Article(id=1192851113620685486, tenantId=1146029695717560320, journalId=1189987059142926344, issueId=1192851112039432863, articleNumber=null, orderNo=null, doi=10.19457/j.1001-2095.dqcd24762, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1668009600000, receivedDateStr=2022-11-10, revisedDate=1673020800000, revisedDateStr=2023-01-07, acceptedDate=null, acceptedDateStr=null, onlineDate=1762327467588, onlineDateStr=2025-11-05, pubDate=1726761600000, pubDateStr=2024-09-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1762327467588, onlineIssueDateStr=2025-11-05, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1762327467588, creator=13701087609, updateTime=1762327467588, updator=13701087609, issue=Issue{id=1192851112039432863, tenantId=1146029695717560320, journalId=1189987059142926344, year='2024', volume='54', issue='9', pageStart='3', pageEnd='96', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1762327467211, creator=13701087609, updateTime=1762328208012, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1192854219242750227, tenantId=1146029695717560320, journalId=1189987059142926344, issueId=1192851112039432863, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1192854219246944532, tenantId=1146029695717560320, journalId=1189987059142926344, issueId=1192851112039432863, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=83, endPage=89, ext={EN=ArticleExt(id=1192851113801040560, articleId=1192851113620685486, tenantId=1146029695717560320, journalId=1189987059142926344, language=EN, title=Vibration Diagnosis Method of Reactor Mechanical Fault Based on Stacked Auto-encoder, columnId=null, journalTitle=Electric Drive, columnName=null, runingTitle=null, highlight=null, articleAbstract=

In order to improve the accuracy of intelligent diagnosis of reactor mechanical fault,according to the correlation characteristics between reactor vibration signal and mechanical state,a vibration diagnosis method of reactor mechanical fault based on stacked auto-encoder(SAE) was proposed. Firstly,the original vibration signal of reactor was decomposed by wavelet packet decomposition algorithm,and the time-frequency energy matrix of the signal was extracted. Then,the diagnosis model of reactor mechanical fault based on SAE was built,the deep feature mining of the time-frequency energy matrix was completed through unsupervised self-learning,and the identification of reactor mechanical fault was realized through supervised fine-tuning. Finally,vibration data of 10 kV oil immersed reactor under different mechanical states was used to train the fault identification model and optimize the super parameters. The numerical results show that the proposed method can identify reactor mechanical fault better than the traditional vibration signal identification method,and the accuracy can reach 98%.

, 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=Jinwei LIU, Jie ZHOU, Chuan LI, Xiao XIAO, Huicheng WU), CN=ArticleExt(id=1192851317178647273, articleId=1192851113620685486, tenantId=1146029695717560320, journalId=1189987059142926344, language=CN, title=基于深度稀疏自编码器的电抗器机械故障振动诊断方法, columnId=1190325456588079763, journalTitle=电气传动, columnName=可靠性与诊断, runingTitle=null, highlight=null, articleAbstract=

为提高电抗器机械故障智能诊断的准确性,基于电抗器振动信号与机械状态之间的关联特性和规律,提出了一种基于深度稀疏自编码器(SAE)的电抗器机械故障振动诊断方法。首先,采用小波包分解算法对电抗器原始振动信号进行分解,提取信号的时频能量矩阵;然后,构建基于SAE网络的电抗器机械故障诊断模型,通过无监督自学习和有监督微调完成时频能量矩阵深层特征挖掘和电抗器机械故障识别分类;最后,以某10 kV油浸式电抗器为试验对象,使用不同机械状态下的振动数据对故障识别模型进行训练优化。算例结果表明,相比于传统振动诊断方法,所提方法能够更好地对电抗器机械故障进行识别分类,准确率可达98%。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=Vt6tFLxXrotPksVcza2YFQ==, magXml=EcfxVdWTq9YDCwptfA+5yw==, pdfUrl=null, pdf=vQmh6Gq9YWPAyjBRoMbuXA==, pdfFileSize=1799070, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=zzNja3mwXmOPqdeJ+KSA6A==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=PnrKWVByuibf0r2mitgzLQ==, mapNumber=null, authorCompany=null, fund=null, authors=

刘锦伟(1990—),男,硕士,工程师,主要研究方向为电力设备检修,Email:

, authorsList=刘锦伟, 周杰, 李川, 肖潇, 伍惠铖)}, authors=[Author(id=1195783831983800869, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=597229377@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1195783832080269864, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, authorId=1195783831983800869, language=EN, stringName=Jinwei LIU, firstName=Jinwei, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=State Grid Jiangxi Electric Power Company Yichun Power Supply Company, Yichun 336000,Jiangxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1195783832172544553, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, authorId=1195783831983800869, language=CN, stringName=刘锦伟, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=国网江西省电力有限公司宜春供电分公司, 江西 宜春 336000, bio={"content":"

刘锦伟(1990—),男,硕士,工程师,主要研究方向为电力设备检修,Email:

"}, bioImg=null, bioContent=

刘锦伟(1990—),男,硕士,工程师,主要研究方向为电力设备检修,Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1195783831891526177, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, xref=null, ext=[AuthorCompanyExt(id=1195783831899914786, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, companyId=1195783831891526177, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Grid Jiangxi Electric Power Company Yichun Power Supply Company, Yichun 336000,Jiangxi, China), AuthorCompanyExt(id=1195783831908303395, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, companyId=1195783831891526177, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=国网江西省电力有限公司宜春供电分公司, 江西 宜春 336000)])]), Author(id=1195783832239653419, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, 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=1195783832327733805, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, authorId=1195783832239653419, language=EN, stringName=Jie ZHOU, firstName=Jie, middleName=null, lastName=ZHOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=State Grid Jiangxi Electric Power Company Yichun Power Supply Company, Yichun 336000,Jiangxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1195783832411619886, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, authorId=1195783832239653419, language=CN, stringName=周杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=国网江西省电力有限公司宜春供电分公司, 江西 宜春 336000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1195783831891526177, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, xref=null, ext=[AuthorCompanyExt(id=1195783831899914786, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, companyId=1195783831891526177, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Grid Jiangxi Electric Power Company Yichun Power Supply Company, Yichun 336000,Jiangxi, China), AuthorCompanyExt(id=1195783831908303395, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, companyId=1195783831891526177, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=国网江西省电力有限公司宜春供电分公司, 江西 宜春 336000)])]), Author(id=1195783832495505968, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, 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=1195783832642306610, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, authorId=1195783832495505968, language=EN, stringName=Chuan LI, firstName=Chuan, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=State Grid Jiangxi Electric Power Company Yichun Power Supply Company, Yichun 336000,Jiangxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1195783832717804083, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, authorId=1195783832495505968, language=CN, stringName=李川, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=国网江西省电力有限公司宜春供电分公司, 江西 宜春 336000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1195783831891526177, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, xref=null, ext=[AuthorCompanyExt(id=1195783831899914786, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, companyId=1195783831891526177, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Grid Jiangxi Electric Power Company Yichun Power Supply Company, Yichun 336000,Jiangxi, China), AuthorCompanyExt(id=1195783831908303395, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, companyId=1195783831891526177, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=国网江西省电力有限公司宜春供电分公司, 江西 宜春 336000)])]), Author(id=1195783832776524341, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, 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=1195783832847827511, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, authorId=1195783832776524341, language=EN, stringName=Xiao XIAO, firstName=Xiao, middleName=null, lastName=XIAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=State Grid Jiangxi Electric Power Company Yichun Power Supply Company, Yichun 336000,Jiangxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1195783832919130680, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, authorId=1195783832776524341, language=CN, stringName=肖潇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=国网江西省电力有限公司宜春供电分公司, 江西 宜春 336000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1195783831891526177, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, xref=null, ext=[AuthorCompanyExt(id=1195783831899914786, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, companyId=1195783831891526177, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Grid Jiangxi Electric Power Company Yichun Power Supply Company, Yichun 336000,Jiangxi, China), AuthorCompanyExt(id=1195783831908303395, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, companyId=1195783831891526177, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=国网江西省电力有限公司宜春供电分公司, 江西 宜春 336000)])]), Author(id=1195783833023988282, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, 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=1195783833166594620, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, authorId=1195783833023988282, language=EN, stringName=Huicheng WU, firstName=Huicheng, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=State Grid Jiangxi Electric Power Company Yichun Power Supply Company, Yichun 336000,Jiangxi, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1195783833229509181, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, authorId=1195783833023988282, language=CN, stringName=伍惠铖, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=国网江西省电力有限公司宜春供电分公司, 江西 宜春 336000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1195783831891526177, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, xref=null, ext=[AuthorCompanyExt(id=1195783831899914786, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, companyId=1195783831891526177, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Grid Jiangxi Electric Power Company Yichun Power Supply Company, Yichun 336000,Jiangxi, China), AuthorCompanyExt(id=1195783831908303395, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, companyId=1195783831891526177, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=国网江西省电力有限公司宜春供电分公司, 江西 宜春 336000)])])], keywords=[Keyword(id=1195783833359532606, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=EN, orderNo=1, keyword=reactor), Keyword(id=1195783833426641471, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=EN, orderNo=2, keyword=mechanical failure), Keyword(id=1195783833518916160, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=EN, orderNo=3, keyword=vibration signal), Keyword(id=1195783833577636417, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=EN, orderNo=4, keyword=wavelet packet decomposition), Keyword(id=1195783833632162370, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=EN, orderNo=5, keyword=stacked auto-encoder(SAE)), Keyword(id=1195783833707659843, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=CN, orderNo=1, keyword=电抗器), Keyword(id=1195783833795740228, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=CN, orderNo=2, keyword=机械故障), Keyword(id=1195783833858654789, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=CN, orderNo=3, keyword=振动信号), Keyword(id=1195783833963512390, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=CN, orderNo=4, keyword=小波包分解), Keyword(id=1195783834018038343, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=CN, orderNo=5, keyword=深度稀疏自编码器)], refs=[Reference(id=1195783836840804953, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=6, pageStart=69, pageEnd=75, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=刘宏, 梁基重, 牛曙, journalName=电力电容器与无功补偿, refType=null, unstructuredReference=刘宏, 梁基重, 牛曙, 等. 匝间短路故障下干式空心电抗器振动特性研究[J]. 电力电容器与无功补偿, 2022, 42(6):69-75., articleTitle=匝间短路故障下干式空心电抗器振动特性研究, refAbstract=null), Reference(id=1195783836899525210, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=6, pageStart=69, pageEnd=75, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=LIU Hong, LIANG Jizhong, NIU Shu, journalName=Power Capacitor & Reactive Power Compensation, refType=null, unstructuredReference=LIU Hong, LIANG Jizhong, NIU Shu, et al. Study on vibration characteristics of dry-type air-core reactor under interturn short circuit fault[J]. Power Capacitor & Reactive Power Compensation, 2022, 42(6):69-75., articleTitle=Study on vibration characteristics of dry-type air-core reactor under interturn short circuit fault, refAbstract=null), Reference(id=1195783836958245467, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=37, issue=9, pageStart=2190, pageEnd=2198, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=王革鹏, 金文德, 曾向阳, journalName=电工技术学报, refType=null, unstructuredReference=王革鹏, 金文德, 曾向阳, 等. 特高压并联电抗器铁心振动的分析与控制研究[J]. 电工技术学报, 2022, 37(9):2190-2198., articleTitle=特高压并联电抗器铁心振动的分析与控制研究, refAbstract=null), Reference(id=1195783837042131548, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=37, issue=9, pageStart=2190, pageEnd=2198, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=WANG Gepeng, JIN Wende, ZENG Xiangyang, journalName=Transactions of China Electrotechnical Society, refType=null, unstructuredReference=WANG Gepeng, JIN Wende, ZENG Xiangyang, et al. Analysis and control research on core vibration of UHV shunt reactor[J]. Transactions of China Electrotechnical Society, 2022, 37(9):2190-2198., articleTitle=Analysis and control research on core vibration of UHV shunt reactor, refAbstract=null), Reference(id=1195783837109240413, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=5, pageStart=204, pageEnd=211, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=马宏忠, 侯鹏飞, 严岩, journalName=电力自动化设备, refType=null, unstructuredReference=马宏忠, 侯鹏飞, 严岩, 等. 高压电抗器绕组和铁芯机械故障的混沌特性分析与特征识别[J]. 电力自动化设备, 2022, 42(5):204-211., articleTitle=高压电抗器绕组和铁芯机械故障的混沌特性分析与特征识别, refAbstract=null), Reference(id=1195783837214098014, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=5, pageStart=204, pageEnd=211, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=MA Hongzhong, HOU Pengfei, YAN Yan, journalName=Electric Power Automation Equipment, refType=null, unstructuredReference=MA Hongzhong, HOU Pengfei, YAN Yan, et al. Chaotic characteristic analysis and feature recognition of mechanical failure of high voltage reactor winding and iron core[J]. Electric Power Automation Equipment, 2022, 42(5):204-211., articleTitle=Chaotic characteristic analysis and feature recognition of mechanical failure of high voltage reactor winding and iron core, refAbstract=null), Reference(id=1195783837310567007, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=37, issue=9, pageStart=2179, pageEnd=2189, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=高树国, 汲胜昌, 孟令明, journalName=电工技术学报, refType=null, unstructuredReference=高树国, 汲胜昌, 孟令明, 等. 基于在线监测系统与声振特征预测模型的高压并联电抗器运行状态评估方法[J]. 电工技术学报, 2022, 37(9):2179-2189., articleTitle=基于在线监测系统与声振特征预测模型的高压并联电抗器运行状态评估方法, refAbstract=null), Reference(id=1195783837423813216, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=37, issue=9, pageStart=2179, pageEnd=2189, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=GAO Shuguo, JI Shengchang, MENG Lingming, journalName=Transactions of China Electrotechnical Society, refType=null, unstructuredReference=GAO Shuguo, JI Shengchang, MENG Lingming, et al. Operation state evaluation method of high-voltage shunt reactor based on on-line monitoring system and vibro-acoustic characteristic prediction model[J]. Transactions of China Electrotechnical Society, 2022, 37(9):2179-2189., articleTitle=Operation state evaluation method of high-voltage shunt reactor based on on-line monitoring system and vibro-acoustic characteristic prediction model, refAbstract=null), Reference(id=1195783837503504993, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=16, pageStart=5960, pageEnd=5970, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=高璐, 汲胜昌, 祝令瑜, journalName=中国电机工程学报, refType=null, unstructuredReference=高璐, 汲胜昌, 祝令瑜, 等. 高压换流站干式空心电抗器的振动产生机理及影响因素研究[J]. 中国电机工程学报, 2022, 42(16):5960-5970,6170., articleTitle=高压换流站干式空心电抗器的振动产生机理及影响因素研究, refAbstract=null), Reference(id=1195783837562225250, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=16, pageStart=5960, pageEnd=5970, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=GAO Lu, JI Shengchang, ZHU Lingyu, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=GAO Lu, JI Shengchang, ZHU Lingyu, et al. Study on vibration mechanism and impact factors of dry-type air-core reactor in HVDC converter stations[J]. Proceedings of the CSEE, 2022, 42(16):5960-5970,6170., articleTitle=Study on vibration mechanism and impact factors of dry-type air-core reactor in HVDC converter stations, refAbstract=null), Reference(id=1195783837729997411, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=8, pageStart=3201, pageEnd=3209, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=祝令瑜, 杜一鸣, 高璐, journalName=高电压技术, refType=null, unstructuredReference=祝令瑜, 杜一鸣, 高璐, 等. 不同频率激励下干式空心电抗器匝间绝缘缺陷振动分布特性[J]. 高电压技术, 2022, 48(8):3201-3209., articleTitle=不同频率激励下干式空心电抗器匝间绝缘缺陷振动分布特性, refAbstract=null), Reference(id=1195783837792911972, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=8, pageStart=3201, pageEnd=3209, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=ZHU Lingyu, DU Yiming, GAO Lu, journalName=High Voltage Engineering, refType=null, unstructuredReference=ZHU Lingyu, DU Yiming, GAO Lu, et al. Vibration distribution characteristics of dry-type air-core reactor with turn-to-turn insulation defects excited by different frequencies[J]. High Voltage Engineering, 2022, 48(8):3201-3209., articleTitle=Vibration distribution characteristics of dry-type air-core reactor with turn-to-turn insulation defects excited by different frequencies, refAbstract=null), Reference(id=1195783837855826533, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2017, volume=54, issue=19, pageStart=117, pageEnd=122, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=钱国超, 于虹, 邹德旭, journalName=电测与仪表, refType=null, unstructuredReference=钱国超, 于虹, 邹德旭, 等. 振动频谱特征值在诊断变压器故障中的应用研究[J]. 电测与仪表, 2017, 54(19):117-122., articleTitle=振动频谱特征值在诊断变压器故障中的应用研究, refAbstract=null), Reference(id=1195783837931324006, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2017, volume=54, issue=19, pageStart=117, pageEnd=122, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=QIAN Guochao, YU Hong, ZOU Dexu, journalName=Electrical Measurement & Instrumentation, refType=null, unstructuredReference=QIAN Guochao, YU Hong, ZOU Dexu, et al. Research on spectrum eigenvalues of transformer vibration and its application on diagnosis[J]. Electrical Measurement & Instrumentation, 2017, 54(19):117-122., articleTitle=Research on spectrum eigenvalues of transformer vibration and its application on diagnosis, refAbstract=null), Reference(id=1195783837998432871, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2014, volume=66, issue=6, pageStart=256, pageEnd=266, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=PAUL O I, LU Yonghua, journalName=App-lied Mechanics and Materials, refType=null, unstructuredReference=PAUL O I, LU Yonghua. Vibration monitoring using wavelets transform feature extraction algorithm and technique[J]. App-lied Mechanics and Materials, 2014, 66(6):256-266., articleTitle=Vibration monitoring using wavelets transform feature extraction algorithm and technique, refAbstract=null), Reference(id=1195783838120067688, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2020, volume=48, issue=17, pageStart=68, pageEnd=76, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=赵若妤, 马宏忠, 魏旭, journalName=电力系统保护与控制, refType=null, unstructuredReference=赵若妤, 马宏忠, 魏旭, 等. 基于 EWT 及多尺度形态谱的高压并联电抗器故障诊断研究[J]. 电力系统保护与控制, 2020, 48(17):68-76., articleTitle=基于 EWT 及多尺度形态谱的高压并联电抗器故障诊断研究, refAbstract=null), Reference(id=1195783838191370857, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=17, pageStart=68, pageEnd=76, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=ZHAO Ruoyu, MA Hongzhong, WEI Xu, journalName=Power System Protection and Control, refType=null, unstructuredReference=ZHAO Ruoyu, MA Hongzhong, WEI Xu, et al. Research on fault diagnosis of a high voltage shunt reactor based on EWT and multiscale spectral spectrum[J]. Power System Protection and Control, 2022, 48(17):68-76., articleTitle=Research on fault diagnosis of a high voltage shunt reactor based on EWT and multiscale spectral spectrum, refAbstract=null), Reference(id=1195783838266868330, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=11, pageStart=42, pageEnd=49, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=高树国, 张明文, 吴书煜, journalName=振动与冲击, refType=null, unstructuredReference=高树国, 张明文, 吴书煜, 等. 基于振动感知的油浸式电抗器松动故障检测方法[J]. 振动与冲击, 2022, 41(11):42-49., articleTitle=基于振动感知的油浸式电抗器松动故障检测方法, refAbstract=null), Reference(id=1195783838354948715, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=11, pageStart=42, pageEnd=49, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=GAO Shuguo, ZHANG Mingwen, WU Shuyu, journalName=Journal of Vibration and Shock, refType=null, unstructuredReference=GAO Shuguo, ZHANG Mingwen, WU Shuyu, et al. Loose fault detection method of oil immersed reactor based on vibration perception[J]. Journal of Vibration and Shock, 2022, 41(11):42-49., articleTitle=Loose fault detection method of oil immersed reactor based on vibration perception, refAbstract=null), Reference(id=1195783838447223404, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2020, volume=50, issue=9, pageStart=99, pageEnd=114, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=张育炜, 石琦, 武恩光, journalName=电气传动, refType=null, unstructuredReference=张育炜, 石琦, 武恩光. 基于支持向量机GIS局放小波包能量谱故障诊断[J]. 电气传动, 2020, 50(9):99-114., articleTitle=基于支持向量机GIS局放小波包能量谱故障诊断, refAbstract=null), Reference(id=1195783841370653293, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2020, volume=50, issue=9, pageStart=99, pageEnd=114, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=ZHANG Yuwei, SHI Qi, WU Enguang, journalName=Electric Drive, refType=null, unstructuredReference=ZHANG Yuwei, SHI Qi, WU Enguang. Fault diagnosis of wavelet packet energy spectrum of partial discharge pulse in GIS based on support vector machine[J]. Electric Drive, 2020, 50(9):99-114., articleTitle=Fault diagnosis of wavelet packet energy spectrum of partial discharge pulse in GIS based on support vector machine, refAbstract=null), Reference(id=1195783841446150766, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2016, volume=42, issue=8, pageStart=2625, pageEnd=2632, url=null, language=null, rfNumber=[12], rfOrder=21, authorNames=吴晓文, 周年光, 裴春明, journalName=高电压技术, refType=null, unstructuredReference=吴晓文, 周年光, 裴春明, 等. 特高压交流变电站可听噪声分离方法[J]. 高电压技术, 2016, 42(8):2625-2632., articleTitle=特高压交流变电站可听噪声分离方法, refAbstract=null), Reference(id=1195783841509065327, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2016, volume=42, issue=8, pageStart=2625, pageEnd=2632, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=WU Xiaowen, ZHOU Nianguang, PEI Chunming, journalName=High Voltage Engineering, refType=null, unstructuredReference=WU Xiaowen, ZHOU Nianguang, PEI Chunming, et al. Separation methodology of audible noises of UHV AC substations[J]. High Voltage Engineering, 2016, 42(8):2625-2632., articleTitle=Separation methodology of audible noises of UHV AC substations, refAbstract=null), Reference(id=1195783841567785584, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=9, pageStart=331, pageEnd=336, url=null, language=null, rfNumber=[13], rfOrder=23, authorNames=张振海, 王维庆, 王海云, journalName=太阳能学报, refType=null, unstructuredReference=张振海, 王维庆, 王海云, 等. 基于改进小波包的风电机组齿轮箱复合故障特征提取研究[J]. 太阳能学报, 2022, 43(9):331-336., articleTitle=基于改进小波包的风电机组齿轮箱复合故障特征提取研究, refAbstract=null), Reference(id=1195783841639088753, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=9, pageStart=331, pageEnd=336, url=null, language=null, rfNumber=[13], rfOrder=24, authorNames=ZHANG Zhenhai, WANG Weiqing, WANG Haiyun, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=ZHANG Zhenhai, WANG Weiqing, WANG Haiyun, et al. Research of composite fault feature extraction of wind turbine gearbox based on improved wavelet packet[J]. Acta Energiae Solaris Sinica, 2022, 43(9):331-336., articleTitle=Research of composite fault feature extraction of wind turbine gearbox based on improved wavelet packet, refAbstract=null), Reference(id=1195783841697809010, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=52, issue=14, pageStart=70, pageEnd=74, url=null, language=null, rfNumber=[14], rfOrder=25, authorNames=任巍, 翟博豪, 彭炜淞, journalName=电气传动, refType=null, unstructuredReference=任巍, 翟博豪, 彭炜淞. 基于半监督堆叠自编码器的轧制力预报建模研究[J]. 电气传动, 2022, 52(14):70-74,80., articleTitle=基于半监督堆叠自编码器的轧制力预报建模研究, refAbstract=null), Reference(id=1195783841764917875, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2022, volume=52, issue=14, pageStart=70, pageEnd=74, url=null, language=null, rfNumber=[14], rfOrder=26, authorNames=REN Wei, ZHAI Bohao, PENG Weisong, journalName=Electric Drive, refType=null, unstructuredReference=REN Wei, ZHAI Bohao, PENG Weisong. Rolling force prediction modeling based on semi-supervised stacked autoencoder[J]. Electric Drive, 2022, 52(14):70-74,80., articleTitle=Rolling force prediction modeling based on semi-supervised stacked autoencoder, refAbstract=null), Reference(id=1195783841827832436, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=9, pageStart=218, pageEnd=230, url=null, language=null, rfNumber=[15], rfOrder=27, authorNames=来杰, 王晓丹, 向前, journalName=通信学报, refType=null, unstructuredReference=来杰, 王晓丹, 向前, 等. 自编码器及其应用综述[J]. 通信学报, 2021, 42(9):218-230., articleTitle=自编码器及其应用综述, refAbstract=null), Reference(id=1195783841882358389, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=9, pageStart=218, pageEnd=230, url=null, language=null, rfNumber=[15], rfOrder=28, authorNames=LAI Jie, WANG Xiaodan, XIANG Qian, journalName=Journal on Communications, refType=null, unstructuredReference=LAI Jie, WANG Xiaodan, XIANG Qian, et al. Review on autoencoder and its application[J]. Journal on Communications, 2021, 42(9):218-230., articleTitle=Review on autoencoder and its application, refAbstract=null), Reference(id=1195783841953661558, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2020, volume=56, issue=9, pageStart=46, pageEnd=53, url=null, language=null, rfNumber=[16], rfOrder=29, authorNames=解颖, 王丰华, 傅正财, journalName=高压电器, refType=null, unstructuredReference=解颖, 王丰华, 傅正财. 基于栈式自编码器的变压器机械故障诊断[J]. 高压电器, 2020, 56(9):46-53., articleTitle=基于栈式自编码器的变压器机械故障诊断, refAbstract=null), Reference(id=1195783842083684983, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, doi=null, pmid=null, pmcid=null, year=2020, volume=56, issue=9, pageStart=46, pageEnd=53, url=null, language=null, rfNumber=[16], rfOrder=30, authorNames=XIE Ying, WANG Fenghua, FU Zhengcai, journalName=High Voltage Apparatus, refType=null, unstructuredReference=XIE Ying, WANG Fenghua, FU Zhengcai. Mechanical fault diagnosis of power transformer based on stacked auto encoder[J]. High Voltage Apparatus, 2020, 56(9):46-53., articleTitle=Mechanical fault diagnosis of power transformer based on stacked auto encoder, refAbstract=null)], funds=[Fund(id=1195783836631089752, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, awardId=5218M0220001, language=CN, fundingSource=国家电网科技项目(5218M0220001), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1195783831891526177, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, xref=null, ext=[AuthorCompanyExt(id=1195783831899914786, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, companyId=1195783831891526177, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Grid Jiangxi Electric Power Company Yichun Power Supply Company, Yichun 336000,Jiangxi, China), AuthorCompanyExt(id=1195783831908303395, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, companyId=1195783831891526177, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=国网江西省电力有限公司宜春供电分公司, 江西 宜春 336000)])], figs=[ArticleFig(id=1195783834169033288, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=EN, label=Fig.1, caption=Structure of auto-encoder, figureFileSmall=Bz97edActgy7RrP/ItyVMQ==, figureFileBig=5VL/MyDiOJRYqz7bLo85bg==, tableContent=null), ArticleFig(id=1195783834240336457, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=CN, label=图1, caption=自编码器的网络结构, figureFileSmall=Bz97edActgy7RrP/ItyVMQ==, figureFileBig=5VL/MyDiOJRYqz7bLo85bg==, tableContent=null), ArticleFig(id=1195783834311639626, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=EN, label=Fig.2, caption=Flow chart of fault diagnosis method, figureFileSmall=diwiTX61HcIyLf67GcYydQ==, figureFileBig=D+8yX4jmIH5483tuecMIjA==, tableContent=null), ArticleFig(id=1195783834408108619, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=CN, label=图2, caption=故障诊断方法流程图, figureFileSmall=diwiTX61HcIyLf67GcYydQ==, figureFileBig=D+8yX4jmIH5483tuecMIjA==, tableContent=null), ArticleFig(id=1195783834471023180, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=EN, label=Fig.3, caption=Test layout and measuring points location, figureFileSmall=DXQ5DPBMKlXVPQ8daY0LjQ==, figureFileBig=gnn2Oyb1wSFxvvYopwcUVw==, tableContent=null), ArticleFig(id=1195783834605240909, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=CN, label=图3, caption=试验布置及测点位置, figureFileSmall=DXQ5DPBMKlXVPQ8daY0LjQ==, figureFileBig=gnn2Oyb1wSFxvvYopwcUVw==, tableContent=null), ArticleFig(id=1195783834689126990, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=EN, label=Fig.4, caption=Reactor vibration signals in different mechanical states, figureFileSmall=mHpU8pOi6IbKGnXuqkze/A==, figureFileBig=Tti7EGz3BYIb4LL5Xrt5Yw==, tableContent=null), ArticleFig(id=1195783835767063119, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=CN, label=图4, caption=不同机械状态的电抗器振动信号, figureFileSmall=mHpU8pOi6IbKGnXuqkze/A==, figureFileBig=Tti7EGz3BYIb4LL5Xrt5Yw==, tableContent=null), ArticleFig(id=1195783835825783376, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=EN, label=Fig.5, caption=Eigenvector distribution of reactor vibration signal, figureFileSmall=mcXihv9fiKuXC4q+k3M1cQ==, figureFileBig=09hH1UWIJI9n/gUVlN6Dkg==, tableContent=null), ArticleFig(id=1195783835947418193, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=CN, label=图5, caption=电抗器振动信号特征向量分布, figureFileSmall=mcXihv9fiKuXC4q+k3M1cQ==, figureFileBig=09hH1UWIJI9n/gUVlN6Dkg==, tableContent=null), ArticleFig(id=1195783836052275794, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=EN, label=Fig.6, caption=Accuracy of SAE-softmax network with different hidden layers, figureFileSmall=T3wdLs9Nggt/IT1mzVpzQg==, figureFileBig=Ejd30GHKwGRy2l92Uqm1mw==, tableContent=null), ArticleFig(id=1195783836161327699, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=CN, label=图6, caption=不同隐含层数量的SAE-softmax网络的准确率, figureFileSmall=T3wdLs9Nggt/IT1mzVpzQg==, figureFileBig=Ejd30GHKwGRy2l92Uqm1mw==, tableContent=null), ArticleFig(id=1195783836308128340, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
运行状态 数据标签 训练集数量/个 测试集数量/个
测点1 测点2 测点3 测点4
正常运行 0 250 250 250 200
铁心松动 1 250 250 250 200
绕组松动 2 250 250 250 200
), ArticleFig(id=1195783836383625813, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=CN, label=表1, caption=

电抗器振动数据集样本分布 Tab.1 Sample distribution of reactor vibration data set

, figureFileSmall=null, figureFileBig=null, tableContent=
运行状态 数据标签 训练集数量/个 测试集数量/个
测点1 测点2 测点3 测点4
正常运行 0 250 250 250 200
铁心松动 1 250 250 250 200
绕组松动 2 250 250 250 200
), ArticleFig(id=1195783836454928982, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=EN, label=null, caption=null, figureFileSmall=null, figureFileBig=null, tableContent=
分类网络 收敛所需迭代次数 收敛所需时间/s 准确率/%
SVM 314 320.26 96.67
BP 536 559.46 94.44
AE 62 58.62 88.02
SAE 85 84.03 98.67
), ArticleFig(id=1195783836517843543, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1192851113620685486, language=CN, label=表2, caption=

不同网络的故障识别结果 Tab.2 Fault identification results corresponding to different networks

, figureFileSmall=null, figureFileBig=null, tableContent=
分类网络 收敛所需迭代次数 收敛所需时间/s 准确率/%
SVM 314 320.26 96.67
BP 536 559.46 94.44
AE 62 58.62 88.02
SAE 85 84.03 98.67
)], 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.dqcd24762, detailUrlEn=https://castjournals.cast.org.cn/joweb/dqcd/EN/10.19457/j.1001-2095.dqcd24762, pdfUrlCn=https://castjournals.cast.org.cn/joweb/dqcd/CN/PDF/10.19457/j.1001-2095.dqcd24762, pdfUrlEn=https://castjournals.cast.org.cn/joweb/dqcd/EN/PDF/10.19457/j.1001-2095.dqcd24762, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于深度稀疏自编码器的电抗器机械故障振动诊断方法
收藏切换
PDF下载
刘锦伟 , 周杰 , 李川 , 肖潇 , 伍惠铖
电气传动 | 可靠性与诊断 2024,54(9): 83-89
收起
收藏切换
电气传动 | 可靠性与诊断 2024, 54(9): 83-89
基于深度稀疏自编码器的电抗器机械故障振动诊断方法
全屏
刘锦伟 , 周杰, 李川, 肖潇, 伍惠铖
作者信息
  • 国网江西省电力有限公司宜春供电分公司, 江西 宜春 336000
  • 刘锦伟(1990—),男,硕士,工程师,主要研究方向为电力设备检修,Email:

Vibration Diagnosis Method of Reactor Mechanical Fault Based on Stacked Auto-encoder
Jinwei LIU , Jie ZHOU, Chuan LI, Xiao XIAO, Huicheng WU
Affiliations
  • State Grid Jiangxi Electric Power Company Yichun Power Supply Company, Yichun 336000,Jiangxi, China
出版时间: 2024-09-20 doi: 10.19457/j.1001-2095.dqcd24762
文章导航
收藏切换

为提高电抗器机械故障智能诊断的准确性,基于电抗器振动信号与机械状态之间的关联特性和规律,提出了一种基于深度稀疏自编码器(SAE)的电抗器机械故障振动诊断方法。首先,采用小波包分解算法对电抗器原始振动信号进行分解,提取信号的时频能量矩阵;然后,构建基于SAE网络的电抗器机械故障诊断模型,通过无监督自学习和有监督微调完成时频能量矩阵深层特征挖掘和电抗器机械故障识别分类;最后,以某10 kV油浸式电抗器为试验对象,使用不同机械状态下的振动数据对故障识别模型进行训练优化。算例结果表明,相比于传统振动诊断方法,所提方法能够更好地对电抗器机械故障进行识别分类,准确率可达98%。

电抗器  /  机械故障  /  振动信号  /  小波包分解  /  深度稀疏自编码器

In order to improve the accuracy of intelligent diagnosis of reactor mechanical fault,according to the correlation characteristics between reactor vibration signal and mechanical state,a vibration diagnosis method of reactor mechanical fault based on stacked auto-encoder(SAE) was proposed. Firstly,the original vibration signal of reactor was decomposed by wavelet packet decomposition algorithm,and the time-frequency energy matrix of the signal was extracted. Then,the diagnosis model of reactor mechanical fault based on SAE was built,the deep feature mining of the time-frequency energy matrix was completed through unsupervised self-learning,and the identification of reactor mechanical fault was realized through supervised fine-tuning. Finally,vibration data of 10 kV oil immersed reactor under different mechanical states was used to train the fault identification model and optimize the super parameters. The numerical results show that the proposed method can identify reactor mechanical fault better than the traditional vibration signal identification method,and the accuracy can reach 98%.

reactor  /  mechanical failure  /  vibration signal  /  wavelet packet decomposition  /  stacked auto-encoder(SAE)
刘锦伟, 周杰, 李川, 肖潇, 伍惠铖. 基于深度稀疏自编码器的电抗器机械故障振动诊断方法. 电气传动, 2024 , 54 (9) : 83 -89 . DOI: 10.19457/j.1001-2095.dqcd24762
Jinwei LIU, Jie ZHOU, Chuan LI, Xiao XIAO, Huicheng WU. Vibration Diagnosis Method of Reactor Mechanical Fault Based on Stacked Auto-encoder[J]. Electric Drive, 2024 , 54 (9) : 83 -89 . DOI: 10.19457/j.1001-2095.dqcd24762
电抗器作为电力系统输变电过程中的关键设备之一,承担着调整无功、限制谐振过电压和抑制工频电压升高等作用[1-2]。但电抗器的机械结构复杂,且长期在室外环境中运行,随着投运年限的增加,易出现内部结构件和铁心绕组松动等机械故障[3]。因此,针对输变电系统中的电抗器等核心设备,应开展机械故障的在线监测工作,为设备运维检修计划的制定提供参考。
电抗器在运行过程中,铁心和绕组等结构发生机械振动产生的信号包含丰富的设备状态信息,对振动信号进行准确监测及分析可实现电抗器机械故障智能诊断[4]。此外,振动诊断方法的传感器无需与电抗器直接接触,灵活方便且易于实现不停电检测,已逐渐成为电气设备机械故障诊断的研究热点。文献[5-6]指出电抗器正常运行时,其振动频率为各谐波频率的二倍频,电抗器发生故障时,其振动信号会产生较多的高频分量;文献[7]采用傅里叶变换法提取了变压器振动信号的基频、频率比重以及频谱复杂度等特征值,据此实现了变压器铁心和绕组松动故障的分类;文献[8]利用小波变换法提取变压器振动信号的小波包能量作为特征向量,并通过支持向量机(support vector machine,SVM)实现变压器正常、变形及绕组松动等状态的识别分类;文献[9]利用经验小波变换和多尺度形态谱提取了高压并联电抗器的振动信号特征量,辅以K-means聚类方法,实现不同工况下电抗器机械状态的识别分类;文献[10]通过经验模态分解提取振动信号的模态能量占比、欧氏距离和频谱复杂程度作为特征矩阵,并通过随机森林算法实现了电抗器内部机械故障分类。现有研究结果对电抗器振动信号进行准确监测及分析可实现电抗器机械故障智能诊断,但现有的故障诊断方法在振动数据深层特征挖掘、故障识别模型运算速度和准确性等方面存在一定的局限性。
针对以上问题,本文提出一种基于深度稀疏自编码器(SAE)网络的电抗器机械故障振动诊断方法。首先,采用小波包分解法对电抗器原始振动信号进行处理,并将得到的小波包时频能量矩阵作为原始特征参数;然后,利用SAE网络对高维时频特征矩阵进行无监督的深层特征挖掘,并结合softmax分类器实现电抗器典型机械故障的识别分类;最后,使用某10 kV油浸式电抗器不同机械状态下的振动数据对SAE网络进行测试分析。
电抗器振动信号属于非线性、非平稳的时变信号,其包含着丰富的设备机械状态信息。传统的傅里叶变换法不适用于非平稳信号的处理,小波包分解法属于非线性时频分析法,它既可以对信号的低频和高频部分进行分解,还能够结合信号的时频特征,自适应地提升时频分辨效果,保留信号原始特征。下面阐述小波包分解原理[11-13]
令小波包函数unt)满足以下的双尺度方程:
$\left\{\begin{array}{l}{u}_{2n}\left(t\right)=\sqrt{2}\sum _{k\in Z}l\left(k\right){u}_{n}\left(2\right.t-k)\\ {u}_{2n+1}\left(t\right)=\sqrt{2}\sum _{k\in Z}g\left(k\right){u}_{n}\left(2\right.t-k)\end{array}\right.$
式中:t为时间;nk分别为频率指标和位置指标;Z为整数集合;lk),gk)分别为方程的低通滤波器和高通滤波器。
{unt)}表示基函数u0t)= φt)的正交小波包,φt)为尺度函数。
假设${U}_{i}^{n}$为函数unt)的闭包空间,且满足函数${g}_{i}^{n}\left(t\right)\in {U}_{i}^{n}$,则${g}_{i}^{n}\left(t\right)$可表示为
${g}_{i}^{n}\left(t\right)=\sum _{j}{d}_{j}^{i,n}{u}_{n}({2}^{i}t-j)$
式中:j为整数;djin为小波包分解系数。
小波包分解过程为
$\left\{\begin{array}{l}{d}_{j}^{i,2n}=\sum _{k}{a}_{k-2j}{d}_{k}^{i+1,n}\\ {d}_{j}^{i,2n+1}=\sum _{k}{b}_{k-2j}{d}_{k}^{i+1,n}\end{array}\right.$
式中:ak-2jbk-2j为滤波器系数。
在电抗器机械故障诊断中,当电抗器机械状态出现异常时,其器身振动特性将会有明显的改变,主要表现在不同频段的振动信号时域波形具有不同的衰减或增强现象,因此形变与正常下的振动信号时域波形在相同频段内的能量分布会有相应的变化,以小波包能量矩阵作为振动信号特征向量更能反映出电抗器不同机械状态振动特性。假设电抗器振动信号St)是长度为N的一维时间序列,则振动信号的小波包能量矩阵计算步骤如下:
1)采用小波包分解算法将电抗器原始振动信号St)进行处理,获得M个不同频带的小波包分量Smm = 1,2,…,M),并将M个小波包分量Sm依次排序,得到小波包分量的时频矩阵SM×N = [S1S2,…,SM]T
2)为了降低时频矩阵的维数,将长度为N的小波包分量Sm等分为P组,即小波包分量的时频矩阵SM×N变换成维数为M×P的分块矩阵,按照下式计算每块矩阵能量值:
${E}_{m,p}=\sqrt{\sum _{t=1}^{N/P}{S}_{m}^{p}{\left(t\right)}^{2}}$
式中:Em,p为在第m个频带第p个时间段小波分量的能量值,p = 1,2,…,P${S}_{m}^{p}\left(t\right)$为在第m个频带第p个时间段小波分量的时域波形。
3)对振动信号的小波包时频能量矩阵EM×P进行归一化处理,计算公式如下:
${G}_{m,p}=\frac{{E}_{m,p}}{E}$
式中:E为小波分量时频能量矩阵能量值的总和。
最后得到电抗器振动信号的时频能量矩阵GM×P
自编码网络(auto-encoder,AE)是一种典型的无监督学习网络,其基本结构是由输入层、隐含层和输出层构成的三层神经网络,分为编码器和解码器两部分[14-16]。自编码器的网络结构如图1所示。
编码器将输入信号x = [x1x2,…,xc]映射到隐含层,形成低维特征量h = [h1h2,…,hd],完成输入数据的降维;解码器将低维特征量h映射到输出层,得到输入的重构信号y = [y1y2,…,yc],完成输入信号的复原。AE网络的编码和解码过程可表示如下:
$h={f}_{{\theta }_{1}}\left(x\right)=S({W}_{1}x+{b}_{1})$
$y={f}_{{\theta }_{2}}\left(h\right)=S({W}_{2}x+{b}_{2})$
式中:S(·)为Sigmoid激活函数;W1b1分别为编码器的权值矩阵和偏置向量;W2b2分别为解码器的权值矩阵和偏置向量。
AE网络以最小化损失函数为目标,利用梯度下降法不断优化网络参数,最终使重构信号y与输入信号x的误差达到最小。AE网络的损失函数可表示为
$\begin{array}{l}L(x,y)=-\frac{1}{c}\sum _{d=1}^{c}[{x}_{d}ln{y}_{d}+(1-{x}_{d})ln(1-{y}_{d})]+\\ \frac{\lambda }{2}\sum _{a=1}^{{h}_{a}+1}\sum _{q=1}^{{s}^{\left(a\right)}}\sum _{r=1}^{{s}^{\left(a\right)}+1}({W}_{qr}^{\left(a\right)}{)}^{2}\end{array}$
式中:λ为权重衰减参数;ha为神经网络隐含层的层数;sa为第a层神经元的个数;${W}_{qr}^{\left(a\right)}$为第a层的第q个神经元与第a+1层的第r个神经元之间的权重系数。
为了进一步提高AE网络的深层特征挖掘能力,在网络中加入稀疏性约束条件,通过抑制AE网络隐含层的多数神经元,激活隐含层少量神经元,以提高AE网络所提取的低维抽象特征的稀疏性。一般选择KL(Kullback-Leibler)散度正则化项作为AE网络稀疏性约束条件,将其添加到损失函数中以实现AE网络的稀疏性效果。假设αrx)为AE网络隐含层第r个神经元对信号x的激活量,ρ为稀疏性参数,则AE网络隐含层第r个神经元的平均激活度为
${\rho }_{r}=\frac{1}{c}\sum _{d=1}^{c}\left[{\alpha }_{r}\right({x}_{d}\left)\right]$
KL散度的计算公式如下:
$\sum _{r=1}^{R}K(\rho ‖{\rho }_{r})=\sum _{r=1}^{R}[\rho ln\frac{\rho }{{\rho }_{r}}+(1-\rho \left)ln\frac{1-\rho }{1-{\rho }_{r}}\right]$
综上,考虑稀疏性约束条件的AE网络损失函数可表示为
$J(W,\theta )=L(x,y)+\beta \sum _{r=1}^{R}K\left(\rho ‖{\rho }_{r}\right)$
式中:$\beta $为AE网络中调整稀疏性约束条件的权重参数。
稀疏自编码器仅属于单层神经网络,考虑到振动信号时频能量矩阵和电抗器机械故障的复杂性,本文将多个稀疏自编码器层层堆叠,形成深度稀疏自编码器网络。基于深度稀疏自编码器网络的电抗器机械故障诊断过程分为无监督预训练和有监督微调两部分。无监督预训练过程就是利用电抗器振动信号的时频能量矩阵对SAE网络的权值矩阵W和偏置向量b进行不断调优,实现SAE网络输出的重构信号y与输入信号x之间的误差最小的过程。以SAE网络的损失函数为目标函数,利用梯度下降法寻找损失函数的最小值,并采用逐层贪婪训练算法训练SAE网络,最终完成整个深度稀疏自编码网络的预训练。
预训练完成后,需要通过无监督微调实现电抗器机械故障分类。将预训练后的SAE网络最后一个隐含层连接至softmax分类器,并将隐含层输出的低维抽象特征和振动信号的标签作为softmax分类器的输入,通过BP算法来对整个SAE-softmax网络进行参数优化,完成电抗器振动信号与机械故障之间映射关系的建立。
综上所述,基于深度稀疏自编码器的电抗器机械故障振动诊断方法的具体流程如图2所示。
为验证基于深度稀疏自编码器的电抗器机械故障诊断方法的有效性,以型号为BKS - 67/10的一台三相油浸式电抗器为研究对象,人工模拟电抗器三种典型的机械运行状态,即正常状态、铁心松动状态和绕组松动状态。其中,电抗器铁心松动和绕组松动状态分别通过调整铁心的拉紧螺栓和绕组的压紧螺栓模拟实现。选用压电式加速传感器和数据采集卡组合作为电抗器振动信号的采集装置,分别采集三种运行状态下的振动信号,采样频率均为16 kHz,样本时长为0.5 s。为了降低传感器测点位置对测量结果的影响,试验中设置4个测点,分别位于电抗器四周箱体的中心处,试验布置和传感器测点位置如图3所示。此外,压电式加速传感器的灵敏度为10.06 mV/g,频响范围为±500 g,数据采集卡有4个模拟输入通道,最大采样频率为102.4 kHz。
限于篇幅,本文以测点2的电抗器振动信号为例进行分析。电抗器在正常运行、铁心松动和绕组松动状态下振动信号的时频域波形如图4所示。
图4可知,正常运行状态下电抗器铁心和绕组振动信号的频率为100 Hz及其倍频分量,且主要分布在1 000 Hz以内。当电抗器处于铁心松动或绕组松动状态时,振动信号时域波形的幅值增大,频率分布也发生变化,出现较多的高频分量。然而,仅通过振动信号时域波形和频率分布的变化难以识别电抗器机械状态,因此应用基于小波包分解的特征矩阵提取算法对电抗器振动信号进行处理。
考虑电抗器振动信号的频率分布、采集装置的采样频率及小波包分量频带等因素,小波包分解算法的参数设置为:三层小波包分解,db4小波基函数,Shannon熵。为了提取振动信号的时频能量矩阵,将每个小波包分量等分为80组,通过式(4)和式(5)得到尺寸为8×80的时频能量矩阵。为了展示特征提取的效果,从电抗器三种机械状态的训练集中分别随机选取100个样本,并使用第21~23个特征的3D散点图来呈现不同机械状态下特征向量的分布,如图5所示。
图5可知,电抗器的特征向量形成边界分明的三簇,呈现出明显的聚类特性,而且每一簇对应电抗器的一种机械状态。结果说明,基于小波包分解的特征提取方法所得到的时频能量矩阵能够作为电抗器机械故障识别的特征量。
在利用SAE网络对电抗器机械故障进行识别时,为了减少单个测点只能反映电抗器局部信息的影响,使用测点1、测点2和测点3的振动数据作为训练集,测点4的振动数据作为测试集。电抗器振动数据集样本分布如表1所示。
对SAE网络参数进行设置:权值矩阵和偏置向量选用服从高斯分布的随机数,激活函数和学习效率分别设置为sigmoid函数和0.8,稀疏因数为0.1。依据电抗器振动信号的特征向量尺寸,确定SAE网络的输入尺寸为640,最后一个隐含层的输出尺寸为80。
为了确定SAE网络的隐含层数量,使用所有的训练集样本对不同结构的网络进行多组测试,不同隐含层数量的SAE网络故障识别准确率如图6所示。
分析图6可知,随着隐含层数量的增加,SAE网络的故障识别准确率也在逐渐提高。但是,当SAE网络的隐含层数量达到3个后,其准确率提升速度明显变慢,综合考虑训练时间以及准确率等因素,选取3个隐含层结构的SAE网络作为故障识别模型。
为了对比不同分类网络故障识别的性能,首先利用基于小波包分解的特征提取方法对所有的电抗器振动数据集进行特征提取,并将得到的时频能量矩阵作为分类网络的输入量;然后分别对支持向量机(SVM)、BP神经网络、AE和SAE 4种分类网络进行超参数优化,并将4种分类网络的故障识别结果进行分析对比。不同网络电抗器机械故障识别结果如表2所示。4种分类网络的最大迭代次数统一设置为832,其超参数调优结果分别为:SVM分类算法选用径向基函数作为核函数;BP神经网络为4层隐含层网络结构,输入层的节点数为640,隐含层的节点数分别为400,320,160和80;AE网络为单隐含层网络结构,输入层和隐含层的的节点数分别为640和80;SAE网络的隐含层数量为3,输入层的节点数为640,隐含层的节点数分别为320,160和80。
表2可以看出,相比于SVM,BP神经网络和AE网络,文中所提的SAE网络在电抗器机械故障识别准确率和运算速度上都具有明显优势。
从故障识别准确率上看,SAE网络能够达到98.67%,优于其他3种网络。同时,AE网络的故障识别准确率最低,不足90%,这是因为AE网络的单隐含层结构存在特征信息的过度压缩,直接将640维的特征向量压缩至80维,导致特征的有效信息丢失,影响故障识别精度。
从运算速度上看,SAE网络收敛至最高准确率所需的迭代时间为84.03 s,其运算速度明显高于SVM和BP神经网络。相较于AE网络,虽然SAE网络运算速度有所下降,但是其使用多隐含层结构逐层压缩高维特征,能够最大程度地保留有效信息,显著地提高了电抗器机械故障识别准确率。
本文提出了一种基于深度稀疏自编码器的电抗器机械故障振动诊断方法,利用电抗器运行时振动信号包含丰富的设备机械状态信息这一特性,通过小波包分解算法和深度自编码器网络实现振动信号特征提取和电抗器机械故障识别。得出结论如下:
1)利用基于小波包分解的特征提取方法对电抗器振动信号进行降维处理,得到的时频能量矩阵同时兼顾了电抗器振动信号的时域和频域特征信息,并且可以较好地表征电抗器不同的机械状态。
2)所建立的基于深度稀疏自编码器的故障识别网络可以较好地识别电抗器的不同机械状态。相比于浅层神经网络,基于多隐层结构的深度稀疏自编码器网络在电抗器机械故障识别问题上具有显著优势。
  • 国家电网科技项目(5218M0220001)
参考文献 引证文献
排序方式:
[1]
刘宏, 梁基重, 牛曙, 等. 匝间短路故障下干式空心电抗器振动特性研究[J]. 电力电容器与无功补偿, 2022, 42(6):69-75.
LIU Hong, LIANG Jizhong, NIU Shu, et al. Study on vibration characteristics of dry-type air-core reactor under interturn short circuit fault[J]. Power Capacitor & Reactive Power Compensation, 2022, 42(6):69-75.
[2]
王革鹏, 金文德, 曾向阳, 等. 特高压并联电抗器铁心振动的分析与控制研究[J]. 电工技术学报, 2022, 37(9):2190-2198.
WANG Gepeng, JIN Wende, ZENG Xiangyang, et al. Analysis and control research on core vibration of UHV shunt reactor[J]. Transactions of China Electrotechnical Society, 2022, 37(9):2190-2198.
[3]
马宏忠, 侯鹏飞, 严岩, 等. 高压电抗器绕组和铁芯机械故障的混沌特性分析与特征识别[J]. 电力自动化设备, 2022, 42(5):204-211.
MA Hongzhong, HOU Pengfei, YAN Yan, et al. Chaotic characteristic analysis and feature recognition of mechanical failure of high voltage reactor winding and iron core[J]. Electric Power Automation Equipment, 2022, 42(5):204-211.
[4]
高树国, 汲胜昌, 孟令明, 等. 基于在线监测系统与声振特征预测模型的高压并联电抗器运行状态评估方法[J]. 电工技术学报, 2022, 37(9):2179-2189.
GAO Shuguo, JI Shengchang, MENG Lingming, et al. Operation state evaluation method of high-voltage shunt reactor based on on-line monitoring system and vibro-acoustic characteristic prediction model[J]. Transactions of China Electrotechnical Society, 2022, 37(9):2179-2189.
[5]
高璐, 汲胜昌, 祝令瑜, 等. 高压换流站干式空心电抗器的振动产生机理及影响因素研究[J]. 中国电机工程学报, 2022, 42(16):5960-5970,6170.
GAO Lu, JI Shengchang, ZHU Lingyu, et al. Study on vibration mechanism and impact factors of dry-type air-core reactor in HVDC converter stations[J]. Proceedings of the CSEE, 2022, 42(16):5960-5970,6170.
[6]
祝令瑜, 杜一鸣, 高璐, 等. 不同频率激励下干式空心电抗器匝间绝缘缺陷振动分布特性[J]. 高电压技术, 2022, 48(8):3201-3209.
ZHU Lingyu, DU Yiming, GAO Lu, et al. Vibration distribution characteristics of dry-type air-core reactor with turn-to-turn insulation defects excited by different frequencies[J]. High Voltage Engineering, 2022, 48(8):3201-3209.
[7]
钱国超, 于虹, 邹德旭, 等. 振动频谱特征值在诊断变压器故障中的应用研究[J]. 电测与仪表, 2017, 54(19):117-122.
QIAN Guochao, YU Hong, ZOU Dexu, et al. Research on spectrum eigenvalues of transformer vibration and its application on diagnosis[J]. Electrical Measurement & Instrumentation, 2017, 54(19):117-122.
[8]
PAUL O I, LU Yonghua. Vibration monitoring using wavelets transform feature extraction algorithm and technique[J]. App-lied Mechanics and Materials, 2014, 66(6):256-266.
[9]
赵若妤, 马宏忠, 魏旭, 等. 基于 EWT 及多尺度形态谱的高压并联电抗器故障诊断研究[J]. 电力系统保护与控制, 2020, 48(17):68-76.
ZHAO Ruoyu, MA Hongzhong, WEI Xu, et al. Research on fault diagnosis of a high voltage shunt reactor based on EWT and multiscale spectral spectrum[J]. Power System Protection and Control, 2022, 48(17):68-76.
[10]
高树国, 张明文, 吴书煜, 等. 基于振动感知的油浸式电抗器松动故障检测方法[J]. 振动与冲击, 2022, 41(11):42-49.
GAO Shuguo, ZHANG Mingwen, WU Shuyu, et al. Loose fault detection method of oil immersed reactor based on vibration perception[J]. Journal of Vibration and Shock, 2022, 41(11):42-49.
[11]
张育炜, 石琦, 武恩光. 基于支持向量机GIS局放小波包能量谱故障诊断[J]. 电气传动, 2020, 50(9):99-114.
ZHANG Yuwei, SHI Qi, WU Enguang. Fault diagnosis of wavelet packet energy spectrum of partial discharge pulse in GIS based on support vector machine[J]. Electric Drive, 2020, 50(9):99-114.
[12]
吴晓文, 周年光, 裴春明, 等. 特高压交流变电站可听噪声分离方法[J]. 高电压技术, 2016, 42(8):2625-2632.
WU Xiaowen, ZHOU Nianguang, PEI Chunming, et al. Separation methodology of audible noises of UHV AC substations[J]. High Voltage Engineering, 2016, 42(8):2625-2632.
[13]
张振海, 王维庆, 王海云, 等. 基于改进小波包的风电机组齿轮箱复合故障特征提取研究[J]. 太阳能学报, 2022, 43(9):331-336.
ZHANG Zhenhai, WANG Weiqing, WANG Haiyun, et al. Research of composite fault feature extraction of wind turbine gearbox based on improved wavelet packet[J]. Acta Energiae Solaris Sinica, 2022, 43(9):331-336.
[14]
任巍, 翟博豪, 彭炜淞. 基于半监督堆叠自编码器的轧制力预报建模研究[J]. 电气传动, 2022, 52(14):70-74,80.
REN Wei, ZHAI Bohao, PENG Weisong. Rolling force prediction modeling based on semi-supervised stacked autoencoder[J]. Electric Drive, 2022, 52(14):70-74,80.
[15]
来杰, 王晓丹, 向前, 等. 自编码器及其应用综述[J]. 通信学报, 2021, 42(9):218-230.
LAI Jie, WANG Xiaodan, XIANG Qian, et al. Review on autoencoder and its application[J]. Journal on Communications, 2021, 42(9):218-230.
[16]
解颖, 王丰华, 傅正财. 基于栈式自编码器的变压器机械故障诊断[J]. 高压电器, 2020, 56(9):46-53.
XIE Ying, WANG Fenghua, FU Zhengcai. Mechanical fault diagnosis of power transformer based on stacked auto encoder[J]. High Voltage Apparatus, 2020, 56(9):46-53.
2024年第54卷第9期
PDF下载
192
90
引用本文
BibTeX
文章信息
doi: 10.19457/j.1001-2095.dqcd24762
  • 接收时间:2022-11-10
  • 首发时间:2025-11-05
  • 出版时间:2024-09-20
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2022-11-10
  • 修回日期:2023-01-07
基金
国家电网科技项目(5218M0220001)
作者信息
    国网江西省电力有限公司宜春供电分公司, 江西 宜春 336000
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/dqcd/CN/10.19457/j.1001-2095.dqcd24762
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