Research on strip surface defect detection based on improved YOLOv5 algorithm

Author:

Lv Shuaishuai12,Tao Chuanzhen2ORCID,Hao Zhuangzhuang2,Ni Hongjun23,Hou Zhengjie2ORCID,Li Xiaoyuan2,Gu Hai3,Shi Weidong12,Chen Linfei2

Affiliation:

1. School of Information Science and Technology, Nantong University, Nantong, China

2. School of Mechanical Engineering, Nantong University, Nantong, China

3. Institute of Intelligent Manufacturing, Nantong Institute of Technology, Nantong, China

Abstract

In the production process of hot rolled strip, there will inevitably be defects such as iron scale, slag inclusion and scratch on the surface, and there is no effective identification method for these defects. Therefore, based on the improved YOLOv5s algorithm, this article proposes an improved YOLOv5s-GCB model by introducing the coordinate attention module, improving the feature fusion structure and lightening the feature extraction backbone network. The experiment shows that the precision of YOLOv5s-GCB is 89.7%, recall is 90.2% and mAP@0.5 is 93.1%, which are 2.1%, 3.0% and 1.6% higher than YOLOv5s, respectively. The average detection time of a single image is 7.9 ms, and the detection speed is improved. Finally, the ablation experiment shows that the proposed improved strategy is feasible, and the detection effect of YOLOv5s-GCB is further verified by the comparison experiment with other target detection models. Therefore, it can be concluded that the proposed method provides an important reference for the detection of indicated defects in strip steel.

Funder

The Innovation Support Program of Jiangsu Province

The Key R&D Program of Jiangsu Province

The Project of Laser Processing and Metal Additive Manufacturing Technology and Application

The Superiority Discipline Construction Project of Jiangsu Universities

The Top Talent Project of Nantong Institute of Technology

The Key disciplines of the 14th five year plan in Jiangsu Province: Mechanical Engineering

Publisher

SAGE Publications

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