Article(id=1205533799770751332, tenantId=1146029695717560320, journalId=1189987059142926344, issueId=1205533795375113021, articleNumber=null, orderNo=null, doi=10.19457/j.1001-2095.dqcd25297, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1690905600000, receivedDateStr=2023-08-02, revisedDate=1693152000000, revisedDateStr=2023-08-28, acceptedDate=null, acceptedDateStr=null, onlineDate=1765351255600, onlineDateStr=2025-12-10, pubDate=1734624000000, pubDateStr=2024-12-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1765351255600, onlineIssueDateStr=2025-12-10, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1765351255600, creator=13701087609, updateTime=1765351255600, updator=13701087609, issue=Issue{id=1205533795375113021, tenantId=1146029695717560320, journalId=1189987059142926344, year='2024', volume='54', issue='12', pageStart='3', pageEnd='93', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1765351254552, creator=13701087609, updateTime=1765351619801, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1205535327520817992, tenantId=1146029695717560320, journalId=1189987059142926344, issueId=1205533795375113021, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1205535327520817993, tenantId=1146029695717560320, journalId=1189987059142926344, issueId=1205533795375113021, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=86, endPage=93, ext={EN=ArticleExt(id=1205533800244707686, articleId=1205533799770751332, tenantId=1146029695717560320, journalId=1189987059142926344, language=EN, title=Fault Diagnosis Method for GIS Equipment Based on Deep Graph Convolutional Neural Network, columnId=null, journalTitle=Electric Drive, columnName=null, runingTitle=null, highlight=null, articleAbstract=

Over the years,machine learning has made some breakthroughs in the insulation defects of gas insulated switchgear(GIS),but the traditional methods have the disadvantages of incomplete information,excessive reliance on artificial feature extraction and low diagnosis rate. In order to solve these problems,a diagnosis method based on deep graph convolutional neural network (DGCN)was proposed. Firstly,a partial discharge (PD) experimental platform was built on a 220 kV real GIS and the partial discharge signals collected by ultra high frequency sensor were converted into frequency domain spectrogram samples by Fourier transform. Then,the spectrogram samples were input into the DGCN,which undergoes graph convolution,coarsening and pooling operations to make the spectrogram structure was clearer and enrich the input information. Finally,the test samples were used to test the DGCN with set parameters. The experimental results show that the proposed method can achieve a recognition rate of 98.77% for GIS fault defects,which is significantly higher than other methods and has good robustness.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Zhipeng LIU, Zhe QU, Cong YU, Qian WU, Bo CHEN, Yaqi FANG), CN=ArticleExt(id=1205533803210080692, articleId=1205533799770751332, tenantId=1146029695717560320, journalId=1189987059142926344, language=CN, title=基于深度图卷积神经网络的GIS设备故障诊断方法, columnId=1190325456588079763, journalTitle=电气传动, columnName=可靠性与诊断, runingTitle=null, highlight=null, articleAbstract=

近年来,机器学习在气体绝缘组合电器(GIS)绝缘缺陷上获得了一定的突破,但传统的方法存在利用信息不全、过度依靠人工特征提取和诊断率较低等缺点,为了解决这些问题,提出了一种基于深度图卷积神经网络(DGCN)的诊断方法。首先,在220 kV真型GIS上搭建了局部放电(PD)实验平台,通过特高频传感器采集到的局部放电信号经傅里叶变换转换为频域谱图样本;然后,将谱图样本输入DGCN,经过图卷积、粗化、池化操作,使谱图结构更加清晰来丰富输入信息;最后,利用测试样本对设定好参数的DGCN进行测试,研究结果表明,提出的诊断方法对GIS故障缺陷的识别率可达98.77%,明显高于其他方法,并且具有较好的鲁棒性。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=3InlJK0EQJ2TcfV68yYl1w==, magXml=77lvVMqv2CNUt2XbClzQYQ==, pdfUrl=null, pdf=mDrVFNZygM6AX/B2FzKE0A==, pdfFileSize=2832354, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=Eu3XwqhRCHtf43yFjzMBgw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=QzN8S+pSJ4P0YquO/5/0GA==, mapNumber=null, authorCompany=null, fund=null, authors=

刘志鹏(1987—),男,本科,高级工程师,主要研究方向为变电设备运行监测,Email:

, authorsList=刘志鹏, 瞿哲, 于聪, 吴芊, 陈博, 方雅琪)}, authors=[Author(id=1205544437154832399, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xtx253836692@outlook.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1205544437268078614, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, authorId=1205544437154832399, language=EN, stringName=Zhipeng LIU, firstName=Zhipeng, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 State Grid Hubei Electric Power Co.,Ltd. Extra High Voltage Company,Wuhan 430050,Hubei,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205544437351964701, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, authorId=1205544437154832399, language=CN, stringName=刘志鹏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 国网湖北省电力有限公司超高压公司,湖北 武汉 430050, bio={"content":"

刘志鹏(1987—),男,本科,高级工程师,主要研究方向为变电设备运行监测,Email:

"}, bioImg=null, bioContent=

刘志鹏(1987—),男,本科,高级工程师,主要研究方向为变电设备运行监测,Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205544436919951361, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, xref=1, ext=[AuthorCompanyExt(id=1205544436928339971, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544436919951361, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 State Grid Hubei Electric Power Co.,Ltd. Extra High Voltage Company,Wuhan 430050,Hubei,China), AuthorCompanyExt(id=1205544436936728580, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544436919951361, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国网湖北省电力有限公司超高压公司,湖北 武汉 430050)])]), Author(id=1205544437448433700, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, 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=1205544437523931180, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, authorId=1205544437448433700, language=EN, stringName=Zhe QU, firstName=Zhe, middleName=null, lastName=QU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 State Grid Hubei Electric Power Co.,Ltd. Extra High Voltage Company,Wuhan 430050,Hubei,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205544437603622962, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, authorId=1205544437448433700, language=CN, stringName=瞿哲, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 国网湖北省电力有限公司超高压公司,湖北 武汉 430050, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205544436919951361, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, xref=1, ext=[AuthorCompanyExt(id=1205544436928339971, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544436919951361, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 State Grid Hubei Electric Power Co.,Ltd. Extra High Voltage Company,Wuhan 430050,Hubei,China), AuthorCompanyExt(id=1205544436936728580, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544436919951361, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国网湖北省电力有限公司超高压公司,湖北 武汉 430050)])]), Author(id=1205544437700091961, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, 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=1205544437813338178, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, authorId=1205544437700091961, language=EN, stringName=Cong YU, firstName=Cong, middleName=null, lastName=YU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 State Grid Hubei Electric Power Co.,Ltd. Extra High Voltage Company,Wuhan 430050,Hubei,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205544437926584395, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, authorId=1205544437700091961, language=CN, stringName=于聪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 国网湖北省电力有限公司超高压公司,湖北 武汉 430050, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205544436919951361, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, xref=1, ext=[AuthorCompanyExt(id=1205544436928339971, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544436919951361, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 State Grid Hubei Electric Power Co.,Ltd. Extra High Voltage Company,Wuhan 430050,Hubei,China), AuthorCompanyExt(id=1205544436936728580, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544436919951361, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国网湖北省电力有限公司超高压公司,湖北 武汉 430050)])]), Author(id=1205544438023053393, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, 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=1205544438136299607, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, authorId=1205544438023053393, language=EN, stringName=Qian WU, firstName=Qian, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 State Grid Hubei Electric Power Co.,Ltd. Extra High Voltage Company,Wuhan 430050,Hubei,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205544438262128732, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, authorId=1205544438023053393, language=CN, stringName=吴芊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 国网湖北省电力有限公司超高压公司,湖北 武汉 430050, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205544436919951361, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, xref=1, ext=[AuthorCompanyExt(id=1205544436928339971, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544436919951361, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 State Grid Hubei Electric Power Co.,Ltd. Extra High Voltage Company,Wuhan 430050,Hubei,China), AuthorCompanyExt(id=1205544436936728580, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544436919951361, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国网湖北省电力有限公司超高压公司,湖北 武汉 430050)])]), Author(id=1205544438400540765, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, orderNo=4, 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=1205544438501204068, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, authorId=1205544438400540765, language=EN, stringName=Bo CHEN, firstName=Bo, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 State Grid Hubei Electric Power Co.,Ltd. Extra High Voltage Company,Wuhan 430050,Hubei,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205544438631227494, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, authorId=1205544438400540765, language=CN, stringName=陈博, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 国网湖北省电力有限公司超高压公司,湖北 武汉 430050, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205544436919951361, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, xref=1, ext=[AuthorCompanyExt(id=1205544436928339971, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544436919951361, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 State Grid Hubei Electric Power Co.,Ltd. Extra High Voltage Company,Wuhan 430050,Hubei,China), AuthorCompanyExt(id=1205544436936728580, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544436919951361, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国网湖北省电力有限公司超高压公司,湖北 武汉 430050)])]), Author(id=1205544438773833834, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, orderNo=5, 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=1205544438870302830, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, authorId=1205544438773833834, language=EN, stringName=Yaqi FANG, firstName=Yaqi, middleName=null, lastName=FANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 Hubei Engineering Research Center for Safety Monitoring of New Energy and Power Grid Equipment,Hubei University of Technology,Wuhan 430068,Hubei,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205544439025492083, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, authorId=1205544438773833834, language=CN, stringName=方雅琪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 湖北工业大学 新能源及电网装备安全监测湖北省工程研究中心,湖北 武汉 430068, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205544437033197577, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, xref=2, ext=[AuthorCompanyExt(id=1205544437041586185, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544437033197577, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Hubei Engineering Research Center for Safety Monitoring of New Energy and Power Grid Equipment,Hubei University of Technology,Wuhan 430068,Hubei,China), AuthorCompanyExt(id=1205544437049974794, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544437033197577, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 湖北工业大学 新能源及电网装备安全监测湖北省工程研究中心,湖北 武汉 430068)])])], keywords=[Keyword(id=1205544439226818684, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, orderNo=1, keyword=gas insulated switchgear (GIS)), Keyword(id=1205544439331676288, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, orderNo=2, keyword=partial discharge (PD)), Keyword(id=1205544439419756676, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, orderNo=3, keyword=fault diagnosis), Keyword(id=1205544439499448455, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, orderNo=4, keyword=insulation defect), Keyword(id=1205544439604306059, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, orderNo=5, keyword=deep graph convolutional neural network (DGCN)), Keyword(id=1205544439700775057, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, orderNo=6, keyword=simple linear clustering method), Keyword(id=1205544439793049751, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, orderNo=1, keyword=气体绝缘组合电器), Keyword(id=1205544439902101657, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, orderNo=2, keyword=局部放电), Keyword(id=1205544440032125082, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, orderNo=3, keyword=故障诊断), Keyword(id=1205544440166342814, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, orderNo=4, keyword=绝缘缺陷), Keyword(id=1205544440250228899, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, orderNo=5, keyword=深度图卷积神经网络), Keyword(id=1205544440317337765, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, orderNo=6, keyword=简单线性聚类法)], refs=[Reference(id=1205544443303682313, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=83, pageEnd=85, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=LI Shengchun, journalName=Beihai,China, refType=null, unstructuredReference=LI Shengchun. Location and analysis of abnormal partial discharge of 750 kV GIS equipment[C]//2021 13th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA), Beihai,China, 2021,83-85., articleTitle=Location and analysis of abnormal partial discharge of 750 kV GIS equipment[C]//2021 13th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA), refAbstract=null), Reference(id=1205544443391762701, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2021, volume=36, issue=2, pageStart=1237, pageEnd=1240, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=REN M, ZHOU J, MIAO J, journalName=IEEE Transactions on Power Delivery, refType=null, unstructuredReference=REN M, ZHOU J, MIAO J. Adopting spectral analysis in partial discharge fault diagnosis of GIS with a micro built-in optical sensor[J]. IEEE Transactions on Power Delivery, 2021, 36(2):1237-1240., articleTitle=Adopting spectral analysis in partial discharge fault diagnosis of GIS with a micro built-in optical sensor, refAbstract=null), Reference(id=1205544443467260176, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2014, volume=40, issue=2, pageStart=465, pageEnd=473, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=唐炬, 曾福平, 范庆涛, journalName=高电压技术, refType=null, unstructuredReference=唐炬, 曾福平, 范庆涛, 等. 基于荧光光纤检测GIS局部放电的多重分形谱识别[J]. 高电压技术, 2014, 40(2):465-473., articleTitle=基于荧光光纤检测GIS局部放电的多重分形谱识别, refAbstract=null), Reference(id=1205544443563729170, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2014, volume=40, issue=2, pageStart=465, pageEnd=473, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=TANG Ju, ZENG Fuping, FAN Qingtao, journalName=High Voltage Engineering, refType=null, unstructuredReference=TANG Ju, ZENG Fuping, FAN Qingtao, et al. Multifractal spectrum identification of partial discharge in GIS based on fluorescence optical fiber detection[J]. High Voltage Engineering, 2014, 40(2):465-473., articleTitle=Multifractal spectrum identification of partial discharge in GIS based on fluorescence optical fiber detection, refAbstract=null), Reference(id=1205544443672781077, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2018, volume=11, issue=5, pageStart=1202, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=NGUYEN M T, NGUYEN V H, YUN S J, journalName=Energies, refType=null, unstructuredReference=NGUYEN M T, NGUYEN V H, YUN S J, et al. Recurrent neural network for partial discharge diagnosis in gas-insulated switchgear[J]. Energies, 2018, 11(5):1202., articleTitle=Recurrent neural network for partial discharge diagnosis in gas-insulated switchgear, refAbstract=null), Reference(id=1205544443765055768, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2016, volume=31, issue=20, pageStart=41, pageEnd=54, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=唐炬, 杨东, 曾福平, journalName=电工技术学报, refType=null, unstructuredReference=唐炬, 杨东, 曾福平, 等. 基于分解组分分析的SF6设备绝缘故障诊断方法与技术的研究现状[J]. 电工技术学报, 2016, 31(20):41-54., articleTitle=基于分解组分分析的SF6设备绝缘故障诊断方法与技术的研究现状, refAbstract=null), Reference(id=1205544443853136157, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2016, volume=31, issue=20, pageStart=41, pageEnd=54, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=TANG Ju, YANG Dong, ZENG Fuping, journalName=Transactions of China Electrotechnical Society, refType=null, unstructuredReference=TANG Ju, YANG Dong, ZENG Fuping, et al. Research status of SF6 insulation equipment fault diagnosis method and technology based on decomposed components analysis[J]. Transactions of China Electrotechnical Society, 2016, 31(20):41-54., articleTitle=Research status of SF6 insulation equipment fault diagnosis method and technology based on decomposed components analysis, refAbstract=null), Reference(id=1205544443932827936, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=张波, journalName=基于超声波法的GIS局部放电模式识别的研究, refType=null, unstructuredReference=张波. 基于超声波法的GIS局部放电模式识别的研究[D]. 北京: 华北电力大学, 2015., articleTitle=null, refAbstract=null), Reference(id=1205544444020908324, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=ZHANG Bo, journalName=Research on partial discharge pattern recogoniton of GIS based on ultrasonic detection, refType=null, unstructuredReference=ZHANG Bo. Research on partial discharge pattern recogoniton of GIS based on ultrasonic detection[D]. Beijing: North China Electric Power University, 2015., articleTitle=null, refAbstract=null), Reference(id=1205544444113183013, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2006, volume=null, issue=null, pageStart=191, pageEnd=194, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=CHATPATTANANAN V, PATTANADECH N, YUTTHAGOWITH P, journalName=2006 IEEE 8th International Conferen-ce on Properties & Applications of Dielectric Materials, refType=null, unstructuredReference=CHATPATTANANAN V, PATTANADECH N, YUTTHAGOWITH P. Partial discharge classification on high voltage equipment with K-means[C]// 2006 IEEE 8th International Conferen-ce on Properties & Applications of Dielectric Materials, 2006:191-194., articleTitle=Partial discharge classification on high voltage equipment with K-means, refAbstract=null), Reference(id=1205544444197069096, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2020, volume=27, issue=6, pageStart=2147, pageEnd=2155, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=CHANG C K, BOYANAPALLI B K, WU R N, journalName=IEEE Transactions on Dielectrics and Electrical Insulation, refType=null, unstructuredReference=CHANG C K, BOYANAPALLI B K, WU R N. Application of fuzzy entropy to improve feature selection for defect recognition using support vector machine in high voltage cable joints[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2020, 27(6):2147-2155., articleTitle=Application of fuzzy entropy to improve feature selection for defect recognition using support vector machine in high voltage cable joints, refAbstract=null), Reference(id=1205544444276760875, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2022, volume=37, issue=9, pageStart=2150, pageEnd=2160, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=王艳新, 闫静, 王建华, journalName=电工技术学报, refType=null, unstructuredReference=王艳新, 闫静, 王建华, 等. 基于域对抗迁移卷积神经网络的小样本GIS绝缘缺陷智能诊断方法[J]. 电工技术学报, 2022, 37(9):2150-2160., articleTitle=基于域对抗迁移卷积神经网络的小样本GIS绝缘缺陷智能诊断方法, refAbstract=null), Reference(id=1205544444356452654, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2022, volume=37, issue=9, pageStart=2150, pageEnd=2160, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=WANG Yanxin, YAN Jing, WANG Jianhua, journalName=Transactions of China Electrotechnical Society, refType=null, unstructuredReference=WANG Yanxin, YAN Jing, WANG Jianhua, et al. Intelligent diagnosis for GIS with small samples using a novel adversarial transfer learning in convolutional neural network[J]. Transactions of China Electrotechnical Society, 2022, 37(9):2150-2160., articleTitle=Intelligent diagnosis for GIS with small samples using a novel adversarial transfer learning in convolutional neural network, refAbstract=null), Reference(id=1205544444436144435, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2020, volume=20, issue=15, pageStart=8413, pageEnd=8422, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=LI J, HUANG R, HE G, journalName=IEEE Sensors Journal, refType=null, unstructuredReference=LI J, HUANG R, HE G, et al. A deep adversarial transfer learning network for machinery emerging fault detection[J]. IEEE Sensors Journal, 2020, 20(15):8413-8422., articleTitle=A deep adversarial transfer learning network for machinery emerging fault detection, refAbstract=null), Reference(id=1205544444528419126, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2021, volume=36, issue=4, pageStart=157, pageEnd=164, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=袁文海, 刘彪, 徐浩, journalName=电力科学与技术学报, refType=null, unstructuredReference=袁文海, 刘彪, 徐浩, 等. 基于复合神经网络的GIS局放故障类型识别[J]. 电力科学与技术学报, 2021, 36(4):157-164., articleTitle=基于复合神经网络的GIS局放故障类型识别, refAbstract=null), Reference(id=1205544444637471035, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2021, volume=36, issue=4, pageStart=157, pageEnd=164, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=YUAN Wenhai, LIU Biao, XU Hao, journalName=Journal of Electric Power Science and Technology, refType=null, unstructuredReference=YUAN Wenhai, LIU Biao, XU Hao, et al. Partial discharge fault type identification of GIS based on composite neural network[J]. Journal of Electric Power Science and Technology, 2021, 36(4):157-164., articleTitle=Partial discharge fault type identification of GIS based on composite neural network, refAbstract=null), Reference(id=1205544444763300155, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2020, volume=14, issue=8, pageStart=864, pageEnd=871, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=WANG Y, YAN J, YANG Z, journalName=IET Science,Measurement & Technology, refType=null, unstructuredReference=WANG Y, YAN J, YANG Z, et al. GIS partial discharge pattern recognition via lightweight convolutional neural network in the ubiquitous power internet of things context[J]. IET Science,Measurement & Technology, 2020, 14(8):864-871., articleTitle=GIS partial discharge pattern recognition via lightweight convolutional neural network in the ubiquitous power internet of things context, refAbstract=null), Reference(id=1205544444893323583, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=6, pageStart=2433, pageEnd=2442, url=null, language=null, rfNumber=[13], rfOrder=17, authorNames=高盎然, 朱永利, 张翼, journalName=电网技术, refType=null, unstructuredReference=高盎然, 朱永利, 张翼, 等. 基于边际谱图像和深度残差网络的变压器局部放电模式识别[J]. 电网技术, 2021, 45(6):2433-2442., articleTitle=基于边际谱图像和深度残差网络的变压器局部放电模式识别, refAbstract=null), Reference(id=1205544444993986881, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=6, pageStart=2433, pageEnd=2442, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=GAO Angran, ZHU Yongli, ZHANG Yi, journalName=Power System Technology, refType=null, unstructuredReference=GAO Angran, ZHU Yongli, ZHANG Yi, et al. Partial discharge pattern recognition of power transformers based on marginal spectrum images and deep residual net-work[J]. Power System Technology, 2021, 45(6):2433-2442., articleTitle=Partial discharge pattern recognition of power transformers based on marginal spectrum images and deep residual net-work, refAbstract=null), Reference(id=1205544445119816005, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2008, volume=20, issue=1, pageStart=61, pageEnd=80, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=SCARSELLI F, GORI M, TSOI A C, journalName=IEEE Transactions on Neural Networks, refType=null, unstructuredReference=SCARSELLI F, GORI M, TSOI A C, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks, 2008, 20(1):61-80., articleTitle=The graph neural network model, refAbstract=null), Reference(id=1205544445224673607, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2018, volume=106, issue=5, pageStart=808, pageEnd=828, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=ORTEGA A, FROSSARD P, KOVACEVIC J, journalName=Proceedings of the IEEE, refType=null, unstructuredReference=ORTEGA A, FROSSARD P, KOVACEVIC J. Graph signal processing:overview,challenges,and applications[J]. Proceedings of the IEEE, 2018, 106 (5):808-828., articleTitle=Graph signal processing:overview,challenges,and applications, refAbstract=null), Reference(id=1205544445329531211, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2013, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=21, authorNames=BRUNA J, ZAREMBA W, SZLAM A, journalName=International Conference on Learning Representations, refType=null, unstructuredReference=BRUNA J, ZAREMBA W, SZLAM A, et al. Spectral networks and locally connected networks on graphs[C]// International Conference on Learning Representations, 2013., articleTitle=Spectral networks and locally connected networks on graphs, refAbstract=null), Reference(id=1205544445409222990, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2017, volume=11, issue=6, pageStart=884, pageEnd=896, url=null, language=null, rfNumber=[17], rfOrder=22, authorNames=SUCH F P, SAH S, DOMINGUEZ M A, journalName=IEEE Journal Selected Topics Signal Processing, refType=null, unstructuredReference=SUCH F P, SAH S, DOMINGUEZ M A, et al. Robust spatial filtering with graph convolutional neural networks[J]. IEEE Journal Selected Topics Signal Processing, 2017, 11 (6):884-896., articleTitle=Robust spatial filtering with graph convolutional neural networks, refAbstract=null), Reference(id=1205544445480526160, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2013, volume=30, issue=3, pageStart=83, pageEnd=98, url=null, language=null, rfNumber=[18], rfOrder=23, authorNames=SHUMAN D I, NARANG S K, FROSSARD P, journalName=IEEE Signal Processing Magazine, refType=null, unstructuredReference=SHUMAN D I, NARANG S K, FROSSARD P, et al. The emer-ging field of signal processing on graphs:extending high-dimensional data analysis to networks and other irregular domains[J]. IEEE Signal Processing Magazine, 2013, 30(3):83-98., articleTitle=The emer-ging field of signal processing on graphs:extending high-dimensional data analysis to networks and other irregular domains, refAbstract=null), Reference(id=1205544445560217938, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=24, pageStart=241, pageEnd=248, url=null, language=null, rfNumber=[19], rfOrder=24, authorNames=陈起磊, 蒋亦悦, 唐瑶, journalName=振动与冲击, refType=null, unstructuredReference=陈起磊, 蒋亦悦, 唐瑶, 等. 基于时域图与改进图卷积神经网络的异步电机故障诊断方法[J]. 振动与冲击, 2022, 41(24):241-248., articleTitle=基于时域图与改进图卷积神经网络的异步电机故障诊断方法, refAbstract=null), Reference(id=1205544445623132500, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=24, pageStart=241, pageEnd=248, url=null, language=null, rfNumber=[19], rfOrder=25, authorNames=CHEN Qilei, JIANG Yiyue, TANG Yao, journalName=Journal of Vibration and Shock, refType=null, unstructuredReference=CHEN Qilei, JIANG Yiyue, TANG Yao, et al. An induction motor fault diagnosis method based on the time-frequency image method and improved graph convolution netword[J]. Journal of Vibration and Shock, 2022, 41(24):241-248., articleTitle=An induction motor fault diagnosis method based on the time-frequency image method and improved graph convolution netword, refAbstract=null), Reference(id=1205544445702824278, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=12, pageStart=2517, pageEnd=2530, url=null, language=null, rfNumber=[20], rfOrder=26, authorNames=刘鹏, 李真芳, 楼良盛, journalName=测绘学报, refType=null, unstructuredReference=刘鹏, 李真芳, 楼良盛, 等. 基于超像素分割与多信息融合的叠掩和阴影区域检测法[J]. 测绘学报, 2022, 51(12):2517-2530., articleTitle=基于超像素分割与多信息融合的叠掩和阴影区域检测法, refAbstract=null), Reference(id=1205544445778321752, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=12, pageStart=2517, pageEnd=2530, url=null, language=null, rfNumber=[20], rfOrder=27, authorNames=LIU Peng, LI Zhenfang, LOU Liangsheng, journalName=Acta Geodaetica et Cartographi-ca Sinica, refType=null, unstructuredReference=LIU Peng, LI Zhenfang, LOU Liangsheng, et al. Layover and shadow regions detection based on superpixel segmentation and multi-information fusion[J]. Acta Geodaetica et Cartographi-ca Sinica, 2022, 51(12):2517-2530., articleTitle=Layover and shadow regions detection based on superpixel segmentation and multi-information fusion, refAbstract=null), Reference(id=1205544445853819226, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=28, authorNames=DEFFERRARD M, BRESSON X, VANDERGHEYNST P, journalName=Proceedings of the 30th International Conferen-ce on Neural Information Processing Systems, refType=null, unstructuredReference=DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering[C]// Proceedings of the 30th International Conferen-ce on Neural Information Processing Systems, 2016., articleTitle=Convolutional neural networks on graphs with fast localized spectral filtering, refAbstract=null), Reference(id=1205544445925122396, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=156, pageStart=107585, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=29, authorNames=ZHANG Dingcheng, STEWART Edward, ENTEZAMI Mani, journalName=Measurement, refType=null, unstructuredReference=ZHANG Dingcheng, STEWART Edward, ENTEZAMI Mani, et al. Intelligent acoustic-based fault diagnosis of roller bearings using a deep graph convolutional network[J]. Measurement, 2020(156):107585., articleTitle=Intelligent acoustic-based fault diagnosis of roller bearings using a deep graph convolutional network, refAbstract=null)], funds=[Fund(id=1205544442955555069, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, awardId=SGNR0000KJJS2200301, language=CN, fundingSource=智能电网保护和运行控制国家重点实验室开放基金(SGNR0000KJJS2200301), fundOrder=null, country=null), Fund(id=1205544443068801283, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, awardId=521520220003, language=CN, fundingSource=国网湖北省电力有限公司科技项目(521520220003), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1205544436919951361, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, xref=1, ext=[AuthorCompanyExt(id=1205544436928339971, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544436919951361, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 State Grid Hubei Electric Power Co.,Ltd. Extra High Voltage Company,Wuhan 430050,Hubei,China), AuthorCompanyExt(id=1205544436936728580, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544436919951361, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国网湖北省电力有限公司超高压公司,湖北 武汉 430050)]), AuthorCompany(id=1205544437033197577, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, xref=2, ext=[AuthorCompanyExt(id=1205544437041586185, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544437033197577, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 Hubei Engineering Research Center for Safety Monitoring of New Energy and Power Grid Equipment,Hubei University of Technology,Wuhan 430068,Hubei,China), AuthorCompanyExt(id=1205544437049974794, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, companyId=1205544437033197577, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 湖北工业大学 新能源及电网装备安全监测湖北省工程研究中心,湖北 武汉 430068)])], figs=[ArticleFig(id=1205544440489304235, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, label=Fig.1, caption=Overall structure of graph convolutional neural network, figureFileSmall=kbg+i+hRQ2BqBwLCbVxQsw==, figureFileBig=mChLvOpCkzEqTpkjrfeJQg==, tableContent=null), ArticleFig(id=1205544440552218799, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, label=图1, caption=图卷积神经网络结构, figureFileSmall=kbg+i+hRQ2BqBwLCbVxQsw==, figureFileBig=mChLvOpCkzEqTpkjrfeJQg==, tableContent=null), ArticleFig(id=1205544440648687794, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, label=Fig.2, caption=Undirected connection graph of five contacts and its adjacency matrix, figureFileSmall=h60WJ5m0fGJ9YPdB3fKVAg==, figureFileBig=GxpDGS6F6b3Y1psUYMQsFQ==, tableContent=null), ArticleFig(id=1205544440774516919, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, label=图2, caption=5个接点的无向连接图和其邻接矩阵, figureFileSmall=h60WJ5m0fGJ9YPdB3fKVAg==, figureFileBig=GxpDGS6F6b3Y1psUYMQsFQ==, tableContent=null), ArticleFig(id=1205544440858403001, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, label=Fig.3, caption=The coarsening and pooling process of graphs, figureFileSmall=KqiWGSY3PnoWW/wKME0tDg==, figureFileBig=OuTPYMsx5OuTufiTb58Abw==, tableContent=null), ArticleFig(id=1205544440988426427, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, label=图3, caption=图的粗化和池化过程, figureFileSmall=KqiWGSY3PnoWW/wKME0tDg==, figureFileBig=OuTPYMsx5OuTufiTb58Abw==, tableContent=null), ArticleFig(id=1205544441080701119, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, label=Fig.4, caption=PD information joint acquisition platform wiring diagram, figureFileSmall=rdmgqv/0t35huUZoJf0MnQ==, figureFileBig=aOz4qYduZhK1IF764ScrRA==, tableContent=null), ArticleFig(id=1205544441164587203, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, label=图4, caption=PD信息联合采集平台接线示意图, figureFileSmall=rdmgqv/0t35huUZoJf0MnQ==, figureFileBig=aOz4qYduZhK1IF764ScrRA==, tableContent=null), ArticleFig(id=1205544441273639111, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, label=Fig.5, caption=Four typical defect schematics, figureFileSmall=LNPO6qMbWituh7a+XG0mJw==, figureFileBig=mm6HgPa+E9OOF1BgAsou5A==, tableContent=null), ArticleFig(id=1205544441378496714, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, label=图5, caption=4种典型缺陷示意图, figureFileSmall=LNPO6qMbWituh7a+XG0mJw==, figureFileBig=mm6HgPa+E9OOF1BgAsou5A==, tableContent=null), ArticleFig(id=1205544441445605581, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, label=Fig.6, caption=UHF PD signal spectra of four typical defects, figureFileSmall=OZU2u7mqhD0iBZcsYuWy+w==, figureFileBig=tZw9wk5eE/jw9xOLJYndXw==, tableContent=null), ArticleFig(id=1205544441563046098, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, label=图6, caption=4种典型缺陷的UHF PD信号图谱, figureFileSmall=OZU2u7mqhD0iBZcsYuWy+w==, figureFileBig=tZw9wk5eE/jw9xOLJYndXw==, tableContent=null), ArticleFig(id=1205544441651126486, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, label=Fig.7, caption=DGCN fault diagnosis process, figureFileSmall=Xo7+0POglhhEuoPVS/YEpA==, figureFileBig=9gB9L6PzNx4Hvz+xYRJj8g==, tableContent=null), ArticleFig(id=1205544441747595481, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, label=图7, caption=DGCN故障诊断流程, figureFileSmall=Xo7+0POglhhEuoPVS/YEpA==, figureFileBig=9gB9L6PzNx4Hvz+xYRJj8g==, tableContent=null), ArticleFig(id=1205544441869230301, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, label=Fig.8, caption=Recognition rate changes with kernel length, figureFileSmall=h8qr18KalK/Oc9fOPHxWqQ==, figureFileBig=FhekSHDV4aioBIdtKjpUzw==, tableContent=null), ArticleFig(id=1205544441965699297, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, label=图8, caption=识别率随核长度变化图, figureFileSmall=h8qr18KalK/Oc9fOPHxWqQ==, figureFileBig=FhekSHDV4aioBIdtKjpUzw==, tableContent=null), ArticleFig(id=1205544442091528417, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, label=Fig.9, caption=The recognition rate of DGCN under different parameters, figureFileSmall=8LaG1bSaQUpjaGpNpxUXmg==, figureFileBig=dGkmAlSK02Tc87RT+XToJA==, tableContent=null), ArticleFig(id=1205544442179608805, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, label=图9, caption=不同参数下DGCN的识别率, figureFileSmall=8LaG1bSaQUpjaGpNpxUXmg==, figureFileBig=dGkmAlSK02Tc87RT+XToJA==, tableContent=null), ArticleFig(id=1205544442267689192, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, label=Fig.10, caption=Comparison of recognition rates of three methods under different voltage levels, figureFileSmall=rFRWmV99wIYfpzncK0RBHQ==, figureFileBig=8DXQJzFkZEAVB3ZyJlz86w==, tableContent=null), ArticleFig(id=1205544442355769578, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, label=图10, caption=不同电压等级下3种方法的识别率对比, figureFileSmall=rFRWmV99wIYfpzncK0RBHQ==, figureFileBig=8DXQJzFkZEAVB3ZyJlz86w==, tableContent=null), ArticleFig(id=1205544442452238574, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, label=Tab.1, caption=

PD test step voltage

, figureFileSmall=null, figureFileBig=null, tableContent=
缺陷 外施电压等级/kV
绝缘子表面金属污秽 14.8→17.1→18.9→21.0→23.9
绝缘子气隙缺陷 9.6→11.4→13.5→15.7→17.9
悬浮电极缺陷 16.7→19.8→21.8→23.7→25.9
金属突出物缺陷 9.1→11.3→13.6→14.9→17.5
), ArticleFig(id=1205544442565484786, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, label=表1, caption=

PD试验阶梯电压

, figureFileSmall=null, figureFileBig=null, tableContent=
缺陷 外施电压等级/kV
绝缘子表面金属污秽 14.8→17.1→18.9→21.0→23.9
绝缘子气隙缺陷 9.6→11.4→13.5→15.7→17.9
悬浮电极缺陷 16.7→19.8→21.8→23.7→25.9
金属突出物缺陷 9.1→11.3→13.6→14.9→17.5
), ArticleFig(id=1205544442678730995, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=EN, label=Tab.2, caption=

Identification rate of GIS insulation defects under different methods

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 识别率/%
绝缘子表面金属污秽 绝缘子气隙 悬浮电极 金属
突出物
总体
DGCN 98.6 97.9 98.8 99.8 98.77
LSTM 90.2 87.62 91.8 89.6 89.81
SAE 88.9 85.6 84.8 86.2 86.38
CNN 85.9 87.5 87.8 89.5 87.68
GCN 91.6 92.3 91.8 90.9 91.65
SVM 81.5 80.6 81.2 79.8 80.78
), ArticleFig(id=1205544442745839863, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1205533799770751332, language=CN, label=表2, caption=

不同方法下GIS绝缘缺陷的识别率

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 识别率/%
绝缘子表面金属污秽 绝缘子气隙 悬浮电极 金属
突出物
总体
DGCN 98.6 97.9 98.8 99.8 98.77
LSTM 90.2 87.62 91.8 89.6 89.81
SAE 88.9 85.6 84.8 86.2 86.38
CNN 85.9 87.5 87.8 89.5 87.68
GCN 91.6 92.3 91.8 90.9 91.65
SVM 81.5 80.6 81.2 79.8 80.78
)], attaches=null, journal=Journal(id=1149695973913305096, delFlag=0, nameCn=电气传动, nameEn=Electric Drive, nameHistory1=null, nameHistory2=null, issn=1001-2095, eissn=null, cn=12-1067/TP, coden=null, periodic=0, language=CN, oaType=null, 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=MX9kQyxauhRIcWSHz1lsfg==, journalPrice=null, startedYear=null, abbrevIsoEn=null, journalRemark=null, publicationField=null, createdTime=1752038480501, updatedTime=1761735785885, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=E, firstLetterEn=E, subjectCode=Engineering, subjectName=Engineering, subjectCodeEn=Engineering, subjectNameEn=null, picCn=MX9kQyxauhRIcWSHz1lsfg==, picEn=R8RQJTk995s1dk9HSLANAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1190369420775096487, language=CN, name=电气传动, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1761735785907, updatedTime=1761735785907, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://tg.au365.cn/Login/index.html, submissionEditorUrl=https://tg.au365.cn/Login/index/cate/3.html, submissionReviewUrl=https://tg.au365.cn/Login/index/cate/2.html, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1190369420829622440, language=EN, name=Electric Drive, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1761735785920, updatedTime=1761735785920, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://tg.au365.cn/Login/index.html, submissionEditorUrl=https://tg.au365.cn/Login/index/cate/3.html, submissionReviewUrl=https://tg.au365.cn/Login/index/cate/2.html, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1189987059142926344, websiteList=[Website(id=1189988338468713189, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189987059142926344, 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/dqcd/CN, language=CN, createTime=1761644928805, createBy=18614031015, updateTime=1761644944247, updateBy=18614031015, name=电气传动-中文, tplId=1146099689490845704, title=电气传动, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1190236467705254391, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=articleTextType, value=kx, createTime=1761704087425, updateTime=1761704087425, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467671699956, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=banner, value=null, createTime=1761704087417, updateTime=1761704087417, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467763974650, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=grayFlag, value=0, createTime=1761704087439, updateTime=1761704087439, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467663311347, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=logo, value=https://castjournals.cast.org.cn/joweb/dqcd/CN/file/pic?fileId=C+51VGe7It8gHMdS0MAlXg==, createTime=1761704087415, updateTime=1761704087415, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467784946172, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=minRunFlag, value=0, createTime=1761704087444, updateTime=1761704087444, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467692671478, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/dqcd/CN/file/pic, createTime=1761704087422, updateTime=1761704087422, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467776557563, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=silenceFlag, value=0, createTime=1761704087442, updateTime=1761704087442, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467680088565, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1761704087419, updateTime=1761704087419, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467713643000, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=themeColor, value=null, createTime=1761704087427, updateTime=1761704087427, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236467726225913, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338468713189, code=themeStyle, value=null, createTime=1761704087430, updateTime=1761704087430, creator=18614031015, updator=18614031015)]), Website(id=1189988338527433447, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1189987059142926344, 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/dqcd/EN, language=EN, createTime=1761644928819, createBy=18614031015, updateTime=1761644963810, updateBy=18614031015, name=电气传动-英文, tplId=1146101810881728533, title=Electric Drive, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1190236496637563393, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=articleTextType, value=kx, createTime=1761704094323, updateTime=1761704094323, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496612397566, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=banner, value=null, createTime=1761704094317, updateTime=1761704094317, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496666923524, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=grayFlag, value=0, createTime=1761704094330, updateTime=1761704094330, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496604008957, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=logo, value=https://castjournals.cast.org.cn/joweb/dqcd/EN/file/pic?fileId=C+51VGe7It8gHMdS0MAlXg==, createTime=1761704094315, updateTime=1761704094315, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496683700742, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=minRunFlag, value=0, createTime=1761704094334, updateTime=1761704094334, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496629174784, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/dqcd/EN/file/pic, createTime=1761704094321, updateTime=1761704094321, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496675312133, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=silenceFlag, value=0, createTime=1761704094332, updateTime=1761704094332, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496620786175, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1761704094319, updateTime=1761704094319, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496650146306, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=themeColor, value=null, createTime=1761704094326, updateTime=1761704094326, creator=18614031015, updator=18614031015), WebsiteProps(id=1190236496658534915, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1189988338527433447, code=themeStyle, value=null, createTime=1761704094328, updateTime=1761704094328, creator=18614031015, updator=18614031015)])], journalTitle=电气传动, weixinUrl=null, journalUrl=https://www.au365.cn/, iacademicId=null, status=1, seqNo=null, journalTitleEn=Electric Drive, journalPhotoCn=MX9kQyxauhRIcWSHz1lsfg==, journalPhotoEn=R8RQJTk995s1dk9HSLANAQ==, journalFirstLetter=E, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/dqcd/CN/10.19457/j.1001-2095.dqcd25297, detailUrlEn=https://castjournals.cast.org.cn/joweb/dqcd/EN/10.19457/j.1001-2095.dqcd25297, pdfUrlCn=https://castjournals.cast.org.cn/joweb/dqcd/CN/PDF/10.19457/j.1001-2095.dqcd25297, pdfUrlEn=https://castjournals.cast.org.cn/joweb/dqcd/EN/PDF/10.19457/j.1001-2095.dqcd25297, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于深度图卷积神经网络的GIS设备故障诊断方法
收藏切换
PDF下载
刘志鹏 1 , 瞿哲 1 , 于聪 1 , 吴芊 1 , 陈博 1 , 方雅琪 2
电气传动 | 可靠性与诊断 2024,54(12): 86-93
收起
收藏切换
电气传动 | 可靠性与诊断 2024, 54(12): 86-93
基于深度图卷积神经网络的GIS设备故障诊断方法
全屏
刘志鹏1 , 瞿哲1, 于聪1, 吴芊1, 陈博1, 方雅琪2
作者信息
  • 1 国网湖北省电力有限公司超高压公司,湖北 武汉 430050
  • 2 湖北工业大学 新能源及电网装备安全监测湖北省工程研究中心,湖北 武汉 430068
  • 刘志鹏(1987—),男,本科,高级工程师,主要研究方向为变电设备运行监测,Email:

Fault Diagnosis Method for GIS Equipment Based on Deep Graph Convolutional Neural Network
Zhipeng LIU1 , Zhe QU1, Cong YU1, Qian WU1, Bo CHEN1, Yaqi FANG2
Affiliations
  • 1 State Grid Hubei Electric Power Co.,Ltd. Extra High Voltage Company,Wuhan 430050,Hubei,China
  • 2 Hubei Engineering Research Center for Safety Monitoring of New Energy and Power Grid Equipment,Hubei University of Technology,Wuhan 430068,Hubei,China
出版时间: 2024-12-20 doi: 10.19457/j.1001-2095.dqcd25297
文章导航
收藏切换

近年来,机器学习在气体绝缘组合电器(GIS)绝缘缺陷上获得了一定的突破,但传统的方法存在利用信息不全、过度依靠人工特征提取和诊断率较低等缺点,为了解决这些问题,提出了一种基于深度图卷积神经网络(DGCN)的诊断方法。首先,在220 kV真型GIS上搭建了局部放电(PD)实验平台,通过特高频传感器采集到的局部放电信号经傅里叶变换转换为频域谱图样本;然后,将谱图样本输入DGCN,经过图卷积、粗化、池化操作,使谱图结构更加清晰来丰富输入信息;最后,利用测试样本对设定好参数的DGCN进行测试,研究结果表明,提出的诊断方法对GIS故障缺陷的识别率可达98.77%,明显高于其他方法,并且具有较好的鲁棒性。

气体绝缘组合电器  /  局部放电  /  故障诊断  /  绝缘缺陷  /  深度图卷积神经网络  /  简单线性聚类法

Over the years,machine learning has made some breakthroughs in the insulation defects of gas insulated switchgear(GIS),but the traditional methods have the disadvantages of incomplete information,excessive reliance on artificial feature extraction and low diagnosis rate. In order to solve these problems,a diagnosis method based on deep graph convolutional neural network (DGCN)was proposed. Firstly,a partial discharge (PD) experimental platform was built on a 220 kV real GIS and the partial discharge signals collected by ultra high frequency sensor were converted into frequency domain spectrogram samples by Fourier transform. Then,the spectrogram samples were input into the DGCN,which undergoes graph convolution,coarsening and pooling operations to make the spectrogram structure was clearer and enrich the input information. Finally,the test samples were used to test the DGCN with set parameters. The experimental results show that the proposed method can achieve a recognition rate of 98.77% for GIS fault defects,which is significantly higher than other methods and has good robustness.

gas insulated switchgear (GIS)  /  partial discharge (PD)  /  fault diagnosis  /  insulation defect  /  deep graph convolutional neural network (DGCN)  /  simple linear clustering method
刘志鹏, 瞿哲, 于聪, 吴芊, 陈博, 方雅琪. 基于深度图卷积神经网络的GIS设备故障诊断方法. 电气传动, 2024 , 54 (12) : 86 -93 . DOI: 10.19457/j.1001-2095.dqcd25297
Zhipeng LIU, Zhe QU, Cong YU, Qian WU, Bo CHEN, Yaqi FANG. Fault Diagnosis Method for GIS Equipment Based on Deep Graph Convolutional Neural Network[J]. Electric Drive, 2024 , 54 (12) : 86 -93 . DOI: 10.19457/j.1001-2095.dqcd25297
气体绝缘组合电器(gas insulated switchgear,GIS)以其结构紧凑、可靠性高和维护率低等特点被广泛用于中、特高压变电站的主要控制和保护设备,在电力传输系统中起着至关重要的作用[1-2]。然而绝缘系统中产生的不可避免的缺陷和绝缘材料劣化会对GIS设备运行可靠性产生威胁。局部放电(partial discharge,PD)作为GIS绝缘缺陷的一种征兆,能反映GIS绝缘状态[3],因此,通过对PD的检测有利于监测GIS的绝缘状况,能为GIS绝缘故障提供早期提示,对电网安全稳定运行具有重要意义。
国内外研究人员利用模式识别技术研究GIS的局部放电掌握设备绝缘缺陷类型和特征,为GIS运维提供了有价值的技术支持。目前PD两种常见的分析模式是基于时间分析模式(time resolved partial discharge,TRPD)和基于相位分析模式(phase resolved partial discharge,PRPD),这两种提取方式分别基于单次PD统计信号、多次PD统计信号,通过时域、频域、傅里叶变换和小波分析等方法提取故障特征量以实现故障模式识别[4]。近年来,各种故障模式识别方法应用于TRPD和PRPD已经非常之多。文献[5]将时域的PD脉冲信号放置在概括神经网络中,利用分区设置的创新方式提取特征,完成了不同PD模式的识别。文献[6]对GIS内的超声PD信号采用TRPD分析方式,提取了时域的5个特征、频域的3个特征,这些特征很好地描述了各缺陷的PD特征信息,通过支持向量机(support vector machine,SVM)分类器测试了提取特征的有效性。文献[7]利用K-means对手工提取的统计特征向量进行聚类,并完全分离所有PD模式。此外,文献[8]将支持向量机与基于模糊熵的特征选择相结合,以提高模式识别的准确性。
然而,上述方法都有一个基本的局限性:仔细选择的特征提取过程通常需要研究人员具有丰富的专业知识,因此容易出现人为的错误。相比之下,得益于机器学习的子学科——深度学习的发展,各种端到端的PD识别深度学习模型被提出,通过自动提取PD特征来缓解人类劳动和提高识别准确性。文献[9]提出一种通过卷积神经网络提取缺陷特征,然后引入域对抗迁移学习,成功识别4类缺陷的诊断。文献[10]引入卷积神经网络作为特征提取器,通过对抗性训练进行特征对齐和迁移,实现了工况的诊断。文献[11]将卷积神经网络与深度置信网络融合成一个复合神经网络,通过引入深度置信网络可以有效地提取特征信号,实现故障类型的分类。文献[12]基于电力物联网建设开发了多个轻量级卷积神经网络,实现了GIS绝缘缺陷的较高精度诊断。
在各种深度学习模型中,卷积神经网络因其良好的计算效率和较高的自动化程度得到了较为广泛的应用,但其对PD数据的个数和质量非常敏感,而且不能充分利用空间局部区域之间的相关性,相比传统卷积神经网络(convolutional neural network,CNN)而言,图卷积神经网络(graph convolutional neural network,GCN)在处理离散空间域信号判别特征提取方面具有一定的优越性[13],因此本文采用深度图卷积神经网络(deep graph convolutional neural network,DGCN)建立了一种基于特高频法的GIS设备绝缘故障诊断方法,所提出的深度图卷积神经网络模型由多个图卷积块、1个全连通层和1个Softmax层构成。图卷积块包括1个图卷积层、1个图粗化层和1个图池层。与传统卷积神经网络中的卷积算子不同,本文使用的图卷积层使用了一个根据切比雪夫多项式构造的快速局部化谱滤波器。将220 kV真型GIS上获取的特高局部放电(PD)信号经傅里叶变换转换为频域谱图样本作为DGCN网络的输入,经过图卷积、粗化、池化操作,使谱图结构更加清晰,以丰富输入信息。最后利用测试样本对设定好参数的DGCN进行测试,并将其性能与其他机器学习和深度学习方法进行对比分析。
图神经网络是最早由Scarselli等人[14]提出的一种新方法,其网络结构如图1所示。其目的是以图理论为基础,在图的领域内构建一个神经网络。在图域中,除了节点的数值之外,还可以通过数据的几何特征来了解节点间的关系[15]。所以,在图形字段中,相对于普通的数据字段,能够提供更多的资讯。Bruna等人[16]以谱图理论为基础,在图神经网络中引入卷积运算,构建了第一个图卷积网络模型,与传统的卷积神经网络方法相比,GCN在处理离散空间域信号鉴别特征提取方面具有优势[17]
由于GIS设备结构和不同电压等级的工作条件可能会有一定变化和差异,传统方法往往需要手动调整参数或依赖领域专家的先验知识。而DGCN具有自适应学习能力,能够通过学习图结构中的特征来自动适应不同的GIS设备。这使得DGCN在不同设备之间的迁移性和泛化性方面具有优势,能够更好地应对实际GIS设备中的变化和差异。
本文的DGCN主要有4个步骤:1)图形作为神经网络的输入,可以表示数据的几何形状和结构,使得与一般的数据格式相比提供了更多的信息;2)为了在图上构造卷积算子,基于图谱理论和切比雪夫展开式构造了快速局部化滤波器;3)利用图的粗化过程将相似的顶点组合在一起;4)对于池化过程,通过创建一个平衡的二叉树,然后运用常规的一维池化,对图顶点进行重新排列。
在处理特高频信号图谱时,首先需要将信号图谱转化为图结构数据。每个节点代表一个特征点或传感器,而边表示节点之间的关系。这种图结构能够有效地捕捉节点之间的空间局部区域的关联性,使得DGCN能够更好地理解和利用节点之间的相互作用。它考虑不同节点之间的距离、连接强度、相对位置等关系,这些关系可以通过构建图的邻接矩阵来表示,其中邻接矩阵的元素反映了节点之间的连接关系。通过将这些关系信息融入DGCN的图卷积操作中,可以更加精确地捕捉节点之间的相互作用和影响,提高对GIS局放故障的诊断准确性。
图数据集为 G = G 1 , G 2 , , G n,第i张图 G i = ν , ε , ω ν R n × f为顶点的特征矩阵,n为节点数量,f为每个结点的特征维度, ε为图节点连接关系, ω R n × n为邻接矩阵,它用来表示任意两个顶点之间的连接关系,如图2所示。图2a是包含4个顶点的无向图,图2b是邻接矩阵。本文将两个顶点的欧式距离设为 ω i j,其计算如下式:
ω i j = | | ν i - ν j | |
式中: ν i ν j分别为图中的ij节点。
拉普拉斯在谱图分析中是一个关键的操作,广泛使用的拉普拉斯矩阵定义如下式所示:
L = I n - D - 1 / 2 ω D - 1 / 2
d i = j = 1 , j i N ω i j
式中:L为拉普拉斯矩阵, L R n × nIn为单位矩阵, I n R n × nD为对角矩阵;di为对角矩阵D中的对角元素,表示节点i的度数;N为节点个数。
由于拉普拉斯矩阵是实对称矩阵,通过正交分解,可以得到:
L = U Λ U T
其中 Λ = d i a g ( λ 1 , λ 2 , , λ n - 1 )
U = ( u 1 , u 2 , , u n - 1 ),由特征向量组成。
定义一个图x ν ( v 1 , v 2 , , v N a ) R N ( x 1 , x 2 , , x N a ),在x图的第i个向量上代表的第i个顶点值的傅里叶变换公式如下:
x ^ = i = 1 N u l ( i ) * × ( i ) = U T x
其傅里叶逆变换如下式:
x = i = 0 N - 1 x ^ ( i ) * u l ( i ) = U x ^
x ^是图信号x在傅里叶变换式中的表示。
在DGCN中,节点之间的关系通过图卷积操作进行建模。图卷积操作利用图数据节点的特征和相邻节点的特征来更新节点的表示。对于每个节点,DGCN会聚集其相邻节点的特征,并将这些特征进行加权平均或拼接,以获得节点的新表示。通过多层图卷积操作,DGCN能够逐渐传播和融合节点之间的信息,从而提取适用于GIS设备的更高层次、更具判别性的特征参量。
通常来说,卷积运算不能直接用于图上,但是文献[17]基于拉普拉斯推广的方法可直接对图进行卷积操作,如下式所示:
y = g θ ( L ) x
将式(4)和式(7)结合,卷积操作可以表示为
y = U g θ ( Λ ) U T x
但是 g θ ( Λ )计算过程时间长且繁琐,本文采用切比雪夫多项式展开来简化这个计算的过程,如下式所示:
g θ ( Λ ) = k = 0 k - 1 θ k T k ( Λ )
g θ ( Λ )可以使用k阶切比雪夫多项式来近似等效。再根据式(8)和式(9),得到图卷积运算公式为
              y = k = 0 k - 1 U θ k T k ( λ 0 )                                   0                                                                                                                                                                                                         0                                   θ k T k ( λ N - 1 ) U T x = k = 0 k - 1 θ k T k L x
式中: θ k为切比雪夫系数,是个向量; T k ( · ) θ k的一个递归系数。
在含有多个图卷积层的GCNs中,样本p的第j个输出特征的公式如下:
y p i = i = 1 F 0 g θ i , j L x p , j
式中:F0为输入特征的数量,即每个节点输入的特征向量的维度。
在对图池化操作之前,需要将图上相似的顶点聚类在一起,本文采用超像素分割法,该方法起源K均值聚类算法,它以图像的特点为基础,将网格形状的像素组织起来,构成一个有可视化的像素子区,也就是超像素块。超像素划分方法能用较少的超像素来取代较多的像素点,能够高效地减少图像处理的复杂性[18-19]
简单线性聚类法是一种高效且易于实现的超像素分割方法[20],在通常情况下,超像素的数量是其唯一需要设定的参数,它的主要步骤是:首先将n个像素块组成的图片转换到CILLAB色彩空间,聚类中心可以表示为
C i = [ e i , a i , b i , c i , e i ,   f i ]
式中:e为亮度;ab为颜色;df为像素的空间信息。
然后围绕着聚类中心,图像会被分割成大小相等的超像素块,两个相邻的超像素块之间的距离如下式所示:
S = ( N p / k p ) 1 / 2
式中:Np为图像中的总像素数: k p为超像素块的数量。
最后,根据梯度最小值的原理,通过迭代优化,将各像素与其簇中心连接起来,并对它们之间的相关性进行调整,使其不会出现在具有较大梯度的边界轮廓上。
图池化类似于传统CNN中的池化操作,但在图数据上进行。它可以减少图中节点的数量,同时保留重要的结构和特征信息。图池化操作使得DGCN可以处理大规模图数据,同时具有泛化和计算效率高的优点。
上一小节中图的粗化过程对顶点进行了聚类操作,但是每组中标记的顶点是无序排列的,会影响图的池化过程,因此,本文将粗化的顶点构建二叉树结构[11,21-22],使用重排方法对顶点进行排序以便后续的池化操作。然后使用一维池化操作处理排列的顶点,图3a展示了用一个大小为2的最大池对一个具有12个顶点的图粗化,每次池化大小为2,图3b展示了如何重新排列顶点的过程以实现池化。
为建立PD样本数据库,本文在220 kV真型GIS试验腔体上搭建PD信息联合采集平台,如图4所示,采用特高频法采集不同缺陷的PD信号。
图4中,T1为柱式调压器,试验过程中输入220 V工频交流电压;T2为无局放工频试验变压器;Rr为工频试验保护电阻,阻值为10 kΩ;C1为耦合电容;Z为监测电阻。本文根据IEC60270标准建立了耦合电容C1和检测阻抗Z串联的局部放电检测回路,通过检测阻抗Z来判断局部放电量的大小;C2/C3为工频分压器。示波器采样频率为3 GHz,工频周期信号由电容C3端通过同轴电缆线传输至泰克高性能数字示波器。本文采用的特高频天线传感器为超宽带椭圆单极子天线(工作频段为300 MHz~3 GHz),置于有机玻璃法兰盘的外壳。试验时腔体中充入0.4 MPa纯净的SF6气体。
本文设计并实现了4种具有普遍代表性的缺陷如图5所示,分别是绝缘子表面金属污秽缺陷、绝缘子气隙缺陷、悬浮电极缺陷和金属突出物缺陷。采用阶梯电压法模拟PD的发展过程[20],每一个电压等级加压24 h,每隔6 h统计一次脉冲电流信号(对应放电量信息)和特高频信息的PD数据,并进行图谱分析。
试验前对搭建的试验平台进行了环境噪声测量,在PD监测和信号采集的过程中,通过提高检测阈值消除环境噪声,保证特高频传感器检测到的信号为PD信号。设置的4种缺陷的起始局放电压分别为14.8 kV,9.6 kV,16.7 kV和9.1 kV,采集了如表1所示的从起始局放阶段逐渐到放电较为严重阶段的电压,以模仿设备绝缘缺陷劣化的过程。每种电压等级采集的数据样本各100组,建立4种典型绝缘缺陷信号数据库,图6显示了典型缺陷的局部放电信号图谱。将采集到的特高频信号随机选取70%作为DGCN的训练集,剩余样本作为测试集。
本文使用特高频传感器来采集PD信号,然后将采集到的时域数据进行傅里叶变换,转换为频域图形,使得频域图形成为谱图样本,其中每个样本由记录信号的4 900个点组成,即 z = [ z 1 , z 2 , , z 4   900 ],映射成一个大小为70×70的矩阵。每个矩阵中的节点与其8个相邻节点通过边相互连接,再根据式(1)计算的欧式距离作为边界权值。
再使用DGCN的多个卷积模块提取抽象的特征,每个模块都含有1个图卷积层、1个图粗化层和1个图池层。图卷积层根据拉普拉斯和切比雪夫多项式实现,图粗化根据超像素分割法实现,用于将领域与池化层兼容聚类在一起,类似地将基于一维池化操作的图池层应用于聚集的领域,然后提取输入中的故障特征,将学习到的特征送入全连通层和SoftMax层进行故障检测,其流程如图7所示。
在训练DGCN之前,需要对它的结构和参数进行优化,使其能达到较好的诊断效果。式(9)为切比雪夫多项式的展开阶数,又称为核长度,是本文提出DGCN网络的一个核心参数。为了得到适合GIS故障诊断的最优值,本文选择核长度数值从4增加到12的故障识别率进行对比,如图8所示。结果表明,当核长度从4增加到8时,测试的识别率随之增加,但当核长度超过8时,随着数值增加,识别率反而下降,因此设计的DGCN选择核长度为8,用于模型当中。
为了确定DGCN的深度和宽度,随机选取了500组PD数据,在测试过程中采取逐步优化的方法。首先将深度设置为1层,宽度分别选择16,32,64,128,观察其识别率的变化情况,由图9可知当深度为1层时,宽度为64时识别率最高。所以当深度为2时,第一层的宽度应当设为64,依次类推。试验结果表明,当深度由1层增加到3层时,DGCN的总体识别率随之升高,再当深度超过3时,其总体识别率反而下降,因此将DGCN的深度设为3层,宽度为64*128*32时,整个网络的性能最好。
为了验证DGCN的优越性,本文选择了长短期神经记忆网络(long short-term memory,LSTM)、堆叠自动编码器(stacked automatic coding,SAE)、卷积神经网络(CNN)、图卷积神经网络(GCN)以及支持向量机(SVM)方法进行比较,每种方法都随机选取300组PD数据进行测试,表2显示的是不同方法下GIS的4种典型缺陷的识别率。如表2所示,DGCN的总体识别率达到98.77%,明显高于其他方法。对比传统的机器学习方法,如SVM,LSTM和SAE,DGCN的识别率分别高出了17.99%,8.96%和12.39%,表明该方法较传统的非图方法具有显著的优势,说明它能充分利用PD信号的数值关系和频域图内部的节点关系。相较于GCN,DGCN的识别率高出7.12%,说明边缘权值的优化丰富了输入信息,使得网络得到了优化。相较于CNN,DGCN的识别率提高了11.09%,这主要是因为CNN对样本的训练数量要求较多,表明DGCN对样本的依赖性较小,更有利于运用到运维现场。
为了避免由于参数初始化引起的偏差,并验证DGCN的稳定性,本文选择悬浮电极缺陷16.7 kV,21.8 kV和25.9 kV三种电压下检测到的PD数据各100组,分别依次对DGCN,LSTM以及CNN进行测试,最终结果如图10所示。试验结果表明,在样本数量较少的情况下,DGCN依旧能有较高的识别率,总体保持在95.05%,而LSTM和CNN这两种深度学习方法,他们在测试数量样本较少的情况下,识别率对比表2而言都有一定的下浮,总体识别率分别下浮了4.28%和6.77%,这两种方法的识别率随着电压等级的升高都有一定幅度的上升,但DGCN几乎保持不变,表明了DGCN具有较好的识别精度和稳定性,验证了DGCN较强的鲁棒性。
本文提出了一种基于深度图卷积神经网络DGCN的GIS故障类型诊断方法,通过特高频传感器采集PD信号,将采集到的时域信号经过傅里叶变换转换为频域图形输入到DGCN网络中。所构建的DGCN包含多个特征提取模块、1个全连通层和1个Softmax层,诊断步骤包括:卷图积、图粗化和图池化。最后通过测试得到了适合于GIS故障诊断的DGCN最优网络参数,将该方法与其他传统方法进行了试验对比和分析,DGCN方法识别率达到98.77%,明显高于其他机器学习方法,表明本文构造的DGCN利用顶点和边构建的图可以为深度学习模型训练出更多有效信息,并且验证了该方法具有较好的鲁棒性。
  • 智能电网保护和运行控制国家重点实验室开放基金(SGNR0000KJJS2200301)
  • 国网湖北省电力有限公司科技项目(521520220003)
参考文献 引证文献
排序方式:
[1]
LI Shengchun. Location and analysis of abnormal partial discharge of 750 kV GIS equipment[C]//2021 13th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA), Beihai,China, 2021,83-85.
[2]
REN M, ZHOU J, MIAO J. Adopting spectral analysis in partial discharge fault diagnosis of GIS with a micro built-in optical sensor[J]. IEEE Transactions on Power Delivery, 2021, 36(2):1237-1240.
[3]
唐炬, 曾福平, 范庆涛, 等. 基于荧光光纤检测GIS局部放电的多重分形谱识别[J]. 高电压技术, 2014, 40(2):465-473.
TANG Ju, ZENG Fuping, FAN Qingtao, et al. Multifractal spectrum identification of partial discharge in GIS based on fluorescence optical fiber detection[J]. High Voltage Engineering, 2014, 40(2):465-473.
[4]
NGUYEN M T, NGUYEN V H, YUN S J, et al. Recurrent neural network for partial discharge diagnosis in gas-insulated switchgear[J]. Energies, 2018, 11(5):1202.
[5]
唐炬, 杨东, 曾福平, 等. 基于分解组分分析的SF6设备绝缘故障诊断方法与技术的研究现状[J]. 电工技术学报, 2016, 31(20):41-54.
TANG Ju, YANG Dong, ZENG Fuping, et al. Research status of SF6 insulation equipment fault diagnosis method and technology based on decomposed components analysis[J]. Transactions of China Electrotechnical Society, 2016, 31(20):41-54.
[6]
张波. 基于超声波法的GIS局部放电模式识别的研究[D]. 北京: 华北电力大学, 2015.
ZHANG Bo. Research on partial discharge pattern recogoniton of GIS based on ultrasonic detection[D]. Beijing: North China Electric Power University, 2015.
[7]
CHATPATTANANAN V, PATTANADECH N, YUTTHAGOWITH P. Partial discharge classification on high voltage equipment with K-means[C]// 2006 IEEE 8th International Conferen-ce on Properties & Applications of Dielectric Materials, 2006:191-194.
[8]
CHANG C K, BOYANAPALLI B K, WU R N. Application of fuzzy entropy to improve feature selection for defect recognition using support vector machine in high voltage cable joints[J]. IEEE Transactions on Dielectrics and Electrical Insulation, 2020, 27(6):2147-2155.
[9]
王艳新, 闫静, 王建华, 等. 基于域对抗迁移卷积神经网络的小样本GIS绝缘缺陷智能诊断方法[J]. 电工技术学报, 2022, 37(9):2150-2160.
WANG Yanxin, YAN Jing, WANG Jianhua, et al. Intelligent diagnosis for GIS with small samples using a novel adversarial transfer learning in convolutional neural network[J]. Transactions of China Electrotechnical Society, 2022, 37(9):2150-2160.
[10]
LI J, HUANG R, HE G, et al. A deep adversarial transfer learning network for machinery emerging fault detection[J]. IEEE Sensors Journal, 2020, 20(15):8413-8422.
[11]
袁文海, 刘彪, 徐浩, 等. 基于复合神经网络的GIS局放故障类型识别[J]. 电力科学与技术学报, 2021, 36(4):157-164.
YUAN Wenhai, LIU Biao, XU Hao, et al. Partial discharge fault type identification of GIS based on composite neural network[J]. Journal of Electric Power Science and Technology, 2021, 36(4):157-164.
[12]
WANG Y, YAN J, YANG Z, et al. GIS partial discharge pattern recognition via lightweight convolutional neural network in the ubiquitous power internet of things context[J]. IET Science,Measurement & Technology, 2020, 14(8):864-871.
[13]
高盎然, 朱永利, 张翼, 等. 基于边际谱图像和深度残差网络的变压器局部放电模式识别[J]. 电网技术, 2021, 45(6):2433-2442.
GAO Angran, ZHU Yongli, ZHANG Yi, et al. Partial discharge pattern recognition of power transformers based on marginal spectrum images and deep residual net-work[J]. Power System Technology, 2021, 45(6):2433-2442.
[14]
SCARSELLI F, GORI M, TSOI A C, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks, 2008, 20(1):61-80.
[15]
ORTEGA A, FROSSARD P, KOVACEVIC J. Graph signal processing:overview,challenges,and applications[J]. Proceedings of the IEEE, 2018, 106 (5):808-828.
[16]
BRUNA J, ZAREMBA W, SZLAM A, et al. Spectral networks and locally connected networks on graphs[C]// International Conference on Learning Representations, 2013.
[17]
SUCH F P, SAH S, DOMINGUEZ M A, et al. Robust spatial filtering with graph convolutional neural networks[J]. IEEE Journal Selected Topics Signal Processing, 2017, 11 (6):884-896.
[18]
SHUMAN D I, NARANG S K, FROSSARD P, et al. The emer-ging field of signal processing on graphs:extending high-dimensional data analysis to networks and other irregular domains[J]. IEEE Signal Processing Magazine, 2013, 30(3):83-98.
[19]
陈起磊, 蒋亦悦, 唐瑶, 等. 基于时域图与改进图卷积神经网络的异步电机故障诊断方法[J]. 振动与冲击, 2022, 41(24):241-248.
CHEN Qilei, JIANG Yiyue, TANG Yao, et al. An induction motor fault diagnosis method based on the time-frequency image method and improved graph convolution netword[J]. Journal of Vibration and Shock, 2022, 41(24):241-248.
[20]
刘鹏, 李真芳, 楼良盛, 等. 基于超像素分割与多信息融合的叠掩和阴影区域检测法[J]. 测绘学报, 2022, 51(12):2517-2530.
LIU Peng, LI Zhenfang, LOU Liangsheng, et al. Layover and shadow regions detection based on superpixel segmentation and multi-information fusion[J]. Acta Geodaetica et Cartographi-ca Sinica, 2022, 51(12):2517-2530.
[21]
DEFFERRARD M, BRESSON X, VANDERGHEYNST P. Convolutional neural networks on graphs with fast localized spectral filtering[C]// Proceedings of the 30th International Conferen-ce on Neural Information Processing Systems, 2016.
[22]
ZHANG Dingcheng, STEWART Edward, ENTEZAMI Mani, et al. Intelligent acoustic-based fault diagnosis of roller bearings using a deep graph convolutional network[J]. Measurement, 2020(156):107585.
2024年第54卷第12期
PDF下载
160
71
引用本文
BibTeX
文章信息
doi: 10.19457/j.1001-2095.dqcd25297
  • 接收时间:2023-08-02
  • 首发时间:2025-12-10
  • 出版时间:2024-12-20
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-08-02
  • 修回日期:2023-08-28
基金
智能电网保护和运行控制国家重点实验室开放基金(SGNR0000KJJS2200301)
国网湖北省电力有限公司科技项目(521520220003)
作者信息
    1 国网湖北省电力有限公司超高压公司,湖北 武汉 430050
    2 湖北工业大学 新能源及电网装备安全监测湖北省工程研究中心,湖北 武汉 430068
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/dqcd/CN/10.19457/j.1001-2095.dqcd25297
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