WeldNet: A deep learning based method for weld seam type identification and initial

doi:10.1016/j.eswa.2023.121700

CORC > 自动化研究所 > 中国科学院自动化研究所 > 多模态人工智能系统全国重点实验室

	WeldNet: A deep learning based method for weld seam type identification and initial
	Ma, Yunkai 2; Fan, Junfeng 2; Zhou, Zhen 1,2; Zhao, Sihan 1,2; Jing, Fengshui 1,2; Tan, Min 1,2
刊名	EXPERT SYSTEMS WITH APPLICATIONS
	2024-03-15
卷号	238 页码:15
关键词	Weld seam type identification Initial point guidance Deep learning Robot welding Vision sensors
ISSN号	0957-4174
DOI	10.1016/j.eswa.2023.121700
通讯作者	Fan, Junfeng(junfeng.fan@ia.ac.cn) ; Jing, Fengshui(fengshui.jing@ia.ac.cn)
英文摘要	To address the limitations associated with the low intelligence of welding robots, a weld seam type identification and initial point guidance method based on deep neural network named WeldNet was proposed. By incorporating channel shuffling and an attention module, the size of the WeldNet model is reduced while preserving high detection accuracy. With the help of the proposed Center-Box annotation method, the optimized WeldNet network can not only automatically identify the type of welding workpieces at a frequency of 66 Hz, but also extract the initial point of the weld seam with an error of less than 1.63 pixels. Based on the principle of "monocular vision dual position shooting", automatic guidance of the initial point of the weld seam is achieved, which greatly improves the intelligence level of welding robots. The experimental results show that the method proposed can accurately identify various types of weld joints such as butt joints, lap joints, and fillet joints with a recognition rate of 99.6%, and the method can also guide the welding torch to align with the initial point of the weld seam with an error of just 0.85 mm.
资助项目	National Natural Science Foundation of China[62173327] ; National Natural Science Foundation of China[62003341] ; National Natural Science Foundation of China[62373354] ; Beijing Natural Science Foundation[4232057] ; Youth Innovation Promotion Association of CAS, China[2022130]
WOS关键词	TRACKING ; RECOGNITION ; SYSTEM ; POSITION
WOS研究方向	Computer Science ; Engineering ; Operations Research & Management Science
语种	英语
出版者	PERGAMON-ELSEVIER SCIENCE LTD
WOS记录号	WOS:001087530500001
资助机构	National Natural Science Foundation of China ; Beijing Natural Science Foundation ; Youth Innovation Promotion Association of CAS, China
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/54379]
专题	多模态人工智能系统全国重点实验室
通讯作者	Fan, Junfeng; Jing, Fengshui
作者单位	1.Univ Chinese Acad Sci, Sch Artificial Intelligence, 19 A Yuquan Rd, Beijing 100049, Peoples R China 2.Chinese Acad Sci, Inst Automat, 95 Zhongguancun East Rd, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Ma, Yunkai,Fan, Junfeng,Zhou, Zhen,et al. WeldNet: A deep learning based method for weld seam type identification and initial[J]. EXPERT SYSTEMS WITH APPLICATIONS,2024,238:15.
APA	Ma, Yunkai,Fan, Junfeng,Zhou, Zhen,Zhao, Sihan,Jing, Fengshui,&Tan, Min.(2024).WeldNet: A deep learning based method for weld seam type identification and initial.EXPERT SYSTEMS WITH APPLICATIONS,238,15.
MLA	Ma, Yunkai,et al."WeldNet: A deep learning based method for weld seam type identification and initial".EXPERT SYSTEMS WITH APPLICATIONS 238(2024):15.