Research on YOLOv 5‑Ganomaly Joint Algorithm for High‑Strength Bolt Detection

Authors

XIE Haibo, School of Civil Engineering , Changsha University of Science & Technology ，Changsha ,Hunan 410144 ,ChinaFollow
ZHU Weijun, School of Civil Engineering , Changsha University of Science & Technology ，Changsha ,Hunan 410144 ,China
ZHANG Bi2, Hunan Central South Bridge Equipment Manufacturing Co ., Ltd.，Huaihua ,Hunan 418000 ,China
ZHANG Dahai, Construction Quality Inspection Center of Hunan Province Co ., Ltd.，Changsha ,Hunan 410000，China

Abstract

High-strength bolt loosening detection of bridges faces problems such as heavy workload，small targets，many anomalies，and difficult collection.Therefore，this paper proposed a semi-supervised deep learning model，which could obtain the bolt loosening detection model even with a small number of negative samples and solve the problem of unbalanced model training samples.The accuracy of the YOLOv 5-CT model for bolt target detection reached 98.33%.By preprocessing bolt data，the reconstruction ability of bolt images by the Ganomaly model was improved.When the hidden space vector value was 100，the model had the highest SAUC and the best discriminant performance.In the model test stage，the threshold of abnormal fraction was set to 0.295，and the accuracy of the calculation model for abnormal loosening detection of high-strength bolts could reach more than 85%.As a result，the automatic identification and detection of bolts were realized.

Publication Date

7-30-2024

DOI

10.14048/j.issn.1671-2579.2024.04.020

First Page

171

Last Page

179

Submission Date

February 2025

Recommended Citation

Haibo, XIE; Weijun, ZHU; Bi2, ZHANG; and Dahai, ZHANG (2024) "Research on YOLOv 5‑Ganomaly Joint Algorithm for High‑Strength Bolt Detection," Journal of China & Foreign Highway: Vol. 44: Iss. 4, Article 20.
DOI: 10.14048/j.issn.1671-2579.2024.04.020
Available at: https://zwgl1980.csust.edu.cn/journal/vol44/iss4/20

Reference

[1]张建平 ,贺淑龙 ,张念来 ,等.矮寨大桥钢桁加劲梁高强度螺栓施工质量控制 [J].桥梁建设 ,2012 ,42(6):103-109.ZHANG Jianping ,HE Shulong ,ZHANG Nianlai ,et al .Construction quality control of high-strength bolts for stiffening steel truss girder of Aizhai Bridge [J].Bridge Construction ,2012 ,42(6):103-109.
[2]杭京 ,杨利斌 ,沈建华 ,等.钢桁架桥预防性养护技术研究[J].中外公路 ,2022 ,42(3):80-84.HANG Jing ,YANG Libin ,SHEN Jianhua ,et al .Research on preventive maintenance of steel truss bridge [J].Journal of China & Foreign Highway ,2022 ,42(3):80-84.
[3]武金 ,屈文忠 ,肖黎 .基于 3/2维谱的螺栓松动非线性检测及定位 [J].振动与冲击 ,2020 ,39(5):157-163.WU Jin ,QU Wenzhong ,XIAO Li .Bolt looseness nonlinearity detection and location based on 3/2-D spectrum [J].Journal of Vibration and Shock ,2020 ,39(5):157-163.
[4]潘勤学 ,邵唱 ,肖定国 ,等.基于形状因子的螺栓紧固力超声检测方法研究 [J].兵工学报 ,2019 ,40(4):880-888.PAN Qinxue ,SHAO Chang ,XIAO Dingguo ,et al .Study of ultrasonic measurement method for bolt fastening force based on shape factor [J].Acta Armamentarii ,2019 ,40(4):880-888.
[5]邵俊华 ,王涛 ,汪正傲 ,等.基于压电阻抗频率变化的螺栓松动检测技术 [J].中国机械工程 ,2019 ,30(12):1395 -1399 ,1408 .SHAO Junhua ,WANG Tao ,WANG Zheng ’ao,et al .Bolt looseness detection using piezoelectric impedance frequency shift method [J].China Mechanical Engineering ,2019 ,30(12):1395 -1399 ,1408 .
[6]蒋田勇 ,方鳞 ,梁仕杰 .基于压电陶瓷的法兰连接中高强度螺栓松动损伤监测试验研究 [J].中外公路 ,2022 ,42(1):95-100.JIANG Tianyong ,FANG Lin ,LIANG Shijie .Experimental research on loose damage monitoring of high-strength bolts in flange connection based on piezoelectric ceramics[J].Journal of China & Foreign Highway ,2022 ,42(1):95-100.
[7]PARK J H ,KIM T H K ,LEE K S ,et al .Novel bolt-loosening detection technique using image processing for bolt joints in steel bridges [C]//The 2015 World Congress on Advances in Structural Engineering and Mechanics .Incheon :ASEM ,2015 :25-29.
[8]HUANG Y H ,LIU L ,YEUNG T W ,et al .Real-time monitoring of clamping force of a bolted joint by use of automatic digital image correlation [J].Optics & Laser Technology ,2009 ,41(4):408-414.
[9]袁明 ,王烁 ,颜东煌 ,等.基于声发射和卷积神经网络的混凝土桥梁损伤预测研究 [J].中外公路 ,2022 ,42(4):69-75.YUAN Ming ,WANG Shuo ,YAN Donghuang ,et al .Study on damage prediction of concrete bridges based on acoustic emission and convolutional neural network [J].Journal of China & Foreign Highway ,2022 ,42(4):69-75.
[10]赵振兵 ,张帅 ,蒋炜 ,等.基于 DBSCAN-FPN 的输电线路螺栓缺销检测方法 [J].中国电力 ,2021 ,54(3):45-54.ZHAO Zhenbing ,ZHANG Shuai ,JIANG Wei ,et al .Detection method for bolts with mission pins on transmission lines based on DBSCAN-FPN [J].Electric Power ,2021 ,54(3):45-54.
[11]罗隆福 ,叶威 ,王健 .基于深度学习的高铁接触网顶紧螺栓的缺陷检测 [J].铁道科学与工程学报 ,2021 ,18(3):605-614.LUO Longfu ,YE Wei ,WANG Jian .Defect detection of the puller bolt in high-speed railway catenary based on deep learning [J].Journal of Railway Science and Engineering ,2021 ,18(3):605-614.
[12]戚银城 ,武学良 ,赵振兵 ,等.嵌入双注意力机制的 Faster R-CNN航拍输电线路螺栓缺陷检测 [J].中国图象图形学报,2021 ,26(11):2594 -2604 .QI Yincheng ,WU Xueliang ,ZHAO Zhenbing ,et al .Bolt defect detection for aerial transmission lines using Faster R-CNN with an embedded dual attention mechanism [J].Journal of Image and Graphics ,2021 ,26(11):2594 -2604 .
[13]宋健，薛松领，李辉，等.螺栓力损失对焊接式索夹疲劳性能的影响 [J].中外公路 ，2023 ,43（5） ：172-176.SONG Jian ，XUE Songling ，LI Hui，et al .Effect of bolt force loss on fatigue performance of welded cable clamp[J].Journal of China & Foreign Highway ,2023，43(5):172-176.[14]李小利 ,曾理 .铁路货车铸件 DR图像的疏松缺陷快速检测[J].铁道科学与工程学报 ,2022 ,19(6):1763 -1773 .LI Xiaoli ,ZENG Li .Rapid detection of porosity defect in DR image of railway freight car casting [J].Journal of Railway Science and Engineering ,2022 ,19(6):1763 -1773 .
[15]王星 ,高峰 ,陈吉 ,等.基于 GAN网络的煤岩图像样本生成方法 [J].煤炭学报 ,2021 ,46(9):3066 -3078 .WANG Xing ,GAO Feng ,CHEN Ji ,et al .Generative adversarial networks based sample generation of coal and rock images [J].Journal of China Coal Society ,2021 ,46(9):3066 -3078 .
[16]孟琭,钟健平 ,李楠 .基于 GAN的医学图像仿真数据集生成算法 [J].东北大学学报 (自然科学版 ),2020 ,41(3):332-336.MENG Lu ,ZHONG Jianping ,LI Nan .Generating algorithm of medical image simulation data sets based on GAN [J].Journal of Northeastern University (Natural Science ),2020 ,41(3):332-336.
[17]陈榆琅 ,高晶敏 ,张科备 ,等.基于生成对抗网络的空间卫星低照度图像增强 [J].中国空间科学技术 ,2021 ,41(3):16-23.CHEN Yulang ,GAO Jingmin ,ZHANG Kebei ,et al .Low-light image enhancement of space satellites based on GAN[J].Chinese Space Science and Technology ,2021 ,41(3):16-23.
[18]AKCAY S ,ATAPOUR-ABARGHOUEI A ,BRECKON T P .GANomaly :Semi-supervised anomaly detection via adversarial training [C]//JAWAHAR C ,LI H ,MORI G ,et al.Asian Conference on Computer Vision .Cham :Springer ,2019 :622-637.
[19]SCHLEGL T ,SEEBÖCK P ,WALDSTEIN S M ,et al .Unsupervised anomaly detection with generative adversarial networks to guide marker discovery [C]//International Conference on Information Processing in Medical Imaging .Cham :Springer ,2017 :146-157.
[20]ZENATI H ,FOO C S ,LECOUAT B ,et al .Efficient GAN-based anomaly detection [EB/OL ].2018 :arXiv :1802 .06222 .
[21]王红雨 ,尹午荣 ,汪梁 ,等.基于 HSV颜色空间的快速边缘提取算法 [J].上海交通大学学报 ,2019 ,53(7):765-772.WANG Hongyu ,YIN Wurong ,WANG Liang ,et al .Fast edge extraction algorithm based on HSV color space [J].Journal of Shanghai JiaoTong University ,2019 ,53(7):765-772.
[22]邵建新 .最小二乘法线性拟合中参数的确定问题 [J].大学物理 ,2003 ,22(1):23-24.SHAO Jianxin .Establishment of parameter in a linearity fitting by method of least squares [J].College Physics ,2003 ,22(1):23-24.