LightYOLO: Lightweight model based on YOLOv8n for defect detection of ultrasonically welded wire terminations

doi:10.1016/j.jestch.2024.101896

CSpace

	LightYOLO: Lightweight model based on YOLOv8n for defect detection of ultrasonically welded wire terminations
	Xu, Jianshu 1,2; Zhao, Lun 1,4; Ren, Yu 1,3; Li, Zhigang 2; Abbas, Zeshan 1; Zhang, Lan 1; Islam, Shafiqul 4
	2024-12
发表期刊	ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH
ISSN	2215-0986
卷号	60
摘要	Defect inspection of the surface in ultrasonically welded wire terminations is an important inspection procedure to ensure welding quality. However, the detection task of ultrasonic welding defects based on deep learning still faces the challenges of low detection accuracy and slow inference speed. Therefore, to solve the above problems, we propose a fast and effective lightweight detection model based on You Only Look Once v8 (YOLOv8n), named LightYOLO. Specifically, first, to achieve fast feature extraction, a Two-Convolution module with FasterNet block and Efficient multi-scale attention (CTFE) structures is introduced in the backbone network. Secondly, Group-Shuffle Convolution (GSConv) is used to construct the feature fusion structure of the neck, which enhances the fusion efficiency of multi-level features. Finally, an auxiliary head training method is introduced to extract shallow details of the network. To verify the effectiveness of the proposed method, we constructed a surface defect data set of ultrasonic welding wire terminals and conducted a series of experiments. The results of experiments show that the precision of LightYOLO is 93.4%, which is 3.5% higher than YOLOv8n(89.9%). In addition, the model size was reduced to 1/2 of the baseline model. LightYOLO shows the potential for rapid detection on edge computing devices. The source code and dataset for our project is accessible at https://github.com/JianshuXu/LightYOLO.
关键词	Ultrasonic metal welding Deep learning Object detection Lightweight
DOI	10.1016/j.jestch.2024.101896
收录类别	SCIE
语种	英语
资助项目	National Natural Science Founda-tion of China [12104324]; Scientific Research Startup Fund for Shenzhen High-Caliber Personnel of SZPU [6022310046K]; SZPU-Newpower Ultrasonic welding R and D [602331009PQ]; Post-doctoral Later-stage Foundation Project of Shenzhen Polytechnic Uni-versity [6023271014K1]
WOS研究方向	Engineering
WOS类目	Engineering, Multidisciplinary
WOS记录号	WOS:001363741500001
出版者	ELSEVIER - DIVISION REED ELSEVIER INDIA PVT LTD
原始文献类型	Article
引用统计	被引频次：2[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.library.ouchn.edu.cn/handle/39V7QQFX/174298
专题	国家开放大学
通讯作者	Zhao, Lun
作者单位	1.Yunnan Open Univ, Sch Mech & Elect Engn, Kunming 650223, Yunnan, Peoples R China; 2.Univ Sci & Technol Liaoning, Sch Elect & Informat Engn, Anshan 114051, Peoples R China; 3.Shenzhen Univ, Sch Biomed Engn, Shenzhen 518060, Peoples R China; 4.Blekinge Inst Technol, Dept Mech Engn, S-37179 Karlskrona, Sweden
推荐引用方式 GB/T 7714	Xu, Jianshu,Zhao, Lun,Ren, Yu,et al. LightYOLO: Lightweight model based on YOLOv8n for defect detection of ultrasonically welded wire terminations[J]. ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH,2024,60.
APA	Xu, Jianshu.,Zhao, Lun.,Ren, Yu.,Li, Zhigang.,Abbas, Zeshan.,...&Islam, Shafiqul.(2024).LightYOLO: Lightweight model based on YOLOv8n for defect detection of ultrasonically welded wire terminations.ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH,60.
MLA	Xu, Jianshu,et al."LightYOLO: Lightweight model based on YOLOv8n for defect detection of ultrasonically welded wire terminations".ENGINEERING SCIENCE AND TECHNOLOGY-AN INTERNATIONAL JOURNAL-JESTECH 60(2024).