Article(id=1194957529772962388, tenantId=1146029695717560320, journalId=1189987059142926344, issueId=1194957528560812573, articleNumber=null, orderNo=null, doi=10.19457/j.1001-2095.dqcd25533, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1701360000000, receivedDateStr=2023-12-01, revisedDate=1703692800000, revisedDateStr=2023-12-28, acceptedDate=null, acceptedDateStr=null, onlineDate=1762829676334, onlineDateStr=2025-11-11, pubDate=1729353600000, pubDateStr=2024-10-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1762829676334, onlineIssueDateStr=2025-11-11, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1762829676334, creator=13701087609, updateTime=1762829676334, updator=13701087609, issue=Issue{id=1194957528560812573, tenantId=1146029695717560320, journalId=1189987059142926344, year='2024', volume='54', issue='10', 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=1762829676042, creator=13701087609, updateTime=1762830003292, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1194958901230678090, tenantId=1146029695717560320, journalId=1189987059142926344, issueId=1194957528560812573, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1194958901230678091, tenantId=1146029695717560320, journalId=1189987059142926344, issueId=1194957528560812573, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=83, endPage=89, ext={EN=ArticleExt(id=1194957530041397847, articleId=1194957529772962388, tenantId=1146029695717560320, journalId=1189987059142926344, language=EN, title=Fault Diagnosis Method for Switchgear Based on SMOTE-SSA-CNN, columnId=null, journalTitle=Electric Drive, columnName=null, runingTitle=null, highlight=null, articleAbstract=

The multi-source monitoring data of switchgear contains rich equipment operating status information,and analyzing it can achieve switchgear fault diagnosis. A fault diagnosis method for switchgear based on SMOTE-SSA-CNN was proposed. Firstly,based on monitoring data such as switchgear voltage,current,and temperature and humidity,the synthetic minority over-sampling technique(SMOTE) algorithm was used to expand the original dataset,solving the problem of severe imbalance between positive and negative samples in the original dataset. Then,the sparrow search algorithm(SSA) was introduced to optimize the hyperparameters of convolutional neural networks(CNN),such as the size and number of convolutional kernels,the number of fully connected layer neurons,and the learning rate,in order to improve the accuracy of the model's fault diagnosis results. Finally,the performance of the established SMOTE-SSA-CNN model was evaluated through example analysis,verifying the effectiveness of the proposed method for switchgear fault diagnosis. Compared with traditional fault diagnosis methods,the proposed method has better convergence and higher accuracy.

, 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=Wei ZHANG), CN=ArticleExt(id=1194957705971479164, articleId=1194957529772962388, tenantId=1146029695717560320, journalId=1189987059142926344, language=CN, title=基于SMOTE-SSA-CNN的开关柜故障诊断方法, columnId=1190325456588079763, journalTitle=电气传动, columnName=可靠性与诊断, runingTitle=null, highlight=null, articleAbstract=

开关柜多源监测数据包含丰富的设备运行状态信息,对其进行分析可实现开关柜故障诊断。提出一种基于SMOTE-SSA-CNN的开关柜故障诊断方法。首先,以开关柜电压、电流和温湿度等监测数据为基础,采用合成少数类样本过采样技术(SMOTE)算法对原始数据集进行样本扩充,解决原始数据集中正负样本严重失衡的问题;然后引入麻雀搜索算法(SSA)对卷积神经网络(CNN)的卷积核大小与数量、全连接层神经元数量、学习率等超参数进行优化,提高模型故障诊断结果的准确率;最后,通过算例分析对建立的SMOTE-SSA-CNN模型性能进行评估,验证了所提方法对开关柜故障诊断的有效性,且与传统故障诊断方法相比,所提方法的收敛性较好,精度较高。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=AZetb2vNHiyOpDJ0VNqScw==, magXml=wyxAOfyY7mJcJTi2Y5iJ6Q==, pdfUrl=null, pdf=6gBleyq/vfCPIvfciaW8Dw==, pdfFileSize=1955543, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=xOn7+usVZVh9HEcP+X7Ezg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=SFKv06TyszaLWJe+I6uTlQ==, mapNumber=null, authorCompany=null, fund=null, authors=

张玮(1989—),男,本科,高级工程师,Email:

, authorsList=张玮)}, authors=[Author(id=1195013676504690749, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=15101460625@136.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1195013676613742656, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, authorId=1195013676504690749, language=EN, stringName=Wei ZHANG, firstName=Wei, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=State Grid Gannan Power Supply Company,Gannan Tibetan Autonomous Prefecture 747000,Gansu,China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1195013676706017345, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, authorId=1195013676504690749, language=CN, stringName=张玮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=国网甘南供电公司,甘肃 甘南藏族自治州 747000, bio={"content":"

张玮(1989—),男,本科,高级工程师,Email:

"}, bioImg=null, bioContent=

张玮(1989—),男,本科,高级工程师,Email:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1195013676391444537, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, xref=null, ext=[AuthorCompanyExt(id=1195013676399833146, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, companyId=1195013676391444537, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Grid Gannan Power Supply Company,Gannan Tibetan Autonomous Prefecture 747000,Gansu,China), AuthorCompanyExt(id=1195013676404027451, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, companyId=1195013676391444537, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=国网甘南供电公司,甘肃 甘南藏族自治州 747000)])])], keywords=[Keyword(id=1195013677096087618, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, orderNo=1, keyword=switchgear), Keyword(id=1195013677347745859, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, orderNo=2, keyword=multi source monitoring data), Keyword(id=1195013677414854724, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, orderNo=3, keyword=synthetic minority over-sampling technique(SMOTE) algorithm), Keyword(id=1195013677519712325, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, orderNo=4, keyword=sparrow search algorithm(SSA)), Keyword(id=1195013677591015494, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, orderNo=5, keyword=convolutional neural network(CNN)), Keyword(id=1195013677662318663, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, orderNo=1, keyword=开关柜), Keyword(id=1195013677733621832, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, orderNo=2, keyword=多源监测数据), Keyword(id=1195013677788147785, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, orderNo=3, keyword=合成少数类样本过采样技术算法), Keyword(id=1195013677859450954, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, orderNo=4, keyword=麻雀搜索算法), Keyword(id=1195013677985280075, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, orderNo=5, keyword=卷积神经网络)], refs=[Reference(id=1195013680346673251, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2022, volume=58, issue=3, pageStart=23, pageEnd=28, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=贺建明, 刘坚钢, 易非凡, journalName=高压电器, refType=null, unstructuredReference=贺建明, 刘坚钢, 易非凡, 等. 开关柜绝缘故障仿真与检测系统研究[J]. 高压电器, 2022, 58(3):23-28., articleTitle=开关柜绝缘故障仿真与检测系统研究, refAbstract=null), Reference(id=1195013680426365028, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2022, volume=58, issue=3, pageStart=23, pageEnd=28, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=HE Jianming, LIU Jiangang, YI Feifan, journalName=High Voltage Apparatus, refType=null, unstructuredReference=HE Jianming, LIU Jiangang, YI Feifan, et al. Research on simulation and detection system of insulation fault of switchgear cabinet[J]. High Voltage Apparatus, 2022, 58(3):23-28., articleTitle=Research on simulation and detection system of insulation fault of switchgear cabinet, refAbstract=null), Reference(id=1195013680497668197, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2017, volume=53, issue=3, pageStart=235, pageEnd=241, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=亢超群, 李二霞, 盛万兴, journalName=高压电器, refType=null, unstructuredReference=亢超群, 李二霞, 盛万兴, 等. 基于多源信息融合的配电真空开关柜动态状态评价研究[J]. 高压电器, 2017, 53(3):235-241., articleTitle=基于多源信息融合的配电真空开关柜动态状态评价研究, refAbstract=null), Reference(id=1195013680577359975, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2017, volume=53, issue=3, pageStart=235, pageEnd=241, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=KANG Chaoqun, LI Erxia, SHENG Wanxing, journalName=High Voltage Apparatus, refType=null, unstructuredReference=KANG Chaoqun, LI Erxia, SHENG Wanxing, et al. Dynamic condition assessment for distribution vacuum switch cabinets based on multi-source information fusion[J]. High Voltage Apparatus, 2017, 53(3):235-241., articleTitle=Dynamic condition assessment for distribution vacuum switch cabinets based on multi-source information fusion, refAbstract=null), Reference(id=1195013680724160617, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=2, pageStart=198, pageEnd=204, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=黄俊宁, 于群, journalName=高压电器, refType=null, unstructuredReference=黄俊宁, 于群. 基于多源数据融合与设备相似性的高压开关柜评价模型[J]. 高压电器, 2023, 59(2):198-204., articleTitle=基于多源数据融合与设备相似性的高压开关柜评价模型, refAbstract=null), Reference(id=1195013680824823915, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2023, volume=59, issue=2, pageStart=198, pageEnd=204, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=HUANG Junning, YU Qun, journalName=High Voltage Apparatus, refType=null, unstructuredReference=HUANG Junning, YU Qun. Evaluation model high voltage switch cabinet based on multi-source data fusion and equipment similarity[J]. High Voltage Apparatus, 2023, 59(2):198-204., articleTitle=Evaluation model high voltage switch cabinet based on multi-source data fusion and equipment similarity, refAbstract=null), Reference(id=1195013680908709998, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2019, volume=55, issue=1, pageStart=27, pageEnd=33, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=徐卫东, 聂一雄, 陈云龙, journalName=高压电器, refType=null, unstructuredReference=徐卫东, 聂一雄, 陈云龙, 等. 固体绝缘开关柜局部放电严重程度评估方法[J]. 高压电器, 2019, 55(1):27-33., articleTitle=固体绝缘开关柜局部放电严重程度评估方法, refAbstract=null), Reference(id=1195013680984207471, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2019, volume=55, issue=1, pageStart=27, pageEnd=33, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=XU Weidong, NIE Yixiong, CHEN Yunlong, journalName=High Voltage Apparatus, refType=null, unstructuredReference=XU Weidong, NIE Yixiong, CHEN Yunlong, et al. Evaluation method of severity of partial discharge in solid insulated switchgear[J]. High Voltage Apparatus, 2019, 55(1):27-33., articleTitle=Evaluation method of severity of partial discharge in solid insulated switchgear, refAbstract=null), Reference(id=1195013681080676464, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2020, volume=56, issue=11, pageStart=127, pageEnd=129, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=李江涛, 孙义, 李擎宇, journalName=高压电器, refType=null, unstructuredReference=李江涛, 孙义, 李擎宇. 大电流开关柜梅花触头热缺陷评估算法研究[J]. 高压电器, 2020, 56(11):127-129., articleTitle=大电流开关柜梅花触头热缺陷评估算法研究, refAbstract=null), Reference(id=1195013681143591025, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2020, volume=56, issue=11, pageStart=127, pageEnd=129, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=LI Jiangtao, SUN Yi, LI Qingyu, journalName=High Voltage Apparatus, refType=null, unstructuredReference=LI Jiangtao, SUN Yi, LI Qingyu. Research on thermal defect assessment algorithms for tulip contacts of high current switchgear[J]. High Voltage Apparatus, 2020, 56(11):127-129., articleTitle=Research on thermal defect assessment algorithms for tulip contacts of high current switchgear, refAbstract=null), Reference(id=1195013681269420146, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=袁港, journalName=基于超声波的高压开关柜局部放电检测方法研究, refType=null, unstructuredReference=袁港. 基于超声波的高压开关柜局部放电检测方法研究[D]. 沈阳: 沈阳农业大学, 2022., articleTitle=null, refAbstract=null), Reference(id=1195013681437192307, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=YUAN Gang, journalName=Research on partial discharge detection method for high-voltage switchgear based on ultrasoun, refType=null, unstructuredReference=YUAN Gang. Research on partial discharge detection method for high-voltage switchgear based on ultrasoun[D]. Shenyang: Shenyang Agricultural University, 2022., articleTitle=null, refAbstract=null), Reference(id=1195013681659490421, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2016, volume=40, issue=11, pageStart=3597, pageEnd=3603, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=辛业春, 崔金栋, 周川, journalName=电网技术, refType=null, unstructuredReference=辛业春, 崔金栋, 周川, 等. 基于多变量多尺度云样本熵和模糊支持向量机的开关柜故障分类[J]. 电网技术, 2016, 40(11):3597-3603., articleTitle=基于多变量多尺度云样本熵和模糊支持向量机的开关柜故障分类, refAbstract=null), Reference(id=1195013682016006265, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2016, volume=40, issue=11, pageStart=3597, pageEnd=3603, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=XIN Yechun, CUI Jindong, ZHOU Chuan, journalName=Power System Technology, refType=null, unstructuredReference=XIN Yechun, CUI Jindong, ZHOU Chuan, et al. Fault classification for smart switchgear based on multivariate multiscale cloud sample entropy and fuzzy support vector machine[J]. Power System Technology, 2016, 40(11):3597-3603., articleTitle=Fault classification for smart switchgear based on multivariate multiscale cloud sample entropy and fuzzy support vector machine, refAbstract=null), Reference(id=1195013682112475260, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=10, pageStart=4123, pageEnd=4134, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=任明, 王玥, 关浩斌, journalName=中国电机工程学报, refType=null, unstructuredReference=任明, 王玥, 关浩斌, 等. 沿面放电光脉冲发展特征与临界击穿判据研究[J]. 中国电机工程学报, 2024, 44(10):4123-4134., articleTitle=沿面放电光脉冲发展特征与临界击穿判据研究, refAbstract=null), Reference(id=1195013682259275903, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=10, pageStart=4123, pageEnd=4134, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=REN Ming, WANG Yue, GUAN Haobin, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=REN Ming, WANG Yue, GUAN Haobin, et al. Development characteristics and critical breakdown criterion of surface discharge light pulse[J]. Proceedings of the CSEE, 2024, 44(10):4123-4134., articleTitle=Development characteristics and critical breakdown criterion of surface discharge light pulse, refAbstract=null), Reference(id=1195013682380910721, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2021, volume=54, issue=2, pageStart=44, pageEnd=51, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=黄雪莜, 熊俊, 张宇, journalName=中国电力, refType=null, unstructuredReference=黄雪莜, 熊俊, 张宇, 等. 基于残差卷积神经网络的开关柜局部放电模式识别[J]. 中国电力, 2021, 54(2):44-51., articleTitle=基于残差卷积神经网络的开关柜局部放电模式识别, refAbstract=null), Reference(id=1195013682435436675, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2021, volume=54, issue=2, pageStart=44, pageEnd=51, url=null, language=null, rfNumber=[9], rfOrder=17, authorNames=HUANG Xueyou, XIONG Jun, ZHANG Yu, journalName=Eelctric Power, refType=null, unstructuredReference=HUANG Xueyou, XIONG Jun, ZHANG Yu, et al. Partial discharge pattern recognition of switchgear based on residual convolutional neural network[J]. Eelctric Power, 2021, 54(2):44-51., articleTitle=Partial discharge pattern recognition of switchgear based on residual convolutional neural network, refAbstract=null), Reference(id=1195013682523517061, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2017, volume=33, issue=3, pageStart=17, pageEnd=22, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=朱正国, 何斌斌, 胡冉, journalName=电网与清洁能源, refType=null, unstructuredReference=朱正国, 何斌斌, 胡冉, 等. 基于卷积神经网络的开关柜局部放电监测[J]. 电网与清洁能源, 2017, 33(3):17-22., articleTitle=基于卷积神经网络的开关柜局部放电监测, refAbstract=null), Reference(id=1195013682649346183, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2017, volume=33, issue=3, pageStart=17, pageEnd=22, url=null, language=null, rfNumber=[10], rfOrder=19, authorNames=ZHU Zhengguo, HE Binbin, HU Ran, journalName=Power System and Clean Energy, refType=null, unstructuredReference=ZHU Zhengguo, HE Binbin, HU Ran, et al. Switch-gear partial discharge detection based on convolutional neural network[J]. Power System and Clean Energy, 2017, 33(3):17-22., articleTitle=Switch-gear partial discharge detection based on convolutional neural network, refAbstract=null), Reference(id=1195013682733232266, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2015, volume=35, issue=1, pageStart=52, pageEnd=59, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=严英杰, 盛戈皞, 陈玉峰, journalName=中国电机工程学报, refType=null, unstructuredReference=严英杰, 盛戈皞, 陈玉峰, 等. 基于大数据分析的输变电设备状态数据异常检测方法[J]. 中国电机工程学报, 2015, 35(1):52-59., articleTitle=基于大数据分析的输变电设备状态数据异常检测方法, refAbstract=null), Reference(id=1195013682817118348, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2015, volume=35, issue=1, pageStart=52, pageEnd=59, url=null, language=null, rfNumber=[11], rfOrder=21, authorNames=YAN Yingjie, SHENG Gehao, CHEN Yufeng, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=YAN Yingjie, SHENG Gehao, CHEN Yufeng, et al. An method for anomaly detection of state information of power equipment based on big data analysis[J]. Proceedings of the CSEE, 2015, 35(1):52-59., articleTitle=An method for anomaly detection of state information of power equipment based on big data analysis, refAbstract=null), Reference(id=1195013682892615823, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2018, volume=44, issue=11, pageStart=3454, pageEnd=3464, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=廖瑞金, 王有元, 刘航, journalName=高电压技术, refType=null, unstructuredReference=廖瑞金, 王有元, 刘航, 等. 输变电设备状态评估方法的研究现状[J]. 高电压技术, 2018, 44(11):3454-3464., articleTitle=输变电设备状态评估方法的研究现状, refAbstract=null), Reference(id=1195013682993279120, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2018, volume=44, issue=11, pageStart=3454, pageEnd=3464, url=null, language=null, rfNumber=[12], rfOrder=23, authorNames=LIAO Ruijin, WANG Youyuan, LIU Hang, journalName=High Voltage Engineering, refType=null, unstructuredReference=LIAO Ruijin, WANG Youyuan, LIU Hang et al. Research status of condition assessment method for power equipment[J]. High Voltage Engineering, 2018, 44(11):3454-3464., articleTitle=Research status of condition assessment method for power equipment, refAbstract=null), Reference(id=1195013683064582291, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2020, volume=46, issue=7, pageStart=2522, pageEnd=2529, url=null, language=null, rfNumber=[13], rfOrder=24, authorNames=刘云鹏, 和家慧, 许自强, journalName=高电压技术, refType=null, unstructuredReference=刘云鹏, 和家慧, 许自强, 等. 基于 SVM SMOTE 的电力变压器故障样本均衡化方法[J]. 高电压技术, 2020, 46(7):2522-2529., articleTitle=基于 SVM SMOTE 的电力变压器故障样本均衡化方法, refAbstract=null), Reference(id=1195013683131691157, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2020, volume=46, issue=7, pageStart=2522, pageEnd=2529, url=null, language=null, rfNumber=[13], rfOrder=25, authorNames=LIU Yunpeng, HE Jiahui, XU Ziqiang, journalName=High Voltage Engineering, refType=null, unstructuredReference=LIU Yunpeng, HE Jiahui, XU Ziqiang, et al. Equalization method of power transformer fault sample based on SVM SMOTE[J]. High Voltage Engineering, 2020, 46(7):2522-2529., articleTitle=Equalization method of power transformer fault sample based on SVM SMOTE, refAbstract=null), Reference(id=1195013683270103191, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2019, volume=43, issue=2, pageStart=42, pageEnd=49, url=null, language=null, rfNumber=[14], rfOrder=26, authorNames=丛伟, 胡亮亮, 孙世军, journalName=电力系统自动化, refType=null, unstructuredReference=丛伟, 胡亮亮, 孙世军, 等. 基于改进深度降噪自编码网络的电网气象防灾方法[J]. 电力系统自动化, 2019, 43(2):42-49., articleTitle=基于改进深度降噪自编码网络的电网气象防灾方法, refAbstract=null), Reference(id=1195013683337212059, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2019, volume=43, issue=2, pageStart=42, pageEnd=49, url=null, language=null, rfNumber=[14], rfOrder=27, authorNames=CONG Wei, HU Liangliang, SUN Shijun, journalName=Automation of Electric Power Systems, refType=null, unstructuredReference=CONG Wei, HU Liangliang, SUN Shijun, et al. Meteorological disaster prevention method for power grid based on improved stacked denoising auto-encoder network[J]. Automation of Electric Power Systems, 2019, 43(2):42-49., articleTitle=Meteorological disaster prevention method for power grid based on improved stacked denoising auto-encoder network, refAbstract=null), Reference(id=1195013683433681053, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=28, authorNames=国家电网公司运维检修部, journalName=电网设备状态检测技术应用典型案例(2011—2013年), refType=null, unstructuredReference=国家电网公司运维检修部. 电网设备状态检测技术应用典型案例(2011—2013年)[M]. 北京: 中国电力出版社, 2014., articleTitle=null, refAbstract=null), Reference(id=1195013683509178527, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=29, authorNames=State Grid Corporation of China Operations and Maintenance Department, journalName=Typical cases of application of state detection technology for power grid equipment(2011—2013), refType=null, unstructuredReference=State Grid Corporation of China Operations and Maintenance Department. Typical cases of application of state detection technology for power grid equipment(2011—2013)[M]. Beijing: China Electric Power Press, 2014., articleTitle=null, refAbstract=null), Reference(id=1195013683576287392, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2017, volume=40, issue=6, pageStart=1229, pageEnd=1251, url=null, language=null, rfNumber=[16], rfOrder=30, authorNames=周飞燕, 金林鹏, 董军, journalName=计算机学报, refType=null, unstructuredReference=周飞燕, 金林鹏, 董军. 卷积神经网络研究综述[J]. 计算机学报, 2017, 40(6):1229-1251., articleTitle=卷积神经网络研究综述, refAbstract=null), Reference(id=1195013683702116514, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2017, volume=40, issue=6, pageStart=1229, pageEnd=1251, url=null, language=null, rfNumber=[16], rfOrder=31, authorNames=ZHOU Feiyan, JIN Linpeng, DONG Jun, journalName=Chinese Journal of Computers, refType=null, unstructuredReference=ZHOU Feiyan, JIN Linpeng, DONG Jun. Review of convolution neural network[J]. Chinese Journal of Computers, 2017, 40(6):1229-1251., articleTitle=Review of convolution neural network, refAbstract=null), Reference(id=1195013683865694372, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2020, volume=46, issue=2, pageStart=413, pageEnd=423, url=null, language=null, rfNumber=[17], rfOrder=32, authorNames=张重远, 罗世豪, 岳浩天, journalName=高电压技术, refType=null, unstructuredReference=张重远, 罗世豪, 岳浩天, 等. 基于Mel时频谱-卷积神经网络的变压器铁芯声纹模式识别方法[J]. 高电压技术, 2020, 46(2):413-423., articleTitle=基于Mel时频谱-卷积神经网络的变压器铁芯声纹模式识别方法, refAbstract=null), Reference(id=1195013683953774758, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2020, volume=46, issue=2, pageStart=413, pageEnd=423, url=null, language=null, rfNumber=[17], rfOrder=33, authorNames=ZHANG Zhongyuan, LUO Shihao, YUE Haotian, journalName=High Voltage Engineering, refType=null, unstructuredReference=ZHANG Zhongyuan, LUO Shihao, YUE Haotian, et al. Pattern recognition of acoustic signals of transformer core based on Mel-spectrum and CNN[J]. High Voltage Engineering, 2020, 46(2):413-423., articleTitle=Pattern recognition of acoustic signals of transformer core based on Mel-spectrum and CNN, refAbstract=null), Reference(id=1195013684067020968, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=8, pageStart=2972, pageEnd=2981, url=null, language=null, rfNumber=[18], rfOrder=34, authorNames=刘展程, 王爽, 唐波, journalName=高电压技术, refType=null, unstructuredReference=刘展程, 王爽, 唐波. 基于 SSA-BiGRU-Attention 模型的变压器油中溶解气体含量预测[J]. 高电压技术, 2022, 48(8):2972-2981., articleTitle=基于 SSA-BiGRU-Attention 模型的变压器油中溶解气体含量预测, refAbstract=null), Reference(id=1195013684159295658, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2022, volume=48, issue=8, pageStart=2972, pageEnd=2981, url=null, language=null, rfNumber=[18], rfOrder=35, authorNames=LIU Zhancheng, WANG Shuang, TANG Bo, journalName=High Voltage Engineering, refType=null, unstructuredReference=LIU Zhancheng, WANG Shuang, TANG Bo. Prediction of dissolved gas content in transformer oil based on SSA-BiGRU-Attention model[J]. High Voltage Engineering, 2022, 48(8):2972-2981., articleTitle=Prediction of dissolved gas content in transformer oil based on SSA-BiGRU-Attention model, refAbstract=null), Reference(id=1195013684268347564, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2023, volume=51, issue=4, pageStart=32, pageEnd=42, url=null, language=null, rfNumber=[19], rfOrder=36, authorNames=王艳, 李伟, 赵洪山, journalName=电力系统保护与控制, refType=null, unstructuredReference=王艳, 李伟, 赵洪山, 等. 基于油中溶解气体分析的DBN-SSAELM变压器故障诊断方法[J]. 电力系统保护与控制, 2023, 51(4):32-42., articleTitle=基于油中溶解气体分析的DBN-SSAELM变压器故障诊断方法, refAbstract=null), Reference(id=1195013684335456429, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, doi=null, pmid=null, pmcid=null, year=2023, volume=51, issue=4, pageStart=32, pageEnd=42, url=null, language=null, rfNumber=[19], rfOrder=37, authorNames=WANG Yan, LI Wei, ZHAO Hongshan, journalName=Power System Protection and Control, refType=null, unstructuredReference=WANG Yan, LI Wei, ZHAO Hongshan, et al. Transformer DGA fault diagnosis method based on DBN-SSAELM[J]. Power System Protection and Control, 2023, 51(4):32-42., articleTitle=Transformer DGA fault diagnosis method based on DBN-SSAELM, refAbstract=null)], funds=[Fund(id=1195013680191484002, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, awardId=21YF5GA159, language=CN, fundingSource=甘肃省重点研发计划(21YF5GA159), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1195013676391444537, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, xref=null, ext=[AuthorCompanyExt(id=1195013676399833146, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, companyId=1195013676391444537, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=State Grid Gannan Power Supply Company,Gannan Tibetan Autonomous Prefecture 747000,Gansu,China), AuthorCompanyExt(id=1195013676404027451, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, companyId=1195013676391444537, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=国网甘南供电公司,甘肃 甘南藏族自治州 747000)])], figs=[ArticleFig(id=1195013678211772492, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, label=Fig.1, caption=SMOTE algorithm expands minority class samples, figureFileSmall=AImV+mOuwjcFJMqiuxL4Iw==, figureFileBig=WRUSQY8t91/3RDSSPqo9cg==, tableContent=null), ArticleFig(id=1195013678274687053, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, label=图1, caption=SMOTE算法扩充少数类样本, figureFileSmall=AImV+mOuwjcFJMqiuxL4Iw==, figureFileBig=WRUSQY8t91/3RDSSPqo9cg==, tableContent=null), ArticleFig(id=1195013678421487694, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, label=Fig.2, caption=Convolutional neural network structure, figureFileSmall=fEKpNCIUH2hKl0ub3XZy/A==, figureFileBig=H8heN82Q5faQrVnc4zkGsg==, tableContent=null), ArticleFig(id=1195013678480207951, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, label=图2, caption=卷积神经网络结构, figureFileSmall=fEKpNCIUH2hKl0ub3XZy/A==, figureFileBig=H8heN82Q5faQrVnc4zkGsg==, tableContent=null), ArticleFig(id=1195013678543122512, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, label=Fig.3, caption=Fault diagnosis process for switchgear based on SMOTE-SSA-CNN, figureFileSmall=grhLpRK+rmfQYpwJvqrBpw==, figureFileBig=0z+ttDwDrnPr1fUuS8RVzw==, tableContent=null), ArticleFig(id=1195013678614425681, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, label=图3, caption=基于SMOTE-SSA-CNN的开关柜故障诊断流程, figureFileSmall=grhLpRK+rmfQYpwJvqrBpw==, figureFileBig=0z+ttDwDrnPr1fUuS8RVzw==, tableContent=null), ArticleFig(id=1195013678702506066, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, label=Fig.4, caption=Diagnosis results of switchgear faults, figureFileSmall=sy6t4tiwER9OPWSfjW/QJw==, figureFileBig=9WmJdxJm9Pyfu41eBzKXkQ==, tableContent=null), ArticleFig(id=1195013678782197843, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, label=图4, caption=开关柜故障诊断结果, figureFileSmall=sy6t4tiwER9OPWSfjW/QJw==, figureFileBig=9WmJdxJm9Pyfu41eBzKXkQ==, tableContent=null), ArticleFig(id=1195013678849306708, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, label=Fig. 5, caption=Confusion matrix of switchgear fault diagnosis results, figureFileSmall=j7xC38cDyf0J8/ew1jVKuw==, figureFileBig=/A8rd/S95Eihrl2l8+Phlg==, tableContent=null), ArticleFig(id=1195013678941581397, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, label=图5, caption=开关柜故障诊断结果混淆矩阵, figureFileSmall=j7xC38cDyf0J8/ew1jVKuw==, figureFileBig=/A8rd/S95Eihrl2l8+Phlg==, tableContent=null), ArticleFig(id=1195013679008690262, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, label=Tab.1, caption=

Monitoring status quantity of switchgear

, figureFileSmall=null, figureFileBig=null, tableContent=
位置 状态量 获取方式
母线室 三相电压 断路器测量
母排温度 温度传感器
母线室温度
母线室湿度 湿度传感器
电缆室 三相电流 断路器测量
电缆接头温度 温度传感器
电缆室温度
电缆室湿度 湿度传感器
断路器室 分断电压 断路器测量
分断电流
故障跳闸延时
接地电流
), ArticleFig(id=1195013679109353559, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, label=表1, caption=

开关柜监测状态量

, figureFileSmall=null, figureFileBig=null, tableContent=
位置 状态量 获取方式
母线室 三相电压 断路器测量
母排温度 温度传感器
母线室温度
母线室湿度 湿度传感器
电缆室 三相电流 断路器测量
电缆接头温度 温度传感器
电缆室温度
电缆室湿度 湿度传感器
断路器室 分断电压 断路器测量
分断电流
故障跳闸延时
接地电流
), ArticleFig(id=1195013679172268120, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, label=Tab.2, caption=

Sample data distribution

, figureFileSmall=null, figureFileBig=null, tableContent=
故障类型 故障标签 训练集 测试集 总计 占总样本数比重/%
正常运行 1 200 50 250 61.73
局部放电 2 60 15 75 18.52
温升故障 3 48 12 60 14.81
机械故障 4 16 4 20 4.94
), ArticleFig(id=1195013679260348505, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, label=表2, caption=

样本分布情况

, figureFileSmall=null, figureFileBig=null, tableContent=
故障类型 故障标签 训练集 测试集 总计 占总样本数比重/%
正常运行 1 200 50 250 61.73
局部放电 2 60 15 75 18.52
温升故障 3 48 12 60 14.81
机械故障 4 16 4 20 4.94
), ArticleFig(id=1195013679361011802, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, label=Tab.3, caption=

Fault diagnosis results of different expansion algorithms

, figureFileSmall=null, figureFileBig=null, tableContent=
扩充方法 准确率/% Kappa系数
未均衡化 71.51 0.68
随机采样法 90.47 0.89
SMOTE 97.50 0.96
), ArticleFig(id=1195013679474258011, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, label=表3, caption=

不同扩充算法的识别结果

, figureFileSmall=null, figureFileBig=null, tableContent=
扩充方法 准确率/% Kappa系数
未均衡化 71.51 0.68
随机采样法 90.47 0.89
SMOTE 97.50 0.96
), ArticleFig(id=1195013679612670044, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, label=Tab.4, caption=

Initial parameters of SSA algorithm

, figureFileSmall=null, figureFileBig=null, tableContent=
参数名称 参数值 参数名称 参数值
种群数 15 预警者 0.2
迭代次数 70 安全值 0.6
发现者 0.8 优化维度 300
), ArticleFig(id=1195013679696556125, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, label=表4, caption=

SSA算法初始参数

, figureFileSmall=null, figureFileBig=null, tableContent=
参数名称 参数值 参数名称 参数值
种群数 15 预警者 0.2
迭代次数 70 安全值 0.6
发现者 0.8 优化维度 300
), ArticleFig(id=1195013679751082078, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, label=Tab.5, caption=

Evaluation index results of SSA-CNN model

, figureFileSmall=null, figureFileBig=null, tableContent=
故障类型 评价指标
准确率/% 查准率/% 查全率/%
正常运行 97.5 100 100
局部放电 96.2 100
温升故障 96.1 98
机械故障 97.9 92
), ArticleFig(id=1195013679809802335, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, label=表5, caption=

SSA-CNN模型的评价指标结果

, figureFileSmall=null, figureFileBig=null, tableContent=
故障类型 评价指标
准确率/% 查准率/% 查全率/%
正常运行 97.5 100 100
局部放电 96.2 100
温升故障 96.1 98
机械故障 97.9 92
), ArticleFig(id=1195013679885299808, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=EN, label=Tab.6, caption=

Output results of different models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 准确率/% Kappa系数 收敛次数
BPNN 84.3 0.81
SVM 83.6 0.79
CNN 91.5 0.88
PSO-CNN 94.3 0.91 47
GA-CNN 92.7 0.90 31
SSA-CNN 97.5 0.95 24
), ArticleFig(id=1195013679964991585, tenantId=1146029695717560320, journalId=1189987059142926344, articleId=1194957529772962388, language=CN, label=表6, caption=

不同模型的输出结果

, figureFileSmall=null, figureFileBig=null, tableContent=
模型 准确率/% Kappa系数 收敛次数
BPNN 84.3 0.81
SVM 83.6 0.79
CNN 91.5 0.88
PSO-CNN 94.3 0.91 47
GA-CNN 92.7 0.90 31
SSA-CNN 97.5 0.95 24
)], 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.dqcd25533, detailUrlEn=https://castjournals.cast.org.cn/joweb/dqcd/EN/10.19457/j.1001-2095.dqcd25533, pdfUrlCn=https://castjournals.cast.org.cn/joweb/dqcd/CN/PDF/10.19457/j.1001-2095.dqcd25533, pdfUrlEn=https://castjournals.cast.org.cn/joweb/dqcd/EN/PDF/10.19457/j.1001-2095.dqcd25533, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于SMOTE-SSA-CNN的开关柜故障诊断方法
收藏切换
PDF下载
张玮
电气传动 | 可靠性与诊断 2024,54(10): 83-89
收起
收藏切换
电气传动 | 可靠性与诊断 2024, 54(10): 83-89
基于SMOTE-SSA-CNN的开关柜故障诊断方法
全屏
张玮
作者信息
  • 国网甘南供电公司,甘肃 甘南藏族自治州 747000
  • 张玮(1989—),男,本科,高级工程师,Email:

Fault Diagnosis Method for Switchgear Based on SMOTE-SSA-CNN
Wei ZHANG
Affiliations
  • State Grid Gannan Power Supply Company,Gannan Tibetan Autonomous Prefecture 747000,Gansu,China
出版时间: 2024-10-20 doi: 10.19457/j.1001-2095.dqcd25533
文章导航
收藏切换

开关柜多源监测数据包含丰富的设备运行状态信息,对其进行分析可实现开关柜故障诊断。提出一种基于SMOTE-SSA-CNN的开关柜故障诊断方法。首先,以开关柜电压、电流和温湿度等监测数据为基础,采用合成少数类样本过采样技术(SMOTE)算法对原始数据集进行样本扩充,解决原始数据集中正负样本严重失衡的问题;然后引入麻雀搜索算法(SSA)对卷积神经网络(CNN)的卷积核大小与数量、全连接层神经元数量、学习率等超参数进行优化,提高模型故障诊断结果的准确率;最后,通过算例分析对建立的SMOTE-SSA-CNN模型性能进行评估,验证了所提方法对开关柜故障诊断的有效性,且与传统故障诊断方法相比,所提方法的收敛性较好,精度较高。

开关柜  /  多源监测数据  /  合成少数类样本过采样技术算法  /  麻雀搜索算法  /  卷积神经网络

The multi-source monitoring data of switchgear contains rich equipment operating status information,and analyzing it can achieve switchgear fault diagnosis. A fault diagnosis method for switchgear based on SMOTE-SSA-CNN was proposed. Firstly,based on monitoring data such as switchgear voltage,current,and temperature and humidity,the synthetic minority over-sampling technique(SMOTE) algorithm was used to expand the original dataset,solving the problem of severe imbalance between positive and negative samples in the original dataset. Then,the sparrow search algorithm(SSA) was introduced to optimize the hyperparameters of convolutional neural networks(CNN),such as the size and number of convolutional kernels,the number of fully connected layer neurons,and the learning rate,in order to improve the accuracy of the model's fault diagnosis results. Finally,the performance of the established SMOTE-SSA-CNN model was evaluated through example analysis,verifying the effectiveness of the proposed method for switchgear fault diagnosis. Compared with traditional fault diagnosis methods,the proposed method has better convergence and higher accuracy.

switchgear  /  multi source monitoring data  /  synthetic minority over-sampling technique(SMOTE) algorithm  /  sparrow search algorithm(SSA)  /  convolutional neural network(CNN)
张玮. 基于SMOTE-SSA-CNN的开关柜故障诊断方法. 电气传动, 2024 , 54 (10) : 83 -89 . DOI: 10.19457/j.1001-2095.dqcd25533
Wei ZHANG. Fault Diagnosis Method for Switchgear Based on SMOTE-SSA-CNN[J]. Electric Drive, 2024 , 54 (10) : 83 -89 . DOI: 10.19457/j.1001-2095.dqcd25533
高压开关柜作为电网的核心设备之一,其健康状况对电力系统的安全稳定运行至关重要[1-3]。但是开关柜的机械结构和运行环境复杂,在长期运行过程中存在表面积污、受潮、绝缘老化等问题,容易引发局部放电、温升、机械等故障[4]。因此,有必要建立高效的开关柜故障诊断模型,及时准确地掌握开关柜的运行状态,进而为设备运维检修计划的制定提供参考。
随着人工智能的发展,BP(back propagation)神经网络、支持向量机(support vector machine,SVM)、卷积神经网络(convolutional neural network,CNN)等机器学习方法在近年被广泛应用于开关柜故障诊断中。文献[5-6]建立了基于BP神经网络的故障诊断模型,将开关柜超声波信号作为输入,实现了开关柜局部放电故障的识别和定位。文献[7]采用降半梯形云模型提取开关柜电压、电流、温湿度等监测数据的特征,并借助模糊支持向量机实现了开关柜不同故障的诊断。文献[8]利用多波段光学传感器得到开关柜沿面放电的光谱比率,结合模糊聚类算法和支持向量机,实现对开关柜放电程度的判别;文献[9-10]构建了基于卷积神经网络的分类模型,将开关柜超声波和地电波数据的时频谱图作为输入特征值,实现了开关柜局部放电故障的识别。现有研究结果表明基于开关柜的多源监测数据和机器学习算法,可实现开关柜不同故障的识别。然而实际运行的开关柜故障是小概率事件,导致原始数据集的正负样本比例严重失衡,同时现有方法通过人工经验设置分类模型的超参数,严重影响了机器学习分类模型的准确性和可靠性。
基于此,本文以开关柜多源监测数据为基础,提出了一种基于SMOTE-SSA-CNN的开关柜故障诊断方法。首先利用合成少数类样本过采样算法对多源监测数据集中的少数类故障样本进行扩充,降低原始数据集的不平衡度;然后基于均衡数据集,构建卷积神经网络分类模型,并通过麻雀搜索算法对卷积神经网络的卷积核大小与数量、全连接层神经元数量、学习率进行优化,避免卷积神经网络模型超参数设置的主观性;最后通过算例验证了所提方法的有效性。
数量充足且正负样本分布均衡的样本集是确保深度学习分类模型准确率和泛化能力的基本前提。然而在实际运行过程中,开关柜故障为小概率事件,加上完善的保护措施,导致监测数据集中故障样本匮乏且正负样本比例失衡。采用基于深度学习算法的分类模型对正负样本失衡的数据集进行分析时,故障识别结果偏向于多数类,而少数类的识别准确率偏低[11-12]
合成少数类样本过采样技术(synthetic minority over-sampling technique,SMOTE)算法是一种随机过采样的改进方法,该方法基于非均衡数据集中少数类样本,通过线性随机插值的方式得到新样本[13-14],实现原始数据集的均衡化处理,进而提高深度学习分类模型的精度和泛化能力。图1为少数类样本扩充基本原理图。具体步骤如下:
1)初始化开关柜原始数据中少数类样本集 S m i n , , n = { x 1 , x 2 , , x n }
2)采用 K近邻算法得到开关柜少数类样本 x n K个近邻样本 Y = { y 1 , y 2 , , y K }
3)随机选取 K个近邻样本 Y的$m\left( m < K \right)$个样本 y i ( i = 1,2 , , m )
4)采用随机线性插值的方式对样本 x n y i进行处理,得到具有相邻样本特征的新样本,实现原始数据集的均衡化。基于随机线性插值的样本合成公式为
z i = x n + ( x n - y i ) r a n d 0,1
式中: z i为新生成的少数类样本; r a n d 0,1为在 0,1范围内的一个随机数。
根据《电网设备状态检测技术应用典型案例》[15]及相关资料,开关柜的机械性能和电气性能主要由母线、电缆和断路器的性能决定,因此,将开关柜分为母线、电缆和断路器3部分。当开关柜在运行期间出现表面积污、受潮、绝缘老化等问题时,易发生局部放电故障,从而导致开关柜内部电气参数产生变化;长期过负荷和接触不良会使开关柜发热,进而可能引发温升故障;随着投运年限和开断次数的增加,断路器的机械性能也会逐渐下降。因此,为了能够对开关柜局部放电、温升、机械等故障进行全面诊断,本文选取母线室、电缆室、断路器室3部分的12种状态量作为多源监测数据,具体如表1所示。
开关柜多源监测数据具有模糊性较强、特征间差异较小等特点,采用BP神经网络、支持向量机等传统分类模型对开关柜故障进行识别时,易出现网络运算效率低、参数调优复杂以及运算结果不收敛等问题。为了深入分析开关柜多源监测数据和故障类型之间的关联性,采用具有强大特征表征能力的卷积神经网络分类模型代替传统分类模型,充分挖掘不同故障类型下特征之间的差异性,高效快速地建立开关柜多源数据与故障类型之间的映射关系,以提升开关柜故障诊断的准确性和可靠性。
CNN是一种典型前馈型深度学习网络,其结构一般由输入层、输出层以及多个卷积层、池化层和全连接层组成,可实现局部特征提取、区域共享权值以及数据池化[16-17]。相较于浅层神经网络,多隐含层结构的CNN模型能够自适应地挖掘数据深层特征,具有运算速率快、避免训练陷入局部极值等优点。CNN的基本结构如图2所示。
一维CNN用于处理一维数组,卷积核沿一个方向滑动,符合开关柜多源监测数据的输入特征。一维CNN的总体数学模型表达式为
x o u t p u t = f S o f t m a x { f f c { f p o o l i n g [ f c o n v ( x i n p u t ) ] } }
式中: x i n p u t为输入特征集; x o u t p u t为输出的分类结果; f c o n v ( )为卷积层计算,包括卷积运算与非线性激活; f p o o l i n g ( )为池化层计算; f f c ( )为全连接层计算; f S o f t m a x ( )为通过函数计算得到的输出结果。
由于CNN模型的卷积核大小与数量、全连接层神经元数量、学习率等超参数通常根据人工经验设定,导致模型的输出结果准确性较差。针对人工经验选取CNN超参数难以构建最优网络问题,本文通过麻雀搜索算法(sparrow search algorithm,SSA)优化CNN模型超参数,进而提升模型的准确性和可靠性。
麻雀搜索算法通过分析麻雀的觅食行为,构建出具有预警机制的发现者-跟随者的智能优化模型。与遗传算法(genetic algorithm,GA)、粒子群优化(particle swarm optimization,PSO)算法等智能优化方法相比较,麻雀搜索算法具有收敛速度快、全局搜索能力强等优点[18-19]。SSA的基本原理如下:
假设存在 n只麻雀构成的种群X
$\boldsymbol{X}=\left[\begin{array}{cccc} x_1^1 & x_1^2 & \cdots & x_1^d \\ x_2^1 & x_2^2 & \cdots & x_2^d \\ \vdots & \vdots & \ddots & \vdots \\ x_n^1 & x_n^2 & \cdots & x_n^d \end{array}\right]$
式中: d为问题维度。
则麻雀种群X中所有麻雀的适应度可表示为
$\boldsymbol{F}_x=\left[\begin{array}{cccc} f\left(\left[x_1^1\right.\right. & x_1^2 & \cdots & \left.\left.x_1^d\right]\right) \\ f\left(\left[x_2^1\right.\right. & x_2^2 & \cdots & \left.\left.x_2^d\right]\right) \\ \vdots & \vdots & \ddots & \vdots \\ f\left(\left[x_n^1\right.\right. & x_n^2 & \cdots & \left.\left.x_n^d\right]\right) \end{array}\right]$
式中: f ( [ x k d ] )为麻雀个体适应度。
依据麻雀觅食行为,麻雀种类可分为3类:发现者、跟随者、警戒者。发现者是麻雀种群中适应度较小的麻雀个体,其主要作用是给麻雀种群寻觅食物,并且将觅食方向提供给跟随者。也就是说,麻雀种群中发现者的觅食范围要大于跟随者。麻雀种群中发现者的位置更新公式为
X k , j t + 1 = X k , j e x p k α t m a x             R 2 < d X k , j + Q L                                               R 2 D
式中: t t m a x分别为迭代次数和最大迭代次数; X k , j ( j = 1,2 , , d )为第 k个麻雀的位置处于第 j维; α 0,1之间的随机数; R 2为预警值, R 2 [ 0,1 ] L 1 × d的单位矩阵; D为安全值, D [ 0.5,1 ]
跟随者的位置更新公式可表示为
X k , j t + 1 = Q e x p X w t - X k , j t                                         k > n / 2 X p t + 1 + X k , j - X p t + 1 A L         k n / 2
式中: X w X p分别为更新后麻雀种群的最差位置和发现者的最优位置; A 1 × d维的随机矩阵,并且有 A + = A T A A T - 1,矩阵 A内所有元素是1或-1的随机数。
麻雀种群中警戒者位置更新公式为
X k , j t + 1 = X b t + β X k , j t - X b t                                   f k > f g X k , j t + K ( | X k , j t - X w t | ( f k - f w ) + ε )                             f k = f g
式中: X b为更新后麻雀种族的最优位置; f k为更新麻雀个体适应度; f g f w分别为更新后麻雀种群最差和最优适应度; β K均为随机数,其中 β服从正态分布, K [ - 1,1 ]
本文将CNN分类模型的卷积核大小与数量、全连接层神经元个数、学习速率等超参数作为麻雀个体,并且以CNN模型输出结果准确率为适应度函数,采用SSA对模型超参数进行优化。满足下式时,最大适应度函数对应的属性值就是CNN分类模型的优化超参数。
m a x F = m a x n = n
基于SMOTE-SSA-CNN的开关柜故障诊断流程如图3所示,主要包括3个部分,即少数类样本扩充、CNN分类模型超参数优化、开关柜故障诊断。具体步骤如下:
1)少数类样本扩充。采用SMOTE算法分别对原始数据集中的开关柜局部放电、温升和机械故障数据进行样本扩充,重新组成均衡化数据集,并将其划分为训练集与测试集。
2)SSA优化CNN超参数。将CNN分类模型的超参数作为SSA的麻雀个体,分类模型准确率作为麻雀个体的适应度函数,计算适应度值并更新种群,直到满足最大迭代次数,得到CNN的最优超参数。
3)变压器故障诊断。基于SMOTE算法得到的扩充数据集,结合SSA算法寻优得到的最优超参数,搭建CNN模型进行开关柜故障诊断。
为评估所提方法的有效性,引入准确率 η A、查准率 η P、查全率 η R和Kappa系数 η K作为故障诊断模型的评价指标,数学表达式为
η A = n / N
η P = n T n P
η R = n T n R
η K = η A - i = 1 4 n R i n P i / N 2 1 - i = 1 4 n R i n P i / N 2
式中: n为诊断的故障类型与实际故障类型相同的样本数; N为开关柜数据集的所有样本数量; n T为开关柜某类故障诊断结果正确的样本数量; n P为预测为该类故障的样本数; n R为该类故障样本数;i为开关柜的4种运行状态, i = 1,2 , 3,4
准确率 η A和Kappa系数 η K是SSA-CNN分类模型对开关柜故障诊断能力的全局指标,数值越大说明分类模型的性能越好; η P为分类模型对一种故障出现误判的评价指标,数值越大说明分类模型的误判率越低; η R为分类模型对某种故障出现漏判的评价指标,数值越大说明分类模型的漏判率越低。
本文以西北某地区电力部门10 kV高压开关柜为研究对象,选取其历史多源监测数据共计405组作为样本数据集,并且按照8∶2的比例将原始数据集划分为测试集和训练集,测试集去除数据标签,训练集保留数据标签,具体样本分布如表2所示。依据文献[15]和相关运维经验,将开关柜运行状态划分为:正常运行、局部放电故障、温升故障和机械故障4类。
表2可知,开关柜正常运行样本数为250组,占总样本数的61.73%,而故障样本数为155组,占总样本数的38.27%,其中机械故障样本数仅为20组,占总样本数的4.94%,开关柜原始数据集的正负样本比例严重失衡,从而会影响后续SSA-CNN模型的故障诊断准确性。因此,采用SMOTE算法分别对局部放电、温升和机械故障的样本数据进行扩充,使得开关柜每种运行状态的样本数量均达到250组。
为了进一步说明本文所提的少数类样本扩充方法对于提高开关柜故障识别准确率的可行性,分别采用随机采样法、SMOTE算法合成原始数据集的少数类样本,并将原始数据集、经样本扩充后的数据集作为SSA-CNN模型的输入,对模型输出结果进行对比,结果如表3所示。
表3可知,原始非均衡样本数据作为训练集时,基于SSA-CNN的故障诊断模型准确率仅为71.51%,Kappa系数为0.68,开关柜故障诊断精度较低。通过随机采样法、SMOTE算法对原始数据集的少数类样本进行扩充后,开关柜故障诊断模型的准确度分别提升了26.51%和36.34%。结果表明本文所提的基于SMOTE算法的少数类样本扩充方法,能够有效解决开关柜原始数据集中正负样本严重失衡的问题,显著提升故障诊断模型的准确性。
根据人工经验搭建基础CNN分类模型,具体设置如下:卷积层采用2层,每层卷积核大小分别为3×3,2×2,数量分别为32和64;每层卷积层后设置池化层、批标准化层,池化核的大小为2×2,步长为1,填充方式为Same;激活函数采用ReLU函数;全连接层采用2层,神经元数量分别为64和32;经过Softmax函数激活,输出量为4;优化器为Adam;学习率为0.001。而对于SSA-CNN分类模型的搭建,卷积层、全连接层、优化器等均与基础CNN模型相同,但卷积核大小与数量、全连接层的神经元个数、初始学习率等超参数则采用SSA优化,SSA初始参数设置如表4所示。
SSA-CNN分类模型对开关柜故障诊断结果如图4所示,混淆矩阵如图5所示,评价指标结果如表5所示。
分析图4表5可知,本文所提的基于SSA-CNN的故障诊断模型对开关柜4种运行状态的查准率均大于96%,查全率均大于92%,总体故障诊断准确率达到了97.5%。结果表明基于SSA-CNN的开关柜分类模型的故障诊断总体性能好,故障诊断灵敏度和可信度高。
为了验证SSA-CNN分类模型的优越性,将均衡化样本数据集作为输入量,采用BP神经网络(BPNN),SVM,CNN,PSO-CNN,GA-CNN等分类模型进行开关柜故障诊断,并与本文所提模型的输出结果进行对比。开关柜故障识别结果如表6所示。
表6可知,BP神经网络、支持向量机等传统分类模型的准确率低于90%,而具有多隐含层结构的CNN模型,能够自适应挖掘多源监测数据的深层特征,其故障识别精度达到91.5%。同时,对于SSA-CNN等改进CNN模型,由于优化了超参数,因此相比基础CNN模型的开关柜故障诊断准确率都得到了不同程度的提高。
横向比较PSO-CNN,GA-CNN,SSA-CNN可知,相比于其他2种分类模型,SSA-CNN模型在故障诊断精度和运算速率上都具备一定的优势。从故障诊断精度上看,SSA-CNN模型的准确率高达97.5%,明显高于其他2种模型。从运算速率上看,SSA-CNN模型收敛至最高准确度所需的迭代次数为24,低于PSO-CNN模型和GA-CNN模型。算例结果表明,所提方法能够有效识别开关柜局部放电故障、温升故障和机械故障,并且与传统故障诊断方法相比,所提方法的收敛性较好,精度较高。
本文提出了一种基于SMOTE-SSA-CNN的开关柜故障诊断方法,并通过算例验证了所提方法的有效性和优越性。得到的结论如下:
1)针对开关柜原始数据集中正负样本严重失衡的问题,采用SMOTE算法生成少数类样本数据,有效降低了原始数据集的不平衡度,使故障诊断结果更加准确。
2)针对人工经验选取CNN超参数难以构建最优网络问题,采用SSA算法优化CNN模型的学习率、卷积核大小与数量、全连接层神经元数量等超参数,算例结果表明改进后的方法收敛性更好,全局搜索能力更强,故障诊断准确率更高。
3)与传统故障诊断模型相比,本文提出的基于SMOTE-SSA-CNN的开关柜故障诊断模型具有更强的故障识别性能,可以满足实际运维检修工作需要,能够在缺少开关柜故障样本数量时,为运维工作人员及时准确地掌握开关柜运行状态提供参考。
  • 甘肃省重点研发计划(21YF5GA159)
参考文献 引证文献
排序方式:
[1]
贺建明, 刘坚钢, 易非凡, 等. 开关柜绝缘故障仿真与检测系统研究[J]. 高压电器, 2022, 58(3):23-28.
HE Jianming, LIU Jiangang, YI Feifan, et al. Research on simulation and detection system of insulation fault of switchgear cabinet[J]. High Voltage Apparatus, 2022, 58(3):23-28.
[2]
亢超群, 李二霞, 盛万兴, 等. 基于多源信息融合的配电真空开关柜动态状态评价研究[J]. 高压电器, 2017, 53(3):235-241.
KANG Chaoqun, LI Erxia, SHENG Wanxing, et al. Dynamic condition assessment for distribution vacuum switch cabinets based on multi-source information fusion[J]. High Voltage Apparatus, 2017, 53(3):235-241.
[3]
黄俊宁, 于群. 基于多源数据融合与设备相似性的高压开关柜评价模型[J]. 高压电器, 2023, 59(2):198-204.
HUANG Junning, YU Qun. Evaluation model high voltage switch cabinet based on multi-source data fusion and equipment similarity[J]. High Voltage Apparatus, 2023, 59(2):198-204.
[4]
徐卫东, 聂一雄, 陈云龙, 等. 固体绝缘开关柜局部放电严重程度评估方法[J]. 高压电器, 2019, 55(1):27-33.
XU Weidong, NIE Yixiong, CHEN Yunlong, et al. Evaluation method of severity of partial discharge in solid insulated switchgear[J]. High Voltage Apparatus, 2019, 55(1):27-33.
[5]
李江涛, 孙义, 李擎宇. 大电流开关柜梅花触头热缺陷评估算法研究[J]. 高压电器, 2020, 56(11):127-129.
LI Jiangtao, SUN Yi, LI Qingyu. Research on thermal defect assessment algorithms for tulip contacts of high current switchgear[J]. High Voltage Apparatus, 2020, 56(11):127-129.
[6]
袁港. 基于超声波的高压开关柜局部放电检测方法研究[D]. 沈阳: 沈阳农业大学, 2022.
YUAN Gang. Research on partial discharge detection method for high-voltage switchgear based on ultrasoun[D]. Shenyang: Shenyang Agricultural University, 2022.
[7]
辛业春, 崔金栋, 周川, 等. 基于多变量多尺度云样本熵和模糊支持向量机的开关柜故障分类[J]. 电网技术, 2016, 40(11):3597-3603.
XIN Yechun, CUI Jindong, ZHOU Chuan, et al. Fault classification for smart switchgear based on multivariate multiscale cloud sample entropy and fuzzy support vector machine[J]. Power System Technology, 2016, 40(11):3597-3603.
[8]
任明, 王玥, 关浩斌, 等. 沿面放电光脉冲发展特征与临界击穿判据研究[J]. 中国电机工程学报, 2024, 44(10):4123-4134.
REN Ming, WANG Yue, GUAN Haobin, et al. Development characteristics and critical breakdown criterion of surface discharge light pulse[J]. Proceedings of the CSEE, 2024, 44(10):4123-4134.
[9]
黄雪莜, 熊俊, 张宇, 等. 基于残差卷积神经网络的开关柜局部放电模式识别[J]. 中国电力, 2021, 54(2):44-51.
HUANG Xueyou, XIONG Jun, ZHANG Yu, et al. Partial discharge pattern recognition of switchgear based on residual convolutional neural network[J]. Eelctric Power, 2021, 54(2):44-51.
[10]
朱正国, 何斌斌, 胡冉, 等. 基于卷积神经网络的开关柜局部放电监测[J]. 电网与清洁能源, 2017, 33(3):17-22.
ZHU Zhengguo, HE Binbin, HU Ran, et al. Switch-gear partial discharge detection based on convolutional neural network[J]. Power System and Clean Energy, 2017, 33(3):17-22.
[11]
严英杰, 盛戈皞, 陈玉峰, 等. 基于大数据分析的输变电设备状态数据异常检测方法[J]. 中国电机工程学报, 2015, 35(1):52-59.
YAN Yingjie, SHENG Gehao, CHEN Yufeng, et al. An method for anomaly detection of state information of power equipment based on big data analysis[J]. Proceedings of the CSEE, 2015, 35(1):52-59.
[12]
廖瑞金, 王有元, 刘航, 等. 输变电设备状态评估方法的研究现状[J]. 高电压技术, 2018, 44(11):3454-3464.
LIAO Ruijin, WANG Youyuan, LIU Hang et al. Research status of condition assessment method for power equipment[J]. High Voltage Engineering, 2018, 44(11):3454-3464.
[13]
刘云鹏, 和家慧, 许自强, 等. 基于 SVM SMOTE 的电力变压器故障样本均衡化方法[J]. 高电压技术, 2020, 46(7):2522-2529.
LIU Yunpeng, HE Jiahui, XU Ziqiang, et al. Equalization method of power transformer fault sample based on SVM SMOTE[J]. High Voltage Engineering, 2020, 46(7):2522-2529.
[14]
丛伟, 胡亮亮, 孙世军, 等. 基于改进深度降噪自编码网络的电网气象防灾方法[J]. 电力系统自动化, 2019, 43(2):42-49.
CONG Wei, HU Liangliang, SUN Shijun, et al. Meteorological disaster prevention method for power grid based on improved stacked denoising auto-encoder network[J]. Automation of Electric Power Systems, 2019, 43(2):42-49.
[15]
国家电网公司运维检修部. 电网设备状态检测技术应用典型案例(2011—2013年)[M]. 北京: 中国电力出版社, 2014.
State Grid Corporation of China Operations and Maintenance Department. Typical cases of application of state detection technology for power grid equipment(2011—2013)[M]. Beijing: China Electric Power Press, 2014.
[16]
周飞燕, 金林鹏, 董军. 卷积神经网络研究综述[J]. 计算机学报, 2017, 40(6):1229-1251.
ZHOU Feiyan, JIN Linpeng, DONG Jun. Review of convolution neural network[J]. Chinese Journal of Computers, 2017, 40(6):1229-1251.
[17]
张重远, 罗世豪, 岳浩天, 等. 基于Mel时频谱-卷积神经网络的变压器铁芯声纹模式识别方法[J]. 高电压技术, 2020, 46(2):413-423.
ZHANG Zhongyuan, LUO Shihao, YUE Haotian, et al. Pattern recognition of acoustic signals of transformer core based on Mel-spectrum and CNN[J]. High Voltage Engineering, 2020, 46(2):413-423.
[18]
刘展程, 王爽, 唐波. 基于 SSA-BiGRU-Attention 模型的变压器油中溶解气体含量预测[J]. 高电压技术, 2022, 48(8):2972-2981.
LIU Zhancheng, WANG Shuang, TANG Bo. Prediction of dissolved gas content in transformer oil based on SSA-BiGRU-Attention model[J]. High Voltage Engineering, 2022, 48(8):2972-2981.
[19]
王艳, 李伟, 赵洪山, 等. 基于油中溶解气体分析的DBN-SSAELM变压器故障诊断方法[J]. 电力系统保护与控制, 2023, 51(4):32-42.
WANG Yan, LI Wei, ZHAO Hongshan, et al. Transformer DGA fault diagnosis method based on DBN-SSAELM[J]. Power System Protection and Control, 2023, 51(4):32-42.
2024年第54卷第10期
PDF下载
166
77
引用本文
BibTeX
文章信息
doi: 10.19457/j.1001-2095.dqcd25533
  • 接收时间:2023-12-01
  • 首发时间:2025-11-11
  • 出版时间:2024-10-20
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2023-12-01
  • 修回日期:2023-12-28
基金
甘肃省重点研发计划(21YF5GA159)
作者信息
    国网甘南供电公司,甘肃 甘南藏族自治州 747000
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/dqcd/CN/10.19457/j.1001-2095.dqcd25533
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