Article(id=1206314801312121140, tenantId=1146029695717560320, journalId=1189987059142926344, issueId=1206314797411418409, articleNumber=null, orderNo=null, doi=10.19457/j.1001-2095.dqcd24578, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1661097600000, receivedDateStr=2022-08-22, revisedDate=1666195200000, revisedDateStr=2022-10-20, acceptedDate=null, acceptedDateStr=null, onlineDate=1765537460877, onlineDateStr=2025-12-12, pubDate=1710864000000, pubDateStr=2024-03-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1765537460877, onlineIssueDateStr=2025-12-12, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1765537460877, creator=13701087609, updateTime=1765537460877, updator=13701087609, issue=Issue{id=1206314797411418409, tenantId=1146029695717560320, journalId=1189987059142926344, year='2024', volume='54', issue='3', pageStart='3', pageEnd='96', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=0, articleOrder=1, issueType=-1, specialIssue=null, createTime=1765537459937, creator=13701087609, updateTime=1765766624077, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1207275981480477057, tenantId=1146029695717560320, journalId=1189987059142926344, issueId=1206314797411418409, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1207275981480477058, tenantId=1146029695717560320, journalId=1189987059142926344, issueId=1206314797411418409, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=84, endPage=90, ext={EN=ArticleExt(id=1206314802079678774, articleId=1206314801312121140, tenantId=1146029695717560320, journalId=1189987059142926344, language=EN, title=Power Quality Disturbance Classification Based on Graph Convolutional Neural Networks and Gramian Angular Field, columnId=null, journalTitle=Electric Drive, columnName=null, runingTitle=null, highlight=null, articleAbstract=

Due to the extensive addition of new energy systems, the number and types of power quality disturbances in the system are also increased accordingly. However, the traditional power quality disturbance (PQD) classification method has the problem of low accuracy and efficiency, and it is difficult to adapt to the existing power quality management of power systems with high new energy penetration. Therefore, a PQD classification method based on graph convolutional neural networks (GCNNs) and Gramian angular field (GAF) was proposed. First, the original PQD signal was normalized and polar coordinate transformation was processed, then GAF was used to graphically transform different kinds of PQD one-dimensional signals to generate two-dimensional images containing different PQD features, and finally, GCNNs were used to train and classify the different kinds of PQD images to achieve the classification of different PQDs. In the experiment part, the IEEE-39 node system was used to simulate and simulate different types of PQD curves, and the method proposed was used for verification. The experiment results show that the proposed method can automatically extract and optimize the features, and meet the high efficiency and accuracy of PQD identification and classification.

, 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=Guanglei HUANG, Qidong TIAN, Zhixian LIN, Weinan ZHENG, Te XU, Bingran LI), CN=ArticleExt(id=1206314806320120174, articleId=1206314801312121140, tenantId=1146029695717560320, journalId=1189987059142926344, language=CN, title=基于图卷积神经网络和格拉姆角场的电能质量扰动分类, columnId=1190325456588079763, journalTitle=电气传动, columnName=可靠性与诊断, runingTitle=null, highlight=null, articleAbstract=

由于新能源系统的广泛加入,系统中的电能质量扰动数量和种类也相应增加,而传统电能质量扰动(PQD)分类方法存在准确率和效率不高的问题,难以适应现有包含高新能源渗透率的电力系统的电能质量管理。因此,提出了一种基于图卷积神经网络(GCNNs)和格拉姆角场(GAF)的电能质量扰动分类方法。首先,对原始的PQD信号进行归一化和极坐标转化处理;然后采用GAF对不同种类的PQD一维信号进行图形化转换,生成包含不同PQD特征的二维图片;最后,采用GCNNs对不同种类的PQD图片进行训练和分类,实现不同PQD的分类。实验部分采用IEEE-39节点系统仿真并模拟不同种类的PQD曲线,对所提方法进行验证。实验结果表明,所提方法可以自动地进行特征的提取和优化,满足PQD识别和分类的高效性和准确性。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=rd1g6c4gl7vcS0GZMBPbLA==, magXml=39cDgS6ZQ933Ih4R3y5uVQ==, pdfUrl=null, pdf=244lRwkuA7KoTWXDGGWkjQ==, pdfFileSize=4926850, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=dmLVgdLDdw4GFcN7NdpsYQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=rEimr7cayYTrTk43R97oLA==, mapNumber=null, authorCompany=null, fund=null, authors=

黄光磊(1994—),男,硕士,工程师,Email:

, authorsList=黄光磊, 田启东, 林志贤, 郑炜楠, 徐特, 李冰然)}, authors=[Author(id=1207275578474975616, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wurong@chuanglintech.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1207275578651136389, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, authorId=1207275578474975616, language=EN, stringName=Guanglei HUANG, firstName=Guanglei, middleName=null, lastName=HUANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Shenzhen Power Supply Bureau Co.,Ltd.,Shenzhen 310030,Guangdong,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207275578755993995, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, authorId=1207275578474975616, language=CN, stringName=黄光磊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 深圳供电局有限公司,广东 深圳 310030, bio={"content":"

黄光磊(1994—),男,硕士,工程师,Email:

"}, bioImg=null, bioContent=

黄光磊(1994—),男,硕士,工程师,Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207275578219123059, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, xref=1, ext=[AuthorCompanyExt(id=1207275578231705972, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578219123059, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Shenzhen Power Supply Bureau Co.,Ltd.,Shenzhen 310030,Guangdong,China), AuthorCompanyExt(id=1207275578240094581, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578219123059, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 深圳供电局有限公司,广东 深圳 310030)])]), Author(id=1207275578894406038, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, 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=1207275579016040862, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, authorId=1207275578894406038, language=EN, stringName=Qidong TIAN, firstName=Qidong, middleName=null, lastName=TIAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Shenzhen Power Supply Bureau Co.,Ltd.,Shenzhen 310030,Guangdong,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207275579129287075, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, authorId=1207275578894406038, language=CN, stringName=田启东, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 深圳供电局有限公司,广东 深圳 310030, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207275578219123059, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, xref=1, ext=[AuthorCompanyExt(id=1207275578231705972, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578219123059, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Shenzhen Power Supply Bureau Co.,Ltd.,Shenzhen 310030,Guangdong,China), AuthorCompanyExt(id=1207275578240094581, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578219123059, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 深圳供电局有限公司,广东 深圳 310030)])]), Author(id=1207275579309642152, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, 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=1207275579393528237, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, authorId=1207275579309642152, language=EN, stringName=Zhixian LIN, firstName=Zhixian, middleName=null, lastName=LIN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Shenzhen Power Supply Bureau Co.,Ltd.,Shenzhen 310030,Guangdong,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207275579531940272, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, authorId=1207275579309642152, language=CN, stringName=林志贤, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 深圳供电局有限公司,广东 深圳 310030, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207275578219123059, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, xref=1, ext=[AuthorCompanyExt(id=1207275578231705972, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578219123059, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Shenzhen Power Supply Bureau Co.,Ltd.,Shenzhen 310030,Guangdong,China), AuthorCompanyExt(id=1207275578240094581, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578219123059, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 深圳供电局有限公司,广东 深圳 310030)])]), Author(id=1207275579687129523, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, 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=1207275579791987132, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, authorId=1207275579687129523, language=EN, stringName=Weinan ZHENG, firstName=Weinan, middleName=null, lastName=ZHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Shenzhen Power Supply Bureau Co.,Ltd.,Shenzhen 310030,Guangdong,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207275580991558082, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, authorId=1207275579687129523, language=CN, stringName=郑炜楠, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 深圳供电局有限公司,广东 深圳 310030, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207275578219123059, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, xref=1, ext=[AuthorCompanyExt(id=1207275578231705972, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578219123059, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Shenzhen Power Supply Bureau Co.,Ltd.,Shenzhen 310030,Guangdong,China), AuthorCompanyExt(id=1207275578240094581, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578219123059, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 深圳供电局有限公司,广东 深圳 310030)])]), Author(id=1207275581088027079, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, 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=1207275581218050511, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, authorId=1207275581088027079, language=EN, stringName=Te XU, firstName=Te, middleName=null, lastName=XU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 Shenzhen Power Supply Bureau Co.,Ltd.,Shenzhen 310030,Guangdong,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207275581314519510, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, authorId=1207275581088027079, language=CN, stringName=徐特, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 深圳供电局有限公司,广东 深圳 310030, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207275578219123059, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, xref=1, ext=[AuthorCompanyExt(id=1207275578231705972, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578219123059, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Shenzhen Power Supply Bureau Co.,Ltd.,Shenzhen 310030,Guangdong,China), AuthorCompanyExt(id=1207275578240094581, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578219123059, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 深圳供电局有限公司,广东 深圳 310030)])]), Author(id=1207275581410988508, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, 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=1207275581536817634, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, authorId=1207275581410988508, language=EN, stringName=Bingran LI, firstName=Bingran, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 State Grid Jiangsu Electric Power Co.,Ltd.,Suzhou 215000,Jiangsu,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1207275581629092329, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, authorId=1207275581410988508, language=CN, stringName=李冰然, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 国家电网江苏省电力有限公司,江苏 苏州 215000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1207275578332369274, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, xref=2, ext=[AuthorCompanyExt(id=1207275578340757883, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578332369274, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 State Grid Jiangsu Electric Power Co.,Ltd.,Suzhou 215000,Jiangsu,China), AuthorCompanyExt(id=1207275578349146492, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578332369274, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 国家电网江苏省电力有限公司,江苏 苏州 215000)])])], keywords=[Keyword(id=1207275581855584752, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=EN, orderNo=1, keyword=power quality disturbance(PQD)), Keyword(id=1207275582010774005, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=EN, orderNo=2, keyword=graph convolutional neural networks (GCNNs)), Keyword(id=1207275582094660089, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=EN, orderNo=3, keyword=Gramian angular field (GAF)), Keyword(id=1207275582161768958, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=EN, orderNo=4, keyword=disturbance classification), Keyword(id=1207275582254043652, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=CN, orderNo=1, keyword=电能质量扰动), Keyword(id=1207275582413427210, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=CN, orderNo=2, keyword=图卷积神经网络), Keyword(id=1207275582530867729, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=CN, orderNo=3, keyword=格拉姆角场), Keyword(id=1207275582686056983, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=CN, orderNo=4, keyword=扰动分类)], refs=[Reference(id=1207275586435764857, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2021, volume=49, issue=13, pageStart=174, pageEnd=186, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=王燕, journalName=电力系统保护与控制, refType=null, unstructuredReference=王燕. 电能质量扰动检测的研究综述[J]. 电力系统保护与控制, 2021, 49(13):174-186., articleTitle=电能质量扰动检测的研究综述, refAbstract=null), Reference(id=1207275586574176890, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2021, volume=49, issue=13, pageStart=174, pageEnd=186, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=WANG Yan, journalName=Power System Protection and Control, refType=null, unstructuredReference=WANG Yan. Review of research development in power quality disturbance detection[J]. Power System Protection and Control, 2021, 49(13):174-186., articleTitle=Review of research development in power quality disturbance detection, refAbstract=null), Reference(id=1207275586737754750, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=21, pageStart=62, pageEnd=66, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=朱永强, 李翔宇, 夏瑞华, journalName=电器与能效管理技术, refType=null, unstructuredReference=朱永强, 李翔宇, 夏瑞华. 电能质量讲座第一讲新能源并网引起电能质量问题综述[J]. 电器与能效管理技术, 2017(21):62-66., articleTitle=电能质量讲座第一讲新能源并网引起电能质量问题综述, refAbstract=null), Reference(id=1207275586821640832, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=21, pageStart=62, pageEnd=66, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=ZHU Yongqiang, LI Xiangyu, XIA Ruihua, journalName=Electrical & Energy Management Technology, refType=null, unstructuredReference=ZHU Yongqiang, LI Xiangyu, XIA Ruihua. Review of power quality problems caused by new energy grid-connected[J]. Electrical & Energy Management Technology, 2017(21):62-66., articleTitle=Review of power quality problems caused by new energy grid-connected, refAbstract=null), Reference(id=1207275586947469958, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=12, pageStart=4104, pageEnd=4121, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=汪飞, 全晓庆, 任林涛, journalName=中国电机工程学报, refType=null, unstructuredReference=汪飞, 全晓庆, 任林涛. 电能质量扰动检测与识别方法研究综述[J]. 中国电机工程学报, 2021, 41(12):4104-4121., articleTitle=电能质量扰动检测与识别方法研究综述, refAbstract=null), Reference(id=1207275587069104772, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=12, pageStart=4104, pageEnd=4121, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=WANG Fei, QUAN Xiaoqing, REN Lintao, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=WANG Fei, QUAN Xiaoqing, REN Lintao. Review of power quality disturbance detection and identification methods[J]. Proceedings of the CSEE, 2021, 41(12):4104-4121., articleTitle=Review of power quality disturbance detection and identification methods, refAbstract=null), Reference(id=1207275587203322503, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2000, volume=15, issue=3, pageStart=1039, pageEnd=1044, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=POISSON O, RIOUAL P, MEUNIER M, journalName=IEEE Transactions on Power Delivery, refType=null, unstructuredReference=POISSON O, RIOUAL P, MEUNIER M. Detection and measurement of power quality disturbances using wavelet transform[J]. IEEE Transactions on Power Delivery, 2000, 15(3):1039-1044., articleTitle=Detection and measurement of power quality disturbances using wavelet transform, refAbstract=null), Reference(id=1207275587308180107, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=1650, pageEnd=1663, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=KHOKHAR S, ZIN A A B M, MOKHTAR A S B, journalName=Renewable and Sustainable Energy Reviews, refType=null, unstructuredReference=KHOKHAR S, ZIN A A B M, MOKHTAR A S B, et al. A comprehensive overview on signal processing and artificial intelligence techniques applications in classification of power quality disturbances[J]. Renewable and Sustainable Energy Reviews, 2015,51:1650-1663., articleTitle=A comprehensive overview on signal processing and artificial intelligence techniques applications in classification of power quality disturbances, refAbstract=null), Reference(id=1207275587387871883, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2006, volume=21, issue=3, pageStart=1663, pageEnd=1669, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=JANIK P, LOBOS T, journalName=IEEE Transactions on Power Delivery, refType=null, unstructuredReference=JANIK P, LOBOS T. Automated classification of power-quality disturbances using SVM and RBF networks[J]. IEEE Transactions on Power Delivery, 2006, 21(3):1663-1669., articleTitle=Automated classification of power-quality disturbances using SVM and RBF networks, refAbstract=null), Reference(id=1207275587480146574, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2022, volume=50, issue=7, pageStart=81, pageEnd=90, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=陈子璇, 席燕辉, 沈银, journalName=电力系统保护与控制, refType=null, unstructuredReference=陈子璇, 席燕辉, 沈银. 基于卡尔曼滤波和深度置信网络的复合电能质量扰动分类[J]. 电力系统保护与控制, 2022, 50(7):81-90., articleTitle=基于卡尔曼滤波和深度置信网络的复合电能质量扰动分类, refAbstract=null), Reference(id=1207275587551449745, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2022, volume=50, issue=7, pageStart=81, pageEnd=90, url=null, language=null, rfNumber=[7], rfOrder=10, authorNames=CHEN Zixuan, XI Yanhui, SHEN Yin, journalName=Power System Protection and Control, refType=null, unstructuredReference=CHEN Zixuan, XI Yanhui, SHEN Yin. Recognition of multiple power quality disturbances based on a Kalman filter and deep belief network[J]. Power System Protection and Control, 2022, 50(7):81-90., articleTitle=Recognition of multiple power quality disturbances based on a Kalman filter and deep belief network, refAbstract=null), Reference(id=1207275587622752917, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2022, volume=34, issue=11, pageStart=17, pageEnd=23, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=刘烨, 程杉, 王瑞, journalName=电力系统及其自动化学报, refType=null, unstructuredReference=刘烨, 程杉, 王瑞, 等. 基于小波降噪和深度学习的电能质量扰动分类方法[J]. 电力系统及其自动化学报, 2022, 34(11):17-23., articleTitle=基于小波降噪和深度学习的电能质量扰动分类方法, refAbstract=null), Reference(id=1207275587744387735, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2022, volume=34, issue=11, pageStart=17, pageEnd=23, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=LIU Ye, CHENG Shan, WANG Rui, journalName=Proceedings of the CSU-EPSA, refType=null, unstructuredReference=LIU Ye, CHENG Shan, WANG Rui, et al. Power quality disturbance classification method based on wavelet denoising and deep learning[J]. Proceedings of the CSU-EPSA, 2022, 34(11):17-23., articleTitle=Power quality disturbance classification method based on wavelet denoising and deep learning, refAbstract=null), Reference(id=1207275587882799769, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2019, volume=38, issue=4, pageStart=18, pageEnd=25, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=吴建章, 沙浩源, 张宸宇, journalName=电力工程技术, refType=null, unstructuredReference=吴建章, 沙浩源, 张宸宇, 等. 基于PSO-SVM的直流配电网电能质量扰动辨识[J]. 电力工程技术, 2019, 38(4):18-25., articleTitle=基于PSO-SVM的直流配电网电能质量扰动辨识, refAbstract=null), Reference(id=1207275587979268762, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2019, volume=38, issue=4, pageStart=18, pageEnd=25, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=WU Jianzhang, SHA Haoyuan, ZHANG Chenyu, journalName=Electric Power Engineering Technology, refType=null, unstructuredReference=WU Jianzhang, SHA Haoyuan, ZHANG Chenyu, et al. Identification of power quality disturbance in DC distribution network based on PSO-SVM[J]. Electric Power Engineering Technology, 2019, 38(4):18-25., articleTitle=Identification of power quality disturbance in DC distribution network based on PSO-SVM, refAbstract=null), Reference(id=1207275588075737758, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2020, volume=48, issue=6, pageStart=53, pageEnd=60, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=王维博, 张斌, 曾文入, journalName=电力系统保护与控制, refType=null, unstructuredReference=王维博, 张斌, 曾文入, 等. 基于特征融合一维卷积神经网络的电能质量扰动分类[J]. 电力系统保护与控制, 2020, 48(6):53-60., articleTitle=基于特征融合一维卷积神经网络的电能质量扰动分类, refAbstract=null), Reference(id=1207275588155429536, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2020, volume=48, issue=6, pageStart=53, pageEnd=60, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=WANG Weibo, ZHANG Bin, ZENG Wenru, journalName=Power System Protection and Control, refType=null, unstructuredReference=WANG Weibo, ZHANG Bin, ZENG Wenru, et al. Power quality disturbance classification of one-dimensional convolutional neural networks based on feature fusion[J]. Power System Protection and Control, 2020, 48(6):53-60., articleTitle=Power quality disturbance classification of one-dimensional convolutional neural networks based on feature fusion, refAbstract=null), Reference(id=1207275588239315619, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2020, volume=48, issue=2, pageStart=86, pageEnd=92, url=null, language=null, rfNumber=[11], rfOrder=17, authorNames=曹梦舟, 张艳, journalName=电力系统保护与控制, refType=null, unstructuredReference=曹梦舟, 张艳. 基于卷积-长短期记忆网络的电能质量扰动分类[J]. 电力系统保护与控制, 2020, 48(2):86-92., articleTitle=基于卷积-长短期记忆网络的电能质量扰动分类, refAbstract=null), Reference(id=1207275588335784614, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2020, volume=48, issue=2, pageStart=86, pageEnd=92, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=CAO Mengzhou, ZHANG Yan, journalName=Power System Protection and Control, refType=null, unstructuredReference=CAO Mengzhou, ZHANG Yan. Classification for power quality disturbances based on CNN-LSTM network[J]. Power System Protection and Control, 2020, 48(2):86-92., articleTitle=Classification for power quality disturbances based on CNN-LSTM network, refAbstract=null), Reference(id=1207275588449030825, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=19, authorNames=KIPF T N, WELLING M, journalName=ICLR, refType=null, unstructuredReference=KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C]// ICLR, 2017., articleTitle=Semi-supervised classification with graph convolutional networks, refAbstract=null), Reference(id=1207275588532916906, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2019, volume=6, issue=1, pageStart=1, pageEnd=23, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=ZHANG S, TONG H, XU J, journalName=Computational Social Networks, refType=null, unstructuredReference=ZHANG S, TONG H, XU J, et al. Graph convolutional networks:a comprehensive review[J]. Computational Social Networks, 2019, 6(1):1-23., articleTitle=Graph convolutional networks:a comprehensive review, refAbstract=null), Reference(id=1207275588612608685, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2005, volume=6, issue=12, pageStart=2153, pageEnd=2175, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=DRINEAS P, MAHONEY M W, CRISTIANINI N, journalName=Journal of Machine Learning Research, refType=null, unstructuredReference=DRINEAS P, MAHONEY M W, CRISTIANINI N. On the nyström method for approximating a gram matrix for improved Kernel-based learning[J]. Journal of Machine Learning Research, 2005, 6(12):2153-2175., articleTitle=On the nyström method for approximating a gram matrix for improved Kernel-based learning, refAbstract=null), Reference(id=1207275588692300464, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2008, volume=23, issue=1, pageStart=249, pageEnd=251, url=null, language=null, rfNumber=[15], rfOrder=22, authorNames=DE ALMEIDA M C, ASADA E N, GARCIA A V, journalName=IEEE Transactions on Power Systems, refType=null, unstructuredReference=DE ALMEIDA M C, ASADA E N, GARCIA A V. On the use of Gram matrix in observability analysis[J]. IEEE Transactions on Power Systems, 2008, 23(1):249-251., articleTitle=On the use of Gram matrix in observability analysis, refAbstract=null), Reference(id=1207275588788769456, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2014, volume=89, issue=5, pageStart=052109, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=STARK C, journalName=Physical Review A, refType=null, unstructuredReference=STARK C. Self-consistent tomography of the state-measurement gram matrix[J]. Physical Review A, 2014, 89(5):052109., articleTitle=Self-consistent tomography of the state-measurement gram matrix, refAbstract=null), Reference(id=1207275589950591666, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=10468, pageEnd=10477, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=XU J, TANG X, ZHU Y, journalName=Proceedings of the IEEE/CVF International Conference on Computer Vision, refType=null, unstructuredReference=XU J, TANG X, ZHU Y, et al. SGMNet:learning rotation-invariant point cloud representations via sorted gram matrix[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision,2021:10468-10477., articleTitle=SGMNet:learning rotation-invariant point cloud representations via sorted gram matrix, refAbstract=null), Reference(id=1207275590051254965, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=499, pageEnd=508, url=null, language=null, rfNumber=[18], rfOrder=25, authorNames=ZHUANG C, QIANG M, journalName=The 2018, refType=null, unstructuredReference=ZHUANG C, QIANG M. Dual graph convolutional networks for graph-based semi-supervised classification[C]// The 2018 World Wide Web Conference,2018:499-508., articleTitle=Dual graph convolutional networks for graph-based semi-supervised classification, refAbstract=null), Reference(id=1207275590139335351, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=3, pageStart=1052, pageEnd=1060, url=null, language=null, rfNumber=[19], rfOrder=26, authorNames=刘菡, 王英男, 李新利, journalName=中国电机工程学报, refType=null, unstructuredReference=刘菡, 王英男, 李新利, 等. 基于互信息-图卷积神经网络的燃煤电站NOx排放预测[J]. 中国电机工程学报, 2022, 42(3):1052-1060., articleTitle=基于互信息-图卷积神经网络的燃煤电站NOx排放预测, refAbstract=null), Reference(id=1207275590239998651, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=3, pageStart=1052, pageEnd=1060, url=null, language=null, rfNumber=[19], rfOrder=27, authorNames=LIU Han, WANG Yingnan, LI Xinli, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=LIU Han, WANG Yingnan, LI Xinli, et al. Prediction of NOx emissions of coal-fired power plants based on mutual information-graph convolutional neural network[J]. Proceedings of the CSEE, 2022, 42(3):1052-1060., articleTitle=Prediction of NOx emissions of coal-fired power plants based on mutual information-graph convolutional neural network, refAbstract=null), Reference(id=1207275590332273339, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=3, pageStart=1017, pageEnd=1026, url=null, language=null, rfNumber=[20], rfOrder=28, authorNames=龚正, 邹阳, 金涛, journalName=中国电机工程学报, refType=null, unstructuredReference=龚正, 邹阳, 金涛, 等. 基于特征融合并行优化模型的电能质量扰动分类方法[J]. 中国电机工程学报, 2023, 43(3):1017-1026., articleTitle=基于特征融合并行优化模型的电能质量扰动分类方法, refAbstract=null), Reference(id=1207275590458102464, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=3, pageStart=1017, pageEnd=1026, url=null, language=null, rfNumber=[20], rfOrder=29, authorNames=GONG Zheng, ZOU Yang, JIN Tao, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=GONG Zheng, ZOU Yang, JIN Tao, et al. Classification method of power quality disturbances based on optimized parallel model of features merging[J]. Proceedings of the CSEE, 2023, 43(3):1017-1026., articleTitle=Classification method of power quality disturbances based on optimized parallel model of features merging, refAbstract=null), Reference(id=1207275590579737283, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2017, volume=34, issue=4, pageStart=408, pageEnd=415, url=null, language=null, rfNumber=[21], rfOrder=30, authorNames=MA J, ZHANG J, XIAO L, journalName=IETE Technical Review, refType=null, unstructuredReference=MA J, ZHANG J, XIAO L, et al. Classification of power qua-lity disturbances via deep learning[J]. IETE Technical Review, 2017, 34(4):408-415., articleTitle=Classification of power qua-lity disturbances via deep learning, refAbstract=null), Reference(id=1207275590692983495, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, doi=null, pmid=null, pmcid=null, year=2006, volume=21, issue=3, pageStart=1663, pageEnd=1669, url=null, language=null, rfNumber=[22], rfOrder=31, authorNames=JANIK P, LOBOS T, journalName=IEEE Transactions on Power Delivery, refType=null, unstructuredReference=JANIK P, LOBOS T. Automated classification of power-quality disturbances using SVM and RBF networks[J]. IEEE Transactions on Power Delivery, 2006, 21(3):1663-1669., articleTitle=Automated classification of power-quality disturbances using SVM and RBF networks, refAbstract=null)], funds=[Fund(id=1207275586209272434, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, awardId=J2019124, language=CN, fundingSource=国网江苏省电力有限公司科技项目(J2019124), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1207275578219123059, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, xref=1, ext=[AuthorCompanyExt(id=1207275578231705972, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578219123059, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 Shenzhen Power Supply Bureau Co.,Ltd.,Shenzhen 310030,Guangdong,China), AuthorCompanyExt(id=1207275578240094581, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578219123059, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 深圳供电局有限公司,广东 深圳 310030)]), AuthorCompany(id=1207275578332369274, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, xref=2, ext=[AuthorCompanyExt(id=1207275578340757883, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578332369274, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 State Grid Jiangsu Electric Power Co.,Ltd.,Suzhou 215000,Jiangsu,China), AuthorCompanyExt(id=1207275578349146492, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, companyId=1207275578332369274, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 国家电网江苏省电力有限公司,江苏 苏州 215000)])], figs=[ArticleFig(id=1207275582908355109, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=EN, label=Fig.1, caption=Graphical conversion of disturbance signal, figureFileSmall=Cqj5bstDcfnujS4RlwuNlg==, figureFileBig=akPFd60AA5q6pX7LL8pEjA==, tableContent=null), ArticleFig(id=1207275582983852586, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=CN, label=图1, caption=扰动信号图形化转换, figureFileSmall=Cqj5bstDcfnujS4RlwuNlg==, figureFileBig=akPFd60AA5q6pX7LL8pEjA==, tableContent=null), ArticleFig(id=1207275583155819055, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=EN, label=Fig.2, caption=Structure diagram of GCNNs, figureFileSmall=1UPchy5G6t0WjwheF52YtA==, figureFileBig=XDjkyMC8SFvXLwI2aJ4cPg==, tableContent=null), ArticleFig(id=1207275583260676660, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=CN, label=图2, caption=图卷积神经网络结构图, figureFileSmall=1UPchy5G6t0WjwheF52YtA==, figureFileBig=XDjkyMC8SFvXLwI2aJ4cPg==, tableContent=null), ArticleFig(id=1207275583331979832, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=EN, label=Fig.3, caption=Classification process of power quality disturbance based on GCNNs, figureFileSmall=7IEOhTqww0BQArdyMazqhQ==, figureFileBig=w3959/T6FVfYgnWSDYfUIQ==, tableContent=null), ArticleFig(id=1207275583394894396, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=CN, label=图3, caption=基于图卷积神经网络的电能质量扰动分类流程, figureFileSmall=7IEOhTqww0BQArdyMazqhQ==, figureFileBig=w3959/T6FVfYgnWSDYfUIQ==, tableContent=null), ArticleFig(id=1207275583487169088, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=EN, label=Fig.4, caption=Connection diagram of IEEE-39 node system, figureFileSmall=d2gFpKLg21gztH1M0yQzRQ==, figureFileBig=gT27+g5Epdvh0Gz0o+vpLw==, tableContent=null), ArticleFig(id=1207275583558472259, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=CN, label=图4, caption=IEEE-39节点系统连接图, figureFileSmall=d2gFpKLg21gztH1M0yQzRQ==, figureFileBig=gT27+g5Epdvh0Gz0o+vpLw==, tableContent=null), ArticleFig(id=1207275583625581127, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=EN, label=Fig.5, caption=Waveforms of different power quality disturbance signal, figureFileSmall=Kke2f2JLAmZ+FRSVi1ikOQ==, figureFileBig=UMU88Nyk7V0zuaxmCxSTeA==, tableContent=null), ArticleFig(id=1207275583717855817, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=CN, label=图5, caption=不同电能质量扰动信号波形, figureFileSmall=Kke2f2JLAmZ+FRSVi1ikOQ==, figureFileBig=UMU88Nyk7V0zuaxmCxSTeA==, tableContent=null), ArticleFig(id=1207275583772381772, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=EN, label=Fig.6, caption=Two-dimensional pictures of different PQD signals, figureFileSmall=B+j5d7PowbQypPOiGUISBg==, figureFileBig=zXUWsiMgsIb8ZZXkr//6eg==, tableContent=null), ArticleFig(id=1207275583944348237, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=CN, label=图6, caption=不同PQD信号的二维图片, figureFileSmall=B+j5d7PowbQypPOiGUISBg==, figureFileBig=zXUWsiMgsIb8ZZXkr//6eg==, tableContent=null), ArticleFig(id=1207275584045011538, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=EN, label=Fig.7, caption=Model training process, figureFileSmall=dyBjSpoZisZQIq/Drbc3jw==, figureFileBig=IlsArKEA6sLofU59DWi6VQ==, tableContent=null), ArticleFig(id=1207275584145674837, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=CN, label=图7, caption=模型训练过程, figureFileSmall=dyBjSpoZisZQIq/Drbc3jw==, figureFileBig=IlsArKEA6sLofU59DWi6VQ==, tableContent=null), ArticleFig(id=1207275584263115352, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=EN, label=Fig.8, caption=Confusion matrix based on classification results, figureFileSmall=siH7a4mIY3+cwuAYqqr/4A==, figureFileBig=jXLjudrbVio6Umzca0d0Eg==, tableContent=null), ArticleFig(id=1207275585462686298, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=CN, label=图8, caption=基于分类结果的混淆矩阵, figureFileSmall=siH7a4mIY3+cwuAYqqr/4A==, figureFileBig=jXLjudrbVio6Umzca0d0Eg==, tableContent=null), ArticleFig(id=1207275585580126813, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=EN, label=Tab.1, caption=

GCNNs structure and operation process

, figureFileSmall=null, figureFileBig=null, tableContent=
层类型 核函数
大小
激活
函数
计算过程 输出
卷积层1 11×11,48 ReLU (227-11)/4 55×55
池化层1 Ks=3,s=2 (55-3)/2+1 27×27
卷积层2 5×5,128 ReLU (31-5)/2+1 27×27×256
池化层2 Ks=3,s=2 (27-3)/2+1 13×13×256
卷积层3 3×3,192 ReLU (15-3)/1+1 13×13×256
卷积层4 3×3,192 ReLU (15-3)/1+1 13×13×256
卷积层5 3×3,192 ReLU (15-3)/1+1 13×13×256
池化层5 Ks=3,s=2 (13-3)/2+1 13×13×256
), ArticleFig(id=1207275585718538852, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=CN, label=表1, caption=

GCNNs的结构及运算过程

, figureFileSmall=null, figureFileBig=null, tableContent=
层类型 核函数
大小
激活
函数
计算过程 输出
卷积层1 11×11,48 ReLU (227-11)/4 55×55
池化层1 Ks=3,s=2 (55-3)/2+1 27×27
卷积层2 5×5,128 ReLU (31-5)/2+1 27×27×256
池化层2 Ks=3,s=2 (27-3)/2+1 13×13×256
卷积层3 3×3,192 ReLU (15-3)/1+1 13×13×256
卷积层4 3×3,192 ReLU (15-3)/1+1 13×13×256
卷积层5 3×3,192 ReLU (15-3)/1+1 13×13×256
池化层5 Ks=3,s=2 (13-3)/2+1 13×13×256
), ArticleFig(id=1207275585848562281, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=EN, label=Tab.2, caption=

Comparison of classification effects with different methods

, figureFileSmall=null, figureFileBig=null, tableContent=
分类方法 扰动类型 分类识别率/%
15 dB 30 dB
SVM/
一维卷积
神经网络/GAF+GCNNs
电压暂降 85.3/98.1/98.6 83.6/96.5/98.2
电压暂升 83.6/97.5/98.5 81.9/95.6/98.6
电压中断 90.3/96.8/97.6 85.6/91.3/98.2
振荡暂态 87.6/93.6/96.8 84.6/94.3/95.3
瞬时脉冲 89.6/90.5/98.4 85.3/94.3/97.5
谐波 90.6/95.6/99.3 89.3/97.3/98.8
暂降加振荡 69.4/85.9/93.7 68.3/87.5/92.7
暂升加振荡 63.2/81.3/94.2 65.6/88.7/93.5
暂降加脉冲 59.3/75.4/94.1 59.380.2/93.3
), ArticleFig(id=1207275585953419885, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1206314801312121140, language=CN, label=表2, caption=

不同方法分类效果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
分类方法 扰动类型 分类识别率/%
15 dB 30 dB
SVM/
一维卷积
神经网络/GAF+GCNNs
电压暂降 85.3/98.1/98.6 83.6/96.5/98.2
电压暂升 83.6/97.5/98.5 81.9/95.6/98.6
电压中断 90.3/96.8/97.6 85.6/91.3/98.2
振荡暂态 87.6/93.6/96.8 84.6/94.3/95.3
瞬时脉冲 89.6/90.5/98.4 85.3/94.3/97.5
谐波 90.6/95.6/99.3 89.3/97.3/98.8
暂降加振荡 69.4/85.9/93.7 68.3/87.5/92.7
暂升加振荡 63.2/81.3/94.2 65.6/88.7/93.5
暂降加脉冲 59.3/75.4/94.1 59.380.2/93.3
)], 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.dqcd24578, detailUrlEn=https://castjournals.cast.org.cn/joweb/dqcd/EN/10.19457/j.1001-2095.dqcd24578, pdfUrlCn=https://castjournals.cast.org.cn/joweb/dqcd/CN/PDF/10.19457/j.1001-2095.dqcd24578, pdfUrlEn=https://castjournals.cast.org.cn/joweb/dqcd/EN/PDF/10.19457/j.1001-2095.dqcd24578, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于图卷积神经网络和格拉姆角场的电能质量扰动分类
收藏切换
PDF下载
黄光磊 1 , 田启东 1 , 林志贤 1 , 郑炜楠 1 , 徐特 1 , 李冰然 2
电气传动 | 可靠性与诊断 2024,54(3): 84-90
收起
收藏切换
电气传动 | 可靠性与诊断 2024, 54(3): 84-90
基于图卷积神经网络和格拉姆角场的电能质量扰动分类
全屏
黄光磊1 , 田启东1, 林志贤1, 郑炜楠1, 徐特1, 李冰然2
作者信息
  • 1 深圳供电局有限公司,广东 深圳 310030
  • 2 国家电网江苏省电力有限公司,江苏 苏州 215000
  • 黄光磊(1994—),男,硕士,工程师,Email:

Power Quality Disturbance Classification Based on Graph Convolutional Neural Networks and Gramian Angular Field
Guanglei HUANG1 , Qidong TIAN1, Zhixian LIN1, Weinan ZHENG1, Te XU1, Bingran LI2
Affiliations
  • 1 Shenzhen Power Supply Bureau Co.,Ltd.,Shenzhen 310030,Guangdong,China
  • 2 State Grid Jiangsu Electric Power Co.,Ltd.,Suzhou 215000,Jiangsu,China
出版时间: 2024-03-20 doi: 10.19457/j.1001-2095.dqcd24578
文章导航
收藏切换

由于新能源系统的广泛加入,系统中的电能质量扰动数量和种类也相应增加,而传统电能质量扰动(PQD)分类方法存在准确率和效率不高的问题,难以适应现有包含高新能源渗透率的电力系统的电能质量管理。因此,提出了一种基于图卷积神经网络(GCNNs)和格拉姆角场(GAF)的电能质量扰动分类方法。首先,对原始的PQD信号进行归一化和极坐标转化处理;然后采用GAF对不同种类的PQD一维信号进行图形化转换,生成包含不同PQD特征的二维图片;最后,采用GCNNs对不同种类的PQD图片进行训练和分类,实现不同PQD的分类。实验部分采用IEEE-39节点系统仿真并模拟不同种类的PQD曲线,对所提方法进行验证。实验结果表明,所提方法可以自动地进行特征的提取和优化,满足PQD识别和分类的高效性和准确性。

电能质量扰动  /  图卷积神经网络  /  格拉姆角场  /  扰动分类

Due to the extensive addition of new energy systems, the number and types of power quality disturbances in the system are also increased accordingly. However, the traditional power quality disturbance (PQD) classification method has the problem of low accuracy and efficiency, and it is difficult to adapt to the existing power quality management of power systems with high new energy penetration. Therefore, a PQD classification method based on graph convolutional neural networks (GCNNs) and Gramian angular field (GAF) was proposed. First, the original PQD signal was normalized and polar coordinate transformation was processed, then GAF was used to graphically transform different kinds of PQD one-dimensional signals to generate two-dimensional images containing different PQD features, and finally, GCNNs were used to train and classify the different kinds of PQD images to achieve the classification of different PQDs. In the experiment part, the IEEE-39 node system was used to simulate and simulate different types of PQD curves, and the method proposed was used for verification. The experiment results show that the proposed method can automatically extract and optimize the features, and meet the high efficiency and accuracy of PQD identification and classification.

power quality disturbance(PQD)  /  graph convolutional neural networks (GCNNs)  /  Gramian angular field (GAF)  /  disturbance classification
黄光磊, 田启东, 林志贤, 郑炜楠, 徐特, 李冰然. 基于图卷积神经网络和格拉姆角场的电能质量扰动分类. 电气传动, 2024 , 54 (3) : 84 -90 . DOI: 10.19457/j.1001-2095.dqcd24578
Guanglei HUANG, Qidong TIAN, Zhixian LIN, Weinan ZHENG, Te XU, Bingran LI. Power Quality Disturbance Classification Based on Graph Convolutional Neural Networks and Gramian Angular Field[J]. Electric Drive, 2024 , 54 (3) : 84 -90 . DOI: 10.19457/j.1001-2095.dqcd24578
随着双碳政策的推行,电力系统中发电侧新能源的渗透率不断提高,在用电侧电动汽车充电、集中化供暖、电气化铁路等都会使系统中的电能质量问题日益突出,对电网的安全运行造成严重威胁。对电力系统电能质量问题进行治理的第一步就是对不同种类电能质量扰动信号(PQD)进行识别和分类[1-3]
PQD分类主要包含两部分,第一部分是对不同PQD信号的特征提取,第二部分是对不同PQD信号的识别[4]。特征提取是指针对不同类型的PQD信号获取区别于其他不同类型的PQD信号的特征并作为识别该PQD信号的标识。PQD信号的识别是指通过不同的分类方法对提取特征之后的PQD信号进行特征的辨识和聚类。常用的特征提取方法有小波变换、希尔伯特黄变换、卡尔曼滤波等[5],常用的识别方法有一维卷积神经网络、K-means聚类、支持向量机等[6]
文献[7]提出一种基于自适应最大似然卡尔曼滤波和深度置信网络相结合的电能质量扰动识别方法。首先使用自适应最大似然卡尔曼滤波对含有噪声的原始扰动信号进行去噪,然后通过深度置信网络对去除噪声的扰动信号进行训练和分类。文献[8]提出了一种基于小波降噪和深度学习的电能质量扰动信号识别方法。首先在信号输入前端采用分层自适应阈值函数降噪法对信号降噪处理,然后在卷积神经网络扰动分类的基础上对网络加入扰动信号的时序性进行识别。文献[9]采用K-means聚类分析的方法对所提特征集的类内聚集性和类间分离性进行了验证,利用粒子群优化算法支持向量机(particle swarm optimization and support vector machine,PSO-SVM)分类器实现了直流电能质量事件的准确辨识。文献[10]采用一维卷积神经网络(convolutional neural network, CNN)和反向传播(back propagation,BP)神经网络对电能质量扰动信号进行分类。首先采用卷积层提取扰动信号的特征向量并进行特征的融合,最后通过BP神经网络实现分类。文献[11]提出一种基于卷积-长短记忆神经网络的电能质量扰动分类方法。首先,将扰动信号进行采样作为输入,然后采用CNN提取特征数据,再对提取的特征数据以序列的形式作为长短记忆网络(long short-term memory, LSTM)的输入,完成PQD信号的分类。上述方法虽然取得了一定的识别和分类的效果,但是由于近年来系统中的PQD信号的种类和数量越来越复杂,并且不同种类的PQD信号相互耦合、叠加,形成了更加复杂的复合扰动,传统的基于一维时间序列的特征PQD分类方法识别率不能满足要求,而基于图形化的特征提取方法和分类方法其权值共享网络结构使之更类似于生物神经网络,降低了网络模型的复杂度,减少了权值的数量。这种网络结构对平移、比例缩放、倾斜或者共他形式的变形具有高度不变性。而且图卷积神经网络(graph convolutional neural networks, GCNNs)采用原始图像作为输入,可以有效地从大量样本中学习到相应的特征,避免了复杂的特征提取过程[12]
因此,本文提出了一种基于格拉姆角场(Gramian angular field, GAF)和GCNNs的PQD信号分类方法。首先,将原始的基于时间序列的一维PQD信号转化为图片,图片既保留了原始电能质量扰动信号的时间序列特征又包含了空间序列特征,对于复杂的PQD信号的识别有着增加特征标识的作用,然后再利用GCNNs对生成的图片进行训练和测试,最终完成不同PQD信号的分类。
格拉姆矩阵实际上可以看作是不同特征之间的偏心协方差矩阵,在feature map中,每一个数字都来自一个特定滤波器在特定位置的卷积,因此每个数字代表一个特征的强度,而格拉姆计算实际上是两两特征之间的相关性[13]。包含不同的电能质量扰动信号实际上是一组与时间刻度相关的一维数据,包含有时间向量和不同时间刻度对应带电压大小的向量。格拉姆矩阵可以将时间向量和包含不同PQD的数据向量进行特征融合,所生成的图片能够表征包含不同PQD信号的特征。其构建的过程大致如下:
1)不同PQD数据的归一化处理。在对不同类型PQD信号进行格拉姆矩阵转化之前需要对带有时间向量的PQD信号进行归一化处理,假设包含某种PQD信号的数据为 X = x 1 , x 2 , , x n,其中 x n 表示在第n个时刻所对应的电压值的大小,则将t时刻的PQD信号xt进行归一化的计算公式为
x ˜ t = m i n ( X ) + x t m a x ( X ) - m i n ( X )
式中: x ˜ t为经过归一化的PQD信号在t时刻的值。
由于不同的PQD信号数据实际上是一组与时间向量紧密相连的一维度数组,为了能够使该数组与时间向量的联系更加紧密,需要对其进行极坐标的转换,计算公式为
φ = a r c c o s ( x ˜ t ) - 1 x ˜ t 1 ,     x ˜ t X r = t N t N
式中: N为该PQD信号进行降采样参数。
2)格拉姆矩阵角场变换。经过极坐标变换和归一化处理之后,根据格拉姆矩阵的定义[14]以及矩阵中每个元素类似向量内积运算的特点,可以采用格拉姆矩阵进行变换。格拉姆矩阵可以表示为[15]
G = x 1 , x 1 x 1 , x 2 x 1 , x n x 2 , x 1 x 2 , x 2 x 2 , x n x n , x 1 x n , x 2 x n , x n
图1为将一维PQD信号转化为二维图片的基本过程示意图。
图卷积神经网络采用原始图像作为输入,有效地从大量样本中学习到相应的特征,避免了复杂的特征提取过程。由于图卷积神经网络可以直接对二维图形进行处理,电能质量扰动信号经过格拉姆角场转化后可以将扰动信号的一维时间序列转化为二维图形特征。另外,图卷积神经网络通过简单的非线性模型从原始图形中提取更加抽象的特征,在整个过程中只需少量的人工参与,所以采用图卷积神经网络对不同电能质量扰动信号进行分类具有不错的分类效果[16-17]
GCNNs本质上是采用图论的方法对二维图片的体征进行提取和运算,然后采用不同的卷积核来提取图形特征。其中,图包含有向图和无向图,其结构Gc可表示如下:
G c = ( V , E )
式中:V为顶点;E为边。
图结构 G c = ( V , E )的特征信息可以用拉普拉斯矩阵的形式表示,其表达式为
L = D - A
采用归一化的拉普拉斯方程表示为
L s y s = I N - D - 1 2 A D - 1 2
其中
D = A i j
式中:A为图的邻接矩阵;INN阶的单位矩阵;D为图中各顶点的度矩阵;Aij为图中点(ij)的邻接矩阵。
图形的关系矩阵经过傅里叶变换之后,图卷积公式的表达式为
g   *   x = U [ ( U T g ) ( U T x ) ]
式中:x为图的Nd维信号, x R N dg为卷积核;U为拉普拉斯矩阵L的特征向量。
图卷积神经网络的基本结构如图2所示[18]
从GCNNs的结构图中可以看出,完整的GCNNs包含输入层、隐藏层和输出层,它的层与层之间的传播方式可以表述为
H ( l + 1 ) = σ [ D ˜ - 1 2 A ˜ D ˜ - 1 2 H ( l ) W ( l ) ]
其中 A ˜ = A + I
D ˜ = A ˜ i j
式中:I为单位矩阵; D ˜ A ˜的度矩阵;H为每一层节点的特征向量矩阵;σ为非线性激活函数; W ( l )为当前层卷积的可训练的参数矩阵[19]l为网络层的标号。
本文所采用的完整的电能质量扰动分类方法的流程如图3所示,从图中可看出主要的步骤有原始PQD信号的预处理、PQD信号的图形化转换、对图片的训练和分类。
第一步是将不同的PQD扰动信号进行归一化处理以及极坐标的转化,完成了数据预处理。由于原始的PQD信号是基于时序特征的一维数据,不同种类的PQD信号种类繁多且不同种类的扰动又可以相互叠加仅依靠时序特征很难直接进行辨识和分类,需要进行进一步处理。
第二步是将处理过的PQD信号通过GAF矩阵进行图形化转换,完成一维的PQD信号到二维图形的构建。经过转化后的二维PQD图片集包含了原始信号的时序特征,又包含了不同扰动类型的空间特征。在GCNNs结构中对平移、比例缩放、倾斜或者其他形式的变形具有高度不变性。而且卷积神经网络采用原始图像作为输入,可以有效地从大量样本中学习到相应的特征,避免了复杂的特征提取过程。
第三步采用GCNNs对图形化的PQD信号进行训练和分类。将不同类型的PQD图片输入到GCNNs中,经过模型中的卷积层、池化层和全连接层,完成图形特征的提取、训练和分类,并通过全连接层来完成最终不同PQD图片的分类。
理想情况下的电能质量扰动信号有电压暂降、电压暂升、电压中断、振荡暂态、谐波、电压尖峰、电压缺口等单一扰动源,但是在实际电网中由于新能源系统中的发电侧和用电侧都存在不同类型的扰动源,且不同程度的扰动信号可以在系统中传播、叠加、耦合[20],因此会产生新的扰动类型,例如包含两种形式的复合电能质量扰动信号:暂降加振荡、暂升加振荡、暂降加脉冲、暂升加脉冲。
在实际的电力系统中由于电能质量问题都是暂态问题,很难直接获取其实际数据。因此,本文采用包含39节点的IEEE-39系统模型仿真不同类型的PQD信号,IEEE-39节点系统又称为新英格兰39节点系统(EN39BS),该基准网络配置于美国新英格兰地区,由39条母线组成,包含了10个发电机母线和19个负荷母线,广泛应用于小信号稳定性分析、动态稳定性分析、电能质量分析与控制等领域[21],拓扑结构如图4所示。
本文通过Matlab搭建的IEEE-39节点仿真模型进行实验。不同类型的扰动波形可通过注入不同的扰动函数来获取[22],不同类型的单一电能质量扰动函数和复合扰动函数详见文献[10]中所述。
在仿真模型搭建完成后,设置相应的节点参数并在模型的节点输入不同PQD信号的数学模型,仿真频率保持与实际系统一致,波形数据经过归一化处理,并设置合理的仿真周期。在模型末端布置示波器,典型的单一电能质量扰动信号波形和复合电能质量扰动波形如图5所示。
将上述不同PQD信号通过图1所示的方法进行图形化转换,生成的不同类型的PQD图片,分别对应于图6所示。
经过图片化的转化之后需要设计适应该图片结构的GCNNs,并利用该网络对生成的图片进行训练和测试,本文将生成图片的70%作为训练集、30%作为测试集。
GCNNs的内部结构及内部的运算过程如表1所示,为了尽可能地保证图片的图形特征和减少网络的运算时间,图片像素被设置为256×256大小。
表1中,Ks为最大池化窗口大小;s为步长,本文的软件部分基于Python中的pytorch模块完成,硬件部分基于Intel(R) Core(TM) i5-10210U CPU @1.60 GHz 2.11 GHz平台完成。
在完成相关参数设置、迭代运行后,演算过程如图7所示。可以看到,当迭代次数达到一定次数后模型开始收敛,说明所设计的系统是稳定的。
为了更加全面地分析该方法的分类结果,而不仅仅使用分类准确率来评判,本文采用混淆矩阵作为评判标准对分类的结果进行评判。通过对数据的可视化分析,上述分类后的混淆矩阵如图8所示。评价指标P代表准确率(precision),R代表召回率(recall),Fscore 代表准确率和召回率的调和平均评估指标,计算公式分别如下:
P = T p T p + F p
R = T N T N + F N
F s c o r e = 2 × P × R P + R
式中: T p为实际上是正类,被预测也为正类的数量; T N为实际上是负类,被预测也为负类的数量; F p为实际上是负类,但是被预测为正类的数量; F N为实际上是正类,但是被预测为负类的数量[21]
图8可知,不同PQD的二维图片的整体分类准确率在98%,相对于直接采用原始一维PQD型号的分类效果有了明显的改善。
为了验证本文所提方法对于PQD分类的提升效果,在采用相同实验平台和相同参数设置的基础上,对比分析了现有典型的PQD分类方法的分类效果,并且在理想原始PQD信号的基础上增加了15 dB和30 dB的噪声环境下的分类效果,分类效果如表2所示。
表2可以看出,在只存在单一扰动源的情况下,本文所提方法与一维卷积神经网络的识别率相近。但是,当存在复合扰动时候,本文所提方法相较于其他两种方法有着明显的提升效果,这是因为复合PQD信号实际上是两种或者两种以上的单一PQD信号的耦合叠加,一维卷积神经网路只能提取其时间特征序列,丢失了耦合之后的空间相关性特征序列。本文一方面采用图形化的方法将一维PQD信号转化为二维图片,不仅包含了不同PQD信号的时间序列特征,还包含了空间序列特征;另一方面所采用的GCNNs网络能够有效提取不同PQD信号的图形特征,并有着不错的聚类效果,在现有电能质量扰动类型更加复杂的电网环境中有着较好的适应能力。
本文结合现有电力系统中电能质量扰动种类和数量不断增加的情况,提出了一种基于GAF和GCNNs的PQD分类方法,将原始基于时间特征序列的一维PQD信号转化为二维具有空间特征的图片,并采用GCNNs进行训练和分类。最后在39节点的IEEE-39系统模型中仿真不同类型的PQD波形,并对所提方法进行验证计算,结果表明:所提方法有着有效的分类效果,尤其对于复合PQD的分类,相较于其他分类方法有着更加出色的分类效果。
  • 国网江苏省电力有限公司科技项目(J2019124)
参考文献 引证文献
排序方式:
[1]
王燕. 电能质量扰动检测的研究综述[J]. 电力系统保护与控制, 2021, 49(13):174-186.
WANG Yan. Review of research development in power quality disturbance detection[J]. Power System Protection and Control, 2021, 49(13):174-186.
[2]
朱永强, 李翔宇, 夏瑞华. 电能质量讲座第一讲新能源并网引起电能质量问题综述[J]. 电器与能效管理技术, 2017(21):62-66.
ZHU Yongqiang, LI Xiangyu, XIA Ruihua. Review of power quality problems caused by new energy grid-connected[J]. Electrical & Energy Management Technology, 2017(21):62-66.
[3]
汪飞, 全晓庆, 任林涛. 电能质量扰动检测与识别方法研究综述[J]. 中国电机工程学报, 2021, 41(12):4104-4121.
WANG Fei, QUAN Xiaoqing, REN Lintao. Review of power quality disturbance detection and identification methods[J]. Proceedings of the CSEE, 2021, 41(12):4104-4121.
[4]
POISSON O, RIOUAL P, MEUNIER M. Detection and measurement of power quality disturbances using wavelet transform[J]. IEEE Transactions on Power Delivery, 2000, 15(3):1039-1044.
[5]
KHOKHAR S, ZIN A A B M, MOKHTAR A S B, et al. A comprehensive overview on signal processing and artificial intelligence techniques applications in classification of power quality disturbances[J]. Renewable and Sustainable Energy Reviews, 2015,51:1650-1663.
[6]
JANIK P, LOBOS T. Automated classification of power-quality disturbances using SVM and RBF networks[J]. IEEE Transactions on Power Delivery, 2006, 21(3):1663-1669.
[7]
陈子璇, 席燕辉, 沈银. 基于卡尔曼滤波和深度置信网络的复合电能质量扰动分类[J]. 电力系统保护与控制, 2022, 50(7):81-90.
CHEN Zixuan, XI Yanhui, SHEN Yin. Recognition of multiple power quality disturbances based on a Kalman filter and deep belief network[J]. Power System Protection and Control, 2022, 50(7):81-90.
[8]
刘烨, 程杉, 王瑞, 等. 基于小波降噪和深度学习的电能质量扰动分类方法[J]. 电力系统及其自动化学报, 2022, 34(11):17-23.
LIU Ye, CHENG Shan, WANG Rui, et al. Power quality disturbance classification method based on wavelet denoising and deep learning[J]. Proceedings of the CSU-EPSA, 2022, 34(11):17-23.
[9]
吴建章, 沙浩源, 张宸宇, 等. 基于PSO-SVM的直流配电网电能质量扰动辨识[J]. 电力工程技术, 2019, 38(4):18-25.
WU Jianzhang, SHA Haoyuan, ZHANG Chenyu, et al. Identification of power quality disturbance in DC distribution network based on PSO-SVM[J]. Electric Power Engineering Technology, 2019, 38(4):18-25.
[10]
王维博, 张斌, 曾文入, 等. 基于特征融合一维卷积神经网络的电能质量扰动分类[J]. 电力系统保护与控制, 2020, 48(6):53-60.
WANG Weibo, ZHANG Bin, ZENG Wenru, et al. Power quality disturbance classification of one-dimensional convolutional neural networks based on feature fusion[J]. Power System Protection and Control, 2020, 48(6):53-60.
[11]
曹梦舟, 张艳. 基于卷积-长短期记忆网络的电能质量扰动分类[J]. 电力系统保护与控制, 2020, 48(2):86-92.
CAO Mengzhou, ZHANG Yan. Classification for power quality disturbances based on CNN-LSTM network[J]. Power System Protection and Control, 2020, 48(2):86-92.
[12]
KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[C]// ICLR, 2017.
[13]
ZHANG S, TONG H, XU J, et al. Graph convolutional networks:a comprehensive review[J]. Computational Social Networks, 2019, 6(1):1-23.
[14]
DRINEAS P, MAHONEY M W, CRISTIANINI N. On the nyström method for approximating a gram matrix for improved Kernel-based learning[J]. Journal of Machine Learning Research, 2005, 6(12):2153-2175.
[15]
DE ALMEIDA M C, ASADA E N, GARCIA A V. On the use of Gram matrix in observability analysis[J]. IEEE Transactions on Power Systems, 2008, 23(1):249-251.
[16]
STARK C. Self-consistent tomography of the state-measurement gram matrix[J]. Physical Review A, 2014, 89(5):052109.
[17]
XU J, TANG X, ZHU Y, et al. SGMNet:learning rotation-invariant point cloud representations via sorted gram matrix[C]// Proceedings of the IEEE/CVF International Conference on Computer Vision,2021:10468-10477.
[18]
ZHUANG C, QIANG M. Dual graph convolutional networks for graph-based semi-supervised classification[C]// The 2018 World Wide Web Conference,2018:499-508.
[19]
刘菡, 王英男, 李新利, 等. 基于互信息-图卷积神经网络的燃煤电站NOx排放预测[J]. 中国电机工程学报, 2022, 42(3):1052-1060.
LIU Han, WANG Yingnan, LI Xinli, et al. Prediction of NOx emissions of coal-fired power plants based on mutual information-graph convolutional neural network[J]. Proceedings of the CSEE, 2022, 42(3):1052-1060.
[20]
龚正, 邹阳, 金涛, 等. 基于特征融合并行优化模型的电能质量扰动分类方法[J]. 中国电机工程学报, 2023, 43(3):1017-1026.
GONG Zheng, ZOU Yang, JIN Tao, et al. Classification method of power quality disturbances based on optimized parallel model of features merging[J]. Proceedings of the CSEE, 2023, 43(3):1017-1026.
[21]
MA J, ZHANG J, XIAO L, et al. Classification of power qua-lity disturbances via deep learning[J]. IETE Technical Review, 2017, 34(4):408-415.
[22]
JANIK P, LOBOS T. Automated classification of power-quality disturbances using SVM and RBF networks[J]. IEEE Transactions on Power Delivery, 2006, 21(3):1663-1669.
2024年第54卷第3期
PDF下载
140
66
引用本文
BibTeX
文章信息
doi: 10.19457/j.1001-2095.dqcd24578
  • 接收时间:2022-08-22
  • 首发时间:2025-12-12
  • 出版时间:2024-03-20
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2022-08-22
  • 修回日期:2022-10-20
基金
国网江苏省电力有限公司科技项目(J2019124)
作者信息
    1 深圳供电局有限公司,广东 深圳 310030
    2 国家电网江苏省电力有限公司,江苏 苏州 215000
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/dqcd/CN/10.19457/j.1001-2095.dqcd24578
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