基于主动视觉感知的熔池特征自动识别

IF 2.2 3区 材料科学 Q2 METALLURGY & METALLURGICAL ENGINEERING
Yongchao Cheng, Qiyue Wang, Wenhua Jiao, Jun Xiao, Shujun Chen, Yuming Zhang
{"title":"基于主动视觉感知的熔池特征自动识别","authors":"Yongchao Cheng, Qiyue Wang, Wenhua Jiao, Jun Xiao, Shujun Chen, Yuming Zhang","doi":"10.29391/2021.100.015","DOIUrl":null,"url":null,"abstract":"While penetration occurs underneath the workpiece, the raw information used to detect it during welding must be measurable to a sensor attached to the torch. Challenges are apparent because it is difficult to find such measurable raw information that fundamentally correlates with the phenomena occurring underneath. Additional challenges arise because the welding process is extremely complex such that analytically correlating any raw information to the underneath phenomena is practically impossible; therefore, handcrafted methods to propose features from raw information are human dependent and labor extensive. In this paper, the profile of the weld pool surface was proposed as the raw information. An innovative method was proposed to acquire it by projecting a single laser stripe on the weld pool surface transversely and intercepting its reflection from the mirror-like weld pool surface. To minimize human intervention, which can affect success, a deep-learning-based method was proposed to automatically recognize features from the single-stripe active vision images by fitting a convolutional neural network (CNN). To train the CNN, spot gas tungsten arc welding experiments were designed and conducted to collect the active vision images in pairs with their actual penetration states measured by a camera that views the backside surface of the workpiece. The CNN architecture was optimized by trying different hyperparameters, including kernel number, kernel size, and node number. The accuracy of the optimized model is about 98% and the cycle time in the personal computer is ~ 0.1 s, which fully meets the required engineering application.","PeriodicalId":23681,"journal":{"name":"Welding Journal","volume":" ","pages":""},"PeriodicalIF":2.2000,"publicationDate":"2021-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"10","resultStr":"{\"title\":\"Automated Recognition of Weld Pool Characteristics from Active Vision Sensing\",\"authors\":\"Yongchao Cheng, Qiyue Wang, Wenhua Jiao, Jun Xiao, Shujun Chen, Yuming Zhang\",\"doi\":\"10.29391/2021.100.015\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"While penetration occurs underneath the workpiece, the raw information used to detect it during welding must be measurable to a sensor attached to the torch. Challenges are apparent because it is difficult to find such measurable raw information that fundamentally correlates with the phenomena occurring underneath. Additional challenges arise because the welding process is extremely complex such that analytically correlating any raw information to the underneath phenomena is practically impossible; therefore, handcrafted methods to propose features from raw information are human dependent and labor extensive. In this paper, the profile of the weld pool surface was proposed as the raw information. An innovative method was proposed to acquire it by projecting a single laser stripe on the weld pool surface transversely and intercepting its reflection from the mirror-like weld pool surface. To minimize human intervention, which can affect success, a deep-learning-based method was proposed to automatically recognize features from the single-stripe active vision images by fitting a convolutional neural network (CNN). To train the CNN, spot gas tungsten arc welding experiments were designed and conducted to collect the active vision images in pairs with their actual penetration states measured by a camera that views the backside surface of the workpiece. The CNN architecture was optimized by trying different hyperparameters, including kernel number, kernel size, and node number. The accuracy of the optimized model is about 98% and the cycle time in the personal computer is ~ 0.1 s, which fully meets the required engineering application.\",\"PeriodicalId\":23681,\"journal\":{\"name\":\"Welding Journal\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":2.2000,\"publicationDate\":\"2021-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"10\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Welding Journal\",\"FirstCategoryId\":\"88\",\"ListUrlMain\":\"https://doi.org/10.29391/2021.100.015\",\"RegionNum\":3,\"RegionCategory\":\"材料科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"METALLURGY & METALLURGICAL ENGINEERING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Welding Journal","FirstCategoryId":"88","ListUrlMain":"https://doi.org/10.29391/2021.100.015","RegionNum":3,"RegionCategory":"材料科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"METALLURGY & METALLURGICAL ENGINEERING","Score":null,"Total":0}
引用次数: 10

摘要

当渗透发生在工件下面时,焊接过程中用于检测它的原始信息必须是连接在火炬上的传感器可测量的。挑战是显而易见的,因为很难找到这种可测量的原始信息,这些信息从根本上与下面发生的现象相关。由于焊接过程极其复杂,因此将任何原始信息与下面的现象进行分析关联实际上是不可能的,因此会出现额外的挑战;因此,从原始信息中提取特征的手工方法依赖于人类,并且需要大量的劳动。本文提出以熔池表面轮廓作为原始信息。提出了一种创新的方法,即在焊缝熔池表面横向投射单个激光条纹,并截取其从镜面熔池表面反射的激光条纹。为了最大限度地减少人为干预对学习成功的影响,提出了一种基于深度学习的方法,通过拟合卷积神经网络(CNN)来自动识别单条纹主动视觉图像的特征。为了训练CNN,设计并进行了点焊钨气弧焊实验,通过观察工件后表面的相机测量到的主动视觉图像与实际穿透状态成对地进行采集。通过尝试不同的超参数,包括内核数、内核大小和节点数,对CNN架构进行优化。优化后的模型精度约为98%,在个人计算机中的循环时间为~ 0.1 s,完全满足工程应用的要求。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Automated Recognition of Weld Pool Characteristics from Active Vision Sensing
While penetration occurs underneath the workpiece, the raw information used to detect it during welding must be measurable to a sensor attached to the torch. Challenges are apparent because it is difficult to find such measurable raw information that fundamentally correlates with the phenomena occurring underneath. Additional challenges arise because the welding process is extremely complex such that analytically correlating any raw information to the underneath phenomena is practically impossible; therefore, handcrafted methods to propose features from raw information are human dependent and labor extensive. In this paper, the profile of the weld pool surface was proposed as the raw information. An innovative method was proposed to acquire it by projecting a single laser stripe on the weld pool surface transversely and intercepting its reflection from the mirror-like weld pool surface. To minimize human intervention, which can affect success, a deep-learning-based method was proposed to automatically recognize features from the single-stripe active vision images by fitting a convolutional neural network (CNN). To train the CNN, spot gas tungsten arc welding experiments were designed and conducted to collect the active vision images in pairs with their actual penetration states measured by a camera that views the backside surface of the workpiece. The CNN architecture was optimized by trying different hyperparameters, including kernel number, kernel size, and node number. The accuracy of the optimized model is about 98% and the cycle time in the personal computer is ~ 0.1 s, which fully meets the required engineering application.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Welding Journal
Welding Journal 工程技术-冶金工程
CiteScore
3.00
自引率
0.00%
发文量
23
审稿时长
3 months
期刊介绍: The Welding Journal has been published continually since 1922 — an unmatched link to all issues and advancements concerning metal fabrication and construction. Each month the Welding Journal delivers news of the welding and metal fabricating industry. Stay informed on the latest products, trends, technology and events via in-depth articles, full-color photos and illustrations, and timely, cost-saving advice. Also featured are articles and supplements on related activities, such as testing and inspection, maintenance and repair, design, training, personal safety, and brazing and soldering.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信