Wire Defect Recognition of Spring-Wire Socket Using Multitask Convolutional Neural Networks

doi:10.1109/TCPMT.2018.2794540

CASIA OpenIR > 中科院工业视觉智能装备工程实验室 > 精密感知与控制

	Wire Defect Recognition of Spring-Wire Socket Using Multitask Convolutional Neural Networks
	Tao, Xian1 ; Wang, Zihao 2; Zhang, Zhengtao1 ; Zhang, Dapeng1 ; Xu, De1 ; Gong, Xinyi1 ; Zhang, Lei 1
发表期刊	IEEE TRANSACTIONS ON COMPONENTS PACKAGING AND MANUFACTURING TECHNOLOGY
	2018-04-01
卷号	8 期号:4 页码:689-698
文章类型	Article
摘要	As a critical electrical connector component in the modern industrial environment, spring-wire sockets and their manufacture quality are closely relevant to equipment safety. These types of defects in a component are difficult to properly distinguish due to the defect similarity and diversity. In such cases, defect types can only be determined using cumbersome human visual inspection. To satisfy the requirements of quality control, a machine vision apparatus for component inspection is presented in this paper. With a brief description of the apparatus system design, our emphasis is put on the defect recognition algorithm. A multitask convolutional neural network (CNN) is proposed for detecting those ambiguous defects. Compared with the image processing method in machine vision, the defect inspection problem is converted into object detection and classification problems. Instead of breaking it down into two separate tasks, we jointly handle both aspects in a single CNN. In addition, data augmentation methods are discussed to analyze their effects on defects recognition. Successful inspection results using the presented model are obtained using challenging real-world defect image data gathered from a spring-wire socket module inspection line in an industrial plant.; As a critical electrical connector component in the modern industrial environment, spring-wire sockets and their manufacture quality are closely relevant to equipment safety. These types of defects in a component are difficult to properly distinguish due to the defect similarity and diversity. In such cases, defect types can only be determined using cumbersome human visual inspection. To satisfy the requirements of quality control, a machine vision apparatus for component inspection is presented in this paper. With a brief description of the apparatus system design, our emphasis is put on the defect recognition algorithm. A multitask convolutional neural network (CNN) is proposed for detecting those ambiguous defects. Compared with the image processing method in machine vision, the defect inspection problem is converted into object detection and classification problems. Instead of breaking it down into two separate tasks, we jointly handle both aspects in a single CNN. In addition, data augmentation methods are discussed to analyze their effects on defects recognition. Successful inspection results using the presented model are obtained using challenging real-world defect image data gathered from a spring-wire socket module inspection line in an industrial plant.
关键词	Convolutional Neural Network (Cnn) Defect Recognition Machine Vision Multitask Learning Spring-wire Sockets
WOS标题词	Science & Technology ; Technology
DOI	10.1109/TCPMT.2018.2794540
关键词[WOS]	VISION INSPECTION SYSTEM ; FEATURE-SELECTION ; SEGMENT DETECTOR ; EDGE-DETECTION ; CLASSIFICATION ; MACHINE ; SCALE ; TUBE
收录类别	SCI
语种	英语
项目资助者	National Natural Science Foundation of China(61703399 ; 61673383 ; 61733004 ; 61421004 ; 61403382)
WOS研究方向	Engineering ; Materials Science
WOS类目	Engineering, Manufacturing ; Engineering, Electrical & Electronic ; Materials Science, Multidisciplinary
WOS记录号	WOS:000429960300022
引用统计	被引频次：58[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/21697
专题	中科院工业视觉智能装备工程实验室_精密感知与控制
作者单位	1.Chinese Acad Sci, Inst Automat, Res Ctr Precis Sensing & Control, Beijing 100190, Peoples R China 2.Civil Aviat Univ China, Sinoeuropean Inst Aviat Engn, Tianjin 300300, Peoples R China
第一作者单位	精密感知与控制研究中心
推荐引用方式 GB/T 7714	Tao, Xian,Wang, Zihao,Zhang, Zhengtao,et al. Wire Defect Recognition of Spring-Wire Socket Using Multitask Convolutional Neural Networks[J]. IEEE TRANSACTIONS ON COMPONENTS PACKAGING AND MANUFACTURING TECHNOLOGY,2018,8(4):689-698.
APA	Tao, Xian.,Wang, Zihao.,Zhang, Zhengtao.,Zhang, Dapeng.,Xu, De.,...&Zhang, Lei.(2018).Wire Defect Recognition of Spring-Wire Socket Using Multitask Convolutional Neural Networks.IEEE TRANSACTIONS ON COMPONENTS PACKAGING AND MANUFACTURING TECHNOLOGY,8(4),689-698.
MLA	Tao, Xian,et al."Wire Defect Recognition of Spring-Wire Socket Using Multitask Convolutional Neural Networks".IEEE TRANSACTIONS ON COMPONENTS PACKAGING AND MANUFACTURING TECHNOLOGY 8.4(2018):689-698.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
tao2018.pdf（4279KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载