CAO Tingyi.Application of ultrasonic C scanning technology in corrosion detection of sulfur-related equipment and pipeline[J].Modern Chemical Research,2021(9):136-137.DOI:10.3969/j.issn.1672-8114.2021.09.063.(in Chinese) |
| [3] |
乔宁宁.大型钢结构钢板腐蚀的电磁检测方法[J].工业技术创新,2021,8(5):89-93.DOI:10.14103/j.issn.2095-8412.2021.10.016. |
| [4] |
QIAO Ningning.Electromagnetic detection method for steel plate corrosion in large steel structures[J].Industrial Technology Innovation,2021,8(5):89-93.DOI:10.14103/j.issn.2095-8412.2021.10.016.(in Chinese) |
| [5] |
鞠晓臣,梁永奇,赵欣欣,采用声发射技术检测钢桥疲劳裂纹[J].哈尔滨工程大学学报,2023,44(4):649-656.DOI:10.11990/jheu.202202028. |
| [6] |
JU Xiaochen,LIANG Yongqi,ZHAO Xinxin,et al.Fatigue crack detection of steel bridges by the acoustic emission technique[J].Journal of Harbin Engineering University,2023,44(4):649-656.DOI:10.11990/jheu.202202028.(in Chinese) |
| [7] |
逯鹏,赵天淞,王剑,基于计算机视觉的钢结构表面损伤识别与健康监测综述[J].工业建筑,2022,52(10):22-27.DOI:10.13204/j.gyjzG22071401. |
| [8] |
LU Peng,ZHAO Tiansong,WANG Jian,et al.Review on damage identification and health monitoring of steel structures based on computer vision[J].Industrial Construction,2022,52(10):22-27.DOI:10.13204/j.gyjzG22071401.(in Chinese) |
| [9] |
CHEN Q C,WEN X,LU S,et al.Corrosion detection for large steel structure base on UAV integrated with image processing system[C]//Proceedings of 2019 International Conference on Aeronautical Materials and Aerospace Engineering(AMAE 2019).Shanghai:Shanghai Institute of Special Equipment Inspection & Technical Research,2019:6. |
| [10] |
HAN Q H,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.DOI:10.1007/s13349-021-00515-7. |
| [11] |
JIANG S,ZHANG J.Real-time crack assessment using deep neural networks with wall-climbing unmanned aerial system[J].Computer-Aided Civil and Infrastructure Engineering,2020,35(6):549-564.DOI:10.1111/mice.12519. |
| [12] |
JIANG S,ZHANG J,WANG W G,et al.Automatic inspection of bridge bolts using unmanned aerial vision and adaptive scale unification-based deep learning[J].Remote Sensing,2023,15(2):328.DOI:10.3390/rs15020328. |
| [13] |
逯鹏,赵天淞,王剑,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.DOI:10.3724/j.gyjzG23062009. |
| [14] |
LU Peng,ZHAO Tiansong,WANG Jian,et al.A method for detecting surface corrosion degree of steel structures based on computer vision[J].Industrial Construction,2024,54(8):133-139.DOI:10.3724/j.gyjzG23062009.(in Chinese) |
| [15] |
KHAYATAZAD M,DE PUE L,DE WAELE W.Detection of corrosion on steel structures using automated image processing[J].Developments in the Built Environment,2020,3:100022.DOI:10.1016/j.dibe.2020.100022. |
| [16] |
梁礼明,龙鹏威,李俞霖.改进轻量高效FMG-YOLOv8s的钢材表面缺陷检测算法[J].计算机工程与应用,2025,61(3):84-93.DOI:10.3778/j.issn.1002-8331.2406-0358. |
| [17] |
LIANG Liming,LONG Pengwei,LI Yulin.Improved lightweight and efficient FMG-YOLOv8s algorithm for steel surface defect detection[J].Computer Engineering and Applications,2025,61(3):84-93.DOI:10.3778/j.issn.1002-8331.2406-0358.(in Chinese) |
| [18] |
唐永,么学春,王晨,基于无人机图像技术和支持向量机(SVM)的桥梁裂缝自动识别系统[J].公路工程,2024,49(6):49-56.DOI:10.19782/j.cnki.1674-0610.2024.06.008. |
| [19] |
TANG Yong,YAO Xuechun,WANG Chen,et al.Automatic bridge crack detection system based on UAV image technology and support vector machine(SVM)[J].Highway Engineering,2024,49(6):49-56.DOI:10.19782/j.cnki.1674-0610.2024.06.008.(in Chinese) |
| [20] |
王爽.基于无人机摄像的桥梁结构位移检测研究[D].重庆:重庆交通大学,2022. |
| [21] |
WANG Shuang.Research on bridge structure displacement detection of unmanned aerial vehicle camera[D].Chongqing:Chongqing Jiaotong University,2022.(in Chinese) |
| [22] |
GB/T 8923.1—2011 涂覆涂料前钢材表面处理 表面清洁度的目视评定 第1部分:未涂覆过的钢材表面和全面清除原有涂层后的钢材表面的锈蚀等级和处理等级[S]. |
| [23] |
GB/T 8923.1—2011 Preparation of steel substrates before application of paints and related products—Visual assessment of surface cleanliness:Part 1:Rust grades and preparation grades of uncoated steel substrates and of steel substrates after overall removal of previous coatings[S].(in Chinese) |
| [24] |
肖乾浩.基于机器学习理论的机械故障诊断方法综述[J].现代制造工程,2021(7):148-161.DOI:10.16731/j.cnki.1671-3133.2021.07.022. |
| [25] |
XIAO Qianhao.Review on mechanical fault diagnosis methods based on machine learning theories[J].Modern Manufacturing Engineering,2021(7):148-161.DOI:10.16731/j.cnki.1671-3133.2021.07.022.(in Chinese) |
| [26] |
郝善行.基于计算机视觉的钢结构局部腐蚀检测及特征提取[D].哈尔滨:哈尔滨工业大学,2022. |
| [27] |
HAO Shanxing.Local corrosion detection and feature extraction of steel structure based on computer vision[D].Harbin:Harbin Institute of Technology,2022.(in Chinese) |
| [28] |
HATAMIZADEH A,HEINRICH G,YIN H X,et al.FasterViT:Fast vision transformers with hierarchical attention[EB/OL].[2025-02-06].2023:arXiv:2306.06189.https://arxiv.org/abs/2306.06189. |
| [29] |
JOCHER G,GRASS V,TSCHIRNER S K,et al.ADAM10 and ADAM17 promote SARS‐CoV‐2 cell entry and spike protein‐mediated lung cell fusion[J].EMBO Reports,2022,23(6):EMBR202154305(2022).DOI:10.15252/embr.202154305. |
| [30] |
REDMON J,FARHADI A.YOLO9000:Better,faster,stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2017:6517-6525. |
| [31] |
王彦生,曹雪虹,焦良葆,基于改进YOLOv5的电厂人员吸烟检测[J].计算机测量与控制,2023,31(5):48-55.DOI:10.16526/j.cnki.11-4762/tp.2023.05.008. |
| [32] |
WANG Yansheng,CAO Xuehong,JIAO Liangbao,et al.Smoking detection of power plant personnel based on improved YOLOv5[J].Computer Measurement & Control,2023,31(5):48-55.DOI:10.16526/j.cnki.11-4762/tp.2023.05.008.(in Chinese) |
国家自然科学基金(52278507)
山东省重点研发计划(重大科技创新工程)项目(2024CXGC10321)
国家重点研发计划(SQ2020YFF0426523)
/
| 〈 |
|
〉 |