南方科技大学知识苑(SUSTech KC): A new lightweight deep neural network for surface scratch detection

题名	A new lightweight deep neural network for surface scratch detection
作者	Li，Wei 1; Zhang，Liangchi2,3,4 ; Wu，Chuhan 1; Cui，Zhenxiang 5; Niu，Chao 5
通讯作者	Zhang，Liangchi
发表日期	2022
DOI	10.1007/s00170-022-10335-8
发表期刊	INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY 影响因子和分区
ISSN	0268-3768
EISSN	1433-3015
摘要	This paper aims to develop a lightweight convolutional neural network, WearNet, to realise automatic scratch detection for components in contact sliding such as those in metal forming. To this end, a large surface scratch dataset obtained from cylinder-on-flat sliding tests was used to train the WearNet with appropriate training parameters such as learning rate, gradient algorithm and mini-batch size. A comprehensive investigation on the network response and decision mechanism was also conducted to show the capability of the developed WearNet. It was found that compared with the existing networks, WearNet can realise an excellent classification accuracy of 94.16% with a much smaller model size and faster detection speed. Besides, WearNet outperformed other state-of-the-art networks when a public image database was used for network evaluation. The application of WearNet in an embedded system further demonstrated such advantages in the detection of surface scratches in sheet metal forming processes.
关键词	Contact sliding Convolutional neural network Sheet metal forming Surface scratch detection
相关链接	[Scopus记录]
收录类别	SCI
语种	英语
学校署名	通讯
资助项目	Baosteel Australia Research and Development Centre (BAJC) portfolio with Project[BA17001] ; ARC Hub for Computational Particle Technology[IH140100035] ; Chinese Guangdong Specific Discipline Project["2020ZDZX2006","ZDSYS20200810171201007"]
WOS研究方向	Automation & Control Systems ; Engineering
WOS类目	Automation & Control Systems ; Engineering, Manufacturing
WOS记录号	WOS:000875077300006
出版者	SPRINGER LONDON LTD
ESI学科分类	ENGINEERING
Scopus记录号	2-s2.0-85140654490
来源库	Scopus
引用统计	被引频次[WOS]：70
成果类型	期刊论文
条目标识符	http://sustech.caswiz.com/handle/2SGJ60CL/407154
专题	工学院_创新智造研究院工学院_力学与航空航天工程系
作者单位	1.School of Mechanical and Manufacturing Engineering,The University of New South Wales,Kensington,2052,Australia 2.Shenzhen Key Laboratory of Cross-Scale Manufacturing Mechanics,Southern University of Science and Technology,Shenzhen,Guangdong,518055,China 3.SUSTech Institute for Manufacturing Innovation,Southern University of Science and Technology,Shenzhen,Guangdong,518055,China 4.Department of Mechanics and Aerospace Engineering,Southern University of Science and Technology,Shenzhen,Guangdong,518055,China 5.Baoshan Iron & Steel Co.,Ltd.,Shanghai,200941,China
通讯作者单位	南方科技大学; 创新智造研究院; 力学与航空航天工程系
推荐引用方式 GB/T 7714	Li，Wei,Zhang，Liangchi,Wu，Chuhan,et al. A new lightweight deep neural network for surface scratch detection[J]. INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY,2022.
APA	Li，Wei,Zhang，Liangchi,Wu，Chuhan,Cui，Zhenxiang,&Niu，Chao.(2022).A new lightweight deep neural network for surface scratch detection.INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY.
MLA	Li，Wei,et al."A new lightweight deep neural network for surface scratch detection".INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY (2022).