Article(id=1278415764348715608, tenantId=1146029695717560320, journalId=1146031787341344770, issueId=1277328335906669390, articleNumber=1003-3033(2026)05-0098-07, orderNo=null, doi=10.16265/j.cnki.issn1003-3033.2026.05.0318, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1763049600000, receivedDateStr=2025-11-14, revisedDate=1770048000000, revisedDateStr=2026-02-03, acceptedDate=null, acceptedDateStr=null, onlineDate=1782727670037, onlineDateStr=2026-06-29, pubDate=1779897600000, pubDateStr=2026-05-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1782727670037, onlineIssueDateStr=2026-06-29, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1782727670037, creator=13701087609, updateTime=1782727670037, 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=98, endPage=104, ext={EN=ArticleExt(id=1278415764801700441, articleId=1278415764348715608, tenantId=1146029695717560320, journalId=1146031787341344770, language=EN, title=A detection algorithm for insulated glove wearing status of distribution network operators, columnId=1277328337617941059, journalTitle=China Safety Science Journal, columnName=Safety Technology and Engineering, runingTitle=null, highlight=null, articleAbstract=

To address the degraded detection performance of insulated glove wearing status caused by small hand regions in complex distribution network operation scenarios, a small-object-oriented detection algorithm, termed LN (LLC (Light-weight, Light, Coordinate) +NWD(Normalized Wasserstein Distance)), -YOLO is proposed.First, an LLC module was designed by integrating lightweight spatial pyramid pooling, a receptive field fusion attention mechanism, and coordinate convolution, thereby enhancing spatial perception through multi-scale feature aggregation and coordinate embedding.Subsequently, the Mixup data augmentation strategy was introduced to improve model robustness, and a NWD loss function is incorporated to optimize small-object detection.Finally, the effectiveness of LLC module was validated through controlled experiments to determine the optimal baseline, followed by ablation and comparative experiments on the proposed method.The results demonstrate that the proposed algorithm achieves a detection accuracy of 90.1%, representing a 2.0% improvement over the baseline, with a detection speed of 56 frames per second and a memory footprint of 15.7 MB, meeting the requirements for accuracy, real-time performance, and edge-device deployment in distribution network operation scenarios.

, authors=Zhiling Yang1, Zhixin Ding1, Jia Li2, Goma F R Pangou1, authorsList=Zhiling Yang, Zhixin Ding, Jia Li, Goma F R Pangou, authorCompany=null, 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, fund=null), CN=ArticleExt(id=1278415771160265327, articleId=1278415764348715608, tenantId=1146029695717560320, journalId=1146031787341344770, language=CN, title=配电网作业人员绝缘手套佩戴状态检测算法, columnId=1277328337940902469, journalTitle=中国安全科学学报, columnName=安全技术与工程, runingTitle=null, highlight=null, articleAbstract=

针对复杂配电网作业场景下手部区域较小造成的作业人员绝缘手套佩戴状态检测效果较差的问题,提出一种针对小目标检测的算法——LN-YOLO,首先,提出轻量空间金字塔池化模块和轻量感受野融合注意力机制,并引入坐标卷积,组成LLC模块,该模块通过聚集感受野特征与嵌入坐标信息,增强卷积的空间感知能力;然后,引入Mixup数据增强策略,提高模型的鲁棒性并在模型中添加针对小目标检测的归一化瓦瑟斯坦距离损失函数;最后,通过LLC模块有效性验证试验确定最佳基线算法,并对文中改进算法进行消融与对比试验。结果表明:改进算法的检测精度达到90.1%,较基线提升2.0%,检测速度达56帧/s,内存占用仅15.7 MB,满足配电网作业场景对绝缘手套检测精度、实时性及边缘设备部署要求。

, authors=杨志凌1, 丁志鑫1, 李佳2, Pangou Goma F R1, authorsList=杨志凌, 丁志鑫, 李佳, Pangou Goma F R, authorCompany=null, correspAuthors=null, authorNote=

杨志凌 (1972—),男,山东德州人,博士,副教授,主要从事机械设备故障预测与健康管理等方面的研究。E-mail:

, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=h+u28gkGbqunw3uR2sCSJg==, magXml=EqbEXtut7JpIMIRqygV4/w==, pdfUrl=null, pdf=GL+QuZz8EEMoJc54K9W/+w==, pdfFileSize=9288469, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=gOp6EQnWy7KfYS7S7PhWCA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=t9LfQt4h3WC0rhyPm0beJw==, mapNumber=null, fund=null)}, authors=[Author(id=1278415771579695735, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yzhil@ncepu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1278415771671970425, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415771579695735, language=EN, stringName=Zhiling Yang, firstName=Zhiling, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Power and Mechanical Engineering, North China Electric Power University, Beijing 100096, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415771751662202, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415771579695735, language=CN, stringName=杨志凌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 华北电力大学 能源动力与机械工程学院, 北京 100096, bio={"img":"iC1gukXo/E0WbxrcTk4DxA==","content":"

杨志凌 (1972—),男,山东德州人,博士,副教授,主要从事机械设备故障预测与健康管理等方面的研究。E-mail:

"}, bioImg=iC1gukXo/E0WbxrcTk4DxA==, bioContent=

杨志凌 (1972—),男,山东德州人,博士,副教授,主要从事机械设备故障预测与健康管理等方面的研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415771407729264, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, xref=1, ext=[AuthorCompanyExt(id=1278415771416117873, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771407729264, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Power and Mechanical Engineering, North China Electric Power University, Beijing 100096, China), AuthorCompanyExt(id=1278415771424506482, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771407729264, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 华北电力大学 能源动力与机械工程学院, 北京 100096)])]), Author(id=1278415771818771068, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1278415771898462846, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415771818771068, language=EN, stringName=Zhixin Ding, firstName=Zhixin, middleName=null, lastName=Ding, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Power and Mechanical Engineering, North China Electric Power University, Beijing 100096, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415771982348927, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415771818771068, language=CN, stringName=丁志鑫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 华北电力大学 能源动力与机械工程学院, 北京 100096, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415771407729264, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, xref=1, ext=[AuthorCompanyExt(id=1278415771416117873, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771407729264, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Power and Mechanical Engineering, North China Electric Power University, Beijing 100096, China), AuthorCompanyExt(id=1278415771424506482, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771407729264, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 华北电力大学 能源动力与机械工程学院, 北京 100096)])]), Author(id=1278415772062040705, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, 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=1278415772133343875, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415772062040705, language=EN, stringName=Jia Li, firstName=Jia, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 State Grid Corporation of China, Beijing 100192, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415772208841348, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415772062040705, language=CN, stringName=李佳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 中国电力科学研究院有限公司, 北京 100192, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415771500003955, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, xref=2, ext=[AuthorCompanyExt(id=1278415771508392564, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771500003955, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 State Grid Corporation of China, Beijing 100192, China), AuthorCompanyExt(id=1278415771516781173, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771500003955, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中国电力科学研究院有限公司, 北京 100192)])]), Author(id=1278415772280144518, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, 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=1278415772359836296, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415772280144518, language=EN, stringName=Goma F R Pangou, firstName=Goma F R, middleName=null, lastName=Pangou, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Power and Mechanical Engineering, North China Electric Power University, Beijing 100096, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415772431139465, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415772280144518, language=CN, stringName=Pangou Goma F R, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 华北电力大学 能源动力与机械工程学院, 北京 100096, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415771407729264, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, xref=1, ext=[AuthorCompanyExt(id=1278415771416117873, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771407729264, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Power and Mechanical Engineering, North China Electric Power University, Beijing 100096, China), AuthorCompanyExt(id=1278415771424506482, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771407729264, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 华北电力大学 能源动力与机械工程学院, 北京 100096)])])], keywords=[Keyword(id=1278415772556968586, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, orderNo=1, keyword=distribution network operations), Keyword(id=1278415772632466059, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, orderNo=2, keyword=insulating gloves), Keyword(id=1278415772720546444, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, orderNo=3, keyword=wearing status), Keyword(id=1278415772796043917, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, orderNo=4, keyword=detection algorithm), Keyword(id=1278415772871541390, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, orderNo=5, keyword=receptive field), Keyword(id=1278415772955427471, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, orderNo=1, keyword=配电网作业), Keyword(id=1278415773043507856, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, orderNo=2, keyword=绝缘手套), Keyword(id=1278415773110616721, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, orderNo=3, keyword=佩戴状态), Keyword(id=1278415773181919890, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, orderNo=4, keyword=检测算法), Keyword(id=1278415773253223059, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, orderNo=5, keyword=感受野)], refs=[Reference(id=1278415779892806321, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2024, volume=60, issue=9, pageStart=111, pageEnd=121, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=王茹, 刘大明, 张健, journalName=计算机工程与应用, refType=null, unstructuredReference=王茹, 刘大明, 张健. Wear-YOLO:变电站电力人员安全装备检测方法研究[J]. 计算机工程与应用, 2024, 60(9):111-121., articleTitle=Wear-YOLO:变电站电力人员安全装备检测方法研究, refAbstract=null), Reference(id=1278415779993469618, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2024, volume=60, issue=9, pageStart=111, pageEnd=121, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Wang Ru, Liu Daming, Zhang Jian, journalName=Computer Engineering and Applications, refType=null, unstructuredReference=Wang Ru, Liu Daming, Zhang Jian. Wear-YOLO: research on detection methods of safety equipment for power personnel in substations[J]. Computer Engineering and Applications, 2024, 60(9): 111-121., articleTitle=Wear-YOLO: research on detection methods of safety equipment for power personnel in substations, refAbstract=null), Reference(id=1278415780094132915, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2023, volume=31, issue=11, pageStart=60, pageEnd=65, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=王彦生, 朱佳佳, 王紫仪, journalName=计算机测量与控制, refType=null, unstructuredReference=王彦生, 朱佳佳, 王紫仪, . 基于改进YOLOv5的电厂人员绝缘手套佩戴检测[J]. 计算机测量与控制, 2023, 31(11):60-65,73., articleTitle=基于改进YOLOv5的电厂人员绝缘手套佩戴检测, refAbstract=null), Reference(id=1278415780198990516, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2023, volume=31, issue=11, pageStart=60, pageEnd=65, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Wang Yansheng, Zhu Jiajia, Wang Ziyi, journalName=Computer Measurement & Control, refType=null, unstructuredReference=Wang Yansheng, Zhu Jiajia, Wang Ziyi, et al. Detection of Insulation gloves worn by power plant personnel base-d on improved YOLOv5[J]. Computer Measurement & Control, 2023, 31(11): 60-65,73., articleTitle=Detection of Insulation gloves worn by power plant personnel base-d on improved YOLOv5, refAbstract=null), Reference(id=1278415780349985461, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=3, pageStart=971, pageEnd=981, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=马富齐, 王波, 董旭柱, journalName=中国电机工程学报, refType=null, unstructuredReference=马富齐, 王波, 董旭柱, . 面向电力生产精细化风险解译的高度相似防护工具智能检测技术研究[J]. 中国电机工程学报, 2024, 44(3):971-981., articleTitle=面向电力生产精细化风险解译的高度相似防护工具智能检测技术研究, refAbstract=null), Reference(id=1278415780417094326, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=3, pageStart=971, pageEnd=981, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Ma Fuqi, Wang Bo, Dong Xuzhu, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=Ma Fuqi, Wang Bo, Dong Xuzhu, et al. Research on intelligent detection technology of highly similar protection tools for refined risk interpretation of power production[J]. Proceedings of the CSEE, 2024, 44(3): 971-981., articleTitle=Research on intelligent detection technology of highly similar protection tools for refined risk interpretation of power production, refAbstract=null), Reference(id=1278415780513563319, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=9, pageStart=1989, pageEnd=1995, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=郑海洋, 宋纯贺, 武婷婷, journalName=小型微型计算机系统, refType=null, unstructuredReference=郑海洋, 宋纯贺, 武婷婷, . 面向绝缘手套佩戴状况检测的小目标检测与匹配算法[J]. 小型微型计算机系统, 2023, 44(9):1989-1995., articleTitle=面向绝缘手套佩戴状况检测的小目标检测与匹配算法, refAbstract=null), Reference(id=1278415780618420920, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2023, volume=44, issue=9, pageStart=1989, pageEnd=1995, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Zheng Haiyang, Song Chunhe, Wu Tingting, journalName=Journal of Chinese Computer Systems, refType=null, unstructuredReference=Zheng Haiyang, Song Chunhe, Wu Tingting, et al. Small target detection and matching algorithm for wearing condition detection of insulating gloves[J]. Journal of Chinese Computer Systems, 2023, 44(9): 1989-1995., articleTitle=Small target detection and matching algorithm for wearing condition detection of insulating gloves, refAbstract=null), Reference(id=1278415780685529785, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=谢世勇, journalName=基于深度学习的电力着装检测系统的设计与实现, refType=null, unstructuredReference=谢世勇. 基于深度学习的电力着装检测系统的设计与实现[D]. 武汉: 华中科技大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1278415780752638650, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Xie Shiyong, journalName=Design and implementation of electric clothing detection system based on deep learning, refType=null, unstructuredReference=Xie Shiyong. Design and implementation of electric clothing detection system based on deep learning[D]. Wuhan: Huazhong University of Science and Technology, 2020., articleTitle=null, refAbstract=null), Reference(id=1278415780836524731, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=刘琦, journalName=基于深度学习的电网作业防护穿戴合规性智能检测方法研究, refType=null, unstructuredReference=刘琦. 基于深度学习的电网作业防护穿戴合规性智能检测方法研究[D]. 大连: 大连海事大学, 2023., articleTitle=null, refAbstract=null), Reference(id=1278415781037851324, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=Liu Qi, journalName=Research on intelligent detection of protective wear for power grid operation based on deep learning, refType=null, unstructuredReference=Liu Qi. Research on intelligent detection of protective wear for power grid operation based on deep learning[D]. Dalian: Dalian Maritime University, 2023., articleTitle=null, refAbstract=null), Reference(id=1278415781130126013, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2024, volume=71, issue=1, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=Tao Caixia, Wang Chaoting, Li Taiguo, journalName=Journal of Engineering and Applied Science, refType=null, unstructuredReference=Tao Caixia, Wang Chaoting, Li Taiguo. Detection research of insulating gloves wearing status based on improved YOLOv8s algorithm[J]. Journal of Engineering and Applied Science, 2024, 71(1): DOI:10.1186/s44147-024-00458-y., articleTitle=Detection research of insulating gloves wearing status based on improved YOLOv8s algorithm, refAbstract=null), Reference(id=1278415781214012094, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2025, volume=35, issue=3, pageStart=36, pageEnd=44, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=柯巍, 朱权洁, 陈长茂, journalName=中国安全科学学报, refType=null, unstructuredReference=柯巍, 朱权洁, 陈长茂, . 基于改进YOLOv11的卷烟仓储人员不安全行为分类及识别[J]. 中国安全科学学报, 2025, 35(3):36-44., articleTitle=基于改进YOLOv11的卷烟仓储人员不安全行为分类及识别, refAbstract=null), Reference(id=1278415781344035519, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2025, volume=35, issue=3, pageStart=36, pageEnd=44, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=Ke Wei, Zhu Quanjie, Chen Changmao, journalName=China Safety Scienee Journal, refType=null, unstructuredReference=Ke Wei, Zhu Quanjie, Chen Changmao, et al. Classification and recognition of unsafe behaviors of tobacco warehouse personnel based on imprved YOLOv11[J]. China Safety Scienee Journal, 2025, 35 (3):36-44., articleTitle=Classification and recognition of unsafe behaviors of tobacco warehouse personnel based on imprved YOLOv11, refAbstract=null), Reference(id=1278415781419532992, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2025, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=Ma Jianhua, Zhou Yongzhang, Zhou Zimeng, journalName=Marine Pollution Bulletin, refType=null, unstructuredReference=Ma Jianhua, Zhou Yongzhang, Zhou Zimeng, et al. Toward smart ocean monitoring: real-time detection of marine litter using YOLOv12 in support of pollution mitigation[J]. Marine Pollution Bulletin, 2025, 217: DOI: 10.1016/j.marpolbul.2025.118136., articleTitle=Toward smart ocean monitoring: real-time detection of marine litter using YOLOv12 in support of pollution mitigation, refAbstract=null), Reference(id=1278415781499224769, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=9605, pageEnd=9616, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=Liu Rosanne, Lehman J, Molino P, journalName=Advances in Neural Information Processing Systems 31, refType=null, unstructuredReference=Liu Rosanne, Lehman J, Molino P, et al. An intriguing failing of convolutional neural networks and the CoordConv solution[C]. Advances in Neural Information Processing Systems 31,2018: 9605-9616., articleTitle=An intriguing failing of convolutional neural networks and the CoordConv solution, refAbstract=null), Reference(id=1278415781604082370, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, doi=null, pmid=null, pmcid=null, year=2024, volume=21, issue=3, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=17, authorNames=Li Hulin, Li Jun, Wei Hanbing, journalName=Journal of Real-Time Image Processing, refType=null, unstructuredReference=Li Hulin, Li Jun, Wei Hanbing, et al. Slim-neck by GSConv: a lightweight-design for real-time detector architectures[J]. Journal of Real-Time Image Processing, 2024, 21(3):DOI:10.1007/s11554-024-01436-6., articleTitle=Slim-neck by GSConv: a lightweight-design for real-time detector architectures, refAbstract=null)], funds=[Fund(id=1278415779645342384, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, awardId=5400-202355219A-1-1-ZN, language=CN, fundingSource=国家电网公司科技项目(5400-202355219A-1-1-ZN), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1278415771407729264, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, xref=1, ext=[AuthorCompanyExt(id=1278415771416117873, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771407729264, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Power and Mechanical Engineering, North China Electric Power University, Beijing 100096, China), AuthorCompanyExt(id=1278415771424506482, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771407729264, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 华北电力大学 能源动力与机械工程学院, 北京 100096)]), AuthorCompany(id=1278415771500003955, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, xref=2, ext=[AuthorCompanyExt(id=1278415771508392564, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771500003955, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 State Grid Corporation of China, Beijing 100192, China), AuthorCompanyExt(id=1278415771516781173, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771500003955, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中国电力科学研究院有限公司, 北京 100192)])], figs=[ArticleFig(id=1278415773408412308, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, label=Fig.1, caption=Network structure of the LN-YOLO, figureFileSmall=ClfO/2xVb/VK18r076P6zQ==, figureFileBig=gOp6EQnWy7KfYS7S7PhWCA==, tableContent=null), ArticleFig(id=1278415775178408598, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, label=图1, caption=LN-YOLO检测算法网络结构, figureFileSmall=ClfO/2xVb/VK18r076P6zQ==, figureFileBig=gOp6EQnWy7KfYS7S7PhWCA==, tableContent=null), ArticleFig(id=1278415775778194071, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, label=Fig.2, caption=Structure of lightweight spatial pyramid pooling, figureFileSmall=IJrUnkyPH5kAX4KO2VAYMw==, figureFileBig=grzB+AM/Vyu+k2KqjLe8zQ==, tableContent=null), ArticleFig(id=1278415775853691545, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, label=图2, caption=轻量空间金字塔池化结构, figureFileSmall=IJrUnkyPH5kAX4KO2VAYMw==, figureFileBig=grzB+AM/Vyu+k2KqjLe8zQ==, tableContent=null), ArticleFig(id=1278415776059212442, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, label=Fig.3, caption=Structure of lightweight separable convolution, figureFileSmall=+bH7M07xW8zzm/7l4LIqgQ==, figureFileBig=Zz8sX+Jv9IMjwEDOExWfaQ==, tableContent=null), ArticleFig(id=1278415776122127003, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, label=图3, caption=轻量级可分离卷积结构, figureFileSmall=+bH7M07xW8zzm/7l4LIqgQ==, figureFileBig=Zz8sX+Jv9IMjwEDOExWfaQ==, tableContent=null), ArticleFig(id=1278415776206013084, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, label=Fig.4, caption=Structure of lightweight receptive field fusion attention, figureFileSmall=hDoK6cJa03W4p1/zdZecfQ==, figureFileBig=THNMFb+L4eCwjwT656bLUw==, tableContent=null), ArticleFig(id=1278415776281510557, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, label=图4, caption=轻量感受野融合注意力结构, figureFileSmall=hDoK6cJa03W4p1/zdZecfQ==, figureFileBig=THNMFb+L4eCwjwT656bLUw==, tableContent=null), ArticleFig(id=1278415776365396638, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, label=Fig.5, caption=Mixup data augmentation effect, figureFileSmall=xiCkGJBFyRWicFU1DaTtzQ==, figureFileBig=fU4QHUjGZDVMxsV7LuzSIg==, tableContent=null), ArticleFig(id=1278415776436699807, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, label=图5, caption=Mixup数据增强效果, figureFileSmall=xiCkGJBFyRWicFU1DaTtzQ==, figureFileBig=fU4QHUjGZDVMxsV7LuzSIg==, tableContent=null), ArticleFig(id=1278415776516391584, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, label=Fig.6, caption=Effective receptive field visualization, figureFileSmall=s70uJSYz0iWY4Mnsrs5kHg==, figureFileBig=CHw8O4oB/RzxycgOZHdaDg==, tableContent=null), ArticleFig(id=1278415776579306145, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, label=图6, caption=有效感受野可视化, figureFileSmall=s70uJSYz0iWY4Mnsrs5kHg==, figureFileBig=CHw8O4oB/RzxycgOZHdaDg==, tableContent=null), ArticleFig(id=1278415776650609314, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, label=Fig.7, caption=Heatmaps generated by LN-YOLO and YOLOv5, figureFileSmall=6H5aKhOZGdjLe13SVvCuOg==, figureFileBig=YWt7yV2N7LQ84O87JnsNPA==, tableContent=null), ArticleFig(id=1278415776742884003, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, label=图7, caption=LN-YOLO与YOLOv5生成的热力图, figureFileSmall=6H5aKhOZGdjLe13SVvCuOg==, figureFileBig=YWt7yV2N7LQ84O87JnsNPA==, tableContent=null), ArticleFig(id=1278415776847741604, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, label=Fig.8, caption=Detection results of LN-YOLO,YOLOv8,YOLOv9, YOLOv10, YOLOv11 and YOLOv12, figureFileSmall=WpfuRvt/3u+iQ3KOwbB4Mw==, figureFileBig=uiK8nQpPpQFAiYf+jCF5Aw==, tableContent=null), ArticleFig(id=1278415776923239077, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, label=图8, caption=LN-YOLO、YOLOv8、YOLOv9、YOLOv10、YOLOv11、YOLOv12检测效果, figureFileSmall=WpfuRvt/3u+iQ3KOwbB4Mw==, figureFileBig=uiK8nQpPpQFAiYf+jCF5Aw==, tableContent=null), ArticleFig(id=1278415777011319462, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, label=Fig.9, caption=Detection results of LN-YOLO, YOLOv5, YOLOv8, YOLOv11, and YOLOv12 in dark and strong light, figureFileSmall=J+GVFzlAOLVdkvwbUtWaGQ==, figureFileBig=sVYUSqB8BEDf5Qyn+94B7g==, tableContent=null), ArticleFig(id=1278415777078428327, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, label=图9, caption=暗环境与强光环境下LN-YOLO、YOLOv5、YOLOv8、YOLOv11、YOLOv12检测效果, figureFileSmall=J+GVFzlAOLVdkvwbUtWaGQ==, figureFileBig=sVYUSqB8BEDf5Qyn+94B7g==, tableContent=null), ArticleFig(id=1278415777267172008, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, label=Table 1, caption=

Verification results of LLC module effectiveness

, figureFileSmall=null, figureFileBig=null, tableContent=
算法 mAP@0.5 内存/MB
基线 +LLC 基线 +LLC
YOLOv5 0.881 0.888 14.4 15.7
YOLOv8 0.869 0.871 22.5 22.3
YOLOv10 0.765 0.853 16.5 18.1
YOLOv11 0.878 0.857 19.2 23.1
YOLOv12 0.882 0.833 18.9 23.0
), ArticleFig(id=1278415777367835305, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, label=表1, caption=

LLC模块有效性验证试验结果

, figureFileSmall=null, figureFileBig=null, tableContent=
算法 mAP@0.5 内存/MB
基线 +LLC 基线 +LLC
YOLOv5 0.881 0.888 14.4 15.7
YOLOv8 0.869 0.871 22.5 22.3
YOLOv10 0.765 0.853 16.5 18.1
YOLOv11 0.878 0.857 19.2 23.1
YOLOv12 0.882 0.833 18.9 23.0
), ArticleFig(id=1278415777468498602, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, label=Table 2, caption=

Ablation experiment data

, figureFileSmall=null, figureFileBig=null, tableContent=
试验 mAP@
0.5
FPS/
(帧/s)
参数量/
MB
计算量/
G
内存/
MB
A 0.881 46 7 027 720 16 14.4
A+B 0.886 46 7 027 720 16 14.4
A+B+C 0.893 56 7 676 094 16.9 15.7
A+B+C+D 0.901 56 7 676 094 16.9 15.7
), ArticleFig(id=1278415777543996075, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, label=表2, caption=

消融试验数据

, figureFileSmall=null, figureFileBig=null, tableContent=
试验 mAP@
0.5
FPS/
(帧/s)
参数量/
MB
计算量/
G
内存/
MB
A 0.881 46 7 027 720 16 14.4
A+B 0.886 46 7 027 720 16 14.4
A+B+C 0.893 56 7 676 094 16.9 15.7
A+B+C+D 0.901 56 7 676 094 16.9 15.7
), ArticleFig(id=1278415777686602412, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, label=Table 3, caption=

Comparative experiment data

, figureFileSmall=null, figureFileBig=null, tableContent=
算法 mAP@0.5 FPS/
(帧/s)
参数量/
MB
计算量/
G
内存/
MB
LN-YOLO 0.901 56 7 676 094 16.9 15.7
YOLOv8 0.869 90 11 136 761 28.7 22.5
YOLOv9 0.911 17 25 439 385 103.2 51.4
YOLOv10 0.765 85 8 068 674 24.5 16.5
YOLOv11 0.878 58 9 413 961 21.3 19.2
YOLOv12 0.882 60 9 232 041 21.2 18.9
), ArticleFig(id=1278415777778877101, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, label=表3, caption=

对比试验数据

, figureFileSmall=null, figureFileBig=null, tableContent=
算法 mAP@0.5 FPS/
(帧/s)
参数量/
MB
计算量/
G
内存/
MB
LN-YOLO 0.901 56 7 676 094 16.9 15.7
YOLOv8 0.869 90 11 136 761 28.7 22.5
YOLOv9 0.911 17 25 439 385 103.2 51.4
YOLOv10 0.765 85 8 068 674 24.5 16.5
YOLOv11 0.878 58 9 413 961 21.3 19.2
YOLOv12 0.882 60 9 232 041 21.2 18.9
), ArticleFig(id=1278415777854374574, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=EN, label=Table 4, caption=

Comparison of experimental data between dark and strong light environments

, figureFileSmall=null, figureFileBig=null, tableContent=
算法 mAP@0.5
暗环境 强光环境
LN-YOLO 0.796 0.803
YOLOv5 0.772 0.788
YOLOv8 0.766 0.777
YOLOv11 0.782 0.758
YOLOv12 0.77 0.713
), ArticleFig(id=1278415779532096175, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, language=CN, label=表4, caption=

暗环境与强光环境对比试验数据

, figureFileSmall=null, figureFileBig=null, tableContent=
算法 mAP@0.5
暗环境 强光环境
LN-YOLO 0.796 0.803
YOLOv5 0.772 0.788
YOLOv8 0.766 0.777
YOLOv11 0.782 0.758
YOLOv12 0.77 0.713
)], 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.issn1003-3033.2026.05.0318, detailUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/10.16265/j.cnki.issn1003-3033.2026.05.0318, pdfUrlCn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/PDF/10.16265/j.cnki.issn1003-3033.2026.05.0318, pdfUrlEn=https://castjournals.cast.org.cn/joweb/zgaqkxxb/EN/PDF/10.16265/j.cnki.issn1003-3033.2026.05.0318, 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
配电网作业人员绝缘手套佩戴状态检测算法
收藏切换
PDF下载
杨志凌 1 , 丁志鑫 1 , 李佳 2 , Pangou Goma F R 1
中国安全科学学报 | 安全技术与工程 2026,36(5): 98-104
收起
收藏切换
中国安全科学学报 |安全技术与工程 2026 , 36 (5) : 98 -104
配电网作业人员绝缘手套佩戴状态检测算法
全屏
[Author(id=1278415771579695735, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yzhil@ncepu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1278415771671970425, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415771579695735, language=EN, stringName=Zhiling Yang, firstName=Zhiling, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Power and Mechanical Engineering, North China Electric Power University, Beijing 100096, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415771751662202, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415771579695735, language=CN, stringName=杨志凌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 华北电力大学 能源动力与机械工程学院, 北京 100096, bio={"img":"iC1gukXo/E0WbxrcTk4DxA==","content":"

杨志凌 (1972—),男,山东德州人,博士,副教授,主要从事机械设备故障预测与健康管理等方面的研究。E-mail:

"}, bioImg=iC1gukXo/E0WbxrcTk4DxA==, bioContent=

杨志凌 (1972—),男,山东德州人,博士,副教授,主要从事机械设备故障预测与健康管理等方面的研究。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415771407729264, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, xref=1, ext=[AuthorCompanyExt(id=1278415771416117873, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771407729264, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Power and Mechanical Engineering, North China Electric Power University, Beijing 100096, China), AuthorCompanyExt(id=1278415771424506482, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771407729264, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 华北电力大学 能源动力与机械工程学院, 北京 100096)])]), Author(id=1278415771818771068, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1278415771898462846, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415771818771068, language=EN, stringName=Zhixin Ding, firstName=Zhixin, middleName=null, lastName=Ding, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Power and Mechanical Engineering, North China Electric Power University, Beijing 100096, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415771982348927, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415771818771068, language=CN, stringName=丁志鑫, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 华北电力大学 能源动力与机械工程学院, 北京 100096, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415771407729264, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, xref=1, ext=[AuthorCompanyExt(id=1278415771416117873, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771407729264, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Power and Mechanical Engineering, North China Electric Power University, Beijing 100096, China), AuthorCompanyExt(id=1278415771424506482, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771407729264, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 华北电力大学 能源动力与机械工程学院, 北京 100096)])]), Author(id=1278415772062040705, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, 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=1278415772133343875, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415772062040705, language=EN, stringName=Jia Li, firstName=Jia, middleName=null, lastName=Li, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 State Grid Corporation of China, Beijing 100192, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415772208841348, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415772062040705, language=CN, stringName=李佳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 中国电力科学研究院有限公司, 北京 100192, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415771500003955, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, xref=2, ext=[AuthorCompanyExt(id=1278415771508392564, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771500003955, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 State Grid Corporation of China, Beijing 100192, China), AuthorCompanyExt(id=1278415771516781173, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771500003955, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中国电力科学研究院有限公司, 北京 100192)])]), Author(id=1278415772280144518, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, 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=1278415772359836296, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415772280144518, language=EN, stringName=Goma F R Pangou, firstName=Goma F R, middleName=null, lastName=Pangou, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Power and Mechanical Engineering, North China Electric Power University, Beijing 100096, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1278415772431139465, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, authorId=1278415772280144518, language=CN, stringName=Pangou Goma F R, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 华北电力大学 能源动力与机械工程学院, 北京 100096, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1278415771407729264, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, xref=1, ext=[AuthorCompanyExt(id=1278415771416117873, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771407729264, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Power and Mechanical Engineering, North China Electric Power University, Beijing 100096, China), AuthorCompanyExt(id=1278415771424506482, tenantId=1146029695717560320, journalId=1146031787341344770, articleId=1278415764348715608, companyId=1278415771407729264, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 华北电力大学 能源动力与机械工程学院, 北京 100096)])])]
杨志凌1 , 丁志鑫1, 李佳2, Pangou Goma F R1
作者信息
  • 1 华北电力大学 能源动力与机械工程学院, 北京 100096
  • 2 中国电力科学研究院有限公司, 北京 100192
作者简介:

杨志凌 (1972—),男,山东德州人,博士,副教授,主要从事机械设备故障预测与健康管理等方面的研究。E-mail:

A detection algorithm for insulated glove wearing status of distribution network operators
Zhiling Yang1 , Zhixin Ding1, Jia Li2, Goma F R Pangou1
Affiliations
  • 1 School of Power and Mechanical Engineering, North China Electric Power University, Beijing 100096, China
  • 2 State Grid Corporation of China, Beijing 100192, China
出版时间: 2026-05-28 doi: 10.16265/j.cnki.issn1003-3033.2026.05.0318
文章导航
收藏切换

针对复杂配电网作业场景下手部区域较小造成的作业人员绝缘手套佩戴状态检测效果较差的问题,提出一种针对小目标检测的算法——LN-YOLO,首先,提出轻量空间金字塔池化模块和轻量感受野融合注意力机制,并引入坐标卷积,组成LLC模块,该模块通过聚集感受野特征与嵌入坐标信息,增强卷积的空间感知能力;然后,引入Mixup数据增强策略,提高模型的鲁棒性并在模型中添加针对小目标检测的归一化瓦瑟斯坦距离损失函数;最后,通过LLC模块有效性验证试验确定最佳基线算法,并对文中改进算法进行消融与对比试验。结果表明:改进算法的检测精度达到90.1%,较基线提升2.0%,检测速度达56帧/s,内存占用仅15.7 MB,满足配电网作业场景对绝缘手套检测精度、实时性及边缘设备部署要求。

配电网作业  /  绝缘手套  /  佩戴状态  /  检测算法  /  感受野

To address the degraded detection performance of insulated glove wearing status caused by small hand regions in complex distribution network operation scenarios, a small-object-oriented detection algorithm, termed LN (LLC (Light-weight, Light, Coordinate) +NWD(Normalized Wasserstein Distance)), -YOLO is proposed.First, an LLC module was designed by integrating lightweight spatial pyramid pooling, a receptive field fusion attention mechanism, and coordinate convolution, thereby enhancing spatial perception through multi-scale feature aggregation and coordinate embedding.Subsequently, the Mixup data augmentation strategy was introduced to improve model robustness, and a NWD loss function is incorporated to optimize small-object detection.Finally, the effectiveness of LLC module was validated through controlled experiments to determine the optimal baseline, followed by ablation and comparative experiments on the proposed method.The results demonstrate that the proposed algorithm achieves a detection accuracy of 90.1%, representing a 2.0% improvement over the baseline, with a detection speed of 56 frames per second and a memory footprint of 15.7 MB, meeting the requirements for accuracy, real-time performance, and edge-device deployment in distribution network operation scenarios.

distribution network operations  /  insulating gloves  /  wearing status  /  detection algorithm  /  receptive field
杨志凌, 丁志鑫, 李佳, Pangou Goma F R. 配电网作业人员绝缘手套佩戴状态检测算法. 中国安全科学学报, 2026 , 36 (5) : 98 -104 . DOI: 10.16265/j.cnki.issn1003-3033.2026.05.0318
Zhiling Yang, Zhixin Ding, Jia Li, Goma F R Pangou. A detection algorithm for insulated glove wearing status of distribution network operators[J]. China Safety Science Journal, 2026 , 36 (5) : 98 -104 . DOI: 10.16265/j.cnki.issn1003-3033.2026.05.0318
配电网作业隐患多、风险高,规范穿戴绝缘手套是保障作业人员安全的关键[1],因此,强化对穿戴状态的合规性检测至关重要。针对传统人工监查效率低下及人力负担重等问题[2],基于计算机视觉与深度学习的自动化检测技术已成为研究热点[3]。在配电网作业中,未佩戴绝缘手套为高危行为,因此绝缘手套佩戴状态检测亟待深入研究。
目前,大量学者对绝缘手套等电力安全装备检测开展了广泛研究。例如:郑海洋等[4]通过改进YOLOv3(You Only Look Once version 3)优化了绝缘手套佩戴状态的识别;谢世勇[5]结合AlphaPose姿态估计与区域裁剪算法实现了安全装备穿戴情况的检测;刘琦[6]利用YOLOv5联合语义分割技术提升了电网作业防护穿戴合规性的检测精度;随着算法的迭代更新,陶彩霞等[7]基于YOLOv8架构提出了改进的绝缘手套检测模型;柯巍等[8]利用YOLOv11进一步优化了绝缘手套的识别方法;而近期的前沿研究也开始尝试验证YOLOv12在相关场景中的应用潜力[9]。尽管上述研究在不同层面推动了技术进步,但在实际配电网作业场景应用中仍面临2大难题:一是模型复杂度过高,难以适配边缘端资源。部分追求高精度的研究采用了多阶段或复杂的网络结构,导致参数量巨大且内存占用过高,难以满足作业现场对实时监测与轻量化部署的要求;二是复杂场景下微小目标的检测能力不足。配电网作业背景杂乱,手部目标占比极小且易受遮挡,而现有的轻量化或前沿算法研究往往忽略了针对小尺度特征的专项优化,导致在手部区域占比极小或存在遮挡的场景下,易出现漏检误检。
综上,现有研究难以在有限算力下兼顾微小目标识别精度,鉴于此,笔者拟构建轻量,轻盈,搭配(Light-weight, Light, Coordinate,LLC)模块,增强手部及绝缘手套等特征的提取能力,并引入Mixup数据增强及归一化瓦瑟斯坦距离(Normalized Wasserstein Distance,NWD)提升小目标检测性能,进而提出面向绝缘手套佩戴状态检测的LN-YOLO算法,以期在保持模型轻量化的同时,现高精度检测绝缘手套佩戴状态。
绝缘手套佩戴状态检测算法LN(LLC+NWD)-YOLO的网络结构如图1所示。首先,由轻量空间金字塔池化、轻量感受野融合注意力和坐标卷积[10]构成LLC模块代替特征融合端的3个C3模块;然后使用Mixup数据增强技术进行数据增强;最后添加NWD损失函数。
原YOLOv5网络中C3模块在特征融合端对小目标检测不够敏感,在融合过程中,小目标的特征可能被背景或大目标的特征“淹没”,导致信息丢失。针对上述问题,设计LLC模块代替C3模块。
传统空间金字塔池化通过多尺度池化层,如5×5,9×9,13×13,实现局部与全局特征融合,但其特征拼接策略容易导致维度膨胀,引发计算冗余性和小目标信息丢失。为此,提出轻量空间金字塔池化,其结构如图2所示,其核心改进包括:①针对不同层级特征分辨率的特性,采用动态调整的多尺度池化窗口策略。②在全连接层后插入轻量级可分离卷积,取代标准卷积块。
1) 多尺度池化窗口策略。轻量空间金字塔池化窗口的选取参考YOLO、残差式多尺度等系列网络。浅层特征图具有较高的空间分辨率,小目标在此层保留足够像素信息,因此,采用[5,9,13]池化窗口,分别用于提取边缘细节、局部语义和大范围上下文信息;在过渡性质的中层选用[3,7,11]窗口,兼顾细节感知与语义扩展;在分辨率较低的深层使用[3,5,7]窗口,避免特征过度压缩,有效保留小目标判别性特征。
2) 轻量级可分离卷积。为进一步提高小目标检测中的特征提取效率与语义感知能力,在轻量空间金字塔中引入轻量级可分离卷积,其结构如图3所示。轻量级可分离卷积由逐深度卷积、通道混洗和通道注意力机制3部分组成。首先,由结构中的逐深度卷积通过逐通道卷积提取空间特征,旨在保持空间特征提取能力的同时,降低参数量与计算复杂度。随后,引入通道混洗以解决跨通道信息阻断问题。最后,通道注意力机制通过自适应平均池化捕获全局统计量,生成通道权重向量,并利用该权重对原始特征图进行动态重加权,使模型能根据上下文调整不同通道的重要性,从而聚焦于与小目标相关的判别性特征。
综上所述,轻量空间金字塔池化通过定制化的多尺度池化窗口匹配不同层级特征图的空间与语义需求,并结合轻量级可分离卷积在降维减参、增强信息流动及特征重加权方面的协同优势,不仅能够强化配电网作业中手部等微小目标的特征提取能力,还能凭借轻量化特性实现检测精度与实时性的良好平衡。
在通过轻量空间金字塔池化捕获多尺度空间上下文信息后,为进一步强化对微小目标关键特征的聚焦能力,设计并引入轻量感受野融合注意力机制,结构如图4所示。针对传统轻量化设计中可分离卷积特征提取能力弱的问题,该模块引入幽灵混洗模块[11],通过将标准卷积与可分离卷积结合并辅以通道混洗,增强了特征融合能力;同时,为克服自注意力机制计算复杂、空间注意力机制全局视野受限的缺陷,融合了感受野注意力机制。两者协同作用,实现了对通道与空间维度关键信息的精准捕获,有效提升了模型对手部及绝缘手套这类小目标特征的感知能力。
具体而言,在轻量感受野融合注意力结构中,幽灵混洗模块首先依次执行1×1轻量压缩和3×3空间上下文建模,旨在保持模型准确率的同时,降低计算复杂度;随后,引入感受野注意力利用多感受野与通道注意力机制,实现多尺度特征捕获与小目标语义的自适应增强;最后,融合多路径输出特征以实现空间-通道联合增强。
综上,轻量感受野融合注意力机制的设计考虑了效率与效果的平衡,使模型更加关注绝缘手套、手部特征,增强了模型对小目标的聚焦能力。
尽管前述模块增强了特征提取与聚焦能力,但标准卷积缺乏对空间位置信息的感知,为此,引入坐标卷积,其在输入特征图的基础上附加2个显式的坐标通道(ij),分别表示每个像素点在水平x和垂直y方向上的归一化坐标。这一设计使得模型在卷积过程中能够感知每个特征点的几何位置信息。最终,坐标卷积与轻量空间金字塔池化的多尺度上下文融合以及轻量感受野融合注意力的聚焦能力互补,进一步提升了模型对微小区域目标的识别鲁棒性和定位准确性。
针对配电网作业环境下绝缘手套佩戴状态难以区分的问题,选择合适的数据增强策略至关重要。传统的Mosaic方法通过4图拼接增加小目标数量,但会破坏图像原有的上下文逻辑并引入人工边界;相比之下,Mixup通过图像线性叠加平滑决策边界,既能模拟复杂重叠场景,又能保持上下文连贯性,更适用于本文模型的应用场景。后续训练选择启用Mixup,其效果如图5所示,2张图像按照一定比例混合形成新图像,并且训练过程中只采用形成的新图像训练。
针对传统交并比损失(Intersection over Union loss,IoU)在检测微小手部目标时,因对位置偏差过度敏感而导致性能显著下降的问题,引入一种基于瓦瑟斯坦距离针对小目标检测的新评估指标NWD替代IoU损失,以提升小目标检测精度。NWD损失公式为:
$ \operatorname{NWD}\left(N_{\mathrm{a}}, N_{\mathrm{b}}\right)=\exp \left(-\frac{\sqrt{W_{2}^{2}\left(N_{\mathrm{a}}, N_{\mathrm{b}}\right)}}{c}\right)$
式中:NaNb为高斯分布;${W}_{2}^{2}({N}_{a},{N}_{b})$为距离度量;c为与数据集相关的常数。
与IoU相比,NWD具有尺度不变性且能够测量不重叠或相互包含的边界框之间的相似性。
试验基于PyTorch深度学习框架,硬件环境采用配备12GB显存的图形处理器。数据集包含2 035张作业现场采集图像,经LabelImg标注为佩戴绝缘手套、普通手套及未佩戴3类,并按8∶1∶1随机划分为训练、验证及测试集。训练阶段采用随机梯度下降优化器,加载预训练权重,设定批次大小为16,轮次为100,初始学习率为0.01,动量与权重衰减分别为0.937和5×10-4。所有试验均在以上环境、条件和数据集下进行。
对于绝缘手套检测算法的评估,需要考虑检测精度、检测速度以及模型复杂度等指标。采用预测框和真实框阈值为0.50时的平均精度均值(mean Average Precision,mAP@0.50)来评估模型检测精度;检测速度通过模型在1s内识别的图像数量来描述,即帧率(Frames Per Second,FPS);模型的复杂度通过参数量和计算量评估。
1) 不同模型集成LLC模块性能对比。为验证LLC模块在不同模型中的适应性并确定最佳基线模型,将其分别集成至YOLOv5、v8、v10、v11及v12框架中进行试验,结果见表1。由表1可知:LLC模块集成在YOLOv5、v8、v10后精度均有提升。具体而言,LLC模块有效优化了YOLOv8的内存冗余,且弥补了YOLOv10浅层感受野的不足,尽管LLC模块在v11、v12中效果不佳,但YOLOv5在集成该模块后,实现了检测精度与内存占用的最优平衡。因此,最终选择YOLOv5作为基线模型。
2) LLC模块有效感受野分析。为验证LLC模块对小目标检测的贡献,在严格控制网络主干、头部结构及颈部特征图参数一致的前提下,对比分析LLC与C3、C2f、C3K2及A2C2f模块在小目标检测头处的有效感受野。图6可视化结果显示:LLC模块生成的深色响应区域范围最广且强度最大,这意味着该模块能更高效地整合上下文信息,增强模型对小目标的特征捕获与辨识能力。
为验证LN-YOLO算法各改进环节的有效性,以YOLOv5s作为基线模型A,采用控制变量法逐步引入各项改进措施以评估其对检测性能的贡献。首先,启用Mixup数据增强策略B,然后,利用轻量化LLC模块替换原有的C3模块C,最后,使用NWD损失函数替代传统的IoU损失函数D。各阶段试验结果见表2。结果显示:引入Mixup与LLC后,mAP@0.5较基线提升1.2%;完整集成NWD后,提升幅度达2.0%。LN-YOLO算法的检测速度达56帧/s,满足实时检测需求。尽管参数量与计算量微增,但模型内存仅增加1.3MB,总计15.7MB,符合边缘设备部署的轻量化要求。
为评估LN-YOLO算法对手部特征的关注程度,对YOLOv5与LN-YOLO输出的部分特征图进行热力图可视化分析,如图7所示,LN-YOLO在手部区域显示出更强的激活响应(深色区域),这证明改进算法对微小目标特征提取的有效性。
为验证改进算法LN-YOLO的有效性和优越性,将LN-YOLO算法与目前一些主流检测算法:YOLOv8、v9、v10、v11、v12对绝缘手套的检测效果比较,试验结果见表3。结果显示:LN-YOLO的检测精度仅次于YOLOv9,但YOLOv9巨大的计算开销不符合边缘实时部署要求。而LN-YOLO在精度、效率与部署适应性上取得了最佳平衡。图8的部分检测效果图进一步证实:相较于对比算法,LN-YOLO在小目标及非正常视角下的检测能力更强。
考虑配电网户外作业光照条件不可控,为验证LN-YOLO算法在不同光照下的泛化能力,使用Albumentations增强数据集,模拟暗光与强光照条件,并选取LN-YOLO、YOLOv5、v8、v11、v12进行对比试验,结果见表4,部分检测效果如图9。试验数据与效果图显示:尽管LN-YOLO在暗光与强光环境下精度较正常环境下降,但其性能仍优于其他对比算法,表明LN-YOLO算法具有较强的泛化性与鲁棒性。
1) 绝缘手套佩戴状态检测算法LN-YOLO通过LLC模块,扩展了有效感受野,增强了手部区域特征捕获能力;同时辅以Mixup数据增强策略提升样本上下文连贯性,并引入NWD损失优化小目标度量方式,从网络结构、数据处理及损失计算3个维度提升了检测性能。
2) 消融与对比试验显示:LN-YOLO在精度上达到90.1%,相比基准模型提升2.0%,且优于YOLOv8、v10、v11、v12等主流算法。在暗光与强光极端环境下,该算法仍表现出优异的泛化性能。另外,模型权重仅为15.7MB,推理速度达56帧/s,打破了高精度模型难以在边缘端实时部署的算力壁垒。
3) 尽管本文算法在现有测试集与模拟工况下表现优异,但面对真实配电网作业中的复杂场景,数据覆盖面仍有扩充空间。后续工作将致力于扩充多场景数据集以进一步验证模型泛化能力,并深耕模型轻量化技术,进一步优化边缘侧的计算效率。
  • 国家电网公司科技项目(5400-202355219A-1-1-ZN)
参考文献 引证文献
排序方式:
[1]
王茹, 刘大明, 张健. Wear-YOLO:变电站电力人员安全装备检测方法研究[J]. 计算机工程与应用, 2024, 60(9):111-121.
Wang Ru, Liu Daming, Zhang Jian. Wear-YOLO: research on detection methods of safety equipment for power personnel in substations[J]. Computer Engineering and Applications, 2024, 60(9): 111-121.
[2]
王彦生, 朱佳佳, 王紫仪, . 基于改进YOLOv5的电厂人员绝缘手套佩戴检测[J]. 计算机测量与控制, 2023, 31(11):60-65,73.
Wang Yansheng, Zhu Jiajia, Wang Ziyi, et al. Detection of Insulation gloves worn by power plant personnel base-d on improved YOLOv5[J]. Computer Measurement & Control, 2023, 31(11): 60-65,73.
[3]
马富齐, 王波, 董旭柱, . 面向电力生产精细化风险解译的高度相似防护工具智能检测技术研究[J]. 中国电机工程学报, 2024, 44(3):971-981.
Ma Fuqi, Wang Bo, Dong Xuzhu, et al. Research on intelligent detection technology of highly similar protection tools for refined risk interpretation of power production[J]. Proceedings of the CSEE, 2024, 44(3): 971-981.
[4]
郑海洋, 宋纯贺, 武婷婷, . 面向绝缘手套佩戴状况检测的小目标检测与匹配算法[J]. 小型微型计算机系统, 2023, 44(9):1989-1995.
Zheng Haiyang, Song Chunhe, Wu Tingting, et al. Small target detection and matching algorithm for wearing condition detection of insulating gloves[J]. Journal of Chinese Computer Systems, 2023, 44(9): 1989-1995.
[5]
谢世勇. 基于深度学习的电力着装检测系统的设计与实现[D]. 武汉: 华中科技大学, 2020.
Xie Shiyong. Design and implementation of electric clothing detection system based on deep learning[D]. Wuhan: Huazhong University of Science and Technology, 2020.
[6]
刘琦. 基于深度学习的电网作业防护穿戴合规性智能检测方法研究[D]. 大连: 大连海事大学, 2023.
Liu Qi. Research on intelligent detection of protective wear for power grid operation based on deep learning[D]. Dalian: Dalian Maritime University, 2023.
[7]
Tao Caixia, Wang Chaoting, Li Taiguo. Detection research of insulating gloves wearing status based on improved YOLOv8s algorithm[J]. Journal of Engineering and Applied Science, 2024, 71(1): DOI:10.1186/s44147-024-00458-y.
[8]
柯巍, 朱权洁, 陈长茂, . 基于改进YOLOv11的卷烟仓储人员不安全行为分类及识别[J]. 中国安全科学学报, 2025, 35(3):36-44.
Ke Wei, Zhu Quanjie, Chen Changmao, et al. Classification and recognition of unsafe behaviors of tobacco warehouse personnel based on imprved YOLOv11[J]. China Safety Scienee Journal, 2025, 35 (3):36-44.
[9]
Ma Jianhua, Zhou Yongzhang, Zhou Zimeng, et al. Toward smart ocean monitoring: real-time detection of marine litter using YOLOv12 in support of pollution mitigation[J]. Marine Pollution Bulletin, 2025, 217: DOI: 10.1016/j.marpolbul.2025.118136.
[10]
Liu Rosanne, Lehman J, Molino P, et al. An intriguing failing of convolutional neural networks and the CoordConv solution[C]. Advances in Neural Information Processing Systems 31,2018: 9605-9616.
[11]
Li Hulin, Li Jun, Wei Hanbing, et al. Slim-neck by GSConv: a lightweight-design for real-time detector architectures[J]. Journal of Real-Time Image Processing, 2024, 21(3):DOI:10.1007/s11554-024-01436-6.
2026年第36卷第5期
PDF下载
184
86
引用本文
BibTeX
文章信息
doi: 10.16265/j.cnki.issn1003-3033.2026.05.0318
  • 接收时间:2025-11-14
  • 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:2025-11-14
  • 修回日期:2026-02-03
基金
国家电网公司科技项目(5400-202355219A-1-1-ZN)
作者信息
    1 华北电力大学 能源动力与机械工程学院, 北京 100096
    2 中国电力科学研究院有限公司, 北京 100192
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/zgaqkxxb/CN/10.16265/j.cnki.issn1003-3033.2026.05.0318
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