Computer Vision-based Detection Method for Steel Bridge Bolt-looseness

被引：0

作者：

Lao W. ^{[1
]}

Xu W. ^{[1
]}

Zhang Q. ^{[1
]}

Luo C. ^{[1
]}

Cui C. ^{[1
]}

Chen J. ^{[2
]}

机构：

[1] School of Civil Engineering, Southwest Jiaotong University, Chengdu

[2] Poly Changda Engineering Co., Ltd., Guangzhou

来源：

Tiedao Xuebao/Journal of the China Railway Society | 2024年 / 46卷 / 01期

关键词：

computer vision; keypoint detection; looseness detection; object detection; steel bridge bolts;

D O I：

10.3969/j.issn.1001-8360.2024.01.010

中图分类号：

学科分类号：

摘要：

In order to improve the intelligence of bolt-looseness detection, a computer vision-based detection method was proposed for steel bridge bolt-looseness. Firstly, bolt keypoint detection model was established based on deep learning theory to annotate the collected bolt images and to build datasets. Then the object detection model YoloV5 and the key-point detection model were trained separately to detect the bolt keypoints from top to bottom using the trained models. The location of bolt center points was determined according to the keypoints, and the perspective transformation matrix was solved according to the relative position of the center points, which was then used to reproject the keypoints. Finally, bolt-looseness was detected according to the position changes of keypoints. The results show that the trained YoloV5 model and keypoint detection model can accurately detect the keypoints of the bolts. The detection accuracy of the key-points is affected by the image acquisition conditions and is more sensitive to angles. Fitting the least-squares solution of the perspective transformation matrix using all center points can improve the accuracy of image geometry correction. The detection error of bolt-looseness under different image acquisition conditions ranges from 0% to 9. 6%, with a false detection rate of 2. 7%, indicating that the proposed method, with high accuracy and stability, has great practical value and broad engineering application prospects. © 2024 Science Press. All rights reserved.

引用

页码：91 / 102

页数：11

共 33 条

[1]

TAO Xiaoyan, SHEN Jiahua, SHI Zhiqiang, Development History and Prospect of High Strength Bolt Connection of Steel Bridge in China, Railway Engineering, 57, 9, pp. 1-4, (2017)

[2]

MIAO R S, SHEN R L, ZHANG S H, Et al., A Review of Bolt Tightening Force Measurement and Loosening Detection, Sensors, 20, 11, (2020)

[3]

YIN T, WANG X Y, ZHU H P., A Probabilistic Approach for the Detection of Bolt Loosening in Periodically Supported Structures Endowed with Bolted Flange Joints, Mechanical Systems and Signal Processing, 128, pp. 588-616, (2019)

[4]

SHAO Junhua, WANG Tao, WANG Zheng' ao, Et al., Bolt Looseness Detection Using Piezoelectric Impedance Frequency Shift Method [J], China Mechanical Engineering, 30, 12, pp. 1395-1399, (2019)

[5]

WU Guannan, XU Chao, Bolt Looseness Detection Based on Chaos Ultrasonic Excitation, Journal of Vibration and Shock, 37, 9, pp. 208-213, (2018)

[6]

HU Wenbo, QIU Shi, XU Xinyue, Et al., Ultrasonic Detection and Classification for Internal Defect of Rail Based on Deep Learning[J], Journal of the China Railway Society, 43, 4, pp. 108-116, (2021)

[7]

LI Ziyi, RAO Zhiqiang, CHANG Hui, Et al., Research on Automatic Segmentation Algorithm of Tunnel Cracks Based on Generative Adversarial Network, Journal of the China Railway Society, 45, 5, pp. 136-142, (2023)

[8]

ZHU Jinsong, LI Huan, WANG Shifang, Defect Recognition for Steel Bridge Based on Convolutional Neural Network and Transfer Learning [J], Journal of Chang ' an University (Natural Science Edition), 41, 3, pp. 52-63, (2021)

[9]

PENG Z Y, WANG C, MA Z J, Et al., A Multifeature Hierarchical Locating Algorithm for Hexagon Nut of Railway Fasteners, IEEE Transactions on Instrumentation and Measurement, 69, 3, pp. 693-699, (2020)

[10]

PAN Y, MA Y L, DONG Y Q, Et al., A Vision-based Monitoring Method for the Looseness of High-strength Bolt, IEEE Transactions on Instrumentation and Measurement, 70, pp. 1-14, (2021)

← 1 2 3 4 →