View in EDS PDF Full Text

PRS-YOLO: Visual Inspection Model for Steel Defects in Spanning Frames.

Saved in:
Bibliographic Details
Title: PRS-YOLO: Visual Inspection Model for Steel Defects in Spanning Frames.
Authors: Zhang, Jian1 454028501@qq.com, Xu, Linyan2 84183432@qq.com, Zou, Zunqiang2 1203066454@qq.com, Lv, Chunhui2 58720945@qq.com, Fan, Xinguang2 fanxg@outlook.co, Li, Dongdong2 274143492@qq.com, Li, Peng2 515706319@qq.com, Zhao, Congcong2 295882420@qq.com, Li, Zhenling2 359824481@qq.com
Source: IAENG International Journal of Computer Science. Mar2026, Vol. 53 Issue 3, p922-932. 11p.
Subjects: Automatic target recognition, Object recognition (Computer vision), Inspection & review, Structural components, Feature extraction, Fault diagnosis, Degradation of steel, Construction industry safety
Abstract: A spanning frame is a kind of temporary structure widely used in many kinds of construction and engineering fields, which is mainly used to support and cross various obstacles, and can be used to ensure the construction safety and smooth progress of the important components. Therefore, it is also very important to troubleshoot the hidden problems of spanning frames. We designed a set of fault and defect detection algorithms based on the target detection method specifically for spanning frames, and designed a target detection model with a more efficient flow of feature information, which successfully realized the detection of faults on spanning frames. Tested in the homemade spanning frame data, in which the detection accuracy of mAP50 is 5.3% higher than that of YOLOv8s, and there is an effective increase in all other evaluation indexes, successfully realizing the detection of spanning frame defects. [ABSTRACT FROM AUTHOR]
Copyright of IAENG International Journal of Computer Science is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Engineering Source
Description
Abstract:A spanning frame is a kind of temporary structure widely used in many kinds of construction and engineering fields, which is mainly used to support and cross various obstacles, and can be used to ensure the construction safety and smooth progress of the important components. Therefore, it is also very important to troubleshoot the hidden problems of spanning frames. We designed a set of fault and defect detection algorithms based on the target detection method specifically for spanning frames, and designed a target detection model with a more efficient flow of feature information, which successfully realized the detection of faults on spanning frames. Tested in the homemade spanning frame data, in which the detection accuracy of mAP50 is 5.3% higher than that of YOLOv8s, and there is an effective increase in all other evaluation indexes, successfully realizing the detection of spanning frame defects. [ABSTRACT FROM AUTHOR]
ISSN:1819656X