A Study on Crack Depth Measurement in Steel Structures Using Image-Based Intensity Differences

Author:

Jung Ju-Yeong1ORCID,Yoon Hyuk-Jin2ORCID,Cho Hyun-Woo3

Affiliation:

1. Korea Railroad Research Institute, Uiwang-si 16105, Republic of Korea

2. Korea Railroad Research Institute, University of Science and Technology, Uiwang-si 16105, Republic of Korea

3. University of Science and Technology, Uiwang-si 16105, Republic of Korea

Abstract

This paper seeks to propose an image-based noncontact testing method in crack depth measurement. To this end, it predicted the crack depth using the intensity values of cracks and verified its validity. To analyze the intensity values of cracks, eight stainless steel specimens with an increase in crack depths ranging from 0 to 17.5 mm at an average of 2.5 mm were fabricated, and a contrast index was attached to the center of the crack of the specimens painted with black matte spray for accurate analysis. Through various experiments, it was found that the intensity values of the cracks which decrease with the depth of the cracks were inductively formulated, and the average error was about 15% when the crack depth predicted by the empirical equation was compared with the actual crack depth. In addition, the validation of the intensity reduction equation obtained by the inductive method was verified, and it was confirmed that the crack depth can be predicted by the intensity value of the crack.

Funder

Korea Railroad Research Institute

Publisher

Hindawi Limited

Subject

Civil and Structural Engineering

Cited by 4 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. PMENet: a parallel UNet based on the fusion of multiple attention mechanisms for road crack segmentation;Signal, Image and Video Processing;2024-05-07

2. A Semantic Segmentation Approach for Road Defect Detection and Quantification;2022 the 5th International Conference on Machine Vision and Applications (ICMVA);2022-02-18

3. Determination of Geometric Parameters of Cracks in Concrete by Image Processing;Advances in Civil Engineering;2019-10-30

4. Image Processing-Based Recognition of Wall Defects Using Machine Learning Approaches and Steerable Filters;Computational Intelligence and Neuroscience;2018-11-15

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3