Article(id=1278415580831126296, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1277328335906669390, articleNumber=1003-3033(2026)05-0234-09, orderNo=null, doi=10.16265/j.cnki.issn1003-3033.2026.05.0395, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1765123200000, receivedDateStr=2025-12-08, revisedDate=1774454400000, revisedDateStr=2026-03-26, acceptedDate=null, acceptedDateStr=null, onlineDate=1782727626282, onlineDateStr=2026-06-29, pubDate=1779897600000, pubDateStr=2026-05-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1782727626282, onlineIssueDateStr=2026-06-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1782727626282, creator=13701087609, updateTime=1782727626282, updator=13701087609, issue=Issue{id=1277328335906669390, tenantId=1146029695717560320, journalId=1146031787341344770, year='2026', volume='36', issue='5', pageStart='1', pageEnd='318', issueExtLink='null', onlineDate='null', pubDate='1779897600000', pubDateStr='2026-05-28', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=1, specialIssue=null, createTime=1782468406892, creator='13701087609', updateTime=1782867658151, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1279002917143286724, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1277328335906669390, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1279002917143286725, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1277328335906669390, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=234, endPage=242, ext={EN=ArticleExt(id=1278415582429156121, articleId=1278415580831126296, tenantId=1146029695717560320, journalId=1146031787341344770, language=EN, title=Improved YOLOv5s for outer surface defect detection of elevator traction steel wire rope, columnId=1277328337617941059, journalTitle=China Safety Science Journal, columnName=Safety Technology and Engineering, runingTitle=null, highlight=null, articleAbstract=

To improve the detection efficiency and automation level of hidden defects on the outer surface of elevator traction steel wire ropes, and reduce the incidence of elevator accidents, an online detection model for defects on the outer surface of elevator traction steel wire ropes based on improved YOLOv5s is constructed. Firstly, the GhostConv module is introduced into the feature extraction layer C3 module to reduce computational complexity, and the Convolutional Block Attention Module (CBAM) is integrated to enhance the feature extraction capability of small-scale defects. A feature extraction module GC-C3 (GhostConv and CBAM-C3) that integrates GhostConv and CBAM is constructed; Secondly, in the feature fusion layer, Path Aggregation Network (PANet) and Bidirectional Feature Pyramid Network (BiFPN) are used to construct a multi-scale feature fusion network PBNet (PANet BiFPN), which combines multi-scale weight allocation strategy to improve the fusion effect of multi-scale defect feature information; Then, dynamically adjusting the quality weights of prediction boxes using Weighted Intersection over Union(WIoU) loss function, reducing the interference of low-quality samples on training. Finally, the model will be deployed to the developed detection system to perform online testing on the surface defects of the traction steel wire rope on the elevator car roof, verify the improvement effect of the model, and provide grading reminders for the defects. The results showed that the average detection accuracy of the improved model was 96.2%, with a detection speed of 192 f/s, which was 4.1% and 12.3% higher than the original model, respectively. The model volume was reduced by 38.9%. According to the online visualization experiment, under the actual operating environment of the traction steel wire rope (light illumination of 200~400 lx, speed of 1.5~2 m/s), the average accuracy of the system for 8 typical external surface defects is still stable at 94.6% or above, which meets the application requirements of online detection of hidden dangers of external surface defects of the traction steel wire rope in service and reduces elevator accidents caused by external surface defects of the traction steel wire rope.

, authors=Chunsheng Li1, Weihong Sun1, **, Man Liang1, Jiefeng Li2, authorsList=Chunsheng Li, Weihong Sun, Man Liang, Jiefeng Li, authorCompany=null, correspAuthors=Weihong Sun, 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, fund=null), CN=ArticleExt(id=1278415587214857010, articleId=1278415580831126296, tenantId=1146029695717560320, journalId=1146031787341344770, language=CN, title=改进YOLOv5s的电梯曳引钢丝绳外表面缺陷检测, columnId=1277328337940902469, journalTitle=中国安全科学学报, columnName=安全技术与工程, runingTitle=null, highlight=null, articleAbstract=

为提升电梯曳引钢丝绳外表面缺陷隐患的检测效率与自动化水平,降低电梯事故发生率,构建一种基于改进YOLOv5s的电梯曳引钢丝绳外表面缺陷在线检测模型。首先,在特征提取模块C3中引入幽灵卷积(GC)模块降低计算量,并融入卷积注意力模块(CBAM)增强小尺度缺陷的特征提取能力,构建融合GC与CBAM的特征提取模块GC-C3(GC and CBAM- C3);其次,在特征融合层采用路径聚合网络(PANet)与双向特征金字塔网络(BiFPN),构建多尺度特征融合网络PBNet(PANet-BiFPN),结合多尺度权重分配策略提升多尺度缺陷特征信息的融合效果;然后,采用加权交并比(WIoU)损失函数动态调整预测框质量权重,减少低质量样本对训练的干扰;最后,将该模型部署至开发的检测系统,在电梯轿顶在线检测试验曳引钢丝绳外表面缺陷,验证模型的改进效果,并对缺陷分级提醒。结果表明:改进后模型的平均检测精度均值为96.2%,检测速度为192帧/s,较原模型分别提升4.1%、12.3%,模型体积减少38.9%;从在线可视化试验得出,在曳引钢丝绳实际运行环境下(光照200~400 lx、速度1.5~2 m/s),系统对8类典型外表面缺陷的平均精度均值仍稳定在94.6%以上,满足服役曳引钢丝绳外表面缺陷隐患在线检测应用需求,减少因曳引钢丝绳外表面缺陷引发的电梯事故。

, authors=李春生1, 孙卫红1, **, 梁曼1, 李杰锋2, authorsList=李春生, 孙卫红, 梁曼, 李杰锋, authorCompany=null, correspAuthors=孙卫红, authorNote=

李春生 (1998—),男,河南周口人,硕士研究生,主要研究方向为机器视觉、深度学习、机电类及承压类等特种设备无损检测技术等。E-mail:

梁曼 讲师。

李杰锋 高级工程师。

, correspAuthorsNote=
** 孙卫红(1969—),男,江西鹰潭人,博士,教授,主要从事机电类、承压类等特种设备无损检测技术、制造业信息化及装置研发等方面的研究。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=nVi2K84pHkx3edkJE3OQzQ==, magXml=XGgoS+/84d60Lh3nfFE9Rw==, pdfUrl=null, pdf=PG9iJVza8y0zetKufNrUtw==, pdfFileSize=14788504, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=JSOs8QkHV50kOe0KZjoxuA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=OPQzpbAeHMa4HvtvwBKtCQ==, mapNumber=null, fund=null)}, authors=[Author(id=1278415587751727930, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=1562642654@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1278415587852391228, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415587751727930, language=EN, stringName=Chunsheng Li, firstName=Chunsheng, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou Zhejiang 310018, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415587940471613, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415587751727930, language=CN, stringName=李春生, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国计量大学 机电工程学院, 浙江 杭州 310018, bio={"img":"uzS21WbD7KhTxm1n0dqBHg==","content":"

李春生 (1998—),男,河南周口人,硕士研究生,主要研究方向为机器视觉、深度学习、机电类及承压类等特种设备无损检测技术等。E-mail:

"}, bioImg=uzS21WbD7KhTxm1n0dqBHg==, bioContent=

李春生 (1998—),男,河南周口人,硕士研究生,主要研究方向为机器视觉、深度学习、机电类及承压类等特种设备无损检测技术等。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415587537818419, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, xref=1, ext=[AuthorCompanyExt(id=1278415587546207028, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587537818419, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou Zhejiang 310018, China), AuthorCompanyExt(id=1278415587554595637, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587537818419, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国计量大学 机电工程学院, 浙江 杭州 310018)])]), Author(id=1278415588041134911, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=whsun@126.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1278415588187935553, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415588041134911, language=EN, stringName=Weihong Sun, firstName=Weihong, middleName=null, lastName=Sun, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, **, address=1 College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou Zhejiang 310018, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415588515091266, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415588041134911, language=CN, stringName=孙卫红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, **, address=1 中国计量大学 机电工程学院, 浙江 杭州 310018, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415587537818419, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, xref=1, ext=[AuthorCompanyExt(id=1278415587546207028, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587537818419, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou Zhejiang 310018, China), AuthorCompanyExt(id=1278415587554595637, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587537818419, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国计量大学 机电工程学院, 浙江 杭州 310018)])]), Author(id=1278415588578005828, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, 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=1278415588666086214, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415588578005828, language=EN, stringName=Man Liang, firstName=Man, middleName=null, lastName=Liang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou Zhejiang 310018, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415588737389383, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415588578005828, language=CN, stringName=梁曼, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国计量大学 机电工程学院, 浙江 杭州 310018, bio={"content":"

梁曼 讲师。

"}, bioImg=null, bioContent=

梁曼 讲师。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415587537818419, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, xref=1, ext=[AuthorCompanyExt(id=1278415587546207028, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587537818419, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou Zhejiang 310018, China), AuthorCompanyExt(id=1278415587554595637, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587537818419, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国计量大学 机电工程学院, 浙江 杭州 310018)])]), Author(id=1278415588796109641, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, 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=1278415588879995723, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415588796109641, language=EN, stringName=Jiefeng Li, firstName=Jiefeng, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Jiangsu Special Equipment Safety Supervision and Inspection Research Institute Suzhou Branch, Suzhou Jiangsu 215031, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415588955493196, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415588796109641, language=CN, stringName=李杰锋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 江苏特种设备安全监督检验研究院苏州分院, 江苏 苏州 215031, bio={"content":"

李杰锋 高级工程师。

"}, bioImg=null, bioContent=

李杰锋 高级工程师。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415587630093110, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, xref=2, ext=[AuthorCompanyExt(id=1278415587638481719, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587630093110, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Jiangsu Special Equipment Safety Supervision and Inspection Research Institute Suzhou Branch, Suzhou Jiangsu 215031, China), AuthorCompanyExt(id=1278415587651064632, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587630093110, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 江苏特种设备安全监督检验研究院苏州分院, 江苏 苏州 215031)])])], keywords=[Keyword(id=1278415589064545101, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, orderNo=1, keyword=YOLOv5s), Keyword(id=1278415589135848270, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, orderNo=2, keyword=elevator traction steel wire rope), Keyword(id=1278415589202957135, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, orderNo=3, keyword=outer surface defects), Keyword(id=1278415589282648912, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, orderNo=4, keyword=defect detection), Keyword(id=1278415589366534993, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, orderNo=5, keyword=feature extraction), Keyword(id=1278415589488169810, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, orderNo=6, keyword=feature fusion), Keyword(id=1278415591115559763, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, orderNo=1, keyword=YOLOv5s), Keyword(id=1278415591228805972, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, orderNo=2, keyword=电梯曳引钢丝绳), Keyword(id=1278415591300109141, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, orderNo=3, keyword=外表面缺陷), Keyword(id=1278415591379800918, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, orderNo=4, keyword=缺陷检测), Keyword(id=1278415591446909783, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, orderNo=5, keyword=特征提取), Keyword(id=1278415591526601560, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, orderNo=6, keyword=特征融合)], refs=[Reference(id=1278415600317862775, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2019, volume=9, issue=13, pageStart=2771, pageEnd=2779, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Zhou Ping, Zhou Gongbo, Zhu Zhencai, journalName=Applied Sciences, refType=null, unstructuredReference=Zhou Ping, Zhou Gongbo, Zhu Zhencai, et al. A review of non-destructive damage detection methods for steel wire ropes[J]. Applied Sciences, 2019, 9(13): 2771-2779., articleTitle=A review of non-destructive damage detection methods for steel wire ropes, refAbstract=null), Reference(id=1278415600707933048, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://www.samr.gov.cn/zw/zfxxgk/fdzdgknr/tzsbs/art/2024/art_aea38293416e4af382c0136d2e73f8a2.html, language=null, rfNumber=[2], rfOrder=1, authorNames=国家市场监督管理总局特种设备安全监察局, journalName=null, refType=null, unstructuredReference=国家市场监督管理总局特种设备安全监察局. 市场监管总局关于2023年全国特种设备安全状况的通告[EB/OL]. (2024-03-23). https://www.samr.gov.cn/zw/zfxxgk/fdzdgknr/tzsbs/art/2024/art_aea38293416e4af382c0136d2e73f8a2.html., articleTitle=市场监管总局关于2023年全国特种设备安全状况的通告, refAbstract=null), Reference(id=1278415600787624825, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2023, volume=2574, issue=1, pageStart=1, pageEnd=11, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=Ren Mingyue, journalName=Journal of Physics: Conference Series, refType=null, unstructuredReference=Ren Mingyue. Design of magnetic flux leakage detector for mine wire rope[J]. Journal of Physics: Conference Series, 2023, 2574(1): 1-11., articleTitle=Design of magnetic flux leakage detector for mine wire rope, refAbstract=null), Reference(id=1278415601110586234, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2022, volume=33, issue=9, pageStart=1044, pageEnd=1050, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=夏慧, 郑军, 邱锦川, journalName=中国机械工程, refType=null, unstructuredReference=夏慧, 郑军, 邱锦川, . 钢丝绳缺陷涡流热成像在线检测方法研究[J]. 中国机械工程, 2022, 33(9): 1044-1050., articleTitle=钢丝绳缺陷涡流热成像在线检测方法研究, refAbstract=null), Reference(id=1278415601232221051, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2022, volume=33, issue=9, pageStart=1044, pageEnd=1050, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=Xia Hui, Zheng Jun, Qiu Jinchuan, journalName=China Mechanical Engineering, refType=null, unstructuredReference=Xia Hui, Zheng Jun, Qiu Jinchuan, et al. Research on ECT for online detection of defects in wire ropes[J]. China Mechanical Engineering, 2022, 33(9): 1044-1050., articleTitle=Research on ECT for online detection of defects in wire ropes, refAbstract=null), Reference(id=1278415601957835644, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2024, volume=15, issue=10, pageStart=295, pageEnd=2, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=Zhao Kun, Wan Xuanhong, Lin Yenchen, journalName=Advanced Energy Materials, refType=null, unstructuredReference=Zhao Kun, Wan Xuanhong, Lin Yenchen, et al. Magnetic field-based non-destructive testing techniques for battery diagnostics[J]. Advanced Energy Materials, 2024, 15(10): 2 404 295-2 404 301., articleTitle=Magnetic field-based non-destructive testing techniques for battery diagnostics, refAbstract=null), Reference(id=1278415602062693245, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2025, volume=42, issue=7, pageStart=1341, pageEnd=1349, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=苏立鹏, 娄益凡, 杨吴奔, journalName=机电工程, refType=null, unstructuredReference=苏立鹏, 娄益凡, 杨吴奔, . 基于改进Faster-RCNN的起重机钢丝绳表面缺陷识别方法[J]. 机电工程, 2025, 42(7):1341-1349., articleTitle=基于改进Faster-RCNN的起重机钢丝绳表面缺陷识别方法, refAbstract=null), Reference(id=1278415602381460350, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2025, volume=42, issue=7, pageStart=1341, pageEnd=1349, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=Su Lipeng, Lou Yifan, Yang Wuben, journalName=Journal of Mechanical and Electrical Engineering, refType=null, unstructuredReference=Su Lipeng, Lou Yifan, Yang Wuben, et al. Method of surface defect recognition of crane wire rope based on improved Faster-RCNN[J]. Journal of Mechanical and Electrical Engineering, 2025, 42(7): 1341-1349., articleTitle=Method of surface defect recognition of crane wire rope based on improved Faster-RCNN, refAbstract=null), Reference(id=1278415602515678079, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=23, pageStart=985, pageEnd=22, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=Zhou Ping, Zhou Gongbo, Wang Shihao, journalName=IEEE Sensors Journal, refType=null, unstructuredReference=Zhou Ping, Zhou Gongbo, Wang Shihao, et al. Visual sensing inspection for the surface damage of steel wire ropes with object detection method[J]. IEEE Sensors Journal, 2022, 22(23): 22 985-22 993., articleTitle=Visual sensing inspection for the surface damage of steel wire ropes with object detection method, refAbstract=null), Reference(id=1278415602956080000, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=17, pageStart=99, pageEnd=106, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=王红尧, 韩爽, 李勤怡, journalName=计算机工程与应用, refType=null, unstructuredReference=王红尧, 韩爽, 李勤怡. 改进YOLOv5的钢丝绳损伤图像识别实验方法研究[J]. 计算机工程与应用, 2023, 59(17): 99-106., articleTitle=改进YOLOv5的钢丝绳损伤图像识别实验方法研究, refAbstract=null), Reference(id=1278415604591858562, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=17, pageStart=99, pageEnd=106, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=Wang Hongyao, Han Shuang, Li Qinyi, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=Wang Hongyao, Han Shuang, Li Qinyi. Experimental research on image recognition of wire rope damage based on improved YOLOv5[J]. Computer Engineering and Applications, 2023, 59(17): 99-106., articleTitle=Experimental research on image recognition of wire rope damage based on improved YOLOv5, refAbstract=null), Reference(id=1278415604965151619, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=6, pageStart=223, pageEnd=235, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=高嘉, 刘涛, 王显峰, journalName=仪器仪表学报, refType=null, unstructuredReference=高嘉, 刘涛, 王显峰, . TWRD-Net:一种用于曳引钢丝绳缺陷的实时检测网络算法[J]. 仪器仪表学报, 2023, 44(6): 223-235., articleTitle=TWRD-Net:一种用于曳引钢丝绳缺陷的实时检测网络算法, refAbstract=null), Reference(id=1278415605493633924, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=6, pageStart=223, pageEnd=235, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=Gao Jia, Liu Tao, Wang Xianfeng, journalName=Chinese Journal of Scientific Instrument, refType=null, unstructuredReference=Gao Jia, Liu Tao, Wang Xianfeng, et al. TWRD-Net: a real-time detection network algorithm for traction wire rope defects[J]. Chinese Journal of Scientific Instrument, 2023, 44 (6): 223-235., articleTitle=TWRD-Net: a real-time detection network algorithm for traction wire rope defects, refAbstract=null), Reference(id=1278415605791429509, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2024, volume=34, issue=9, pageStart=87, pageEnd=98, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=李刚, 杜亚波, 杨庆贺, journalName=中国安全科学学报, refType=null, unstructuredReference=李刚, 杜亚波, 杨庆贺, . 基于多尺度特征融合和注意力机制的矿区道路障碍检测[J]. 中国安全科学学报, 2024, 34(9): 87-98., articleTitle=基于多尺度特征融合和注意力机制的矿区道路障碍检测, refAbstract=null), Reference(id=1278415606600930184, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2024, volume=34, issue=9, pageStart=87, pageEnd=98, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=Li Gang, Du Yabo, Yang Qinghe, journalName=China Safety Science Journal, refType=null, unstructuredReference=Li Gang, Du Yabo, Yang Qinghe, et al. Obstacle detection on mining roads based on multi-scale feature fusion and attention mechanism[J]. China Safety Science Journal, 2024, 34(9): 87-98., articleTitle=Obstacle detection on mining roads based on multi-scale feature fusion and attention mechanism, refAbstract=null), Reference(id=1278415607825666953, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2021, volume=32, issue=4, pageStart=1201, pageEnd=1227, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=陈科圻, 朱志亮, 邓小明, journalName=软件学报, refType=null, unstructuredReference=陈科圻, 朱志亮, 邓小明, . 多尺度目标检测的深度学习研究综述[J]. 软件学报, 2021, 32(4): 1201-1227., articleTitle=多尺度目标检测的深度学习研究综述, refAbstract=null), Reference(id=1278415609167844236, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2021, volume=32, issue=4, pageStart=1201, pageEnd=1227, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=Chen Keqi, Zhu Zhiliang, Deng Xiaoming, journalName=Journal of Software, refType=null, unstructuredReference=Chen Keqi, Zhu Zhiliang, Deng Xiaoming, et al. Deep learning for multi-scale object detection: a survey[J]. Journal of Software, 2021, 32(4): 1201-1227., articleTitle=Deep learning for multi-scale object detection: a survey, refAbstract=null), Reference(id=1278415609641800589, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2023, volume=36, issue=17, pageStart=9903, pageEnd=9917, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=Du Yingjie, Liu Xiaofeng, Yi Yuwei, journalName=Neural Computing and Applications, refType=null, unstructuredReference=Du Yingjie, Liu Xiaofeng, Yi Yuwei, et al. Incorporating bidirectional feature pyramid network and lightweight network: a YOLOv5-GBC distracted driving behavior detection model[J]. Neural Computing and Applications, 2023, 36(17): 9903-9917., articleTitle=Incorporating bidirectional feature pyramid network and lightweight network: a YOLOv5-GBC distracted driving behavior detection model, refAbstract=null), Reference(id=1278415610048648078, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=2, pageStart=241, pageEnd=213, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=Zhen Yan, Zhang An, Zhao Xiaoming, journalName=Geoenergy Science and Engineering, refType=null, unstructuredReference=Zhen Yan, Zhang An, Zhao Xiaoming, et al. Prediction of deep low permeability sandstone seismic reservoir based on CBAM-CNN[J]. Geoenergy Science and Engineering, 2024, 24(2): 213 241-213 248., articleTitle=Prediction of deep low permeability sandstone seismic reservoir based on CBAM-CNN, refAbstract=null), Reference(id=1278415610350637968, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2025, volume=35, issue=1, pageStart=67, pageEnd=74, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=赵江平, 王欣然, 吴立舟, journalName=中国安全科学学报, refType=null, unstructuredReference=赵江平, 王欣然, 吴立舟. 改进YOLOv5s的路面坑槽目标检测模型[J]. 中国安全科学学报, 2025, 35(1): 67-74., articleTitle=改进YOLOv5s的路面坑槽目标检测模型, refAbstract=null), Reference(id=1278415610770068369, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, doi=null, pmid=null, pmcid=null, year=2025, volume=35, issue=1, pageStart=67, pageEnd=74, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=Zhao Jiangping, Wang Xinran, Wu Lizhou, journalName=China Safety Science Journal, refType=null, unstructuredReference=Zhao Jiangping, Wang Xinran, Wu Lizhou. Model of pavement pothole target detection with improved YOLOv5s[J]. China Safety Science Journal, 2025, 35(1): 67-74., articleTitle=Model of pavement pothole target detection with improved YOLOv5s, refAbstract=null)], funds=[Fund(id=1278415598241682293, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, awardId=2023YFF06149000, language=CN, fundingSource=国家重点研发计划资助项目(2023YFF06149000), fundOrder=null, country=null), Fund(id=1278415598606586742, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, awardId=KJ(Y)2023052, language=CN, fundingSource=江苏省特种设备监督检验研究院科技计划项目(KJ(Y)2023052), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1278415587537818419, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, xref=1, ext=[AuthorCompanyExt(id=1278415587546207028, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587537818419, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou Zhejiang 310018, China), AuthorCompanyExt(id=1278415587554595637, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587537818419, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国计量大学 机电工程学院, 浙江 杭州 310018)]), AuthorCompany(id=1278415587630093110, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, xref=2, ext=[AuthorCompanyExt(id=1278415587638481719, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587630093110, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Jiangsu Special Equipment Safety Supervision and Inspection Research Institute Suzhou Branch, Suzhou Jiangsu 215031, China), AuthorCompanyExt(id=1278415587651064632, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587630093110, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 江苏特种设备安全监督检验研究院苏州分院, 江苏 苏州 215031)])], figs=[ArticleFig(id=1278415591665013593, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, label=Fig.1, caption=Common types of defects on outer surface of elevator traction steel wire rope, figureFileSmall=oC6190TBdB+Ik0IbbnWqLg==, figureFileBig=JSOs8QkHV50kOe0KZjoxuA==, tableContent=null), ArticleFig(id=1278415591740511066, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, label=图1, caption=电梯曳引钢丝绳外表面常见缺陷类型, figureFileSmall=oC6190TBdB+Ik0IbbnWqLg==, figureFileBig=JSOs8QkHV50kOe0KZjoxuA==, tableContent=null), ArticleFig(id=1278415592017335131, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, label=Fig.2, caption=Construction process of detection system, figureFileSmall=mSVqOV9YQUv23n9Gl+gjZQ==, figureFileBig=LcvPiu34+Ud+MMvLeIkRcg==, tableContent=null), ArticleFig(id=1278415592092832604, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, label=图2, caption=检测系统构建流程, figureFileSmall=mSVqOV9YQUv23n9Gl+gjZQ==, figureFileBig=LcvPiu34+Ud+MMvLeIkRcg==, tableContent=null), ArticleFig(id=1278415592155747165, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, label=Fig.3, caption=Improved YOLOv5s structure, figureFileSmall=ohoEcgFxd23srZU/LFQSVg==, figureFileBig=WL8COLrpS+FP2KtEpcmlFw==, tableContent=null), ArticleFig(id=1278415592306742110, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, label=图3, caption=改进后的YOLOv5s结构, figureFileSmall=ohoEcgFxd23srZU/LFQSVg==, figureFileBig=WL8COLrpS+FP2KtEpcmlFw==, tableContent=null), ArticleFig(id=1278415592399016799, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, label=Fig.4, caption=Comparison between C3 and GC-C3, figureFileSmall=phcBoJOjh1BPLT9h34bNpA==, figureFileBig=mJOh4lu24pv8yp3pOqHKww==, tableContent=null), ArticleFig(id=1278415592487097184, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, label=图4, caption=C3与GC-C3对比, figureFileSmall=phcBoJOjh1BPLT9h34bNpA==, figureFileBig=mJOh4lu24pv8yp3pOqHKww==, tableContent=null), ArticleFig(id=1278415592566788961, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, label=Fig.5, caption=Comparison of PANet, BiFPN, PBNet, figureFileSmall=3kYFxRE8AbJrh3MORlrQDA==, figureFileBig=0dIcp50a+OHCiOVaKpvBxA==, tableContent=null), ArticleFig(id=1278415592713589602, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, label=图5, caption=PANet、BiFPN、PBNet对比, figureFileSmall=3kYFxRE8AbJrh3MORlrQDA==, figureFileBig=0dIcp50a+OHCiOVaKpvBxA==, tableContent=null), ArticleFig(id=1278415592852001635, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, label=Fig.6, caption=Minimum bounding rectangle formed by predicted box and ground truth boxes, figureFileSmall=2GCQFCrWvtdhANa4HpJnOA==, figureFileBig=k7zvXHqHhlRZZsAQ8Ye5cA==, tableContent=null), ArticleFig(id=1278415592935887716, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, label=图6, caption=预测框、真实框构成的最小外接矩形框, figureFileSmall=2GCQFCrWvtdhANa4HpJnOA==, figureFileBig=k7zvXHqHhlRZZsAQ8Ye5cA==, tableContent=null), ArticleFig(id=1278415593279820645, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, label=Fig.7, caption=Comparison of convergence process of P, mAP@0.5, and R during the improvement stage of ablation experiment, figureFileSmall=t58/c8jpL7FLLs1v8CvJ9A==, figureFileBig=3o/y7k0X8DuYErJjup8Qgw==, tableContent=null), ArticleFig(id=1278415593409844070, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, label=图7, caption=消融试验改进阶段P、mAP@0.5、R收敛过程对比, figureFileSmall=t58/c8jpL7FLLs1v8CvJ9A==, figureFileBig=3o/y7k0X8DuYErJjup8Qgw==, tableContent=null), ArticleFig(id=1278415593674085223, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, label=Fig.8, caption=Comparison of defect detection test indicators, figureFileSmall=1II48RU7LHNxpGiUwp3X1A==, figureFileBig=T/XNYJ/f41wUMvNnbp3vzQ==, tableContent=null), ArticleFig(id=1278415594001240936, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, label=图8, caption=缺陷检测试验指标对比, figureFileSmall=1II48RU7LHNxpGiUwp3X1A==, figureFileBig=T/XNYJ/f41wUMvNnbp3vzQ==, tableContent=null), ArticleFig(id=1278415595657991017, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, label=Fig.9, caption=Visual comparison of model detection performance before and after improvement, figureFileSmall=1RivyWII8Z7OVj7XcdlYlQ==, figureFileBig=Kk8My+ExBBDYHvFhg4Pfgw==, tableContent=null), ArticleFig(id=1278415595762848618, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, label=图9, caption=改进前后模型检测效果可视化对比, figureFileSmall=1RivyWII8Z7OVj7XcdlYlQ==, figureFileBig=Kk8My+ExBBDYHvFhg4Pfgw==, tableContent=null), ArticleFig(id=1278415596106781548, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, label=Fig.10, caption=Detection device and system, figureFileSmall=xH93BjSpo/ouXk+kr6JFWQ==, figureFileBig=ojt6m5cVTCyZhCsxukmLXA==, tableContent=null), ArticleFig(id=1278415596211639149, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, label=图10, caption=检测装置与系统, figureFileSmall=xH93BjSpo/ouXk+kr6JFWQ==, figureFileBig=ojt6m5cVTCyZhCsxukmLXA==, tableContent=null), ArticleFig(id=1278415596920476526, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, label=Fig.11, caption=Online detection results, figureFileSmall=zaz6CVjOYelqXj7sMqOqnQ==, figureFileBig=hdqx2hFNU5rjMm+y2k3C+A==, tableContent=null), ArticleFig(id=1278415596983391087, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, label=图11, caption=在线检测结果, figureFileSmall=zaz6CVjOYelqXj7sMqOqnQ==, figureFileBig=hdqx2hFNU5rjMm+y2k3C+A==, tableContent=null), ArticleFig(id=1278415597348295536, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, label=Table 1, caption=

Results of ablation test

, figureFileSmall=null, figureFileBig=null, tableContent=
试验 YOLOv5s GC-C3 PBNet WIoU P/% R/% mAP@0.5/% FPS/
(帧/s)
模型体
积/MB
浮点运
算量/G
1 91.0 93.2 92.1 171 14.4 15.8
2 91.5 93.8 92.5 214 6.2 7.5
3 93.5 93.7 94.0 146 15.9 16.1
4 91.4 93.5 92.4 175 14.4 15.7
5 93.7 94.5 94.8 189 8.1 8.3
6 92.7 94.0 93.2 218 6.2 7.6
7 94.5 94.3 95.8 169 16.0 15.9
8 94.8 94.2 96.2 192 8.8 9.3
), ArticleFig(id=1278415597465736049, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, label=表1, caption=

消融试验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
试验 YOLOv5s GC-C3 PBNet WIoU P/% R/% mAP@0.5/% FPS/
(帧/s)
模型体
积/MB
浮点运
算量/G
1 91.0 93.2 92.1 171 14.4 15.8
2 91.5 93.8 92.5 214 6.2 7.5
3 93.5 93.7 94.0 146 15.9 16.1
4 91.4 93.5 92.4 175 14.4 15.7
5 93.7 94.5 94.8 189 8.1 8.3
6 92.7 94.0 93.2 218 6.2 7.6
7 94.5 94.3 95.8 169 16.0 15.9
8 94.8 94.2 96.2 192 8.8 9.3
), ArticleFig(id=1278415597822251891, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=EN, label=Table 2, caption=

Comparison of detection results of different models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 P/% mAP@0.5/% FPS/(帧/s)
Faster RCNN 80.4 89.6 41
SSD 79.7 87.3 76
YOLOv4 91.8 89.4 102
YOLOv5s 91.0 92.1 171
YOLOv7 91.4 91.3 98
YOLOv8 91.3 91.6 131
改进模型 94.8 96.2 192
), ArticleFig(id=1278415597893555060, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, language=CN, label=表2, caption=

不同模型检测结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 P/% mAP@0.5/% FPS/(帧/s)
Faster RCNN 80.4 89.6 41
SSD 79.7 87.3 76
YOLOv4 91.8 89.4 102
YOLOv5s 91.0 92.1 171
YOLOv7 91.4 91.3 98
YOLOv8 91.3 91.6 131
改进模型 94.8 96.2 192
)], attaches=null, journal=Journal(id=1123942128916217864, delFlag=0, nameCn=中国安全科学学报, nameEn=China Safety Science Journal, nameHistory1=null, nameHistory2=null, issn=1003-3033, eissn=, cn=11-2865/X, coden=null, periodic=0, language=CN, oaType=0, 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=fkqsFM6VKlHC4gCtS5XqTw==, journalPrice=null, startedYear=null, abbrevIsoEn=Chin Saf Sci J, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1784015834644, createdBy=null, updatedBy=13041195026, firstLetterCn=Z, firstLetterEn=Z, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=fkqsFM6VKlHC4gCtS5XqTw==, picEn=SHn9HgqSxtJrOcAxqD++4Q==, jcr=null, cjcr=null, exts=[JournalExt(id=1283818719495308010, language=CN, name=中国安全科学学报, nameHistory1=null, nameHistory2=null, managedBy=中国科学技术协会, sponsoredBy=中国职业安全健康协会, publishedBy=《中国安全科学学报》编辑部, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.cssjj.com.cn/, createdTime=1784015834926, updatedTime=1784015834926, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=http://www.cssjj.com.cn/CN/column/item15.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""}), JournalExt(id=1283818719541445355, language=EN, name=China Safety Science Journal, 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=http://www.cssjj.com.cn/EN/1003-3033/home.shtml, createdTime=1784015834937, updatedTime=1784015834937, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=https://synbioj.cip.com.cn/EN/column/column3.shtml, submissionAuthorUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionReviewUrl=https://zgaqkxxbauthor.manuscriptcloud.com/login, submissionCeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, submissionAeEditorUrl=https://zgaqkxxbeditor.manuscriptcloud.com/login, option={"copyright":""})], databaseList=null, tenantJournalId=1146031787341344770, websiteList=[Website(id=1148243202345263519, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, 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/zgaqkxxb/CN, language=CN, createTime=1751692112766, createBy=18614031015, updateTime=1753502583634, updateBy=18614031015, name=《中国安全科学学报》中文站点, tplId=1146099689490845704, title=中国安全科学学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148618794941046792, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=articleTextType, value=kx, createTime=1751781661020, updateTime=1751781661020, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794911686661, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=banner, value=null, createTime=1751781661012, updateTime=1751781661012, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794894909444, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1751781661008, updateTime=1751781661008, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794932658183, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751781661017, updateTime=1751781661017, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618794924269574, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202345263519, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751781661015, updateTime=1751781661015, creator=18614031015, updator=18614031015)]), Website(id=1155836763751993353, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031787341344770, 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/zgaqkxxb/EN, language=EN, createTime=1753502558893, createBy=18614031015, updateTime=1753524450387, updateBy=18614031015, name=《中国安全科学学报》英文站点, tplId=1146101810881728533, title=China Safety Science Journal, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155895925743669425, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=articleTextType, value=kx, createTime=1753516664205, updateTime=1753516664205, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925722697902, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=banner, value=null, createTime=1753516664200, updateTime=1753516664200, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925714309293, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=tui0IVO9FMwB61HHtX5scg==, createTime=1753516664198, updateTime=1753516664198, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925735280816, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753516664203, updateTime=1753516664203, creator=18614031015, updator=18614031015), WebsiteProps(id=1155895925731086511, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155836763751993353, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753516664202, updateTime=1753516664202, creator=18614031015, updator=18614031015)])], journalTitle=中国安全科学学报, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=China Safety Science Journal, journalPhotoCn=fkqsFM6VKlHC4gCtS5XqTw==, journalPhotoEn=SHn9HgqSxtJrOcAxqD++4Q==, journalFirstLetter=Z, journalRecommend=null, journalNew=null, journalCollection=1, 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, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2026.05.0395, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/10.16265/j.cnki.issn1003-3033.2026.05.0395, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/PDF/10.16265/j.cnki.issn1003-3033.2026.05.0395, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/PDF/10.16265/j.cnki.issn1003-3033.2026.05.0395, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1779897600000, fullTextJson=null, articleText=null, reference=null)
收藏切换
改进YOLOv5s的电梯曳引钢丝绳外表面缺陷检测
收藏切换
PDF下载
李春生 1 , 孙卫红 1, ** , 梁曼 1 , 李杰锋 2
中国安全科学学报 | 安全技术与工程 2026,36(5): 234-242
收起
收藏切换
中国安全科学学报 |安全技术与工程 2026 , 36 (5) : 234 -242
改进YOLOv5s的电梯曳引钢丝绳外表面缺陷检测
全屏
[Author(id=1278415587751727930, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=1562642654@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1278415587852391228, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415587751727930, language=EN, stringName=Chunsheng Li, firstName=Chunsheng, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou Zhejiang 310018, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415587940471613, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415587751727930, language=CN, stringName=李春生, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国计量大学 机电工程学院, 浙江 杭州 310018, bio={"img":"uzS21WbD7KhTxm1n0dqBHg==","content":"

李春生 (1998—),男,河南周口人,硕士研究生,主要研究方向为机器视觉、深度学习、机电类及承压类等特种设备无损检测技术等。E-mail:

"}, bioImg=uzS21WbD7KhTxm1n0dqBHg==, bioContent=

李春生 (1998—),男,河南周口人,硕士研究生,主要研究方向为机器视觉、深度学习、机电类及承压类等特种设备无损检测技术等。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415587537818419, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, xref=1, ext=[AuthorCompanyExt(id=1278415587546207028, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587537818419, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou Zhejiang 310018, China), AuthorCompanyExt(id=1278415587554595637, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587537818419, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国计量大学 机电工程学院, 浙江 杭州 310018)])]), Author(id=1278415588041134911, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=whsun@126.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1278415588187935553, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415588041134911, language=EN, stringName=Weihong Sun, firstName=Weihong, middleName=null, lastName=Sun, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, **, address=1 College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou Zhejiang 310018, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415588515091266, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415588041134911, language=CN, stringName=孙卫红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, **, address=1 中国计量大学 机电工程学院, 浙江 杭州 310018, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415587537818419, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, xref=1, ext=[AuthorCompanyExt(id=1278415587546207028, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587537818419, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou Zhejiang 310018, China), AuthorCompanyExt(id=1278415587554595637, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587537818419, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国计量大学 机电工程学院, 浙江 杭州 310018)])]), Author(id=1278415588578005828, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, 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=1278415588666086214, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415588578005828, language=EN, stringName=Man Liang, firstName=Man, middleName=null, lastName=Liang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou Zhejiang 310018, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415588737389383, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415588578005828, language=CN, stringName=梁曼, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 中国计量大学 机电工程学院, 浙江 杭州 310018, bio={"content":"

梁曼 讲师。

"}, bioImg=null, bioContent=

梁曼 讲师。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415587537818419, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, xref=1, ext=[AuthorCompanyExt(id=1278415587546207028, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587537818419, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou Zhejiang 310018, China), AuthorCompanyExt(id=1278415587554595637, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587537818419, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 中国计量大学 机电工程学院, 浙江 杭州 310018)])]), Author(id=1278415588796109641, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, 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=1278415588879995723, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415588796109641, language=EN, stringName=Jiefeng Li, firstName=Jiefeng, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Jiangsu Special Equipment Safety Supervision and Inspection Research Institute Suzhou Branch, Suzhou Jiangsu 215031, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415588955493196, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, authorId=1278415588796109641, language=CN, stringName=李杰锋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 江苏特种设备安全监督检验研究院苏州分院, 江苏 苏州 215031, bio={"content":"

李杰锋 高级工程师。

"}, bioImg=null, bioContent=

李杰锋 高级工程师。

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415587630093110, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, xref=2, ext=[AuthorCompanyExt(id=1278415587638481719, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587630093110, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Jiangsu Special Equipment Safety Supervision and Inspection Research Institute Suzhou Branch, Suzhou Jiangsu 215031, China), AuthorCompanyExt(id=1278415587651064632, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415580831126296, companyId=1278415587630093110, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 江苏特种设备安全监督检验研究院苏州分院, 江苏 苏州 215031)])])]
李春生1 , 孙卫红1, ** , 梁曼1, 李杰锋2
作者信息
  • 1 中国计量大学 机电工程学院, 浙江 杭州 310018
  • 2 江苏特种设备安全监督检验研究院苏州分院, 江苏 苏州 215031
通讯作者:
** 孙卫红(1969—),男,江西鹰潭人,博士,教授,主要从事机电类、承压类等特种设备无损检测技术、制造业信息化及装置研发等方面的研究。E-mail:
作者简介:

李春生 (1998—),男,河南周口人,硕士研究生,主要研究方向为机器视觉、深度学习、机电类及承压类等特种设备无损检测技术等。E-mail:

梁曼 讲师。

李杰锋 高级工程师。

Improved YOLOv5s for outer surface defect detection of elevator traction steel wire rope
Chunsheng Li1 , Weihong Sun1, ** , Man Liang1, Jiefeng Li2
Affiliations
  • 1 College of Mechanical and Electrical Engineering, China Jiliang University, Hangzhou Zhejiang 310018, China
  • 2 Jiangsu Special Equipment Safety Supervision and Inspection Research Institute Suzhou Branch, Suzhou Jiangsu 215031, China
出版时间: 2026-05-28 doi: 10.16265/j.cnki.issn1003-3033.2026.05.0395
文章导航
收藏切换

为提升电梯曳引钢丝绳外表面缺陷隐患的检测效率与自动化水平,降低电梯事故发生率,构建一种基于改进YOLOv5s的电梯曳引钢丝绳外表面缺陷在线检测模型。首先,在特征提取模块C3中引入幽灵卷积(GC)模块降低计算量,并融入卷积注意力模块(CBAM)增强小尺度缺陷的特征提取能力,构建融合GC与CBAM的特征提取模块GC-C3(GC and CBAM- C3);其次,在特征融合层采用路径聚合网络(PANet)与双向特征金字塔网络(BiFPN),构建多尺度特征融合网络PBNet(PANet-BiFPN),结合多尺度权重分配策略提升多尺度缺陷特征信息的融合效果;然后,采用加权交并比(WIoU)损失函数动态调整预测框质量权重,减少低质量样本对训练的干扰;最后,将该模型部署至开发的检测系统,在电梯轿顶在线检测试验曳引钢丝绳外表面缺陷,验证模型的改进效果,并对缺陷分级提醒。结果表明:改进后模型的平均检测精度均值为96.2%,检测速度为192帧/s,较原模型分别提升4.1%、12.3%,模型体积减少38.9%;从在线可视化试验得出,在曳引钢丝绳实际运行环境下(光照200~400 lx、速度1.5~2 m/s),系统对8类典型外表面缺陷的平均精度均值仍稳定在94.6%以上,满足服役曳引钢丝绳外表面缺陷隐患在线检测应用需求,减少因曳引钢丝绳外表面缺陷引发的电梯事故。

YOLOv5s  /  电梯曳引钢丝绳  /  外表面缺陷  /  缺陷检测  /  特征提取  /  特征融合

To improve the detection efficiency and automation level of hidden defects on the outer surface of elevator traction steel wire ropes, and reduce the incidence of elevator accidents, an online detection model for defects on the outer surface of elevator traction steel wire ropes based on improved YOLOv5s is constructed. Firstly, the GhostConv module is introduced into the feature extraction layer C3 module to reduce computational complexity, and the Convolutional Block Attention Module (CBAM) is integrated to enhance the feature extraction capability of small-scale defects. A feature extraction module GC-C3 (GhostConv and CBAM-C3) that integrates GhostConv and CBAM is constructed; Secondly, in the feature fusion layer, Path Aggregation Network (PANet) and Bidirectional Feature Pyramid Network (BiFPN) are used to construct a multi-scale feature fusion network PBNet (PANet BiFPN), which combines multi-scale weight allocation strategy to improve the fusion effect of multi-scale defect feature information; Then, dynamically adjusting the quality weights of prediction boxes using Weighted Intersection over Union(WIoU) loss function, reducing the interference of low-quality samples on training. Finally, the model will be deployed to the developed detection system to perform online testing on the surface defects of the traction steel wire rope on the elevator car roof, verify the improvement effect of the model, and provide grading reminders for the defects. The results showed that the average detection accuracy of the improved model was 96.2%, with a detection speed of 192 f/s, which was 4.1% and 12.3% higher than the original model, respectively. The model volume was reduced by 38.9%. According to the online visualization experiment, under the actual operating environment of the traction steel wire rope (light illumination of 200~400 lx, speed of 1.5~2 m/s), the average accuracy of the system for 8 typical external surface defects is still stable at 94.6% or above, which meets the application requirements of online detection of hidden dangers of external surface defects of the traction steel wire rope in service and reduces elevator accidents caused by external surface defects of the traction steel wire rope.

YOLOv5s  /  elevator traction steel wire rope  /  outer surface defects  /  defect detection  /  feature extraction  /  feature fusion
李春生, 孙卫红, 梁曼, 李杰锋. 改进YOLOv5s的电梯曳引钢丝绳外表面缺陷检测. 中国安全科学学报, 2026 , 36 (5) : 234 -242 . DOI: 10.16265/j.cnki.issn1003-3033.2026.05.0395
Chunsheng Li, Weihong Sun, Man Liang, Jiefeng Li. Improved YOLOv5s for outer surface defect detection of elevator traction steel wire rope[J]. China Safety Science Journal, 2026 , 36 (5) : 234 -242 . DOI: 10.16265/j.cnki.issn1003-3033.2026.05.0395
曳引钢丝绳作为电梯、索道、大型游乐设施等特种设备动力传输系统的核心部件,其服役状态直接关系到设备运行的可靠性与人员生命安全。随着我国城镇化进程的加速和高层建筑数量的激增,电梯保有量持续增长,使得电梯曳引钢丝绳的安全监测需求持续上升。然而,在复杂交变载荷作用下,曳引钢丝绳外表面易产生磨损、断丝、笼状畸变等渐进式损伤[1]。2023年,全国特种设备安全状况通告中已结案事故的原因分析显示:84.44%的事故源于维护缺失或违章操作,15.56%的事故源于设备自身缺陷或安全部件失效[2],凸显出曳引钢丝绳缺陷精准检测的迫切性。当前,人工目检和传统无损检测技术[3-5]存在检测效率低、环境适应性差等问题,难以满足实时动态监测需求。因此,需要研发一套实时且精确的自动化检测系统,以检测电梯曳引钢丝绳外表面缺陷隐患。
近年来,基于深度学习的目标检测技术为曳引钢丝绳缺陷检测提供了新的技术路径。深度学习通过多层网络架构与参数自优化机制提取目标特征,获取图像中目标的类别与位置信息,根据架构差异分为高精度的2阶段模型和速度快的单阶段模型。苏立鹏等[6]通过改进快速卷积神经网络(Faster Region-based Convolutional Neural Networks,Faster RCNN),结合多尺度输入和可变形卷积,曳引钢丝绳缺陷检测精度为90.2%,但2阶段算法因层级化架构设计导致计算量较大,难以满足在线场景检测需求,且精度仍有待提高。Zhou Ping等[7]提出了轻量化设计的改进方案,采用Mobilenet重构YOLOv3特征提取网络,降低计算量并提高检测精度,但其浅层网络对小尺度缺陷的特征表征能力不足,特别是在复杂环境下表现不佳。王红尧等[8]通过构建 4尺度检测架构增强YOLOv5的多尺度感知能力,以提升多尺度检测能力,但模型的实时性不足。高嘉等[9]提出的跨层级特征融合机制通过加权金字塔优化检测速度,但网络参数冗余度较高,嵌入式适配性不足。同时,上述研究主要聚焦于断丝、磨损、断丝挤出等小尺度缺陷的检测,尚未覆盖电梯曳引钢丝绳服役时产生的各类典型多尺度缺陷,虽取得一定成效,但所用算法检测小尺度缺陷的尺度仅为8×8像素,导致小尺度缺陷在特征融合时信息易发生丢失[10-11],且曳引钢丝绳图像内或图像间被检测缺陷的尺度和形状等特征均呈现多样化,导致现有检测算法在应对曳引钢丝绳外表面多尺度缺陷检测时仍存在巨大挑战。
鉴于此,笔者拟针对电梯曳引钢丝绳缺陷检测问题,提出一种改进的YOLOv5s网络模型,通过在C3模块中引入幽灵卷积(GhostConv,GC)[12]模块与卷积注意力模块(Convolutional Block Attention Module,CBAM)[13],构建特征提取模块GC-C3;设计融合路径聚合网络(Path Aggregation Network,PANet)与双向特征金字塔网络(Bidirectional Feature Pyramid Network,BiFPN)的多尺度特征融合网络PBNet(PANet-BiFPN);同时引入加权交并比(Wise Intersection Over Union,WIoU)损失函数,提升检测模型对8类典型外表面缺陷的平均精度均值(mean Average Precision,mAP)和帧率(Frames Per Second,FPS);在此基础上,将改进的YOLOv5s模型部署至开发的检测系统,并在电梯轿顶进行试验验证,以期提高曳引钢丝绳缺陷检测模型的适用性。
电梯在实际运行时,曳引钢丝绳主要受轻载(拉伸力通常小于破断载荷的1/12)且持续弯曲的交变应力,内部钢丝因外层钢丝保护受应力相对较小,缺陷出现概率较低;外表面因反复拉伸、弯曲等交变应力,极易出现断丝、断股、断丝挤出、断股挤出等缺陷,若不及时检测及更换,会显著削弱曳引钢丝绳的承载能力,引发电梯事故,导致人员伤亡和财产损失。服役曳引钢丝绳外表面常见的8类典型缺陷如图1所示,由图1可知:断丝、断丝挤出等小尺度缺陷在产生初期因微动磨损和交变应力导致应力集中,引发缺陷扩展并降低曳引钢丝绳载荷能力,若持续服役会逐渐演变为中、大尺度缺陷;而中、大尺度缺陷如笼状畸变、断股挤出等因张力失衡引发局部应力激增,易造成断股或整绳断裂。这些缺陷不仅直接削弱曳引钢丝绳的抗拉强度,更易在电梯运行中因摩擦突变引发突发性断裂而造成伤亡事故。
首先,实地调研苏州某电梯检验中心,收集更换下来的曳引钢丝绳(已报废)与服役中的曳引钢丝绳(未报废),拍摄不同阶段的曳引钢丝绳外表面缺陷图像,构建从初期到失效或报废阶段的不同尺度及形状的8类缺陷图像数据集。然后,针对检测精度、速度、缺陷特征,基于YOLOv5s网络提出一种电梯曳引钢丝绳外表面缺陷在线检测方法,使其适用于电梯服役曳引钢丝绳实际检测场景。最后,开发嵌入式系统,可视化界面包括图像识别画面,检测精度、置信度、数量统计,缺陷所在楼层。基于此,在电梯轿顶曳引钢丝绳两侧架设高帧率工业相机以覆盖检测区域,实时采集图像数据流,最终检测曳引钢丝绳外表面缺陷,系统构建流程如图2所示。
YOLOv5分为n、s、m、l、x等5种模型,精度递增而推理速度递减,均由骨干特征提取网络、颈部特征融合网络和头部预测网络构成:骨干采用卷积(Conv)与C3提取特征信息;颈部通过特征融合网络(Path Aggregation Network,PANet)结构实现多尺度特征融合;头部使用完全交并比(Complete Intersection over Union,CIoU)损失函数对目标分类、预测目标框回归、计算置信度损失,完成目标框的预测及调整。相较于YOLOv8、YOLOv11等最新检测算法具有较高的灵活性及稳定性,且模型参数量较小,便于嵌入式部署,因此,系统以YOLOv5s为基准,改进后的网络结构如图3所示。
曳引钢丝绳在线检测场景中,检测速度直接影响检测效率与模型部署的可行性。原YOLOv5s中C3由2个并行分支构成,如图4a所示,其中,左侧分支通过1个卷积和k个堆叠的Bottleneck模块提取高维语义特征,但k个堆叠的Bottleneck操作导致计算量显著增加;右侧分支通过1个卷积操作保留浅层特征后与左侧分支特征拼接融合。C3虽能兼顾多尺度特征提取,却牺牲了模型的轻量化特性,影响其推理速度。若部署系统的模型对采集的视频流推理速度不足,导致检测速度与工业相机采集速度不匹配,将会影响在线检测效果。
GC-C3结构如图4b所示。在Bottleneck结构中引入GhostConv模块,通过在传统卷积操作基础上引入线性变换生成冗余特征图,以降低模型参数量与计算复杂度。针对小尺度缺陷特征易丢失问题,在Bottleneck中嵌入CBAM机制,强化模型对缺陷图像关键区域的聚焦能力。针对卷积操作过程中输出特征图尺寸变化,采用自适应分支策略,当输出特征图尺寸不变时,采用图4b结构中分支1,堆叠2个GhostConv模块,维持特征维度信息;当输出特征图尺寸减半时,采用图4b结构中分支2支路,并在GhostConv模块间加入步长为2的DWConv卷积,减少特征信息损失。最终,通过GhostConv与CBAM的协同优化,在降低计算量的同时,GC-C3模块高效提取了曳引钢丝绳多尺度缺陷特征。
原YOLOv5s采用的PANet结构,如图5a所示,通过双向采样实现多尺度特征传递,但其代数相加的融合方式易丢失小尺度缺陷特征,导致深层网络对曳引钢丝绳小尺度缺陷的融合能力显著下降。基于此,现有研究提出如图5b所示的BiFPN结构,通过移除冗余节点和跨层连接优化特征复用,但其在自底向上的特征传递路径中,高层特征图(第6、7层)因分辨率降低导致特征信息丢失,曳引钢丝绳多尺度缺陷特征在高层语义表达中被弱化,最终影响模型对多尺度缺陷的融合。
因此,提出改进的PBNet,如图5c所示。PBNet在PANet基础上删除第3、7层未参与特征融合的冗余节点,并在第4、5、6同尺度特征层之间添加输入节点到输出节点的连接,增强同尺度特征交互。基于浅层网络富含高分辨率空间信息的特性,将第3层的特征信息融入第5、6、7层,补偿空间信息损失,增强多尺度缺陷特征的融合能力。此外,引入快速归一化加权,通过动态权重分配平衡多尺度特征融合,提升多尺度缺陷的融合能力。其过程见下式:
$ T=\sum_{i} \frac{Q_{i}}{e+\sum_{j} Q_{j}} \times S_{i}^{u}$
式中:T为特征分配权重;e为防溢出值;Qi为第i层输入特征可学习的权重;j为特征融合操作中所有输入特征的索引;${S}_{ i}^{u}$为第i层输入特征。
PANet网络具体融合过程以第5层为例,计算见下式:
$ S_{5}^{\mathrm{v}}=\operatorname{Conv}\left(\frac{Q_{5} S_{5}^{\mathrm{u}}+Q_{6} R S_{6}^{\mathrm{v}}}{Q_{5}+Q_{6}+\mathrm{e}}\right)$
$ S_{5}^{\mathrm{t}}=\operatorname{Conv}\left(\frac{Q_{1} S_{5}^{\mathrm{u}}+Q_{2} S_{5}^{\mathrm{v}}+Q_{4} R S_{4}^{\mathrm{t}}+Q_{3} R S_{3}^{\mathrm{t}}}{Q_{1}+Q_{2}+Q_{4}+Q_{3}+\mathrm{e}}\right)$
式中:${S}_{5}^{v}$为第5层的中间特征;Q1Q2Q3Q4Q5Q6为特征权重参数;${S}_{5}^{t}$为第5层的输出特征;R为上采样或下采样操作。
在训练曳引钢丝绳缺陷检测模型时,受复杂背景干扰与多尺度缺陷分布影响,模型易受缺陷标注框尺寸失配影响:标注框过大引入冗余特征,标注框过小则容易遗漏关键信息;同时,相邻缺陷的特征标注混淆进一步加剧低质量样本对训练的干扰。原YOLOv5s的CIoU损失函数虽能提升定位精度,但其纵横交并比描述存在模糊性,且未考虑预测框与真实框的方向不匹配问题,限制模型对多尺度缺陷的检测性能。
引入动态非单调聚焦机制WIoU损失函数,定义如下:
$ L_{\mathrm{WIoU}}=r R_{\mathrm{WIoU}} L_{\mathrm{IoU}}$
$ \begin{array}{c}R_{\text {WIoU }}=\exp \left(\frac{\left(x-x_{\mathrm{t}}\right)^{2}+\left(y-y_{\mathrm{t}}\right)^{2}}{\left(W_{\mathrm{g}}^{2}+H_{\mathrm{g}}^{2}\right)^{2}}\right)= \\\quad \exp \left(\frac{\left(w-w_{\mathrm{g}}\right)^{2}+\left(h-h_{\mathrm{g}}\right)^{2}}{\left(W_{\mathrm{g}}^{2}+H_{\mathrm{g}}^{2}\right)^{2}}\right)\end{array}$
式中:LWIoU为WIoU的损失项;RWIoU为包围框中心归一化距离;LIoU为边界框回归损失项;r为动态非单调聚焦系数;xy为预测框中心位置坐标;xtyt为真实框中心坐标;WgHg为最小外接矩形框宽、高;wh为预测框宽、高;wtht为标注框的宽、高。
$ \beta=\frac{L_{\mathrm{IoU}}^{*}}{L_{\mathrm{IoU}}} \in[0,+\infty]$
$ r=\frac{\beta}{\delta \alpha^{\beta-\delta}}$
式中:β为离群度;${L}_{IoU}^{*}$为梯度增益;αδ为超参数。
WIoU损失函数采用梯度增益分配策略和“离群度”概念,对不同质量预测框差异化处理,抑制低质量样本的负向训练干扰。基于预测框与真实框的最小包围框(图6)尺寸(Wg,Hg)重构惩罚项系数RWIoU,均衡高低质量预测框的权重分布。最后,通过动态非单调聚焦系数r自适应调节RWIoU,强化普通质量样本的优化效果,从而加速模型收敛并提升泛化能力。
拍摄更换下来的电梯曳引钢丝绳图像共4 124张,涵盖服役阶段的不同尺度、形状的断丝、断股、断丝挤出、磨损、笼状畸变、绳股松散、绳芯外露及断股挤出8类典型外表面缺陷,并按7∶2∶1比例分为训练集、验证集和测试集。
为保证试验的可重复性,对曳引钢丝绳缺陷检测提供可靠基础,训练时统一设置初始学习率为0.01,批处理大小为8,初始学习动量为0.937,权重衰减系数为0.00045,输入图像分辨率为640×640,每次训练迭代300轮。
采用mAP@0.5、精确率P、召回率R评估检测模型精度;采用模型体积V、FPS、浮点运算量评估检测模型性能[14]
为量化改进模块的贡献,以YOLOv5s为基准模型,在相同试验条件下,分析改进模块对模型实际性能的影响,共设置8种试验方案,消融试验结果见表1,不同改进模型对应的P、mAP@0.5和R收敛曲线如图7所示。
图7可知:随着改进模块的逐步引入,模型的P、mAP@0.5和R在训练150轮次后趋于稳定。其中,改进YOLOv5s模型的P、mAP@0.5比消融试验改进阶段的模型都高,同时R比基准模型提高1%。试验表明:改进的YOLOv5s模型对电梯曳引钢丝绳外表面缺陷检测具有更优性能。
表1可知:试验1为基准模型。试验2在基准模型中将特征提取模块C3替换为GC-C3,模型体积减少56.9%,FPS提高至214帧/s,mAP@0.5略有提升,说明GC-C3在维持多尺度缺陷特征提取能力的前提下,轻量化效果显著。试验3在基准模型中采用多尺度融合网络PBNet,模型mAP@0.5、PR均提升明显,模型体积变大,FPS明显下降,说明通过增加网络深度提升了检测精度,但牺牲了部分实时性。试验4采用WIoU损失函数,P、mAP@0.5、FPS均略微提高。试验5、6、7将3个改进模块两两组合加入基准模型中,可以看出,GC-C3主导轻量化效率,PBNet驱动精度提升,WIoU增强定位鲁棒性。基于此,试验8将3个改进模块同时加入基准模型中,mAP@0.5、PR分别提升至96.2%、94.8%、94.2%,模型体积压缩至8.8MB,FPS达到192帧/s,表明同时组合3个改进模块时,模型检测速率与精度均取得最佳效果。
为验证改进模型的有效性,在覆盖8类典型缺陷的测试集上开展改进前后模型的对比试验,结果如图8所示。各类缺陷检测的mAP@0.5、RP相较于原模型均有提升。其中,绳芯外露、绳股松散及断股等中、大尺度缺陷的P、mAP@0.5均有显著提高,体现了改进模型对多尺度特征的提取能力;同时,PBNet模块持续优化特征融合,使磨损、断丝等小尺度缺陷的识别精度持续提升。
为直观验证改进效果,选取3张覆盖8类多尺度缺陷的图片,将原模型与改进模型的检测结果同人工标注(图9a)进行对比。在图9b中,原模型对处在A、B边缘位置的磨损、断丝及E处等小尺度缺陷检测效果不佳,存在漏检现象。在图9c中,改进后的模型对边缘磨损和断丝等小尺度缺陷的检测效果明显提升,均能有效检出图9a中标记的缺陷位置及类型。为便于观察检测结果,局部放大图9中C、D、E等3处缺陷区域的检测结果,相较于原模型,改进后模型的置信度值与检测框定位均有所提高。
综上,改进后YOLOv5s网络模型在电梯曳引钢丝绳8类典型缺陷上检测的mAP@0.5、PR分别提升4.1%、3.8%和1%,均优于原模型,模型体积减少38.9%、浮点运算量减少41.1%、FPS提升12.3%,说明改进模型在保持实时性的同时,显著提升多尺度缺陷的检测鲁棒性,满足电梯曳引钢丝绳在线检测的高精度与高效率需求。
为进一步体现改进模型的检测优势,选取多种主流算法模型Faster RCNN、单步多框检测器(Single Shot MultiBox Detector,SSD)、YOLOv4、YOLOv5s、YOLOv7、YOLOv8在曳引钢丝绳缺陷数据集上试验,试验结果见表2表2显示,改进模型的mAP@0.5相比Faster RCNN、SSD、YOLOv4、YOLOv5s、YOLOv7、YOLOv8分别提高6.6%、8.9%、6.8%、4.1%、4.9%、4.6%,验证了改进模型对曳引钢丝绳缺陷检测效果最佳。同时,较高的FPS(192帧/s)能够满足曳引钢丝绳缺陷在线检测需求。
为验证改进模型在曳引钢丝绳服役状态下的检测效果,在苏州某电梯检验中心将试验机房服役的曳引钢丝绳替换为表面包含服役阶段的不同尺度、形状的断丝、断股、笼状畸变等8类典型缺陷钢丝绳,确保缺陷类型、尺度及分布覆盖实际工况下的常见失效模式。
检测系统如图10所示,由图像采集与传输、处理单元与算法部署、实时处理与检测结果输出3部分构成。2台最大FPS为222帧/s的工业相机架设于电梯曳引钢丝绳两侧,上下布置,通过USB3.0将双路视频流实时传输至工控机(Jetson TX2)。工控机运行Ubuntu18.2操作系统并集成DeepStream框架,加载经TensorRT优化的改进YOLOv5s模型,并通过DeepStream部署到工控机上,实时检测视频流缺陷,并将检测结果(类别、数量、置信度等)输出到可视化界面。电梯曳引钢丝绳缺陷检测系统通过可视化界面实时呈现在线检测结果,如图11所示。不同缺陷类型风险程度不同,系统提供分级提醒:对断丝、轻微磨损等低风险缺陷进行弱提醒(建议人工复检);对断股、笼状畸变等高危缺陷进行强提醒(建议更换曳引钢丝绳)。可视化测试结果表明:在实际运行环境下(绳速1.5~2m/s、光照200~400 lx),系统对两侧缺陷的在线检测精度保持在94.6%以上,FPS稳定在186帧/s左右。表明:该系统能高效准确地识别断丝、笼状畸变等典型缺陷,辅助维保人员制定针对性策略,降低电梯运行风险,保障乘梯安全。
1) 提出一种基于改进YOLOv5s的电梯曳引钢丝绳外表面缺陷检测模型。改进后模型的mAP@0.5、精确率、召回率较原模型分别提升4.1%、3.8%、1.0%,检测速度提升12.3%,模型体积缩减38.9%,显著提升了模型对多尺度缺陷的检测能力和检测速度,满足在线检测需求。
2) 将改进后的检测模型部署至嵌入式检测系统,在光照200~400 lx、曳引钢丝绳运行速度1.5~2m/s等工况下,仍保持186 帧/s的检测帧率及94.6%以上的检测精度,能够在线精准识别电梯曳引钢丝绳服役阶段产生的8类典型外表面缺陷,及时帮助维保人员根据系统提醒制定维保策略,有效降低因曳引钢丝绳外表面缺陷引发的电梯事故风险。
  • 国家重点研发计划资助项目(2023YFF06149000)
  • 江苏省特种设备监督检验研究院科技计划项目(KJ(Y)2023052)
参考文献 引证文献
排序方式:
[1]
Zhou Ping, Zhou Gongbo, Zhu Zhencai, et al. A review of non-destructive damage detection methods for steel wire ropes[J]. Applied Sciences, 2019, 9(13): 2771-2779.
[2]
国家市场监督管理总局特种设备安全监察局. 市场监管总局关于2023年全国特种设备安全状况的通告[EB/OL]. (2024-03-23). https://www.samr.gov.cn/zw/zfxxgk/fdzdgknr/tzsbs/art/2024/art_aea38293416e4af382c0136d2e73f8a2.html. https://www.samr.gov.cn/zw/zfxxgk/fdzdgknr/tzsbs/art/2024/art_aea38293416e4af382c0136d2e73f8a2.html
[3]
Ren Mingyue. Design of magnetic flux leakage detector for mine wire rope[J]. Journal of Physics: Conference Series, 2023, 2574(1): 1-11.
[4]
夏慧, 郑军, 邱锦川, . 钢丝绳缺陷涡流热成像在线检测方法研究[J]. 中国机械工程, 2022, 33(9): 1044-1050.
Xia Hui, Zheng Jun, Qiu Jinchuan, et al. Research on ECT for online detection of defects in wire ropes[J]. China Mechanical Engineering, 2022, 33(9): 1044-1050.
[5]
Zhao Kun, Wan Xuanhong, Lin Yenchen, et al. Magnetic field-based non-destructive testing techniques for battery diagnostics[J]. Advanced Energy Materials, 2024, 15(10): 2 404 295-2 404 301.
[6]
苏立鹏, 娄益凡, 杨吴奔, . 基于改进Faster-RCNN的起重机钢丝绳表面缺陷识别方法[J]. 机电工程, 2025, 42(7):1341-1349.
Su Lipeng, Lou Yifan, Yang Wuben, et al. Method of surface defect recognition of crane wire rope based on improved Faster-RCNN[J]. Journal of Mechanical and Electrical Engineering, 2025, 42(7): 1341-1349.
[7]
Zhou Ping, Zhou Gongbo, Wang Shihao, et al. Visual sensing inspection for the surface damage of steel wire ropes with object detection method[J]. IEEE Sensors Journal, 2022, 22(23): 22 985-22 993.
[8]
王红尧, 韩爽, 李勤怡. 改进YOLOv5的钢丝绳损伤图像识别实验方法研究[J]. 计算机工程与应用, 2023, 59(17): 99-106.
Wang Hongyao, Han Shuang, Li Qinyi. Experimental research on image recognition of wire rope damage based on improved YOLOv5[J]. Computer Engineering and Applications, 2023, 59(17): 99-106.
[9]
高嘉, 刘涛, 王显峰, . TWRD-Net:一种用于曳引钢丝绳缺陷的实时检测网络算法[J]. 仪器仪表学报, 2023, 44(6): 223-235.
Gao Jia, Liu Tao, Wang Xianfeng, et al. TWRD-Net: a real-time detection network algorithm for traction wire rope defects[J]. Chinese Journal of Scientific Instrument, 2023, 44 (6): 223-235.
[10]
李刚, 杜亚波, 杨庆贺, . 基于多尺度特征融合和注意力机制的矿区道路障碍检测[J]. 中国安全科学学报, 2024, 34(9): 87-98.
Li Gang, Du Yabo, Yang Qinghe, et al. Obstacle detection on mining roads based on multi-scale feature fusion and attention mechanism[J]. China Safety Science Journal, 2024, 34(9): 87-98.
[11]
陈科圻, 朱志亮, 邓小明, . 多尺度目标检测的深度学习研究综述[J]. 软件学报, 2021, 32(4): 1201-1227.
Chen Keqi, Zhu Zhiliang, Deng Xiaoming, et al. Deep learning for multi-scale object detection: a survey[J]. Journal of Software, 2021, 32(4): 1201-1227.
[12]
Du Yingjie, Liu Xiaofeng, Yi Yuwei, et al. Incorporating bidirectional feature pyramid network and lightweight network: a YOLOv5-GBC distracted driving behavior detection model[J]. Neural Computing and Applications, 2023, 36(17): 9903-9917.
[13]
Zhen Yan, Zhang An, Zhao Xiaoming, et al. Prediction of deep low permeability sandstone seismic reservoir based on CBAM-CNN[J]. Geoenergy Science and Engineering, 2024, 24(2): 213 241-213 248.
[14]
赵江平, 王欣然, 吴立舟. 改进YOLOv5s的路面坑槽目标检测模型[J]. 中国安全科学学报, 2025, 35(1): 67-74.
Zhao Jiangping, Wang Xinran, Wu Lizhou. Model of pavement pothole target detection with improved YOLOv5s[J]. China Safety Science Journal, 2025, 35(1): 67-74.
2026年第36卷第5期
PDF下载
177
79
引用本文
BibTeX
文章信息
doi: 10.16265/j.cnki.issn1003-3033.2026.05.0395
  • 接收时间:2025-12-08
  • 首发时间:2026-06-29
  • 出版时间:2026-05-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-12-08
  • 修回日期:2026-03-26
基金
国家重点研发计划资助项目(2023YFF06149000)
江苏省特种设备监督检验研究院科技计划项目(KJ(Y)2023052)
作者信息
    1 中国计量大学 机电工程学院, 浙江 杭州 310018
    2 江苏特种设备安全监督检验研究院苏州分院, 江苏 苏州 215031

通讯作者:

** 孙卫红(1969—),男,江西鹰潭人,博士,教授,主要从事机电类、承压类等特种设备无损检测技术、制造业信息化及装置研发等方面的研究。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2026.05.0395
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