Article(id=1156983790938710261, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156983783787421903, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2402648, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1712851200000, receivedDateStr=2024-04-12, revisedDate=1731859200000, revisedDateStr=2024-11-18, acceptedDate=null, acceptedDateStr=null, onlineDate=1753776031478, onlineDateStr=2025-07-29, pubDate=1739808000000, pubDateStr=2025-02-18, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753776031478, onlineIssueDateStr=2025-07-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753776031478, creator=13701087609, updateTime=1753776031478, updator=13701087609, issue=Issue{id=1156983783787421903, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='5', pageStart='1753', pageEnd='2192', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1753776029774, creator=13701087609, updateTime=1769691857141, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1223739602251436918, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156983783787421903, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1223739602251436919, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1156983783787421903, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=2027, endPage=2033, ext={EN=ArticleExt(id=1156983792947781882, articleId=1156983790938710261, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Weld Defect Detection Based on Improved Faster R-CNN Method, columnId=1156262729162810294, journalTitle=Science Technology and Engineering, columnName=Papers·Automation and Computational Technology, runingTitle=null, highlight=null, articleAbstract=

Weld defects present within pipelines constitute a considerable threat for leakage and rupture accidents. To elevate the detection precision of these defects, X-ray inspection was employed as a means to identify and locate them with greater accuracy. However, the diverse types, small sizes, and complex backgrounds of weld defects posed challenges for accurate detection. To address the limitations of current deep learning-based models, such as inadequate adaptability to complex backgrounds and lighting variations, as well as poor performance in detecting small targets, an improved faster region convolutional neural networks(Faster R-CNN) network model was investigated. This model incorporated a channel attention mechanism into the backbone network, modified the residual block structure, and employed ROI Align to replace the traditional ROI Pooling. The results show that compared to the original algorithm, the improved Faster R-CNN model achieves significant improvements in mean average precision (mAP) and F1, with respective increases of 15.82% and 16.44%. It is concluded that this improved model can meet the high-precision requirements for weld defect detection and holds significant theoretical importance as well as promising prospects for engineering applications.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Li-qiong CHEN, Hou-jin MEI, Hong-xuan HU, Kui ZHAO), CN=ArticleExt(id=1156983917623468047, articleId=1156983790938710261, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于改进Faster R-CNN的焊缝缺陷检测方法, columnId=1156262729783567290, journalTitle=科学技术与工程, columnName=论文·自动化技术、计算机技术, runingTitle=null, highlight=null, articleAbstract=

管道内部的焊缝缺陷是导致管道发生泄漏和破裂事故的主要原因,而X射线能够有效地检测到这些缺陷。然而,焊缝缺陷存在种类多、尺寸小和背景复杂等问题,影响检测精度。针对目前基于深度学习的焊缝缺陷检测模型对图像复杂背景和光照变化的适应性不足、小目标检测效果不佳的问题。在快速区域卷积神经网络(faster region convolutional neural networks,Faster R-CNN)网络的主干网络上添加通道注意力机制和对残差块结构进行修改,并采用ROI Align替换传统Faster R-CNN网络的ROI Pooling的改进模型。实验结果表明:改进后的Faster R-CNN网络模型与原算法相比,平均精度值(mean average precision,mAP)和F1分别比原算法提升了15.82%和16.44%,能够满足焊缝缺陷检测的高精度要求,具有重要的理论意义与良好的工程应用前景。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=XPJtBCfV7ypSafcl/n2hNA==, magXml=kRjegP7vJqIQoLIsjpW2UA==, pdfUrl=null, pdf=+AatS8m7QRagG1Nz+3bw4Q==, pdfFileSize=6543088, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=96srRhO6QLtJc9tCNighRQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=PUZotjhdsVuX5NleJWcf4A==, mapNumber=null, authorCompany=null, fund=null, authors=

陈利琼(1976—),女,汉族,四川遂宁人,博士后,教授。研究方向:油气管道完整性管理和油气储运安全技术等。E-mail:

, authorsList=陈利琼, 梅后金, 胡洪宣, 赵奎)}, authors=[Author(id=1225467180930744337, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=121488667@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1225467181073350686, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, authorId=1225467180930744337, language=EN, stringName=Li-qiong CHEN, firstName=Li-qiong, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 National Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467182461665329, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, authorId=1225467180930744337, language=CN, stringName=陈利琼, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 西南石油大学油气藏地质及开发工程全国重点实验室, 成都 610500, bio={"content":"

陈利琼(1976—),女,汉族,四川遂宁人,博士后,教授。研究方向:油气管道完整性管理和油气储运安全技术等。E-mail:

"}, bioImg=null, bioContent=

陈利琼(1976—),女,汉族,四川遂宁人,博士后,教授。研究方向:油气管道完整性管理和油气储运安全技术等。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467180335154141, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, xref=1, ext=[AuthorCompanyExt(id=1225467180385485792, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, companyId=1225467180335154141, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 National Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China), AuthorCompanyExt(id=1225467180423234531, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, companyId=1225467180335154141, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西南石油大学油气藏地质及开发工程全国重点实验室, 成都 610500)])]), Author(id=1225467182612660288, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1225467182839152736, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, authorId=1225467182612660288, language=EN, stringName=Hou-jin MEI, firstName=Hou-jin, middleName=null, lastName=MEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 National Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467183002730614, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, authorId=1225467182612660288, language=CN, stringName=梅后金, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 西南石油大学油气藏地质及开发工程全国重点实验室, 成都 610500, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467180335154141, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, xref=1, ext=[AuthorCompanyExt(id=1225467180385485792, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, companyId=1225467180335154141, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 National Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China), AuthorCompanyExt(id=1225467180423234531, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, companyId=1225467180335154141, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西南石油大学油气藏地质及开发工程全国重点实验室, 成都 610500)])]), Author(id=1225467183124365447, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1225467183359246490, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, authorId=1225467183124365447, language=EN, stringName=Hong-xuan HU, firstName=Hong-xuan, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Southwest Pipeline Co., Ltd., PipeChina, Chengdu 610000, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467183518630052, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, authorId=1225467183124365447, language=CN, stringName=胡洪宣, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 国家管网集团西南管道有限责任公司, 成都 610000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467180721030138, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, xref=2, ext=[AuthorCompanyExt(id=1225467180729418747, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, companyId=1225467180721030138, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Southwest Pipeline Co., Ltd., PipeChina, Chengdu 610000, China), AuthorCompanyExt(id=1225467180767167485, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, companyId=1225467180721030138, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 国家管网集团西南管道有限责任公司, 成都 610000)])]), Author(id=1225467183757705403, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1225467184105832664, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, authorId=1225467183757705403, language=EN, stringName=Kui ZHAO, firstName=Kui, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 National Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1225467184286187753, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, authorId=1225467183757705403, language=CN, stringName=赵奎, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 西南石油大学油气藏地质及开发工程全国重点实验室, 成都 610500, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1225467180335154141, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, xref=1, ext=[AuthorCompanyExt(id=1225467180385485792, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, companyId=1225467180335154141, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 National Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China), AuthorCompanyExt(id=1225467180423234531, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, companyId=1225467180335154141, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西南石油大学油气藏地质及开发工程全国重点实验室, 成都 610500)])])], keywords=[Keyword(id=1225467184646897934, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=EN, orderNo=1, keyword=deep learning), Keyword(id=1225467184823058714, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=EN, orderNo=2, keyword=defect detection), Keyword(id=1225467185053745456, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=EN, orderNo=3, keyword=X-ray image), Keyword(id=1225467185158603068, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=EN, orderNo=4, keyword=Faster R-CNN), Keyword(id=1225467185292820812, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=CN, orderNo=1, keyword=深度学习), Keyword(id=1225467185372512604, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=CN, orderNo=2, keyword=缺陷检测), Keyword(id=1225467185523507564, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=CN, orderNo=3, keyword=X射线图像), Keyword(id=1225467187041845631, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=CN, orderNo=4, keyword=Faster R-CNN)], refs=[Reference(id=1225467193417188137, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=6, pageStart=632, pageEnd=639, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=丁建林, 西昕, 张对红, journalName=油气储运, refType=null, unstructuredReference=丁建林, 西昕, 张对红. 能源安全战略下中国管道输送技术发展与展望[J]. 油气储运, 2022, 41(6): 632-639., articleTitle=能源安全战略下中国管道输送技术发展与展望, refAbstract=null), Reference(id=1225467193593348915, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=6, pageStart=632, pageEnd=639, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Ding Jianlin, Xi Xin, Zhang Duihong, journalName=Oil and Gas Storage and Transportation, refType=null, unstructuredReference=Ding Jianlin, Xi Xin, Zhang Duihong. Development and prospect of pipeline transportation technology in China under energy security strategy[J]. Oil and Gas Storage and Transportation, 2022, 41(6): 632-639., articleTitle=Development and prospect of pipeline transportation technology in China under energy security strategy, refAbstract=null), Reference(id=1225467193777898304, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2017, volume=25, issue=null, pageStart=134, pageEnd=152, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Verma J, Taiwade R V, journalName=Journal of Manufacturing Processes, refType=null, unstructuredReference=Verma J, Taiwade R V. Effect of welding processes and conditions on the microstructure, mechanical properties and corrosion resistance of duplex stainless steel weldments: a review[J]. Journal of Manufacturing Processes, 2017, 25: 134-152., articleTitle=Effect of welding processes and conditions on the microstructure, mechanical properties and corrosion resistance of duplex stainless steel weldments: a review, refAbstract=null), Reference(id=1225467194008585036, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=2, pageStart=100052, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=Woldesellasse H, Tesfamariam S, journalName=Journal of Infrastructure Intelligence and Resilience, refType=null, unstructuredReference=Woldesellasse H, Tesfamariam S. Risk analysis of onshore oil and gas pipelines: literature review and bibliometric analysis[J]. Journal of Infrastructure Intelligence and Resilience, 2023, (2): 100052., articleTitle=Risk analysis of onshore oil and gas pipelines: literature review and bibliometric analysis, refAbstract=null), Reference(id=1225467194243466081, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=30, pageStart=13288, pageEnd=13292, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=余泽禹, 袁洪强, 卫小龙, journalName=科学技术与工程, refType=null, unstructuredReference=余泽禹, 袁洪强, 卫小龙, 等. 基于深度学习的管道焊缝超声检测缺陷识别方法[J]. 科学技术与工程, 2022, 22(30): 13288-13292., articleTitle=基于深度学习的管道焊缝超声检测缺陷识别方法, refAbstract=null), Reference(id=1225467194537067375, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=30, pageStart=13288, pageEnd=13292, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=Yu Zeyu, Yuan Hongqiang, Wei Xiaolong, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Yu Zeyu, Yuan Hongqiang, Wei Xiaolong, et al. Defect identification method of pipeline weld ultrasonic testing based on deep learning[J]. Science Technology and Engineering, 2022, 22(30): 13288-13292., articleTitle=Defect identification method of pipeline weld ultrasonic testing based on deep learning, refAbstract=null), Reference(id=1225467195975713668, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2021, volume=279, issue=null, pageStart=123583, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=Chen C, Li C J, Reniers G, journalName=Journal of Cleaner Production, refType=null, unstructuredReference=Chen C, Li C J, Reniers G, et al. Safety and security of oil and gas pipeline transportation: a systematic analysis of research trends and future needs using WoS[J]. Journal of Cleaner Production, 2021, 279: 123583., articleTitle=Safety and security of oil and gas pipeline transportation: a systematic analysis of research trends and future needs using WoS, refAbstract=null), Reference(id=1225467196214789020, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=5, pageStart=1893, pageEnd=1899, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=陈传智, 李宁, 王畅, journalName=科学技术与工程, refType=null, unstructuredReference=陈传智, 李宁, 王畅, 等. 基于多尺度一维卷积神经网络的弯管冲蚀损伤智能检测方法[J]. 科学技术与工程, 2024, 24(5): 1893-1899., articleTitle=基于多尺度一维卷积神经网络的弯管冲蚀损伤智能检测方法, refAbstract=null), Reference(id=1225467196365783975, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=5, pageStart=1893, pageEnd=1899, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=Chen Chuanzhi, Li Ning, Wang Chang, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Chen Chuanzhi, Li Ning, Wang Chang, et al. Intelligent detection method for bending pipe erosion damage based on multi-scale one-dimensional convolutional neural network[J]. Science Technology and Engineering, 2024, 24(5): 1893-1899., articleTitle=Intelligent detection method for bending pipe erosion damage based on multi-scale one-dimensional convolutional neural network, refAbstract=null), Reference(id=1225467196483224500, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2023, volume=38, issue=null, pageStart=254, pageEnd=274, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=Cai X, Chen Y T, Ma H B, journalName=Nondestructive Testing and Evaluation, refType=null, unstructuredReference=Cai X, Chen Y T, Ma H B, et al. Visual inspection method of steel pipe surface cracks based on dry magnetic particle feature enhancement[J]. Nondestructive Testing and Evaluation, 2023, 38: 254-274., articleTitle=Visual inspection method of steel pipe surface cracks based on dry magnetic particle feature enhancement, refAbstract=null), Reference(id=1225467196713911241, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=8, pageStart=3387, pageEnd=3395, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=吴昉, 王伟, 刘卫朋, journalName=科学技术与工程, refType=null, unstructuredReference=吴昉, 王伟, 刘卫朋. 结合注意力机制和卷积神经网络的X射线焊缝缺陷检测[J]. 科学技术与工程, 2023, 23(8): 3387-3395., articleTitle=结合注意力机制和卷积神经网络的X射线焊缝缺陷检测, refAbstract=null), Reference(id=1225467196961375191, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=8, pageStart=3387, pageEnd=3395, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=Wu Fang, Wang Wei, Liu Weipeng, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Wu Fang, Wang Wei, Liu Weipeng. X-ray weld defect detection combined with attention mechanism and convolutional neural network[J]. Science Technology and Engineering, 2023, 23(8): 3387-3395., articleTitle=X-ray weld defect detection combined with attention mechanism and convolutional neural network, refAbstract=null), Reference(id=1225467197158507492, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2023, volume=66, issue=7, pageStart=50, pageEnd=56, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=缪寅宵, 孙增玉, 杨奕, journalName=航空制造技术, refType=null, unstructuredReference=缪寅宵, 孙增玉, 杨奕, 等. 基于深度学习的X射线胶片数字化与缺陷检测算法[J]. 航空制造技术, 2023, 66(7): 50-56., articleTitle=基于深度学习的X射线胶片数字化与缺陷检测算法, refAbstract=null), Reference(id=1225467197422748656, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2023, volume=66, issue=7, pageStart=50, pageEnd=56, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=Miao Yinxiao, Sun Zengyu, Yang Yi, journalName=Aeronautical Manufacturing Technology, refType=null, unstructuredReference=Miao Yinxiao, Sun Zengyu, Yang Yi, et al. Algorithm of X-ray film digitization and defect detection based on depth learning[J]. Aeronautical Manufacturing Technology, 2023, 66(7): 50-56., articleTitle=Algorithm of X-ray film digitization and defect detection based on depth learning, refAbstract=null), Reference(id=1225467197624075262, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2020, volume=39, issue=3, pageStart=68, pageEnd=75, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=Ajmi C, Zapata J, Martínez-Alvarez, journalName=Journal of Nondestructive Evaluation, refType=null, unstructuredReference=Ajmi C, Zapata J, Martínez-Alvarez, et al. Using deep learning for defect classification on a small weld X-ray image dataset[J]. Journal of Nondestructive Evaluation, 2020, 39(3): 68-75., articleTitle=Using deep learning for defect classification on a small weld X-ray image dataset, refAbstract=null), Reference(id=1225467197892509712, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2016, volume=18, issue=28, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=Li Q, Guo Y, Tian C, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Li Q, Guo Y, Tian C, et al. Effect of material crack flaws on dynamic fracture behavior[J]. Science Technology and Engineering, 2016, 18(28): 1-5., articleTitle=Effect of material crack flaws on dynamic fracture behavior, refAbstract=null), Reference(id=1225467198194499626, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=87, pageEnd=92, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=Lestari V P, Kosasih R, Handhika T, journalName=null, refType=null, unstructuredReference=Lestari V P, Kosasih R, Handhika T, et al. Fire hotspots detection system on CCTV videos using you only look once (YOLO) method and tiny YOLO model for high buildings evacuation[C]//2019 2nd International Conference of Computer and Informatics Engineering (IC2IE). Banyuwangi: IEEE, 2019: 87-92., articleTitle=Fire hotspots detection system on CCTV videos using you only look once (YOLO) method and tiny YOLO model for high buildings evacuation, refAbstract=null), Reference(id=1225467198441963587, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=6517, pageEnd=6525, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=Redmon J, Farhadi A, journalName=null, refType=null, unstructuredReference=Redmon J, Farhadi A. YOLO9000:better, faster, stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017: 6517-6525., articleTitle=YOLO9000:better, faster, stronger, refAbstract=null), Reference(id=1225467198605541455, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=1440, pageEnd=1448, url=null, language=null, rfNumber=[14], rfOrder=18, authorNames=Girshick R, journalName=2015 IEEE International Conference on Computer Vision (ICCV), refType=null, unstructuredReference=Girshick R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV). Santiago: IEEE, 2015: 1440-1448., articleTitle=Fast R-CNN, refAbstract=null), Reference(id=1225467198781702241, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2023, volume=133, issue=null, pageStart=102764, pageEnd=102773, url=null, language=null, rfNumber=[15], rfOrder=19, authorNames=Ji C, Wang H, Li H, journalName=NDT & E International: Independent Nondestructive Testing and Evaluation, refType=null, unstructuredReference=Ji C, Wang H, Li H. Defects detection in weld joints based on visual attention and deep learning[J]. NDT & E International: Independent Nondestructive Testing and Evaluation, 2023, 133: 102764-102773., articleTitle=Defects detection in weld joints based on visual attention and deep learning, refAbstract=null), Reference(id=1225467199012388977, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2023, volume=56, issue=null, pageStart=832, pageEnd=843, url=null, language=null, rfNumber=[16], rfOrder=20, authorNames=Chen C, Wang S, Huang S, journalName=Measurement & Control, refType=null, unstructuredReference=Chen C, Wang S, Huang S. An improved Faster R-CNN-based weld ultrasonic atlas defect detection method[J]. Measurement & Control, 2023, 56: 832-843., articleTitle=An improved Faster R-CNN-based weld ultrasonic atlas defect detection method, refAbstract=null), Reference(id=1225467200388120703, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=21, authorNames=全国锅炉压力容器标准化技术委员会, journalName=承压设备无损检测第2部分:射线检测:NB/T47013.2—2015, refType=null, unstructuredReference=全国锅炉压力容器标准化技术委员会. 承压设备无损检测第2部分:射线检测:NB/T47013.2—2015[S]. 北京: 中国标准出版社, 2015., articleTitle=null, refAbstract=null), Reference(id=1225467200820134043, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=22, authorNames=National Boiler and Pressure Vessel Standardization Technical Committee, journalName=Non-destructivetestingforpressureequipment-Part2:radiographictesting:NB/T47013.2—2015, refType=null, unstructuredReference=National Boiler and Pressure Vessel Standardization Technical Committee. Non-destructivetestingforpressureequipment-Part2:radiographictesting:NB/T47013.2—2015[S]. Beijing: Standards Press of China, 2015., articleTitle=null, refAbstract=null), Reference(id=1225467201034043564, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2021, volume=57, issue=20, pageStart=64, pageEnd=72, url=null, language=null, rfNumber=[18], rfOrder=23, authorNames=张宸嘉, 朱磊, 俞璐, journalName=计算机工程与应用, refType=null, unstructuredReference=张宸嘉, 朱磊, 俞璐. 卷积神经网络中的注意力机制综述[J]. 计算机工程与应用, 2021, 57(20): 64-72., articleTitle=卷积神经网络中的注意力机制综述, refAbstract=null), Reference(id=1225467201285701817, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, doi=null, pmid=null, pmcid=null, year=2021, volume=57, issue=20, pageStart=64, pageEnd=72, url=null, language=null, rfNumber=[18], rfOrder=24, authorNames=Zhang Chenjia, Zhu Lie, Yu Lu, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=Zhang Chenjia, Zhu Lie, Yu Lu. A review of attention mechanisms in convolutional neural networks[J]. Computer Engineering and Applications, 2021, 57(20): 64-72., articleTitle=A review of attention mechanisms in convolutional neural networks, refAbstract=null)], funds=[Fund(id=1225467192628658945, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, awardId=2016YFC0802100, language=CN, fundingSource=国家重点研发计划(2016YFC0802100), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1225467180335154141, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, xref=1, ext=[AuthorCompanyExt(id=1225467180385485792, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, companyId=1225467180335154141, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 National Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China), AuthorCompanyExt(id=1225467180423234531, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, companyId=1225467180335154141, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 西南石油大学油气藏地质及开发工程全国重点实验室, 成都 610500)]), AuthorCompany(id=1225467180721030138, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, xref=2, ext=[AuthorCompanyExt(id=1225467180729418747, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, companyId=1225467180721030138, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Southwest Pipeline Co., Ltd., PipeChina, Chengdu 610000, China), AuthorCompanyExt(id=1225467180767167485, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, companyId=1225467180721030138, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 国家管网集团西南管道有限责任公司, 成都 610000)])], figs=[ArticleFig(id=1225467187507413413, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=EN, label=Fig.1, caption=X-ray image of the weld, figureFileSmall=VHBjU/BY/Ia4oIXwz4RsMg==, figureFileBig=JVol8oXpVyWTdfmhQeTLfw==, tableContent=null), ArticleFig(id=1225467187721322939, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=CN, label=图1, caption=X射线焊缝图像, figureFileSmall=VHBjU/BY/Ia4oIXwz4RsMg==, figureFileBig=JVol8oXpVyWTdfmhQeTLfw==, tableContent=null), ArticleFig(id=1225467187889095120, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=EN, label=Fig.2, caption=The network structure of Faster R-CNN, figureFileSmall=oXBdZ0r/v7gks3siUHBAlA==, figureFileBig=DQSBAYHUDkvdkCR3J9wWtw==, tableContent=null), ArticleFig(id=1225467188031701472, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=CN, label=图2, caption=Faster R-CNN网络结构, figureFileSmall=oXBdZ0r/v7gks3siUHBAlA==, figureFileBig=DQSBAYHUDkvdkCR3J9wWtw==, tableContent=null), ArticleFig(id=1225467188379828732, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=EN, label=Fig.3, caption=Attention-ResNet34 network structure, figureFileSmall=Q2VbiNH+N/fLvsemKv4r2A==, figureFileBig=qxQv1jZT7abBOTXUVU2KKA==, tableContent=null), ArticleFig(id=1225467188639875606, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=CN, label=图3, caption=Attention-ResNet34网络结构, figureFileSmall=Q2VbiNH+N/fLvsemKv4r2A==, figureFileBig=qxQv1jZT7abBOTXUVU2KKA==, tableContent=null), ArticleFig(id=1225467188811842090, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=EN, label=Fig.4, caption=Image of RoI Pooling and RoI Align, figureFileSmall=I7DFFSZ/h9lBGEZl+xhPAA==, figureFileBig=PkjFIDmUixQN/ay728iTRg==, tableContent=null), ArticleFig(id=1225467189000585788, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=CN, label=图4, caption=RoI Pooling and RoI Align 示意图, figureFileSmall=I7DFFSZ/h9lBGEZl+xhPAA==, figureFileBig=PkjFIDmUixQN/ay728iTRg==, tableContent=null), ArticleFig(id=1225467189105443402, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=EN, label=Fig.5, caption=Geometric enhancement, figureFileSmall=5ETpjQWSnZdDEPVRy/lw9g==, figureFileBig=p8o8kwEuiW23TVBzeqlVwQ==, tableContent=null), ArticleFig(id=1225467189407433310, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=CN, label=图5, caption=几何增强, figureFileSmall=5ETpjQWSnZdDEPVRy/lw9g==, figureFileBig=p8o8kwEuiW23TVBzeqlVwQ==, tableContent=null), ArticleFig(id=1225467189587788397, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=EN, label=Fig.6, caption=P-R diagram of different models, figureFileSmall=bbQCiHeMxRdo0ZUWf2m8Jg==, figureFileBig=PStZln6CoIF8u6XAxaxs3A==, tableContent=null), ArticleFig(id=1225467189701034622, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=CN, label=图6, caption=不同模型的P-R曲线图, figureFileSmall=bbQCiHeMxRdo0ZUWf2m8Jg==, figureFileBig=PStZln6CoIF8u6XAxaxs3A==, tableContent=null), ArticleFig(id=1225467189805892234, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=EN, label=Fig.7, caption=Comparison of detection results of different models, figureFileSmall=N4H9Jcdl11u4hy3kw6qu2g==, figureFileBig=aNNQUxlqgRIIgZDuZd8FXA==, tableContent=null), ArticleFig(id=1225467189919138452, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=CN, label=图7, caption=不同模型检测结果对比, figureFileSmall=N4H9Jcdl11u4hy3kw6qu2g==, figureFileBig=aNNQUxlqgRIIgZDuZd8FXA==, tableContent=null), ArticleFig(id=1225467190049161891, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=EN, label=Table 1, caption=

Ablation experiment results

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 mAP/% F1/%
ResNet34 76.52 77.12
Attention-ResNet34 84.48 85.37
Attention-ResNet34+ RoI Align 92.34 93.56
), ArticleFig(id=1225467191504585400, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=CN, label=表1, caption=

消融实验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 mAP/% F1/%
ResNet34 76.52 77.12
Attention-ResNet34 84.48 85.37
Attention-ResNet34+ RoI Align 92.34 93.56
), ArticleFig(id=1225467191848518355, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=EN, label=Table 2, caption=

Comparative experimental results of different models

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 mAP/% F1/%
SSD 71.72 73.23
YOLOv5 83.13 83.27
本文模型 92.34 93.56
), ArticleFig(id=1225467192116953824, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1156983790938710261, language=CN, label=表2, caption=

不同模型对比实验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 mAP/% F1/%
SSD 71.72 73.23
YOLOv5 83.13 83.27
本文模型 92.34 93.56
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2402648, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2402648, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2402648, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2402648, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于改进Faster R-CNN的焊缝缺陷检测方法
收藏切换
PDF下载
陈利琼 1 , 梅后金 1 , 胡洪宣 2 , 赵奎 1
科学技术与工程 | 论文·自动化技术、计算机技术 2025,25(5): 2027-2033
收起
收藏切换
科学技术与工程 | 论文·自动化技术、计算机技术 2025, 25(5): 2027-2033
基于改进Faster R-CNN的焊缝缺陷检测方法
全屏
陈利琼1 , 梅后金1, 胡洪宣2, 赵奎1
作者信息
  • 1 西南石油大学油气藏地质及开发工程全国重点实验室, 成都 610500
  • 2 国家管网集团西南管道有限责任公司, 成都 610000
  • 陈利琼(1976—),女,汉族,四川遂宁人,博士后,教授。研究方向:油气管道完整性管理和油气储运安全技术等。E-mail:

Weld Defect Detection Based on Improved Faster R-CNN Method
Li-qiong CHEN1 , Hou-jin MEI1, Hong-xuan HU2, Kui ZHAO1
Affiliations
  • 1 National Key Laboratory of Oil and Gas Reservoir Geology and Exploitation, Southwest Petroleum University, Chengdu 610500, China
  • 2 Southwest Pipeline Co., Ltd., PipeChina, Chengdu 610000, China
出版时间: 2025-02-18 doi: 10.12404/j.issn.1671-1815.2402648
文章导航
收藏切换

管道内部的焊缝缺陷是导致管道发生泄漏和破裂事故的主要原因,而X射线能够有效地检测到这些缺陷。然而,焊缝缺陷存在种类多、尺寸小和背景复杂等问题,影响检测精度。针对目前基于深度学习的焊缝缺陷检测模型对图像复杂背景和光照变化的适应性不足、小目标检测效果不佳的问题。在快速区域卷积神经网络(faster region convolutional neural networks,Faster R-CNN)网络的主干网络上添加通道注意力机制和对残差块结构进行修改,并采用ROI Align替换传统Faster R-CNN网络的ROI Pooling的改进模型。实验结果表明:改进后的Faster R-CNN网络模型与原算法相比,平均精度值(mean average precision,mAP)和F1分别比原算法提升了15.82%和16.44%,能够满足焊缝缺陷检测的高精度要求,具有重要的理论意义与良好的工程应用前景。

深度学习  /  缺陷检测  /  X射线图像  /  Faster R-CNN

Weld defects present within pipelines constitute a considerable threat for leakage and rupture accidents. To elevate the detection precision of these defects, X-ray inspection was employed as a means to identify and locate them with greater accuracy. However, the diverse types, small sizes, and complex backgrounds of weld defects posed challenges for accurate detection. To address the limitations of current deep learning-based models, such as inadequate adaptability to complex backgrounds and lighting variations, as well as poor performance in detecting small targets, an improved faster region convolutional neural networks(Faster R-CNN) network model was investigated. This model incorporated a channel attention mechanism into the backbone network, modified the residual block structure, and employed ROI Align to replace the traditional ROI Pooling. The results show that compared to the original algorithm, the improved Faster R-CNN model achieves significant improvements in mean average precision (mAP) and F1, with respective increases of 15.82% and 16.44%. It is concluded that this improved model can meet the high-precision requirements for weld defect detection and holds significant theoretical importance as well as promising prospects for engineering applications.

deep learning  /  defect detection  /  X-ray image  /  Faster R-CNN
陈利琼, 梅后金, 胡洪宣, 赵奎. 基于改进Faster R-CNN的焊缝缺陷检测方法. 科学技术与工程, 2025 , 25 (5) : 2027 -2033 . DOI: 10.12404/j.issn.1671-1815.2402648
Li-qiong CHEN, Hou-jin MEI, Hong-xuan HU, Kui ZHAO. Weld Defect Detection Based on Improved Faster R-CNN Method[J]. Science Technology and Engineering, 2025 , 25 (5) : 2027 -2033 . DOI: 10.12404/j.issn.1671-1815.2402648
天然气长输管道作为能源供应的重要通道,在现代社会的经济发展和生活中扮演着至关重要的角色[1]。然而,由于焊接工艺和外部环境的影响,管道在焊接过程中难免会产生裂纹、气孔等不同类型的焊缝缺陷,这不仅会降低环焊缝的使用寿命,更会严重危害管道安全[2]。天然气易燃、易爆的性质也导致管道发生事故可能会造成严重的环境污染、财产损失和人员伤亡[3]。因此,对天然气长输管道焊缝缺陷进行高效的识别与检测对保障管道安全运行至关重要,而X射线可以有效地检测到管道内部的焊接缺陷。X射线检测作为传统工业生产中的主要缺陷识别方法,由于其人工评价方法的主观性,当检测量较大时容易发生漏检和误检等事故,而引入深度学习领域的目标检测技术,可以有效地提高检测效率[4]
随着人工智能技术在计算机视觉领域的发展,人工智能算法在焊缝缺陷检测与识别应用中已经取得了显著的成果[5]。目前,基于人工智能算法的管道焊缝缺陷射线识别技术主要有两种:一种是需要手动设计特征提取器的传统神经网络算法[6],一种是能够自动提取并学习图像特征的深度学习的目标检测算法[7]。传统神经网络对X射线图像中的焊缝进行识别,首先对X射线检测图像进行分割、去噪的预处理,后使用预先设计的特征提取方法进行提取,最后进行分类与识别[8]。由于X射线图像的复杂性,传统神经网络算法难以对图像进行精确分割,无法充分利用图像中所包含的丰富信息[9]。特征筛选和参数化过程受到人为因素的影响,容易导致检测精度和效率较低[10]。对于不同类型的焊缝缺陷和不同类型的X射线图像,其检测效果不够稳定。而基于深度学习的卷积神经网络,无需人工提取和特征描述,能够自动提取并学习图像中的特征,对图像进行精确的分割和分类,并根据其特征进行分类与智能识别,提高了焊缝缺陷检测的精度和效率,实现了从输入焊缝X射线检测图像到输出焊缝缺陷分类与定位的智能检测[11]。然而,将深度学习技术应用于天然气管道焊缝缺陷检测仍存在诸多不足,例如缺陷类型及形状大小不同带来的挑战。
目前,广泛使用的基于深度学习卷积神经网络的目标识别和检测算法主要有两种:一种以YOLO(you only look once)[12]和SSD(single shot multibox detector)[13]系列为代表的单阶段算法,检测速度快,实时性高,但准确率较低;另一种是以R-CNN(region-CNN)[14]系列为代表的两阶段检测算法,包括R-CNN、Fast R-CNN、Faster R-CNN等,该方法检测速度相对较慢,实时性较差,但检测精度高,应用范围广。R-CNN可以看作是一种基于分类概念的目标检测算法,通过提取候选区域并使用卷积神经网络对每个区域进行分类,以确定目标的存在和类别,具有良好的精确度[15]。Faster R-CNN模型因其高效率和高精度的特性,受到科研工作者的广泛青睐,而传统的Faster-RCNN模型的骨干网络通常为VGG16以及ResNet34,属于隐藏层较少的浅层神经网络,难以解决复杂背景干扰下的管道焊缝检测问题[16]。因此,研究旨在提出一种改进的Faster R-CNN模型,实现复杂背景下天然气管道焊缝缺陷的自动化检测。通过优化Faster R-CNN模型的关键组件,包括特征提取和目标定位等,提高了模型的检测性能。同时,引入了注意力机制,以更有效地识别突出的缺陷特征,从而提高检测的准确性和稳定性。
研究目的是为天然气长输管道焊缝缺陷检测领域提供一种精确而高效的解决方法。通过对比实验验证和性能评估,展示所提出的方法相对于传统方法的优势,以期为管道安全运行和可靠性提供更有效的技术支持。
正确认识管道焊缝的缺陷类型是焊缝缺陷检测的基础。典型的管道焊缝缺陷包括裂纹、未熔合、未焊透、气孔以及夹渣,如图1所示。裂纹缺陷通常由于焊接过程中产生的应力以及错误的焊接操作、材料问题等因素导致焊缝金属与母材金属之间的连续性中断,在X射线图像上呈现为形状和厚度不规则的白线,根据形状可分为横向或纵向裂纹。气孔缺陷是焊接过程中,熔池中的气体未在金属凝固前逸出,残存于焊缝中所形成的空穴。X射线图像中表现为轮廓清晰的圆形或椭圆形黑色斑点,根据其形状可分为球形气孔、均布气孔、局部密集气孔。未熔合是指焊缝金属与母材金属,或焊缝金属之间未熔化结合在一起的缺陷。X射线图像中的特征是一条连续或断续的黑线。未焊透是指焊接时接头的根部未完全熔透的现象。夹渣缺陷是焊接过程中残留在焊缝中的熔渣,其特征通常表现为形状不规则的黑影。
深度学习因具有强大的特征学习能力、数据处理能力,在目标检测领域占据主导地位,按照其处理流程和方式的不同,可分为一阶段检测模型和两阶段检测模型两类。一阶段检测模型速度更快、实时性更强,而两阶段检测模型具有更高的精度。由于《承压设备无损检测 第2部分:射线检测》(NB/T 47013.2—2015)[17]中对于精度的高要求,故采用两阶段模型中具有代表性的Faster R-CNN作为基础模型。Faster R-CNN是一种高效的卷积神经网络方法,首先通过特征提取网络对输入的X射线图像进行卷积、池化和非线性激活,生成特征图[18]。接着,区域建议网络(region proposal network,RPN)从特征图中提取候选目标区域。然后,RoI Pooling模块将这些候选区域的特征转化为固定大小的特征向量,并通过分类器对每个候选框内的目标进行分类,同时边界框回归器微调位置。最后,通过回归技术进一步细化矩形框的位置,从而实现焊缝缺陷检测。
针对天然气长输管道中普遍存在的焊缝缺陷形状大小多样以及背景噪声干扰问题,设计了基于Faster R-CNN的焊缝缺陷检测模型,整体结构如图2所示。对Faster R-CNN检测模型进行的改进如下。
(1)针对ResNet34在焊缝缺陷检测中的不足,改进了残差块结构,强化了模型的特征捕捉能力。
(2)添加了通道注意力机制,有效减少了背景和噪声的影响。
(3)使用ROI Align替代RoI Pooling提高模型的鲁棒性。
在焊缝缺陷检测任务中,VGG16网络作为原始的Faster R-CNN的骨干网络时,存在计算量大、训练时间长以及特征提取能力较弱的问题。而增加了残差结构的ResNet34网络结构,更容易训练且拥有更强的特征提取能力。但传统的ResNet34网络在面临复杂背景和噪声干扰时的对焊缝缺陷的识别能力有限,容易产生误检或漏检问题。
为了提高模型对于焊缝缺陷特征部位的关注程度,抑制背景和噪声的干扰,在ResNet34网络中使用了通道注意力机制。通道注意力机制是通过使用自适应的全局平均池化,获得每个通道的重要性权重,然后将权重与对应的通道进行加权相乘,得到加权后的特征图。最后得到对于分类识别任务关键的通道。
改进后的ResNet-34网络结构如图3所示。首先是一层7×7的卷积层,步长为2,将输入图像尺寸从68×68×1变为34×34×64。然后经过一层池化层,尺寸变为17×17×64。接下来进入4个残差块,每个残差块由2个基本块组成,基本块中包含2个卷积层和一个注意力机制模块。其中第一个残差块会对输入特征图进行下采样,其他残差块不会改变特征图的尺寸。接着加入一个全局平均池化层,将特征图大小变为1×1×512。最后使用一个全连接层将特征向量映射到目标分类数,输出分类概率。
在传统的Faster-RCNN模型中,ROI Pooling被用于将ROI区域划分为固定大小的子区域,并对每个子区域进行特征提取。然而,这种固定大小的池化方式容易导致部分边界像素丢失,从而影响特征表示的精度。量化误差导致的位置偏差会对小缺陷的检测造成巨大的影响,尤其是气孔这类像素大小在20以下的缺陷,若缩放为原来的1/32,0.5像素的误差就会造成缺失。此外,粗糙的ROI Pooling只能处理等比例缩放,如果缺陷特征图的长宽比和ROI区域的长宽比不一样,则还需要进行额外的插值操作。
为了解决这些问题,提出使用ROI Align替代ROI Pooling来获取更精确的特征表示。如图4所示,ROI Align是将ROI区域划分为更小的子区域,并计算每个子区域与特征图之间的重叠度。然后,对于每个子区域,ROI Align使用双线性插值来计算其在特征图中的像素值。最后,将所有子区域的特征拼接在一起,形成ROI Align的输出特征。这种处理方式可以避免区域不匹配问题,提高模型准确性并加强对细小缺陷的检测能力。
详细介绍了所进行的实验设置,以评估研究中引入的改进方法,旨在验证改进方法的有效性和实用性。
研究所提出的改进Faster R-CNN焊缝检测模型基于PyTorch深度学习框架和Python 3.10.5脚本语言,并在Windows 11操作系统、i7-7700 CPU 和NVDIA GeForce RTX 3090 19500MHz显卡、32 GB RAM的环境下进行了测试和训练。
用于缺陷分析的X射线数据集图像来自西南管道有限责任公司川气东送天然气长输管道的578张X70钢管X射线图像。所有图像均经过专业标注,分辨率为每英寸630点,8位灰度值,文件格式为TIFF。然后,使用高斯滤波进行降噪、Otsu二值化分割和双三次插值对图像进行预处理,并将图像缩放到128×128像素。最终原始数据集包括127张气孔缺陷图像、101张未焊透缺陷图像、95张未融和缺陷图像、98张夹渣缺陷图像和147张裂纹缺陷图像。
由于焊接缺陷可以呈现各种形状,并且可能出现在管道的任何位置。因此,通过几何变换的数据增强可以有效地增加数据集的多样性。如图5所示,通过对图像进行旋转180°、水平翻转和垂直翻转将数据集扩展为2 312张。
为了全面地对模型进行评价,采用精确率(precision,P)、召回率(recall,R)、F1、平均精准度(average precision,AP)和平均精确率(mean average precision,mAP)进行评估。
精确率指在模型预测为焊缝缺陷的样本中,真正为焊缝缺陷的样本所占的比例。召回率指模型能够找出所有实际为焊缝缺陷的样本的比例,其计算方法如式(2)所示。F1是精确率和召回率的调和平均数,其取值范围在0~1,F1越高,表示模型的综合性能越好。
P=$\frac{TP}{TP+FP}$×100%
R=$\frac{TP}{TP+FN}$×100%
F1=$\frac{2PR}{P+R}$×100%
式中:TP(true positive)表示模型正确预测为焊缝缺陷的样本数;FP(false positive)表示被模型错误预测为焊缝缺陷的非缺陷样本数;FN(false negative)表示实际为焊缝缺陷但被模型错误预测为非缺陷的样本数。
AP是单类别缺陷的平均精准度,对应于P-R曲线下的面积,mAP是多类别缺陷AP的平均值。
AP=∫P(R)dR
mAP=$\frac{\sum AP}{N}$×100%
式中:P(R)为在召回率为R的情况下,模型的精度;N为模型类别数量。
Faster R-CNN网络模型在特征提取、候选区域生成和定位准确性方面进行了改进。为了验证每个模块改进方法的有效性和合理性,通过消融实验进行验证,实验结果如表1所示。
表1可知,在Faster R-CNN(ResNet34)模型中,添加通道注意力机制,该操作使得模型性能显著提高,总体平均精度均值提升7.96%,最终平均精度达到84.48%。而使用ROI Align替换掉ROI Pooling,这一改动使得模型平均精度提高6.42%。F1达到了93.56%。消融实验结果表明,研究提出的在ResNet34作为骨干网络的Faster R-CNN模型中添加通道注意力机制和修改残差块结构,增强了模型的特征提取能力,并使得模型聚焦于焊缝缺陷特征通道,有效抑制背景和噪声的干扰。引用ROI Align技术,提高了模型对于气孔、夹渣等不规则形状焊缝缺陷的检测精度。
为了全面评估本文模型的相对有效性,选择SSD、YOLOV5和改进的 Faster R-CNN 进行比较。2 312幅焊接缺陷图像被分为8∶1∶1的训练集、验证集和测试集。分别与SSD和YOLOV5模型进行对比,相应结果如表2所示。
表2可知,本文模型与其他先进检测模型相比,在天然气长输管道焊缝缺陷检测任务中表现优异,能够满足实际应用中对于检测精度的高标准。所提出的新模型与其他先进模型检测同一目标时的视觉对比如图7所示,与SSD检测模型相比,本文模型能够成功识别出其漏检的夹渣缺陷。与YOLOV5检测模型相比,本文模型中有着更高的精度和更强的鲁棒性。
针对天然气长输管道焊缝缺陷射线检测问题,提出了一种基于改进Faster R-CNN的创新方法。通过融合通道注意力机制、优化残差块结构,并引入ROI Align技术,显著提高了焊缝缺陷检测的精度和鲁棒性。结合工程实例进行的验证实验结果表明,改进后的模型在性能上取得了显著提升,模型平均精度值(mAP)和F1分别达到了92.34%和93.56%,满足达到工业检测的高精度要求,为天然气长输管道焊缝检测领域的发展提供了重要研究思路。
  • 国家重点研发计划(2016YFC0802100)
参考文献 引证文献
排序方式:
[1]
丁建林, 西昕, 张对红. 能源安全战略下中国管道输送技术发展与展望[J]. 油气储运, 2022, 41(6): 632-639.
Ding Jianlin, Xi Xin, Zhang Duihong. Development and prospect of pipeline transportation technology in China under energy security strategy[J]. Oil and Gas Storage and Transportation, 2022, 41(6): 632-639.
[2]
Verma J, Taiwade R V. Effect of welding processes and conditions on the microstructure, mechanical properties and corrosion resistance of duplex stainless steel weldments: a review[J]. Journal of Manufacturing Processes, 2017, 25: 134-152.
[3]
Woldesellasse H, Tesfamariam S. Risk analysis of onshore oil and gas pipelines: literature review and bibliometric analysis[J]. Journal of Infrastructure Intelligence and Resilience, 2023, (2): 100052.
[4]
余泽禹, 袁洪强, 卫小龙, 等. 基于深度学习的管道焊缝超声检测缺陷识别方法[J]. 科学技术与工程, 2022, 22(30): 13288-13292.
Yu Zeyu, Yuan Hongqiang, Wei Xiaolong, et al. Defect identification method of pipeline weld ultrasonic testing based on deep learning[J]. Science Technology and Engineering, 2022, 22(30): 13288-13292.
[5]
Chen C, Li C J, Reniers G, et al. Safety and security of oil and gas pipeline transportation: a systematic analysis of research trends and future needs using WoS[J]. Journal of Cleaner Production, 2021, 279: 123583.
[6]
陈传智, 李宁, 王畅, 等. 基于多尺度一维卷积神经网络的弯管冲蚀损伤智能检测方法[J]. 科学技术与工程, 2024, 24(5): 1893-1899.
Chen Chuanzhi, Li Ning, Wang Chang, et al. Intelligent detection method for bending pipe erosion damage based on multi-scale one-dimensional convolutional neural network[J]. Science Technology and Engineering, 2024, 24(5): 1893-1899.
[7]
Cai X, Chen Y T, Ma H B, et al. Visual inspection method of steel pipe surface cracks based on dry magnetic particle feature enhancement[J]. Nondestructive Testing and Evaluation, 2023, 38: 254-274.
[8]
吴昉, 王伟, 刘卫朋. 结合注意力机制和卷积神经网络的X射线焊缝缺陷检测[J]. 科学技术与工程, 2023, 23(8): 3387-3395.
Wu Fang, Wang Wei, Liu Weipeng. X-ray weld defect detection combined with attention mechanism and convolutional neural network[J]. Science Technology and Engineering, 2023, 23(8): 3387-3395.
[9]
缪寅宵, 孙增玉, 杨奕, 等. 基于深度学习的X射线胶片数字化与缺陷检测算法[J]. 航空制造技术, 2023, 66(7): 50-56.
Miao Yinxiao, Sun Zengyu, Yang Yi, et al. Algorithm of X-ray film digitization and defect detection based on depth learning[J]. Aeronautical Manufacturing Technology, 2023, 66(7): 50-56.
[10]
Ajmi C, Zapata J, Martínez-Alvarez, et al. Using deep learning for defect classification on a small weld X-ray image dataset[J]. Journal of Nondestructive Evaluation, 2020, 39(3): 68-75.
[11]
Li Q, Guo Y, Tian C, et al. Effect of material crack flaws on dynamic fracture behavior[J]. Science Technology and Engineering, 2016, 18(28): 1-5.
[12]
Lestari V P, Kosasih R, Handhika T, et al. Fire hotspots detection system on CCTV videos using you only look once (YOLO) method and tiny YOLO model for high buildings evacuation[C]//2019 2nd International Conference of Computer and Informatics Engineering (IC2IE). Banyuwangi: IEEE, 2019: 87-92.
[13]
Redmon J, Farhadi A. YOLO9000:better, faster, stronger[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Honolulu: IEEE, 2017: 6517-6525.
[14]
Girshick R. Fast R-CNN[C]//2015 IEEE International Conference on Computer Vision (ICCV). Santiago: IEEE, 2015: 1440-1448.
[15]
Ji C, Wang H, Li H. Defects detection in weld joints based on visual attention and deep learning[J]. NDT & E International: Independent Nondestructive Testing and Evaluation, 2023, 133: 102764-102773.
[16]
Chen C, Wang S, Huang S. An improved Faster R-CNN-based weld ultrasonic atlas defect detection method[J]. Measurement & Control, 2023, 56: 832-843.
[17]
全国锅炉压力容器标准化技术委员会. 承压设备无损检测第2部分:射线检测:NB/T47013.2—2015[S]. 北京: 中国标准出版社, 2015.
National Boiler and Pressure Vessel Standardization Technical Committee. Non-destructivetestingforpressureequipment-Part2:radiographictesting:NB/T47013.2—2015[S]. Beijing: Standards Press of China, 2015.
[18]
张宸嘉, 朱磊, 俞璐. 卷积神经网络中的注意力机制综述[J]. 计算机工程与应用, 2021, 57(20): 64-72.
Zhang Chenjia, Zhu Lie, Yu Lu. A review of attention mechanisms in convolutional neural networks[J]. Computer Engineering and Applications, 2021, 57(20): 64-72.
2025年第25卷第5期
PDF下载
437
189
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2402648
  • 接收时间:2024-04-12
  • 首发时间:2025-07-29
  • 出版时间:2025-02-18
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-04-12
  • 修回日期:2024-11-18
基金
国家重点研发计划(2016YFC0802100)
作者信息
    1 西南石油大学油气藏地质及开发工程全国重点实验室, 成都 610500
    2 国家管网集团西南管道有限责任公司, 成都 610000
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2402648
分享至
全文二维码

扫描看全文

引用本文
BibTeX
本文的引用情况
2种不同金属材料的力学参数

Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)

Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏