Article(id=1251505542196310129, tenantId=1146029695717560320, journalId=1251233954884272221, issueId=1251505536634667461, articleNumber=null, orderNo=null, doi=10.13682/j.issn.2095-6533.2025.06.012, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1730736000000, receivedDateStr=2024-11-05, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1776311773107, onlineDateStr=2026-04-16, pubDate=1762704000000, pubDateStr=2025-11-10, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1776311773107, onlineIssueDateStr=2026-04-16, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1776311773107, creator=13701087609, updateTime=1776311773107, updator=13701087609, issue=Issue{id=1251505536634667461, tenantId=1146029695717560320, journalId=1251233954884272221, year='2025', volume='30', issue='6', pageStart='1', pageEnd='130', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1776311771782, creator=13701087609, updateTime=1776311824541, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1251505758014226723, tenantId=1146029695717560320, journalId=1251233954884272221, issueId=1251505536634667461, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1251505758014226724, tenantId=1146029695717560320, journalId=1251233954884272221, issueId=1251505536634667461, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=104, endPage=112, ext={EN=ArticleExt(id=1251505542422802555, articleId=1251505542196310129, tenantId=1146029695717560320, journalId=1251233954884272221, language=EN, title=An X-ray weld defect detection method, columnId=null, journalTitle=Journal of Xi'an University of Posts and Telecommunications, columnName=null, runingTitle=null, highlight=null, articleAbstract=

To address the issues of missed detection and low detection accuracy in X-ray weld defect detection,an improved YOLOv8-based detection method is proposed.Firstly,the efficient multi-scale attention(EMA)mechanism is improved by replacing the 3×3 convolutional kernel with a 5×5 kernel to expand the receptive field,and replacing the average pooling with the multi-scale pooling to extract multi-scale features.The improved EMA module is embedded into the backbone network to enhance the model's ability to detect defects at various scales.Then the spatial pyramid pooling fast module is improved by introducing adaptive average pooling and max pooling layers,to improve the perception of weld edge information.Finally,in the neck part,Dual convolution is used to replace traditional convolution,to reduce the parameter number of the model.The WIoU(wise intersection over union)loss function is adopted to replace the CIoU(complete intersection over union)loss function to improve the convergence speed of the model. Experimental results show that,compared to YOLOv8n,the proposed algorithm reduces the number of parameters by 4.02%and increases the mean average precision by 5.9%,which is well-suited for X-ray weld defect detection tasks.

, 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=Xiaoyin WANG, Mengyuan QIN, Guanxiong LI, Shuyan WANG), CN=ArticleExt(id=1251505547657294191, articleId=1251505542196310129, tenantId=1146029695717560320, journalId=1251233954884272221, language=CN, title=一种X射线焊缝缺陷检测方法, columnId=1251505537641300427, journalTitle=西安邮电大学学报, columnName=人工智能目标检测, runingTitle=null, highlight=null, articleAbstract=

针对X射线焊缝缺陷检测中存在的漏检、检测精度低等问题,提出一种X射线焊缝缺陷检测方法。首先,将高效多尺度注意力(Efficient Multi-scale Attention,EMA)模块中3×3卷积核替换为5×5卷积核,以扩大感受野,同时将平均池化改为多尺度池化,以提取多尺度特征。将改进后的EMA模块嵌入主干网络,增强多尺度缺陷检测能力。然后,引入自适应平均池化层和最大池化层,改进空间金字塔池化模块,提升对焊缝边缘信息的感知能力。最后,在颈部采用Dual卷积替代传统卷积,降低模型参数量,并使用WIoU(Wise Intersection over Union)损失函数替代CIoU(Complete Intersection over Union)损失函数,提高模型的收敛速度。实验结果表明,与YOLOv8n相比,所提方法的参数量降低了4.02%,平均精度均值提升了5.9%,可适用于X射线焊缝缺陷检测任务。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=XuBeRXIA1SUdldOeEPZrGg==, magXml=LQ0jqp0T3+N0J8T0NySEXA==, pdfUrl=null, pdf=AFmbKZ+ZhQPhBzZislftvw==, pdfFileSize=4702406, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=g82n7MyIU9CM3K3hcumngw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=KRi0sv+gDgUUaax2Qar4zg==, mapNumber=null, authorCompany=null, fund=null, authors=

王小银(1976-),女,陕西西安人,硕士,西安邮电大学教授,主要研究方向为人工智能、大数据挖掘等。E-mail:

秦梦媛(1997-),女,山西吕梁人,西安邮电大学硕士研究生,主要研究方向为焊缝缺陷检测技术。E-mail:

李冠雄(1986-),男,河南开封人,博士,开封迪尔空分实业有限公司董事,主要研究方向为智能空分技术。E-mail:

王曙燕(1964-),女,河南南阳人,博士,西安邮电大学教授,主要研究方向为智能信息处理、大数据分析、软件测试。E-mail:

, authorsList=王小银, 秦梦媛, 李冠雄, 王曙燕)}, authors=[Author(id=1251505548152222100, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xywang@xupt.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1251505548257079707, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, authorId=1251505548152222100, language=EN, stringName=Xiaoyin WANG, firstName=Xiaoyin, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.School of Computer Science,Xi'an University of Posts and Telecommunications,Xi'an 710121,China
2.Shaanxi Key Laboratory of Intelligent Software Technology,Xi'an 710121,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251505548357743008, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, authorId=1251505548152222100, language=CN, stringName=王小银, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.西安邮电大学计算机学院,陕西西安 710121
2.智能软件技术陕西省高等学校重点实验室,陕西西安 710121, bio={"img":"JTGNhWsSF2nJvts3gB/oog==","content":"

王小银(1976-),女,陕西西安人,硕士,西安邮电大学教授,主要研究方向为人工智能、大数据挖掘等。E-mail:

"}, bioImg=JTGNhWsSF2nJvts3gB/oog==, bioContent=

王小银(1976-),女,陕西西安人,硕士,西安邮电大学教授,主要研究方向为人工智能、大数据挖掘等。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251505547887980924, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, xref=1., ext=[AuthorCompanyExt(id=1251505547896369533, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505547887980924, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Computer Science,Xi'an University of Posts and Telecommunications,Xi'an 710121,China), AuthorCompanyExt(id=1251505547904758143, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505547887980924, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安邮电大学计算机学院,陕西西安 710121)]), AuthorCompany(id=1251505547980255621, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, xref=2., ext=[AuthorCompanyExt(id=1251505547988644230, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505547980255621, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Shaanxi Key Laboratory of Intelligent Software Technology,Xi'an 710121,China), AuthorCompanyExt(id=1251505547992838535, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505547980255621, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.智能软件技术陕西省高等学校重点实验室,陕西西安 710121)])]), Author(id=1251505548458406307, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=945647006@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1251505548554875304, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, authorId=1251505548458406307, language=EN, stringName=Mengyuan QIN, firstName=Mengyuan, middleName=null, lastName=QIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Computer Science,Xi'an University of Posts and Telecommunications,Xi'an 710121,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251505548621984171, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, authorId=1251505548458406307, language=CN, stringName=秦梦媛, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.西安邮电大学计算机学院,陕西西安 710121, bio={"img":"uGPsLf4WN3xg5UJ9qm4NpA==","content":"

秦梦媛(1997-),女,山西吕梁人,西安邮电大学硕士研究生,主要研究方向为焊缝缺陷检测技术。E-mail:

"}, bioImg=uGPsLf4WN3xg5UJ9qm4NpA==, bioContent=

秦梦媛(1997-),女,山西吕梁人,西安邮电大学硕士研究生,主要研究方向为焊缝缺陷检测技术。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251505547887980924, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, xref=1., ext=[AuthorCompanyExt(id=1251505547896369533, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505547887980924, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Computer Science,Xi'an University of Posts and Telecommunications,Xi'an 710121,China), AuthorCompanyExt(id=1251505547904758143, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505547887980924, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安邮电大学计算机学院,陕西西安 710121)])]), Author(id=1251505548722647472, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=lgxd_feng@sina.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1251505548810727862, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, authorId=1251505548722647472, language=EN, stringName=Guanxiong LI, firstName=Guanxiong, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.Kaifeng Dier Air Separation Industrial Co.,LTD,Kaifeng 475000,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251505548886225342, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, authorId=1251505548722647472, language=CN, stringName=李冠雄, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3.开封迪尔空分实业有限公司,河南开封 475000, bio={"img":"OaxgyU/WXMtuLSbkCrmuAw==","content":"

李冠雄(1986-),男,河南开封人,博士,开封迪尔空分实业有限公司董事,主要研究方向为智能空分技术。E-mail:

"}, bioImg=OaxgyU/WXMtuLSbkCrmuAw==, bioContent=

李冠雄(1986-),男,河南开封人,博士,开封迪尔空分实业有限公司董事,主要研究方向为智能空分技术。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251505548076724621, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, xref=3., ext=[AuthorCompanyExt(id=1251505548085113230, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505548076724621, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Kaifeng Dier Air Separation Industrial Co.,LTD,Kaifeng 475000,China), AuthorCompanyExt(id=1251505548089307535, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505548076724621, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.开封迪尔空分实业有限公司,河南开封 475000)])]), Author(id=1251505548961722819, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wsylxj@126.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1251505549079163340, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, authorId=1251505548961722819, language=EN, stringName=Shuyan WANG, firstName=Shuyan, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Computer Science,Xi'an University of Posts and Telecommunications,Xi'an 710121,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1251505549167243730, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, authorId=1251505548961722819, language=CN, stringName=王曙燕, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.西安邮电大学计算机学院,陕西西安 710121, bio={"img":"dMJV6E42m77hQagG0iOxTQ==","content":"

王曙燕(1964-),女,河南南阳人,博士,西安邮电大学教授,主要研究方向为智能信息处理、大数据分析、软件测试。E-mail:

"}, bioImg=dMJV6E42m77hQagG0iOxTQ==, bioContent=

王曙燕(1964-),女,河南南阳人,博士,西安邮电大学教授,主要研究方向为智能信息处理、大数据分析、软件测试。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1251505547887980924, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, xref=1., ext=[AuthorCompanyExt(id=1251505547896369533, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505547887980924, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Computer Science,Xi'an University of Posts and Telecommunications,Xi'an 710121,China), AuthorCompanyExt(id=1251505547904758143, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505547887980924, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安邮电大学计算机学院,陕西西安 710121)])])], keywords=[Keyword(id=1251505549288878554, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, orderNo=1, keyword=weld defect detection), Keyword(id=1251505549355987422, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, orderNo=2, keyword=YOLOv8n), Keyword(id=1251505549456650722, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, orderNo=3, keyword=efficient mutti-scale attention), Keyword(id=1251505549574091240, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, orderNo=4, keyword=Dual convolution), Keyword(id=1251505549645394411, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, orderNo=5, keyword=WIoU loss function), Keyword(id=1251505549725086192, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, orderNo=1, keyword=焊缝缺陷检测), Keyword(id=1251505549834138101, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, orderNo=2, keyword=YOLOv8n), Keyword(id=1251505549930607098, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, orderNo=3, keyword=高效多尺度注意力), Keyword(id=1251505550106767870, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, orderNo=4, keyword=Dual卷积), Keyword(id=1251505550199042561, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, orderNo=5, keyword=WIoU损失函数)], refs=[Reference(id=1251505553533514390, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2024, volume=51, issue=20, pageStart=12, pageEnd=21, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=吴磊, 储钰昆, 杨洪刚, journalName=中国激光, refType=null, unstructuredReference=吴磊,储钰昆,杨洪刚,.基于YOLOv7TS的铝合金焊缝DR图像缺陷检测技术[J].中国激光,2024, 51(20):12-21., articleTitle=基于YOLOv7TS的铝合金焊缝DR图像缺陷检测技术, refAbstract=null), Reference(id=1251505553613206171, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2024, volume=51, issue=20, pageStart=12, pageEnd=21, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=WU L, CHU Y K, YANG H G, journalName=Chinese Journal of Lasers, refType=null, unstructuredReference=WU L,CHU Y K,YANG H G,et al.Aluminum alloy weld DR image defect detection technology based on YOLOv7TS[J].Chinese Journal of Lasers,2024, 51(20):12-21.(in Chinese), articleTitle=Aluminum alloy weld DR image defect detection technology based on YOLOv7TS, refAbstract=null), Reference(id=1251505553692897950, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2020, volume=48, issue=4, pageStart=1875, pageEnd=1897, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=SCHMIDT-HIEBER J, journalName=Annals of Statistics, refType=null, unstructuredReference=SCHMIDT-HIEBER J. Nonparametric regression using deep neural networks with ReLU activation function[J]. Annals of Statistics, 2020, 48 (4):1875-1897., articleTitle=Nonparametric regression using deep neural networks with ReLU activation function, refAbstract=null), Reference(id=1251505553768395426, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2017, volume=39, issue=6, pageStart=1137, pageEnd=1149, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=REN S Q, HE K M, GIRSHICK R, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=REN S Q,HE K M,GIRSHICK R,et al.Faster RCNN:Toward real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149., articleTitle=Faster RCNN:Toward real-time object detection with region proposal networks, refAbstract=null), Reference(id=1251505553843892901, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=21, pageEnd=37, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=LIU W, ANGUELOV D, ERHAN D, journalName=null, refType=null, unstructuredReference=LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single shot MultiBox detector[C]//Computer Vision-ECCV 2016.Cham:Springer,2016:21-37., articleTitle=SSD:Single shot MultiBox detector, refAbstract=null), Reference(id=1251505553948750504, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=779, pageEnd=788, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=REDMON J, DIVVALA S, GIRSHICK R, journalName=null, refType=null, unstructuredReference=REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once: Unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016:779-788., articleTitle=You only look once: Unified, real-time object detection, refAbstract=null), Reference(id=1251505554041025197, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=2999, pageEnd=3007, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=LIN T Y, GOYAL P, GIRSHICK R, journalName=null, refType=null, unstructuredReference=LIN T Y,GOYAL P,GIRSHICK R,et al.Focal loss for dense object detection[C]//2017 IEEE International Conference on Computer Vision. Venice:IEEE, 2017:2999-3007., articleTitle=Focal loss for dense object detection, refAbstract=null), Reference(id=1251505554120716977, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2021, volume=11, issue=null, pageStart=1447, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=LAWAL M O, journalName=Scientific Reports, refType=null, unstructuredReference=LAWAL M O.Tomato detection based on modified YOLOv3 framework[J]. Scientific Reports, 2021, 11:1447., articleTitle=Tomato detection based on modified YOLOv3 framework, refAbstract=null), Reference(id=1251505554212991668, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2023, volume=28, issue=3, pageStart=88, pageEnd=96, url=null, language=null, rfNumber=[8], rfOrder=8, authorNames=江祥奎, 杜遥遥, 胡浩昌, journalName=西安邮电大学学报, refType=null, unstructuredReference=江祥奎,杜遥遥,胡浩昌.一种改进YOLOv5s小目标无人机实时检测算法[J].西安邮电大学学报,2023, 28(3):88-96., articleTitle=一种改进YOLOv5s小目标无人机实时检测算法, refAbstract=null), Reference(id=1251505554296877750, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2023, volume=28, issue=3, pageStart=88, pageEnd=96, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=JIANG X K, DU Y Y, HU H C, journalName=Journal of Xi'an University of Posts and Telecommunications, refType=null, unstructuredReference=JIANG X K, DU Y Y, HU H C. An improved YOLOv5s real-time detection algorithm for small target UAVs[J].Journal of Xi'an University of Posts and Telecommunications,2023,28(3):88-96.(in Chinese), articleTitle=An improved YOLOv5s real-time detection algorithm for small target UAVs, refAbstract=null), Reference(id=1251505554397541049, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2024, volume=52, issue=6, pageStart=226, pageEnd=237, url=null, language=null, rfNumber=[9], rfOrder=10, authorNames=李德永, 王国法, 郭永存, journalName=煤炭科学技术, refType=null, unstructuredReference=李德永,王国法,郭永存,.基于CFS-YOLO算法的复杂工况环境下煤矸图像识别方法[J].煤炭科学技术,2024,52(6):226-237., articleTitle=基于CFS-YOLO算法的复杂工况环境下煤矸图像识别方法, refAbstract=null), Reference(id=1251505554460455613, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2024, volume=52, issue=6, pageStart=226, pageEnd=237, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=LI D Y, WANG G F, GUO Y C, journalName=Coal Science and Technology, refType=null, unstructuredReference=LI D Y,WANG G F,GUO Y C,et al.Image recognition method of coal gangue in complex working conditions based on CES-YOLO algorithm[J].Coal Science and Technology,2024,52(6):226-237.(in Chinese), articleTitle=Image recognition method of coal gangue in complex working conditions based on CES-YOLO algorithm, refAbstract=null), Reference(id=1251505554615644868, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2023, volume=5, issue=4, pageStart=1680, pageEnd=1716, url=null, language=null, rfNumber=[10], rfOrder=12, authorNames=TERVEN J, CÓRDOVA-ESPARZA D M, ROMERO-GONZÁLEZ J A, journalName=Machine Learning and Knowledge Extraction, refType=null, unstructuredReference=TERVEN J,CÓRDOVA-ESPARZA D M,ROMERO-GONZÁLEZ J A.A comprehensive review of YOLO architectures in computer vision:From YOLOv1 to YOLOv8 and YOLO-NAS[J].Machine Learning and Knowledge Extraction,2023,5(4):1680-1716., articleTitle=A comprehensive review of YOLO architectures in computer vision:From YOLOv1 to YOLOv8 and YOLO-NAS, refAbstract=null), Reference(id=1251505554699530954, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2022, volume=49, issue=21, pageStart=130, pageEnd=138, url=null, language=null, rfNumber=[11], rfOrder=13, authorNames=程松, 杨洪刚, 徐学谦, journalName=中国激光, refType=null, unstructuredReference=程松,杨洪刚,徐学谦,.基于YOLOv5的改进轻量型X射线铝合金焊缝缺陷检测算法[J].中国激光, 2022,49(21):130-138., articleTitle=基于YOLOv5的改进轻量型X射线铝合金焊缝缺陷检测算法, refAbstract=null), Reference(id=1251505554808582860, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2022, volume=49, issue=21, pageStart=130, pageEnd=138, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=CHENG S, YANG H G, XU X Q, journalName=Chinese Journal of Lasers, refType=null, unstructuredReference=CHENG S,YANG H G,XU X Q,et al.Improved lightweight X-ray aluminum alloy weld defects detection algorithm based on YOLOv5[J].Chinese Journal of Lasers,2022,49(21):130-138.(in Chinese), articleTitle=Improved lightweight X-ray aluminum alloy weld defects detection algorithm based on YOLOv5, refAbstract=null), Reference(id=1251505554900857554, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2024, volume=47, issue=11, pageStart=123, pageEnd=130, url=null, language=null, rfNumber=[12], rfOrder=15, authorNames=张上, 许欢, 张岳, journalName=电子测量技术, refType=null, unstructuredReference=张上,许欢,张岳.轻量级锻件表面裂纹检测算法[J].电子测量技术,2024,47(11):123-130., articleTitle=轻量级锻件表面裂纹检测算法, refAbstract=null), Reference(id=1251505554976355031, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2024, volume=47, issue=11, pageStart=123, pageEnd=130, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=ZHANG S, XU H, ZHANG Y, journalName=Electronic Measurement Technology, refType=null, unstructuredReference=ZHANG S,XU H,ZHANG Y.Lightweight forged part surface crack detection algorithm[J].Electronic Measurement Technology,2024,47(11):123-130.(in Chinese), articleTitle=Lightweight forged part surface crack detection algorithm, refAbstract=null), Reference(id=1251505555047658204, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=7, pageStart=7430, pageEnd=7439, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=LIU M Y, CHEN Y P, XIE J M, journalName=IEEE Sensors Journal, refType=null, unstructuredReference=LIU M Y,CHEN Y P,XIE J M,et al.LF-YOLO:A lighter and faster YOLO for weld defect detection of Xray image[J].IEEE Sensors Journal,2023,23(7):7430-7439., articleTitle=LF-YOLO:A lighter and faster YOLO for weld defect detection of Xray image, refAbstract=null), Reference(id=1251505555186070241, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2024, volume=29, issue=3, pageStart=75, pageEnd=82, url=null, language=null, rfNumber=[14], rfOrder=18, authorNames=江祥奎, 杨刚, 杜遥遥, journalName=西安邮电大学学报, refType=null, unstructuredReference=江祥奎,杨刚,杜遥遥.基于轻量化YOLOv8n的动态视觉SLAM算法[J].西安邮电大学学报,2024,29 (3):75-82., articleTitle=基于轻量化YOLOv8n的动态视觉SLAM算法, refAbstract=null), Reference(id=1251505555269956324, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2024, volume=29, issue=3, pageStart=75, pageEnd=82, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=JIANG X K, YANG G, DU Y Y, journalName=Journal of Xi'an University of Posts and Telecommunications, refType=null, unstructuredReference=JIANG X K,YANG G,DU Y Y.Dynamic visual SLAM algorithm based on lightweight YOLOv8n[J]. Journal of Xi'an University of Posts and Telecommunications,2024,29(3):75-82.(in Chinese), articleTitle=Dynamic visual SLAM algorithm based on lightweight YOLOv8n, refAbstract=null), Reference(id=1251505555362231016, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=8759, pageEnd=8768, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=LIU S, QI L, QIN H F, journalName=null, refType=null, unstructuredReference=LIU S,QI L,QIN H F,et al.Path aggregation network for instance segmentation[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:8759-8768., articleTitle=Path aggregation network for instance segmentation, refAbstract=null), Reference(id=1251505555475477229, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=1, pageEnd=5, url=null, language=null, rfNumber=[16], rfOrder=21, authorNames=OUYANG D L, HE S, ZHANG G Z, journalName=null, refType=null, unstructuredReference=OUYANG D L,HE S,ZHANG G Z,et al.Efficient multi-scale attention module with cross-spatial learning[C]//ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing. Rhodes Island:IEEE,2023:1-5., articleTitle=Efficient multi-scale attention module with cross-spatial learning, refAbstract=null), Reference(id=1251505555567751921, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=346, pageEnd=361, url=null, language=null, rfNumber=[17], rfOrder=22, authorNames=HE K M, ZHANG X Y, REN S Q, journalName=null, refType=null, unstructuredReference=HE K M,ZHANG X Y,REN S Q,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[C]//Computer Vision-ECCV 2014. Cham:Springer,2014:346-361., articleTitle=Spatial pyramid pooling in deep convolutional networks for visual recognition, refAbstract=null), Reference(id=1251505555651638006, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=285, pageEnd=289, url=null, language=null, rfNumber=[18], rfOrder=23, authorNames=ZHOU Y T, PIAO J C, journalName=null, refType=null, unstructuredReference=ZHOU Y T,PIAO J C.A lightweight YOLOv7 algorithm for steel surface defect detection[C]//2023 IEEE 6th International Conference on Pattern Recognition and Artificial Intelligence.Haikou:IEEE,2023:285-289., articleTitle=A lightweight YOLOv7 algorithm for steel surface defect detection, refAbstract=null), Reference(id=1251505555735524089, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2019, volume=36, issue=12, pageStart=150, pageEnd=155, url=null, language=null, rfNumber=[19], rfOrder=24, authorNames=李卫疆, 伊靖, journalName=计算机应用与软件, refType=null, unstructuredReference=李卫疆,伊靖.基于扩展特征矩阵和双层卷积神经网络的微博文本情感分类[J].计算机应用与软件, 2019,36(12):150-155., articleTitle=基于扩展特征矩阵和双层卷积神经网络的微博文本情感分类, refAbstract=null), Reference(id=1251505555790050043, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2019, volume=36, issue=12, pageStart=150, pageEnd=155, url=null, language=null, rfNumber=[19], rfOrder=25, authorNames=LIW J, YIJ, journalName=Computer Applications and Software, refType=null, unstructuredReference=LIW J,YIJ.Weibo text sentiment classification based on extended feature matrix and double-layer convolution neural network[J].Computer Applications and Software,2019,36(12):150-155.(in Chinese), articleTitle=Weibo text sentiment classification based on extended feature matrix and double-layer convolution neural network, refAbstract=null), Reference(id=1251505555869741822, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2017, volume=60, issue=6, pageStart=84, pageEnd=90, url=null, language=null, rfNumber=[20], rfOrder=26, authorNames=KRIZHEVSKY A, SUTSKEVER I, HINTON G E, journalName=Communications of the ACM, refType=null, unstructuredReference=KRIZHEVSKY A,SUTSKEVER I,HINTON G E. ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60 (6):84-90., articleTitle=ImageNet classification with deep convolutional neural networks, refAbstract=null), Reference(id=1251505555945239297, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=4830, pageEnd=4839, url=null, language=null, rfNumber=[21], rfOrder=27, authorNames=SINGH P, VERMA V K, RAI P, journalName=null, refType=null, unstructuredReference=SINGH P,VERMA V K,RAI P,et al.HetConv:Heterogeneous kernel-based convolutions for deep CNNs[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach:IEEE, 2020:4830-4839., articleTitle=HetConv:Heterogeneous kernel-based convolutions for deep CNNs, refAbstract=null), Reference(id=1251505556033319685, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2022, volume=52, issue=8, pageStart=8574, pageEnd=8586, url=null, language=null, rfNumber=[22], rfOrder=28, authorNames=ZHENG Z H, WANG P, REN D W, journalName=IEEE Transactions on Cybernetics, refType=null, unstructuredReference=ZHENG Z H,WANG P,REN D W,et al.Enhancing geometric factors in model learning and inference for object detection and instance segmentation[J].IEEE Transactions on Cybernetics, 2022, 52 (8):8574-8586., articleTitle=Enhancing geometric factors in model learning and inference for object detection and instance segmentation, refAbstract=null), Reference(id=1251505556117205770, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2024-10-28, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=29, authorNames=TONG Z J, CHEN Y H, XU Z W, journalName=null, refType=null, unstructuredReference=TONG Z J,CHEN Y H,XU Z W,et al.Wise-IoU:Bounding box regression loss with dynamic focusing mechanism[EB/OL].[2024-10-28].https://arxiv.org/abs/2301.10051., articleTitle=Wise-IoU:Bounding box regression loss with dynamic focusing mechanism, refAbstract=null), Reference(id=1251505556209480460, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2024, volume=39, issue=6, pageStart=116, pageEnd=124, url=null, language=null, rfNumber=[24], rfOrder=30, authorNames=苏志威, 黄子涵, 邱发生, journalName=航空动力学报, refType=null, unstructuredReference=苏志威,黄子涵,邱发生,.基于改进YOLOv8的航空铝合金焊缝缺陷检测方法[J].航空动力学报, 2024,39(6):116-124., articleTitle=基于改进YOLOv8的航空铝合金焊缝缺陷检测方法, refAbstract=null), Reference(id=1251505556293366542, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2024, volume=39, issue=6, pageStart=116, pageEnd=124, url=null, language=null, rfNumber=[24], rfOrder=31, authorNames=SU Z W, HUANG Z H, QIU F S, journalName=Journal of Aerospace Power, refType=null, unstructuredReference=SU Z W,HUANG Z H,QIU F S,et al.Weld defect detection of aviation aluminum alloy based on improved YOLOv8[J].Journal of Aerospace Power,2024,39 (6):116-124.(in Chinese), articleTitle=Weld defect detection of aviation aluminum alloy based on improved YOLOv8, refAbstract=null), Reference(id=1251505556381446931, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2024, volume=60, issue=2, pageStart=191, pageEnd=199, url=null, language=null, rfNumber=[25], rfOrder=32, authorNames=吴明杰, 云利军, 陈载清, journalName=计算机工程与应用, refType=null, unstructuredReference=吴明杰,云利军,陈载清,.改进YOLOv5s的无人机视角下小目标检测算法[J].计算机工程与应用, 2024,60(2):191-199., articleTitle=改进YOLOv5s的无人机视角下小目标检测算法, refAbstract=null), Reference(id=1251505556486304533, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, doi=null, pmid=null, pmcid=null, year=2024, volume=60, issue=2, pageStart=191, pageEnd=199, url=null, language=null, rfNumber=[25], rfOrder=33, authorNames=WU M J, YUN L J, CHEN Z Q, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=WU M J,YUN L J,CHEN Z Q,et al.Improved YOLOv5s small object detection algorithm in UAV view[J]. Computer Engineering and Applications, 2024,60(2):191-199.(in Chinese), articleTitle=Improved YOLOv5s small object detection algorithm in UAV view, refAbstract=null)], funds=null, companyList=[AuthorCompany(id=1251505547887980924, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, xref=1., ext=[AuthorCompanyExt(id=1251505547896369533, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505547887980924, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Computer Science,Xi'an University of Posts and Telecommunications,Xi'an 710121,China), AuthorCompanyExt(id=1251505547904758143, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505547887980924, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安邮电大学计算机学院,陕西西安 710121)]), AuthorCompany(id=1251505547980255621, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, xref=2., ext=[AuthorCompanyExt(id=1251505547988644230, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505547980255621, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Shaanxi Key Laboratory of Intelligent Software Technology,Xi'an 710121,China), AuthorCompanyExt(id=1251505547992838535, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505547980255621, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.智能软件技术陕西省高等学校重点实验室,陕西西安 710121)]), AuthorCompany(id=1251505548076724621, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, xref=3., ext=[AuthorCompanyExt(id=1251505548085113230, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505548076724621, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Kaifeng Dier Air Separation Industrial Co.,LTD,Kaifeng 475000,China), AuthorCompanyExt(id=1251505548089307535, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, companyId=1251505548076724621, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.开封迪尔空分实业有限公司,河南开封 475000)])], figs=[ArticleFig(id=1251505550345843208, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=kVoUwj/R9a2x21KxzLBZZg==, figureFileBig=g82n7MyIU9CM3K3hcumngw==, tableContent=null), ArticleFig(id=1251505550421340684, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=图1, caption=YOLOv8n网络结构示意图, figureFileSmall=kVoUwj/R9a2x21KxzLBZZg==, figureFileBig=g82n7MyIU9CM3K3hcumngw==, tableContent=null), ArticleFig(id=1251505550777856535, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=0kzyhrrb/4+pfdAdXn3GPA==, figureFileBig=6WUH59pEhFQWRyiQ7DUChA==, tableContent=null), ArticleFig(id=1251505550861742618, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=图2, caption=X射线焊缝缺陷检测方法的网络结构示意图, figureFileSmall=0kzyhrrb/4+pfdAdXn3GPA==, figureFileBig=6WUH59pEhFQWRyiQ7DUChA==, tableContent=null), ArticleFig(id=1251505550924657182, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=8Ly8k1chufSTtkeuOwYT+w==, figureFileBig=xVYriSkgUnkFkJqIEOKDeA==, tableContent=null), ArticleFig(id=1251505551000154656, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=图3, caption=EMA_Mul工作原理示意图, figureFileSmall=8Ly8k1chufSTtkeuOwYT+w==, figureFileBig=xVYriSkgUnkFkJqIEOKDeA==, tableContent=null), ArticleFig(id=1251505551088235047, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=aO1kX81QyG39iPgcocGEUQ==, figureFileBig=AGUO/yr4KaF2Fgy7SKOvSw==, tableContent=null), ArticleFig(id=1251505551184704040, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=图4, caption=多尺度池化模块结构示意图, figureFileSmall=aO1kX81QyG39iPgcocGEUQ==, figureFileBig=AGUO/yr4KaF2Fgy7SKOvSw==, tableContent=null), ArticleFig(id=1251505551260201514, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=rUQoC+d3rn0n1ob4MiAgCg==, figureFileBig=s5Uj/FDNAFjH9ehXhO6s9w==, tableContent=null), ArticleFig(id=1251505551360864815, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=图5, caption=SimSPPF_Avg模块结构示意图, figureFileSmall=rUQoC+d3rn0n1ob4MiAgCg==, figureFileBig=s5Uj/FDNAFjH9ehXhO6s9w==, tableContent=null), ArticleFig(id=1251505551465722420, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=RdVzW1tBh6bXdtZSWKV1EA==, figureFileBig=8Utu7sZ8dMU9UCnnCTVRrQ==, tableContent=null), ArticleFig(id=1251505551562191419, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=图6, caption=DualConv结构示意图, figureFileSmall=RdVzW1tBh6bXdtZSWKV1EA==, figureFileBig=8Utu7sZ8dMU9UCnnCTVRrQ==, tableContent=null), ArticleFig(id=1251505551650271803, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=EJyBf/NDRSH5RHbqHNRJTQ==, figureFileBig=bFtD2Clek4yRZ7LStCm4zg==, tableContent=null), ArticleFig(id=1251505551721574973, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=图7, caption=C2f_Dual模块结构示意图, figureFileSmall=EJyBf/NDRSH5RHbqHNRJTQ==, figureFileBig=bFtD2Clek4yRZ7LStCm4zg==, tableContent=null), ArticleFig(id=1251505551797072449, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=XZ5cJm0Kj4CKsODCEhRPSg==, figureFileBig=lKuW14Lk4QThX/V2xXQxgg==, tableContent=null), ArticleFig(id=1251505551906124357, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=图8, caption=部分训练集图像示例, figureFileSmall=XZ5cJm0Kj4CKsODCEhRPSg==, figureFileBig=lKuW14Lk4QThX/V2xXQxgg==, tableContent=null), ArticleFig(id=1251505551998399049, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=ozI6jPgJd+qwjC1BPbqCWw==, figureFileBig=LeJKVRuKQTX/EPMcs9fUlA==, tableContent=null), ArticleFig(id=1251505552082285134, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=图9, caption=两种方法的PR曲线对比, figureFileSmall=ozI6jPgJd+qwjC1BPbqCWw==, figureFileBig=LeJKVRuKQTX/EPMcs9fUlA==, tableContent=null), ArticleFig(id=1251505552145199698, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=La2l7cfXudzZlcnN6HSwGQ==, figureFileBig=zsHpV25p21n366vwV1iRKg==, tableContent=null), ArticleFig(id=1251505552212308565, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=图10, caption=两种损失函数损失值变化对比结果, figureFileSmall=La2l7cfXudzZlcnN6HSwGQ==, figureFileBig=zsHpV25p21n366vwV1iRKg==, tableContent=null), ArticleFig(id=1251505552300388956, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=dbvuhAMfG5cUEARHNnca2Q==, figureFileBig=4wYl1NPoPRL/B3iO/3DGaQ==, tableContent=null), ArticleFig(id=1251505552409440864, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=图11, caption=5组消融实验的训练曲线对比结果, figureFileSmall=dbvuhAMfG5cUEARHNnca2Q==, figureFileBig=4wYl1NPoPRL/B3iO/3DGaQ==, tableContent=null), ArticleFig(id=1251505552484938341, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=5qOeSRq1qbUnObjJJE3ANg==, figureFileBig=WJwyO39HVaWoqLH9BW5M7w==, tableContent=null), ArticleFig(id=1251505552547852904, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=图12, caption=两种方法检测结果对比, figureFileSmall=5qOeSRq1qbUnObjJJE3ANg==, figureFileBig=WJwyO39HVaWoqLH9BW5M7w==, tableContent=null), ArticleFig(id=1251505552623350380, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
模块mAP@0.5/%模型参数量/MGFLPsFPS
EMA77.83.018.2145.1
EMA_Mul78.83.018.2146.6
), ArticleFig(id=1251505552694653551, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=表1, caption=

EMA模块对比实验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模块mAP@0.5/%模型参数量/MGFLPsFPS
EMA77.83.018.2145.1
EMA_Mul78.83.018.2146.6
), ArticleFig(id=1251505552774345332, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
模块mAP@0.5/%模型参数量/MGFLPsFPS
SPPF75.63.018.1187.5
SimSPPF77.13.018.1246.4
SimSPPF_Avg81.53.078.3172.7
), ArticleFig(id=1251505552866620023, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=表2, caption=

SPPF模块对比实验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模块mAP@0.5/%模型参数量/MGFLPsFPS
SPPF75.63.018.1187.5
SimSPPF77.13.018.1246.4
SimSPPF_Avg81.53.078.3172.7
), ArticleFig(id=1251505552963089023, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
实验EMA_MulSimSPPF_AvgC2f_DualWIoU精确率/%召回率/%mAP@0.5/%模型参数量/MGFLOPsFPS
178.273.775.63.018.1187.5
279.676.978.83.018.2146.6
379.978.680.53.078.4146.7
478.677.680.32.897.9132.6
583.575.881.52.897.9135.4
), ArticleFig(id=1251505553038586499, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=表3, caption=

消融实验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
实验EMA_MulSimSPPF_AvgC2f_DualWIoU精确率/%召回率/%mAP@0.5/%模型参数量/MGFLOPsFPS
178.273.775.63.018.1187.5
279.676.978.83.018.2146.6
379.978.680.53.078.4146.7
478.677.680.32.897.9132.6
583.575.881.52.897.9135.4
), ArticleFig(id=1251505553130861190, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
缺陷种类YOLOv8n改进方法
裂纹68.378.8
未熔合/未焊透78.481.8
气孔67.575.5
夹渣88.389.7
), ArticleFig(id=1251505553231524491, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=表4, caption=

改进前后各类缺陷的mAP@0.5/%

, figureFileSmall=null, figureFileBig=null, tableContent=
缺陷种类YOLOv8n改进方法
裂纹68.378.8
未熔合/未焊透78.481.8
气孔67.575.5
夹渣88.389.7
), ArticleFig(id=1251505553307021967, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
方法mAP@0.5/%模型参数量/MGFLOPsFPS
Faster R-CNN72.3136.80401.857.4
RetinaNet80.836.40147.085.3
YOLOv5n77.22.507.1173.9
YOLOv8n75.63.008.1187.5
YOLOv976.260.90266.2228.8
YOLOv11n80.12.606.4165.5
所提方法81.52.897.9135.4
), ArticleFig(id=1251505553424462483, tenantId=1146029695717560320, journalId=1251233954884272221, articleId=1251505542196310129, language=CN, label=表5, caption=

不同方法的对比实验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
方法mAP@0.5/%模型参数量/MGFLOPsFPS
Faster R-CNN72.3136.80401.857.4
RetinaNet80.836.40147.085.3
YOLOv5n77.22.507.1173.9
YOLOv8n75.63.008.1187.5
YOLOv976.260.90266.2228.8
YOLOv11n80.12.606.4165.5
所提方法81.52.897.9135.4
)], attaches=null, journal=Journal(id=1251231493423411294, delFlag=0, nameCn=西安邮电大学学报, nameEn=Journal of Xi'an University of Posts and Telecommunications, nameHistory1=null, nameHistory2=null, issn=2095-6533, eissn=, cn=61-1493/TN, coden=null, periodic=双月刊, language=CN, oaType=1, 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=, officePhone=, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=tH6CrDBQFqwqmwUccjpjow==, journalPrice=null, startedYear=null, abbrevIsoEn=Journal of Xi'an University of Posts and Telecommunications, journalRemark=null, publicationField=null, createdTime=1776246434792, updatedTime=1776251858439, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=J, firstLetterEn=J, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=tH6CrDBQFqwqmwUccjpjow==, picEn=TGVaHCgPGQlZdesVp9aDew==, jcr=null, cjcr=null, exts=[JournalExt(id=1251254241990493156, language=CN, name=西安邮电大学学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1776251858470, updatedTime=1776251858470, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://xayd.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://xayd.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://xayd.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1251254242036630501, language=EN, name=Journal of Xi'an University of Posts and Telecommunications, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1776251858481, updatedTime=1776251858481, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://xayd.cbpt.cnki.net/index.aspx?t=1, submissionEditorUrl=https://xayd.cbpt.cnki.net/index.aspx?t=3, submissionReviewUrl=https://xayd.cbpt.cnki.net/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1251233954884272221, websiteList=[Website(id=1251257283410346025, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1251233954884272221, 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/xayddxxb/CN, language=CN, createTime=1776252583601, createBy=18614031015, updateTime=1776252942185, updateBy=18614031015, name=西安邮电大学学报-中文, tplId=1146099689490845704, title=西安邮电大学学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1251258885185683591, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283410346025, code=articleTextType, value=kx, createTime=1776252965494, updateTime=1776252965494, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258885160517764, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283410346025, code=banner, value=null, createTime=1776252965488, updateTime=1776252965488, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258885202460810, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283410346025, code=grayFlag, value=0, createTime=1776252965498, updateTime=1776252965498, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258885152129155, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283410346025, code=logo, value=https://castjournals.cast.org.cn/joweb/xayddxxb/CN/file/pic?fileId=oIRdMBF7r3ynDYM5hP49NA==, createTime=1776252965486, updateTime=1776252965486, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258885219238028, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283410346025, code=minRunFlag, value=0, createTime=1776252965502, updateTime=1776252965502, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258885177294982, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283410346025, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/xayddxxb/CN/file/pic, createTime=1776252965492, updateTime=1776252965492, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258885210849419, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283410346025, code=silenceFlag, value=0, createTime=1776252965500, updateTime=1776252965500, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258885168906373, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283410346025, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1776252965490, updateTime=1776252965490, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258885194072200, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283410346025, code=themeColor, value=null, createTime=1776252965496, updateTime=1776252965496, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258885198266505, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283410346025, code=themeStyle, value=null, createTime=1776252965497, updateTime=1776252965497, creator=18614031015, updator=18614031015)]), Website(id=1251257283594895425, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1251233954884272221, 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/xayddxxb/EN, language=EN, createTime=1776252583645, createBy=18614031015, updateTime=1776252932924, updateBy=18614031015, name=西安邮电大学学报-英文, tplId=1146101810881728533, title=Journal of Xi'an University of Posts and Telecommunications, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1251258912788398232, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283594895425, code=articleTextType, value=kx, createTime=1776252972075, updateTime=1776252972075, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258912767426709, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283594895425, code=banner, value=null, createTime=1776252972070, updateTime=1776252972070, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258912805175451, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283594895425, code=grayFlag, value=0, createTime=1776252972079, updateTime=1776252972079, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258912759038100, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283594895425, code=logo, value=https://castjournals.cast.org.cn/joweb/xayddxxb/EN/file/pic?fileId=oIRdMBF7r3ynDYM5hP49NA==, createTime=1776252972068, updateTime=1776252972068, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258912813564061, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283594895425, code=minRunFlag, value=0, createTime=1776252972081, updateTime=1776252972081, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258912780009623, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283594895425, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/xayddxxb/EN/file/pic, createTime=1776252972073, updateTime=1776252972073, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258912809369756, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283594895425, code=silenceFlag, value=0, createTime=1776252972080, updateTime=1776252972080, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258912771621014, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283594895425, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1776252972071, updateTime=1776252972071, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258912792592537, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283594895425, code=themeColor, value=null, createTime=1776252972076, updateTime=1776252972076, creator=18614031015, updator=18614031015), WebsiteProps(id=1251258912796786842, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1251257283594895425, code=themeStyle, value=null, createTime=1776252972077, updateTime=1776252972077, creator=18614031015, updator=18614031015)])], journalTitle=西安邮电大学学报, weixinUrl=null, journalUrl=https://xayd.cbpt.cnki.net/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Journal of Xi'an University of Posts and Telecommunications, journalPhotoCn=tH6CrDBQFqwqmwUccjpjow==, journalPhotoEn=TGVaHCgPGQlZdesVp9aDew==, journalFirstLetter=J, 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=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/xayddxxb/CN/10.13682/j.issn.2095-6533.2025.06.012, detailUrlEn=https://castjournals.cast.org.cn/joweb/xayddxxb/EN/10.13682/j.issn.2095-6533.2025.06.012, pdfUrlCn=https://castjournals.cast.org.cn/joweb/xayddxxb/CN/PDF/10.13682/j.issn.2095-6533.2025.06.012, pdfUrlEn=https://castjournals.cast.org.cn/joweb/xayddxxb/EN/PDF/10.13682/j.issn.2095-6533.2025.06.012, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
一种X射线焊缝缺陷检测方法
收藏切换
PDF下载
王小银 1, 2 , 秦梦媛 1 , 李冠雄 3 , 王曙燕 1
西安邮电大学学报 | 人工智能目标检测 2025,30(6): 104-112
收起
收藏切换
西安邮电大学学报 | 人工智能目标检测 2025, 30(6): 104-112
一种X射线焊缝缺陷检测方法
全屏
王小银1, 2 , 秦梦媛1 , 李冠雄3 , 王曙燕1
作者信息
  • 1.西安邮电大学计算机学院,陕西西安 710121
  • 2.智能软件技术陕西省高等学校重点实验室,陕西西安 710121
  • 3.开封迪尔空分实业有限公司,河南开封 475000
  • 王小银(1976-),女,陕西西安人,硕士,西安邮电大学教授,主要研究方向为人工智能、大数据挖掘等。E-mail:

    秦梦媛(1997-),女,山西吕梁人,西安邮电大学硕士研究生,主要研究方向为焊缝缺陷检测技术。E-mail:

    李冠雄(1986-),男,河南开封人,博士,开封迪尔空分实业有限公司董事,主要研究方向为智能空分技术。E-mail:

    王曙燕(1964-),女,河南南阳人,博士,西安邮电大学教授,主要研究方向为智能信息处理、大数据分析、软件测试。E-mail:

An X-ray weld defect detection method
Xiaoyin WANG1, 2 , Mengyuan QIN1 , Guanxiong LI3 , Shuyan WANG1
Affiliations
  • 1.School of Computer Science,Xi'an University of Posts and Telecommunications,Xi'an 710121,China
  • 2.Shaanxi Key Laboratory of Intelligent Software Technology,Xi'an 710121,China
  • 3.Kaifeng Dier Air Separation Industrial Co.,LTD,Kaifeng 475000,China
出版时间: 2025-11-10 doi: 10.13682/j.issn.2095-6533.2025.06.012
文章导航
收藏切换

针对X射线焊缝缺陷检测中存在的漏检、检测精度低等问题,提出一种X射线焊缝缺陷检测方法。首先,将高效多尺度注意力(Efficient Multi-scale Attention,EMA)模块中3×3卷积核替换为5×5卷积核,以扩大感受野,同时将平均池化改为多尺度池化,以提取多尺度特征。将改进后的EMA模块嵌入主干网络,增强多尺度缺陷检测能力。然后,引入自适应平均池化层和最大池化层,改进空间金字塔池化模块,提升对焊缝边缘信息的感知能力。最后,在颈部采用Dual卷积替代传统卷积,降低模型参数量,并使用WIoU(Wise Intersection over Union)损失函数替代CIoU(Complete Intersection over Union)损失函数,提高模型的收敛速度。实验结果表明,与YOLOv8n相比,所提方法的参数量降低了4.02%,平均精度均值提升了5.9%,可适用于X射线焊缝缺陷检测任务。

焊缝缺陷检测  /  YOLOv8n  /  高效多尺度注意力  /  Dual卷积  /  WIoU损失函数

To address the issues of missed detection and low detection accuracy in X-ray weld defect detection,an improved YOLOv8-based detection method is proposed.Firstly,the efficient multi-scale attention(EMA)mechanism is improved by replacing the 3×3 convolutional kernel with a 5×5 kernel to expand the receptive field,and replacing the average pooling with the multi-scale pooling to extract multi-scale features.The improved EMA module is embedded into the backbone network to enhance the model's ability to detect defects at various scales.Then the spatial pyramid pooling fast module is improved by introducing adaptive average pooling and max pooling layers,to improve the perception of weld edge information.Finally,in the neck part,Dual convolution is used to replace traditional convolution,to reduce the parameter number of the model.The WIoU(wise intersection over union)loss function is adopted to replace the CIoU(complete intersection over union)loss function to improve the convergence speed of the model. Experimental results show that,compared to YOLOv8n,the proposed algorithm reduces the number of parameters by 4.02%and increases the mean average precision by 5.9%,which is well-suited for X-ray weld defect detection tasks.

weld defect detection  /  YOLOv8n  /  efficient mutti-scale attention  /  Dual convolution  /  WIoU loss function
王小银, 秦梦媛, 李冠雄, 王曙燕. 一种X射线焊缝缺陷检测方法. 西安邮电大学学报, 2025 , 30 (6) : 104 -112 . DOI: 10.13682/j.issn.2095-6533.2025.06.012
Xiaoyin WANG, Mengyuan QIN, Guanxiong LI, Shuyan WANG. An X-ray weld defect detection method[J]. Journal of Xi'an University of Posts and Telecommunications, 2025 , 30 (6) : 104 -112 . DOI: 10.13682/j.issn.2095-6533.2025.06.012
焊接技术在现代工业中被广泛应用,在国内制造业中占重要战略地位。在焊接过程中,可能会产生类似裂纹、夹渣、未熔合、未焊透和气孔等缺陷[1]。因此,在焊接完成后必须进行精准的缺陷检测,从而采取修复措施。目前焊缝内部缺陷通常使用X射线检测方法。操作人员通过观察X射线图像中的特征,判断产品是否存在缺陷,但是在人工评定过程中,大部分时间都花在查看无缺陷图像上,导致操作人员劳动强度大、效率难以提高。因此,迫切需要计算机技术辅助人工进行复评复查,以提高检测效率[2]
随着人工智能的兴起,深度学习已经被广泛应用于工业焊缝缺陷检测领域。目前基于深度学习的缺陷检测算法从结构上一般可划分为两阶段算法和一阶段算法。两阶段算法包括区域卷积神经网络[3](Region-based Convolutional Neural Network,R-CNN)等,一阶段算法包括SSD[4](Single Shot MultiBox Detector)、YOLO(You Only Look Once)系列[5]和RetinaNet[6]等。两阶段算法通常检测精度更高,尤其是在复杂场景或目标较小的情况下,但需要更多的计算资源和时间。而一阶段算法的优点是速度快,能够快速识别和定位目标,适用于实时检测任务。目前主流的一阶段算法主要是YOLO系列算法,其中YOLOv3[7]、YOLOv5[8]、YOLOv6[9]和YOLOv8[10]等被广泛应用。在众多学者的共同努力下,YOLO算法通过不断优化与创新,能够高效处理各种复杂场景下的检测任务。如文献[11]提出了一种基于YOLOv5的轻量型焊缝缺陷检测方法,其在主干部分加入SELayer注意力机制,减少了模型的参数量。文献[12]提出了一种轻量化卷积模块GSConvns,并结合LAMP(Learning Algorithmfor Model Pruning)剪枝策略,通过去除不重要的权重参数,使得改进后的YOLOv8模型参数量和计算量均降低了80%以上。文献[13]提出了一种融合增强多尺度特征(Reinforced Multiscale Feature,RMF)模块和高效特征提取模块(Efficient Feature Extraction,EFE)的LF-YOLO算法,提升了焊缝缺陷检测速度。
上述方法虽然在一定程度上实现了轻量化,但在减少模型参数量的同时往往导致检测精度下降。尽管YOLO系列已发展到YOLOv11,但其成熟度和稳定性仍需进一步验证。相比之下,YOLOv8应用更加成熟,适合工业X射线焊缝缺陷检测的实际需求。因此,针对X射线焊缝缺陷检测中存在的漏检、误检、检测精度低等问题,本文选取参数量最小的YOLOv8n作为改进对象,提出一种X射线焊缝缺陷检测方法,以期在显著降低模型参数量的同时,进一步提升检测精度。该方法将3×3卷积核替换为5×5卷积核,对高效多尺度注意力(Efficient Multi-Scale Attention,EMA)模块进行改进,以扩大感受野捕捉更大范围的上下文信息。同时,将平均池化改为多尺度池化,并行使用2×2、4×4、6×6和8×8池化核,以提取多尺度特征。将改进后的EMA模块嵌入主干网络,然后引入自适应平均池化层和自适应最大池化层,改进空间金字塔池化(Spatial Pyramid Pooling Fast,SPPF)模块,设计SimSPPF_Avg模块,利用两种池化操作平衡全局与局部信息,提升对焊缝边缘特征的感知能力,从而提高缺陷检测精度。在颈部网络中,利用Dual-Conv改进C2f模块,设计轻量化的C2f_DualConv模块,减少模型的参数量。同时,使用WIoU(Wise Intersection over Union)损失函数替代CIoU(Complete Intersection over Union)损失函数,通过动态非单调聚焦机制调整边界框回归权重,从而提高模型的收敛速度。
YOLOv8提供了n、s、m、l、x共5种模型,满足不同计算资源和应用场景的需求。其中n模型在所有模型中规模最小,x模型规模最大。因此YOLOv8n最适合X射线焊缝缺陷检测任务。
YOLOv8n模型是由输入层、主干网络、颈部网络和检测头等4部分组成。输入层采用Mosaic的数据增强方法,增加数据集的多样性,并针对不同大小的模型进行超参数调整。主干网络是模型的核心,负责从输入图像中提取高维语义特征,由多个Conv模块、C2f模块和SPPF模块组成。颈部网络主要用于特征融合,采用特征金字塔网络[14](Feature Pyramid Network,FPN)和路径聚合网络[15](Path Aggregation Network,PAN)结构。检测头是最终输出检测结果的模块,YOLOv8n从原来的耦合头变成了解耦头,将分类和检测头分离,从基于锚框(Anchor-Based)改为无锚框(Anchor-Free)。YOLOv8n网络结构示意图如图1所示。
为了提高YOLOv8n模型的检测效率,X射线焊缝缺陷检测方法分别从主干网络、颈部网络、损失函数等方面进行改进,其网络结构示意图如图2所示。
EMA[16]是一种高效的多尺度注意力机制,不仅可以通过全局信息编码调整并行子网络的通道权重,还可以通过跨尺度交互融合两个并行子网络的输出特征。
将EMA模块中3×3的卷积核替换为5×5的卷积核,以扩大感受野,使模型能够捕捉更大空间范围内的上下文信息。同时,将3×3卷积后的平均池化操作改为多尺度池化,并行使用2×2、4×4、6×6和8×8的池化核对输入特征图进行处理,以提取多尺度特征。在YOLOv8n的主干网络中引入改进后的EMA模块,并将其命名为EMA_Mul,其工作原理示意图如图3所示。
在EMA模块中引入多尺度池化模块,其核心思想来源于空间金字塔池化[17],通过并行使用2×2、4×4、6×6和8×8池化核对输入特征图进行处理。使用不同大小的池化核对输入特征图进行池化操作,不同大小的池化核可以提取多尺度特征。小池化核捕捉细节特征,而大池化核则关注整体结构。如细小裂纹适合小池化核,而未焊透这类缺陷更易被大池化核识别。多尺度池化模块结构示意图如图4所示。
假设输入特征图为XRB×C×H×W,其中B表示批量大小,C表示通道数,HW分别表示特征图的高度和宽度。对输入特征图进行4种不同大小的池化操作(MaxPool2d),分别表示为
将池化后的特征图上采样回原始尺寸,并将原始特征图和上采样后的特征图在通道维度上拼接。最后,使用1×1卷积减少通道数,并将结果与原始输入特征图融合,输出特征图的尺寸与输入特征图的尺寸一致。EMA_Mul在保留EMA注意力核心思想的基础上,通过引入多尺度池化和更大卷积核,增强了模型的特征提取能力。
YOLOv8n采用SPPF结构,以丰富特征图中包含的特征信息。然而,SPPF仅依赖最大池化操作来提取特征,可能会导致一些重要的局部信息丢失。为此,使用SimSPPF[18]模块替代YOLOv8n原有的SPPF模块,并对其进行改进,设计SimSPPF_Avg模块。
SimSPPF_Avg模块将输入特征图划分为4个部分。第一部分串联3个尺寸为5×5的最大池化层(MaxPool2d),第二部分和第三部分分别通过自适应最大池化层(AdaptiveMaxPool2d)和自适应平均池化层(AdaptiveAvgPool2d)处理,第四部分通过SimConv处理。将上述所有部分特征通过Concat层进行融合,从而生成固定尺寸的特征图。Sim-SPPF_Avg模块结构示意图如图5所示。
SimSPPF_Avg模块通过引入自适应平均池化层和自适应最大池化层,有效平衡了全局与局部信息,显著提升了模型对焊缝边缘特征的感知能力。
在YOLOv8n网络中,颈部网络的C2f模块通过残差连接学习特征。利用DualConv[19]改进C2f模块,设计轻量化的C2f_Dual模块。DualConv结合了组卷积[20]和异构卷积[21]的优点,并且比标准卷积更加轻量化。在DualConv中,一部分卷积核同时执行3×3和1×1卷积操作,而另一部分卷积核只执行1×1卷积操作。3×3卷积采用组卷积的方式处理输入特征映射图的通道,而1×1卷积则对所有的输入特征映射图通道进行处理。这种设计使得DualConv可以视为3×3组卷积和1×1逐点卷积的结合,在减少参数量的同时保持了特征提取的能力。DualConv结构示意图如图6所示。
基于DualConv构建C2f_Dual模块,并对C2f中的Bottleneck进行改进,命名为DualBottleneck。C2f_Dual模块结构示意图如图7所示。
YOLOv8n通常使用CIoU损失函数,其计算表达式[22]
其中,
式中:LCIoU为损失函数值;LIoU为预测框和真实框重叠面积的交并比值;b为预测框;bgt为真实框中心;ρ(·)表示欧氏距离;c表示预测框和真实框的最小闭包框对角线距离;αv为惩罚因子;w为预测框的宽;h为预测框的高;wgt为真实框的宽;hgt为真实框的高。
CIoU损失函数虽然引入了宽高比的惩罚项,但在实际应用中,宽高比的定义并不十分清晰。对于形状复杂的缺陷,预测框的宽高比可能与真实框有较大差异,从而影响检测效果。为此,选择使用WIoU损失函数[23]替换CIoU损失函数。WIoU损失函数引入了动态非单调聚焦机制,对于高质量的边界框,WIoU会降低其损失权重,以避免其在梯度更新过程中产生过大的影响。对于低质量的边界框,WIoU会增加其损失权重,使模型能够更有效地识别和调整样本。这种动态调整机制不仅使模型在训练过程中更加稳定,还显著降低了损失值,同时加快了收敛速度。
预测框的异常程度定义为
式中:为变量转换成的常量。
根据β构建动态非单调聚焦机制,并与基于注意力的边界框损失相结合,得到能随时分配符合当时情况梯度增益的WIoU损失函数为
其中,
式中:RWIoU∈[1,e),会显著放大正常质量锚框的LIoU
实验平台基于64位的Windows11操作系统,内存为24GiB。硬件配置:CPU为18Vcpu;AMD EPYC 9754;GPU为NVIDIA RTX4090。编译环境为Python3.10+PyTorch 2.1.0+CUDA 12.1。将初始学习率设置为0.0001,批量大小设置为16,优化器为Adamw,实验训练的轮数设置为300,输入图像尺寸为640×640。
实验采用GDxray数据集,并在公开数据集的基础上添加开封迪尔空分公司提供的X射线焊缝缺陷图像,制作焊缝缺陷图像数据集。该数据集包含在焊接过程中出现的气孔、夹渣、未熔合、未焊透和裂纹等5类缺陷,其中未熔合和未焊透的影像特征相似,难以区分,故将这两类缺陷合为一类缺陷进行识别[24]。使用传统图像增强方法对训练数据集进行增强,如旋转,增加噪音等方式。最终按照7∶1.5∶1.5的比例分别生成训练集、验证集和测试集。训练集、验证集、测试集的图像分别为1610张、345张和345张。部分训练集图像示例如图8所示。
为了能够有效直观地展示对YOLOv8n的改进效果,采用精确率、召回率、模型参数量、平均精度均值@0.5(Mean Average Precision@0.5,mAP@0.5),每秒10亿次的浮点运算数(Giga Floatingpoint Operations Per Second,GFLPs)和每秒检测帧数(Frame Per Second,FPS)作为性能评价指标[25]
为了验证所提方法的有效性,将其与YOLOv8n进行对比实验,实验过程保持参数设置一致。两种方法的PR(Precision-Recall)曲线对比如图9所示。PR曲线是精确率-召回率曲线,可以反映模型的改进效果。从图9可以看出,裂纹、未熔合/未焊透、夹渣、气孔缺陷的检测精确率都有所提高,因此所提方法相比于YOLOv8n在所有目标类别上均表现出更高的检测效率。
为了验证EMA_Mul模块的检测效果,将其与EMA模块进行对比实验,结果如表1所示。
表1实验结果可知,EMA_Mul模块比原始EMA模块的mAP提升了1%,表明其改进后的特征提取能力更强。
为了验证SimSPPF_Avg模块在X射线焊缝缺陷检测任务中的提升效果,将其与SPPF模块、SimSPPF模块进行对比实验,结果如表2所示。
表2结果可知,SimSPPF_Avg模块的mAP比SPPF模块高5.9%,比SimSPPF模块高4.4%,效果更好。
为了验证WIoU损失函数在焊缝缺陷检测任务中的优越效果,基于CIoU损失函数和WIoU损失函数的YOLOv8n模型在300个训练轮次中的损失值随迭代轮次的变化对比结果如图10所示。
图10可以看出,使用WIoU的YOLOv8n模型的损失值在训练初期和中期下降得更快,且最终损失值略低于YOLOv8n模型,表明使用WIoU损失函数检测效果更好。
为了全面体现各项改进对YOLOv8n模型性能提升的效果,设计5组消融实验进行对比,以评估每个模块改进对模型性能的独立影响。消融实验结果如表3所示。由表3数据可以看出,与实验1原始YOLOv8n模型相比,实验5所提方法在精确率、召回率和mAP分别提升了5.3%、2.1%和5.9%,同时模型参数量降低了4.02%,GFLPs减少了0.2G,FPS达到135.4。因此,模块的改进不仅显著提升了模型的检测精度,还实现了模型的轻量化。
为了更直观地展示改进效果,5组消融实验在300个训练周期中的训练曲线对比结果如图11所示。可以看出,所提方法的mAP收敛值显著高于其他模型,进一步验证了改进措施的有效性。
YOLOv8n和所提方法在各类焊缝缺陷检测任务中的mAP@0.5对比如表4所示。可以看出,所提方法在各类缺陷上的检测精度均有提升,其中裂纹的mAP提升了10.5%,提升幅度最大;气孔的mAP提升了8.0%;未熔合/未焊透的mAP提升了3.4%;夹渣的mAP提升了1.4%。由此证明所提方法对不同种类的焊缝缺陷检测都具有普适性。
为了更直观地验证所提方法的检测效果,从测试集中选取了几张具有代表性的图片,分别采用所提方法和YOLOv8n进行检测,两种方法检测结果对比如图12所示。可以看出,所提方法在夹渣、气孔等缺陷的漏检现象得到了改善,并且检测结果的置信度也有所提高,说明检测结果的准确性也有所提升。
为了进一步验证所提方法在目标检测任务中的综合性能,将其与Faster R-CNN、RetinaNet、YOLOv5n、YOLOv8n、YOLOv9和YOLOv11n等主流目标检测算法进行对比实验,结果如表5所示。实验在相同的实验环境和参数设置下进行,使用同一数据集对各算法的性能进行全面评估。
表5可以看出,所提方法的mAP为81.5%,显著优于其他方法,表明所提方法在检测精度上具有明显优势。虽然YOLOv11n的模型参数和检测速度略高于所提方法,但所提方法的mAP高于YOLOv11n。因此,所提方法在检测精度与轻量化之间取得了良好的平衡。
针对X射线焊缝缺陷检测任务中存在的不足,提出了一种X射线焊缝缺陷检测方法。将改进的EMA模块引入主干网络中,捕捉更大范围的上下文信息。设计SimSPPF_Avg模块,提升对焊缝边缘特征的感知能力。同时将颈部网络的C2f模块替换为C2f_Dual模块,减少模型的参数量。最后使用WIoU损失函数代替CIoU损失函数,提高模型的收敛速度。实验结果表明,所提方法与YOLOv8n相比,模型参数量减少4.02%,mAP提升5.9%,在检测精度和轻量化方面均表现出显著优势,更适用于X射线焊缝缺陷检测任务。
参考文献 引证文献
排序方式:
[1]
吴磊,储钰昆,杨洪刚,.基于YOLOv7TS的铝合金焊缝DR图像缺陷检测技术[J].中国激光,2024, 51(20):12-21.
WU L,CHU Y K,YANG H G,et al.Aluminum alloy weld DR image defect detection technology based on YOLOv7TS[J].Chinese Journal of Lasers,2024, 51(20):12-21.(in Chinese)
[2]
SCHMIDT-HIEBER J. Nonparametric regression using deep neural networks with ReLU activation function[J]. Annals of Statistics, 2020, 48 (4):1875-1897.
[3]
REN S Q,HE K M,GIRSHICK R,et al.Faster RCNN:Toward real-time object detection with region proposal networks[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6):1137-1149.
[4]
LIU W,ANGUELOV D,ERHAN D,et al.SSD:Single shot MultiBox detector[C]//Computer Vision-ECCV 2016.Cham:Springer,2016:21-37.
[5]
REDMON J,DIVVALA S,GIRSHICK R,et al.You only look once: Unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas: IEEE, 2016:779-788.
[6]
LIN T Y,GOYAL P,GIRSHICK R,et al.Focal loss for dense object detection[C]//2017 IEEE International Conference on Computer Vision. Venice:IEEE, 2017:2999-3007.
[7]
LAWAL M O.Tomato detection based on modified YOLOv3 framework[J]. Scientific Reports, 2021, 11:1447.
[8]
江祥奎,杜遥遥,胡浩昌.一种改进YOLOv5s小目标无人机实时检测算法[J].西安邮电大学学报,2023, 28(3):88-96.
JIANG X K, DU Y Y, HU H C. An improved YOLOv5s real-time detection algorithm for small target UAVs[J].Journal of Xi'an University of Posts and Telecommunications,2023,28(3):88-96.(in Chinese)
[9]
李德永,王国法,郭永存,.基于CFS-YOLO算法的复杂工况环境下煤矸图像识别方法[J].煤炭科学技术,2024,52(6):226-237.
LI D Y,WANG G F,GUO Y C,et al.Image recognition method of coal gangue in complex working conditions based on CES-YOLO algorithm[J].Coal Science and Technology,2024,52(6):226-237.(in Chinese)
[10]
TERVEN J,CÓRDOVA-ESPARZA D M,ROMERO-GONZÁLEZ J A.A comprehensive review of YOLO architectures in computer vision:From YOLOv1 to YOLOv8 and YOLO-NAS[J].Machine Learning and Knowledge Extraction,2023,5(4):1680-1716.
[11]
程松,杨洪刚,徐学谦,.基于YOLOv5的改进轻量型X射线铝合金焊缝缺陷检测算法[J].中国激光, 2022,49(21):130-138.
CHENG S,YANG H G,XU X Q,et al.Improved lightweight X-ray aluminum alloy weld defects detection algorithm based on YOLOv5[J].Chinese Journal of Lasers,2022,49(21):130-138.(in Chinese)
[12]
张上,许欢,张岳.轻量级锻件表面裂纹检测算法[J].电子测量技术,2024,47(11):123-130.
ZHANG S,XU H,ZHANG Y.Lightweight forged part surface crack detection algorithm[J].Electronic Measurement Technology,2024,47(11):123-130.(in Chinese)
[13]
LIU M Y,CHEN Y P,XIE J M,et al.LF-YOLO:A lighter and faster YOLO for weld defect detection of Xray image[J].IEEE Sensors Journal,2023,23(7):7430-7439.
[14]
江祥奎,杨刚,杜遥遥.基于轻量化YOLOv8n的动态视觉SLAM算法[J].西安邮电大学学报,2024,29 (3):75-82.
JIANG X K,YANG G,DU Y Y.Dynamic visual SLAM algorithm based on lightweight YOLOv8n[J]. Journal of Xi'an University of Posts and Telecommunications,2024,29(3):75-82.(in Chinese)
[15]
LIU S,QI L,QIN H F,et al.Path aggregation network for instance segmentation[C]//2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Salt Lake City:IEEE,2018:8759-8768.
[16]
OUYANG D L,HE S,ZHANG G Z,et al.Efficient multi-scale attention module with cross-spatial learning[C]//ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing. Rhodes Island:IEEE,2023:1-5.
[17]
HE K M,ZHANG X Y,REN S Q,et al.Spatial pyramid pooling in deep convolutional networks for visual recognition[C]//Computer Vision-ECCV 2014. Cham:Springer,2014:346-361.
[18]
ZHOU Y T,PIAO J C.A lightweight YOLOv7 algorithm for steel surface defect detection[C]//2023 IEEE 6th International Conference on Pattern Recognition and Artificial Intelligence.Haikou:IEEE,2023:285-289.
[19]
李卫疆,伊靖.基于扩展特征矩阵和双层卷积神经网络的微博文本情感分类[J].计算机应用与软件, 2019,36(12):150-155.
LIW J,YIJ.Weibo text sentiment classification based on extended feature matrix and double-layer convolution neural network[J].Computer Applications and Software,2019,36(12):150-155.(in Chinese)
[20]
KRIZHEVSKY A,SUTSKEVER I,HINTON G E. ImageNet classification with deep convolutional neural networks[J].Communications of the ACM,2017,60 (6):84-90.
[21]
SINGH P,VERMA V K,RAI P,et al.HetConv:Heterogeneous kernel-based convolutions for deep CNNs[C]//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition.Long Beach:IEEE, 2020:4830-4839.
[22]
ZHENG Z H,WANG P,REN D W,et al.Enhancing geometric factors in model learning and inference for object detection and instance segmentation[J].IEEE Transactions on Cybernetics, 2022, 52 (8):8574-8586.
[23]
TONG Z J,CHEN Y H,XU Z W,et al.Wise-IoU:Bounding box regression loss with dynamic focusing mechanism[EB/OL].[2024-10-28].https://arxiv.org/abs/2301.10051.
[24]
苏志威,黄子涵,邱发生,.基于改进YOLOv8的航空铝合金焊缝缺陷检测方法[J].航空动力学报, 2024,39(6):116-124.
SU Z W,HUANG Z H,QIU F S,et al.Weld defect detection of aviation aluminum alloy based on improved YOLOv8[J].Journal of Aerospace Power,2024,39 (6):116-124.(in Chinese)
[25]
吴明杰,云利军,陈载清,.改进YOLOv5s的无人机视角下小目标检测算法[J].计算机工程与应用, 2024,60(2):191-199.
WU M J,YUN L J,CHEN Z Q,et al.Improved YOLOv5s small object detection algorithm in UAV view[J]. Computer Engineering and Applications, 2024,60(2):191-199.(in Chinese)
2025年第30卷第6期
PDF下载
90
43
引用本文
BibTeX
文章信息
doi: 10.13682/j.issn.2095-6533.2025.06.012
  • 接收时间:2024-11-05
  • 首发时间:2026-04-16
  • 出版时间:2025-11-10
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-11-05
基金
作者信息
    1.西安邮电大学计算机学院,陕西西安 710121
    2.智能软件技术陕西省高等学校重点实验室,陕西西安 710121
    3.开封迪尔空分实业有限公司,河南开封 475000
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/xayddxxb/CN/10.13682/j.issn.2095-6533.2025.06.012
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