Article(id=1146828030355308578, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1146828028623066093, articleNumber=null, orderNo=null, doi=10.13234/j.issn.2095-2805.2025.1.143, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=research-article, receivedDate=1652284800000, receivedDateStr=2022-05-12, revisedDate=1656172800000, revisedDateStr=2022-06-26, acceptedDate=1657123200000, acceptedDateStr=2022-07-07, onlineDate=1751354709470, onlineDateStr=2025-07-01, pubDate=1738166400000, pubDateStr=2025-01-30, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1751354709470, onlineIssueDateStr=2025-07-01, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=1752073878861, onlineFirstDateStr=2025-07-09, sourceXml=null, magXml=null, createTime=1751354709470, creator=13701087609, updateTime=1751354709470, updator=13701087609, issue=Issue{id=1146828028623066093, tenantId=1146029695717560320, journalId=1146031654075715584, year='2025', volume='23', issue='1', pageStart='1', pageEnd='258', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1751354709057, creator=13701087609, updateTime=1765499536223, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1206155733847044492, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1146828028623066093, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1206155733847044493, tenantId=1146029695717560320, journalId=1146031654075715584, issueId=1146828028623066093, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=143, endPage=150, ext={EN=ArticleExt(id=1149844445857866569, articleId=1146828030355308578, tenantId=1146029695717560320, journalId=1146031654075715584, language=EN, title=Research on Fault Diagnosis of Photovoltaic Array Based on SOA-SVM Model, columnId=1152281492550987902, journalTitle=Journal of Power Supply, columnName=Renewable Energy System, runingTitle=null, highlight=null, articleAbstract=

Aimed at the problem that the accuracy of photovoltaic array fault diagnosis based on support vector machine (SVM) is not high and it is easily affected by the kernel function and penalty factor parameters, a photovoltaic array fault diagnosis method based on SVM optimized by the seagull optimization algorithm (SOA) is proposed. The SOA is introduced to optimize the parameters of the SVM model, and an SOA-SVM fault diagnosis model based on the optimal parameters is established. MATLAB software is used to build a photovoltaic array simulation model, and the characteristic parameters under different fault types are extracted and further inputted into the SOA-SVM model for fault diagnosis. Experimental results show that the fault diagnosis accuracy of the SVM model optimized by SOA is significantly improved. Compared with the ABC-SVM and PSO-SVM models, the SOA-SVM model converges faster in the optimization process and has a higher fault diagnosis accuracy.

, correspAuthors=Peisheng SUN, 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=Peisheng SUN, Tangxian CHEN, Chen CHENG, Zheng LI), CN=ArticleExt(id=1146828034423783691, articleId=1146828030355308578, tenantId=1146029695717560320, journalId=1146031654075715584, language=CN, title=基于SOA-SVM模型的光伏阵列故障诊断研究, columnId=1149829992055595012, journalTitle=电源学报, columnName=新能源系统, runingTitle=null, highlight=null, articleAbstract=

针对支持向量机SVM(support vector machine)用于光伏阵列故障诊断时准确率不高、且易受核函数与惩罚因子参数影响的问题,提出1种基于海鸥优化算法SOA(seagull optimization algorithm)支持向量机的光伏阵列故障诊断方法。引入海鸥优化算法对SVM模型进行参数寻优,建立基于最优参数的SOA-SVM故障诊断模型;利用MATLAB软件搭建光伏阵列仿真模型,提取不同故障类型下的特征参数并输入到SOA-SVM模型进行故障诊断。实验结果表明:经SOA优化后的SVM模型故障诊断准确率显著提高,且相比于基于人工蜂群ABC(artificial bee colony)算法的ABC-SVM模型和基于粒子群优化PSO(particle swarm optimization)算法的PSO-SVM模型,SOA-SVM模型具有更快的寻优收敛迭代速度和更高的故障诊断准确率。

, correspAuthors=孙培胜, authorNote=null, correspAuthorsNote=
孙培胜(1996— ),男,硕士研究生。研究方向:光伏发电故障诊断技术。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=zeIZSGyFzImYL+LIJSHiTQ==, magXml=jrNN/TrE3rs4PmK4Xn353A==, pdfUrl=null, pdf=A4OC3Jbh/KvfqsZL2xxPfA==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=x2PyhzfI5krVPnSCXMPNyA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=837SnhMeIgwcAZ8Z6aLFDw==, mapNumber=null, authorCompany=null, fund=null, authors=

陈堂贤(1965— ),男,学士副教授。研究方向:柔性电力系统、风能及新能源发电技术。E-mail:

程陈(1998— ),男,硕士研究生。研究方向:光伏发电技术。E-mail:

李正(1997— ),男,硕士研究生。研究方向:柔性直流输电技术。E-mail:

, authorsList=孙培胜, 陈堂贤, 程陈, 李正)}, authors=[Author(id=1205931304139419973, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=sps9610@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1205931304261054799, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, authorId=1205931304139419973, language=EN, stringName=Peisheng SUN, firstName=Peisheng, middleName=null, lastName=SUN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205931304370106711, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, authorId=1205931304139419973, language=CN, stringName=孙培胜, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=三峡大学电气与新能源学院,宜昌 443002, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205931304005202230, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, xref=null, ext=[AuthorCompanyExt(id=1205931304017785142, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, companyId=1205931304005202230, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China), AuthorCompanyExt(id=1205931304026173752, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, companyId=1205931304005202230, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=三峡大学电气与新能源学院,宜昌 443002)])]), Author(id=1205931304458187104, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=114830073@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1205931304584016239, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, authorId=1205931304458187104, language=EN, stringName=Tangxian CHEN, firstName=Tangxian, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205931305771004277, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, authorId=1205931304458187104, language=CN, stringName=陈堂贤, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=三峡大学电气与新能源学院,宜昌 443002, bio={"content":"

陈堂贤(1965— ),男,学士副教授。研究方向:柔性电力系统、风能及新能源发电技术。E-mail:

"}, bioImg=null, bioContent=

陈堂贤(1965— ),男,学士副教授。研究方向:柔性电力系统、风能及新能源发电技术。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205931304005202230, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, xref=null, ext=[AuthorCompanyExt(id=1205931304017785142, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, companyId=1205931304005202230, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China), AuthorCompanyExt(id=1205931304026173752, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, companyId=1205931304005202230, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=三峡大学电气与新能源学院,宜昌 443002)])]), Author(id=1205931305955553664, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=839524742@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1205931306110742927, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, authorId=1205931305955553664, language=EN, stringName=Chen CHENG, firstName=Chen, middleName=null, lastName=CHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205931306211406236, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, authorId=1205931305955553664, language=CN, stringName=程陈, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=三峡大学电气与新能源学院,宜昌 443002, bio={"content":"

程陈(1998— ),男,硕士研究生。研究方向:光伏发电技术。E-mail:

"}, bioImg=null, bioContent=

程陈(1998— ),男,硕士研究生。研究方向:光伏发电技术。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205931304005202230, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, xref=null, ext=[AuthorCompanyExt(id=1205931304017785142, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, companyId=1205931304005202230, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China), AuthorCompanyExt(id=1205931304026173752, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, companyId=1205931304005202230, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=三峡大学电气与新能源学院,宜昌 443002)])]), Author(id=1205931306307875235, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=sdwfcylz@126.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1205931306404344238, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, authorId=1205931306307875235, language=EN, stringName=Zheng LI, firstName=Zheng, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1205931306479841719, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, authorId=1205931306307875235, language=CN, stringName=李正, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=三峡大学电气与新能源学院,宜昌 443002, bio={"content":"

李正(1997— ),男,硕士研究生。研究方向:柔性直流输电技术。E-mail:

"}, bioImg=null, bioContent=

李正(1997— ),男,硕士研究生。研究方向:柔性直流输电技术。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1205931304005202230, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, xref=null, ext=[AuthorCompanyExt(id=1205931304017785142, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, companyId=1205931304005202230, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China), AuthorCompanyExt(id=1205931304026173752, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, companyId=1205931304005202230, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=三峡大学电气与新能源学院,宜昌 443002)])])], keywords=[Keyword(id=1205931306685362636, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, orderNo=1, keyword=Photovoltaic array), Keyword(id=1205931306802803157, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, orderNo=2, keyword=fault diagnosis), Keyword(id=1205931306907660765, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, orderNo=3, keyword=seagull optimization algorithm (SOA)), Keyword(id=1205931306991546852, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, orderNo=4, keyword=support vector machine (SVM)), Keyword(id=1205931307113181680, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, orderNo=1, keyword=光伏阵列), Keyword(id=1205931307239010810, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, orderNo=2, keyword=故障诊断), Keyword(id=1205931307356451330, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, orderNo=3, keyword=海鸥优化算法), Keyword(id=1205931307448726027, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, orderNo=4, keyword=支持向量机)], refs=[Reference(id=1205931311856939728, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=12, pageStart=465, pageEnd=470, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=高伟, 黄俊铭, journalName=太阳能学报, refType=null, unstructuredReference=高伟, 黄俊铭. 基于SSELM的光伏组件故障智能诊断方法[J]. 太阳能学报, 2021, 42(12): 465-470., articleTitle=基于SSELM的光伏组件故障智能诊断方法, refAbstract=null), Reference(id=1205931311986963156, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=12, pageStart=465, pageEnd=470, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=Gao Wei, Huang Junming, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=Gao Wei, Huang Junming. Intelligent fault diagnosis method of photovoltaic module via SSELM[J]. Acta Energiae Solaris Sinica, 2021, 42(12): 465-470. (in Chinese), articleTitle=Intelligent fault diagnosis method of photovoltaic module via SSELM, refAbstract=null), Reference(id=1205931312175706844, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=12, pageStart=140, pageEnd=148, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=余玲珍, 覃涛, 龙道银, journalName=激光杂志, refType=null, unstructuredReference=余玲珍, 覃涛, 龙道银, 等. TGBA优化核极限学习机的光伏阵列故障诊断[J]. 激光杂志, 2021, 42(12): 140-148., articleTitle=TGBA优化核极限学习机的光伏阵列故障诊断, refAbstract=null), Reference(id=1205931312284758757, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=42, issue=12, pageStart=140, pageEnd=148, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=Yu Lingzhen, Qin Tao, Long Daoyin, journalName=Laser Journal, refType=null, unstructuredReference=Yu Lingzhen, Qin Tao, Long Daoyin, et al. Fault diagnosis of PV array based on TGBA optimized kernel extreme learning machine[J]. Laser Journal, 2021, 42(12): 140-148. (in Chinese), articleTitle=Fault diagnosis of PV array based on TGBA optimized kernel extreme learning machine, refAbstract=null), Reference(id=1205931312389616361, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2019, volume=43, issue=9, pageStart=1525, pageEnd=1527, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=宋文海, 李田泽, 田晖, journalName=电源技术, refType=null, unstructuredReference=宋文海, 李田泽, 田晖, 等. 基于概率神经网络的光伏阵列故障诊断研究[J]. 电源技术, 2019, 43(9): 1525-1527, 1567., articleTitle=基于概率神经网络的光伏阵列故障诊断研究, refAbstract=null), Reference(id=1205931312502862573, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2019, volume=43, issue=9, pageStart=1525, pageEnd=1527, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=Song Wenhai, Li Tianze, Tian Hui, journalName=Chinese Journal of Power Sources, refType=null, unstructuredReference=Song Wenhai, Li Tianze, Tian Hui, et al. Research on fault diagnosis of PV array based on PNN[J]. Chinese Journal of Power Sources, 2019, 43(9): 1525-1527, 1567. (in Chinese), articleTitle=Research on fault diagnosis of PV array based on PNN, refAbstract=null), Reference(id=1205931312616108787, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=22, issue=10, pageStart=57, pageEnd=64, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=陈世群, 高伟, 陈孝琪, journalName=电气技术, refType=null, unstructuredReference=陈世群, 高伟, 陈孝琪, 等. 一种基于极限学习机和皮尔逊相关系数的光伏阵列故障快速诊断方法[J]. 电气技术, 2021, 22(10): 57-64., articleTitle=一种基于极限学习机和皮尔逊相关系数的光伏阵列故障快速诊断方法, refAbstract=null), Reference(id=1205931312737743608, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=22, issue=10, pageStart=57, pageEnd=64, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=Chen Shiqun, Gao Wei, Chen Xiaoqi, journalName=Electrical Engineering, refType=null, unstructuredReference=Chen Shiqun, Gao Wei, Chen Xiaoqi, et al. A fast fault diagnosis method for photovoltaic array via extreme learning machine and Pearson’s correlation coefficient[J]. Electrical Engineering, 2021, 22(10): 57-64. (in Chinese), articleTitle=A fast fault diagnosis method for photovoltaic array via extreme learning machine and Pearson’s correlation coefficient, refAbstract=null), Reference(id=1205931312846795517, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2017, volume=31, issue=8, pageStart=1239, pageEnd=1246, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=梅恒荣, 殷礼胜, 刘冬梅, journalName=电子测量与仪器学报, refType=null, unstructuredReference=梅恒荣, 殷礼胜, 刘冬梅, 等. 改进粒子群算法优化的SVM模拟电路故障诊断[J]. 电子测量与仪器学报, 2017, 31(8): 1239-1246., articleTitle=改进粒子群算法优化的SVM模拟电路故障诊断, refAbstract=null), Reference(id=1205931312951653121, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2017, volume=31, issue=8, pageStart=1239, pageEnd=1246, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=Mei Hengrong, Yin Lisheng, Liu Dongmei, journalName=Journal of Electronic Measurement and Instru-mentation, refType=null, unstructuredReference=Mei Hengrong, Yin Lisheng, Liu Dongmei, et al. Ana-logue circuit fault diagnosis based on SVM optimized by IPSO[J]. Journal of Electronic Measurement and Instru-mentation, 2017, 31(8): 1239-1246. (in Chinese), articleTitle=Ana-logue circuit fault diagnosis based on SVM optimized by IPSO, refAbstract=null), Reference(id=1205931313052316421, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=3, pageStart=370, pageEnd=373, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=刘东, 李田泽, 刘开石, journalName=电源技术, refType=null, unstructuredReference=刘东, 李田泽, 刘开石, 等. GA-BP神经网络在光伏阵列故障检测中的应用研究[J]. 电源技术, 2021, 45(3): 370-373., articleTitle=GA-BP神经网络在光伏阵列故障检测中的应用研究, refAbstract=null), Reference(id=1205931313136202505, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=3, pageStart=370, pageEnd=373, url=null, language=null, rfNumber=[6], rfOrder=11, authorNames=Liu Dong, Li Tianze, Liu Kaishi, journalName=Chinese Journal of Power Sources, refType=null, unstructuredReference=Liu Dong, Li Tianze, Liu Kaishi, et al. Research on GA-BP neural network in photovoltaic array fault detection[J]. Chinese Journal of Power Sources, 2021, 45(3): 370-373. (in Chinese), articleTitle=Research on GA-BP neural network in photovoltaic array fault detection, refAbstract=null), Reference(id=1205931313262031632, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2020, volume=44, issue=1, pageStart=76, pageEnd=79, url=null, language=null, rfNumber=[7], rfOrder=12, authorNames=张杰, 易辉, 张霞, journalName=电源技术, refType=null, unstructuredReference=张杰, 易辉, 张霞, 等. 基于布谷鸟算法的光伏组件故障诊断模型优化[J]. 电源技术, 2020, 44(1): 76-79., articleTitle=基于布谷鸟算法的光伏组件故障诊断模型优化, refAbstract=null), Reference(id=1205931313421415188, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2020, volume=44, issue=1, pageStart=76, pageEnd=79, url=null, language=null, rfNumber=[7], rfOrder=13, authorNames=Zhang Jie, Yi Hui, Zhang Xia, journalName=Chinese Journal of Power Sources, refType=null, unstructuredReference=Zhang Jie, Yi Hui, Zhang Xia, et al. Optimization of fault diagnosis model for photovoltaic module based on cuckoo algorithm[J]. Chinese Journal of Power Sources, 2020, 44(1): 76-79. (in Chinese), articleTitle=Optimization of fault diagnosis model for photovoltaic module based on cuckoo algorithm, refAbstract=null), Reference(id=1205931313530467099, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=58, issue=2, pageStart=118, pageEnd=124, url=null, language=null, rfNumber=[8], rfOrder=14, authorNames=马纪梅, 张志耀, 张启然, journalName=电测与仪表, refType=null, unstructuredReference=马纪梅, 张志耀, 张启然. 基于改进RBF神经网络的光伏组件故障诊断[J]. 电测与仪表, 2021, 58(2): 118-124., articleTitle=基于改进RBF神经网络的光伏组件故障诊断, refAbstract=null), Reference(id=1205931314734232350, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=58, issue=2, pageStart=118, pageEnd=124, url=null, language=null, rfNumber=[8], rfOrder=15, authorNames=Ma Jimei, Zhang Zhiyao, Zhang Qiran, journalName=Electrical Measurement & Instrumentation, refType=null, unstructuredReference=Ma Jimei, Zhang Zhiyao, Zhang Qiran. Fault diagnosis of photovoltaic modules based on improved RBF neural network[J]. Electrical Measurement & Instrumentation, 2021, 58(2): 118-124. (in Chinese), articleTitle=Fault diagnosis of photovoltaic modules based on improved RBF neural network, refAbstract=null), Reference(id=1205931314834895648, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=39, issue=6, pageStart=760, pageEnd=765, url=null, language=null, rfNumber=[9], rfOrder=16, authorNames=张晓鹏, 张兴忠, journalName=可再生能源, refType=null, unstructuredReference=张晓鹏, 张兴忠. 基于高斯核函数的支持向量机光伏故障诊断研究[J]. 可再生能源, 2021, 39(6): 760-765., articleTitle=基于高斯核函数的支持向量机光伏故障诊断研究, refAbstract=null), Reference(id=1205931314952336165, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=39, issue=6, pageStart=760, pageEnd=765, url=null, language=null, rfNumber=[9], rfOrder=17, authorNames=Zhang Xiaopeng, Zhang Xingzhong, journalName=Renewable Energy Resources, refType=null, unstructuredReference=Zhang Xiaopeng, Zhang Xingzhong. Research on photov-oltaic fault diagnosis based on time domain characteristics[J]. Renewable Energy Resources, 2021, 39(6): 760-765. (in Chinese), articleTitle=Research on photov-oltaic fault diagnosis based on time domain characteristics, refAbstract=null), Reference(id=1205931315048805162, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2023, volume=45, issue=2, pageStart=5380, pageEnd=5395, url=null, language=null, rfNumber=[10], rfOrder=18, authorNames=Wang Junjie, Gao Dedong, Zhu Shaokang, journalName=Utilization, and Environmental Effects, refType=null, unstructuredReference=Wang Junjie, Gao Dedong, Zhu Shaokang, et al. Fault diagnosis method of photovoltaic array based on support vector machine[J]. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 2023, 45(2): 5380-5395., articleTitle=Fault diagnosis method of photovoltaic array based on support vector machine, refAbstract=null), Reference(id=1205931315136885548, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=9, pageStart=1171, pageEnd=1174, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=刘开石, 李田泽, 刘东, journalName=电源技术, refType=null, unstructuredReference=刘开石, 李田泽, 刘东, 等. 基于ABC-SVM算法的光伏阵列故障诊断[J]. 电源技术, 2021, 45(9): 1171-1174., articleTitle=基于ABC-SVM算法的光伏阵列故障诊断, refAbstract=null), Reference(id=1205931315237548850, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=9, pageStart=1171, pageEnd=1174, url=null, language=null, rfNumber=[11], rfOrder=20, authorNames=Liu Kaishi, Li Tianze, Liu Dong, journalName=Chinese Journal of Power Sources, refType=null, unstructuredReference=Liu Kaishi, Li Tianze, Liu Dong, et al. Fault diagnosis of PV array based on ABC-SVM algorithm[J]. Chinese Journal of Power Sources, 2021, 45(9): 1171-1174. (in Chinese), articleTitle=Fault diagnosis of PV array based on ABC-SVM algorithm, refAbstract=null), Reference(id=1205931315367572274, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2017, volume=45, issue=5, pageStart=652, pageEnd=658, url=null, language=null, rfNumber=[12], rfOrder=21, authorNames=林培杰, 陈志聪, 吴丽君, journalName=福州大学学报(自然科学版), refType=null, unstructuredReference=林培杰, 陈志聪, 吴丽君, 等. 一种PSO-SVM的光伏阵列故障检测与分类[J]. 福州大学学报(自然科学版), 2017, 45(5): 652-658., articleTitle=一种PSO-SVM的光伏阵列故障检测与分类, refAbstract=null), Reference(id=1205931315443069751, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2017, volume=45, issue=5, pageStart=652, pageEnd=658, url=null, language=null, rfNumber=[12], rfOrder=22, authorNames=Lin Peijie, Chen Zhicong, Wu Lijun, journalName=Journal of Fuzhou University (Natural Science Edition), refType=null, unstructuredReference=Lin Peijie, Chen Zhicong, Wu Lijun, et al. Fault detection and classification for photovoltaic arrays based on PSO-SVM[J]. Journal of Fuzhou University (Natural Science Edition), 2017, 45(5): 652-658. (in Chinese), articleTitle=Fault detection and classification for photovoltaic arrays based on PSO-SVM, refAbstract=null), Reference(id=1205931315539538744, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=9, issue=null, pageStart=69307, pageEnd=69315, url=null, language=null, rfNumber=[13], rfOrder=23, authorNames=Tuerxun W, Xu Chang, Guo Hongyu, journalName=IEEE Access, refType=null, unstructuredReference=Tuerxun W, Xu Chang, Guo Hongyu, et al. Fault diagn-osis of wind turbines based on a support vector machine optimized by the sparrow search algorithm[J]. IEEE Access, 2021, 9: 69307-69315., articleTitle=Fault diagn-osis of wind turbines based on a support vector machine optimized by the sparrow search algorithm, refAbstract=null), Reference(id=1205931315623424829, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2016, volume=174, issue=null, pageStart=643, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=24, authorNames=Yin Zuyu, Hou Jian, journalName=Neurocomputing, refType=null, unstructuredReference=Yin Zuyu, Hou Jian. Recent advances on SVM based fault diagnosis and process monitoring in complicated industrial processes[J]. Neurocomputing, 2016, 174: 643-650., articleTitle=Recent advances on SVM based fault diagnosis and process monitoring in complicated industrial processes, refAbstract=null), Reference(id=1205931315711505214, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=25, authorNames=尹嘉鹏, journalName=支持向量机核函数及关键参数选择研究, refType=null, unstructuredReference=尹嘉鹏. 支持向量机核函数及关键参数选择研究[D]. 哈尔滨: 哈尔滨工业大学, 2016., articleTitle=null, refAbstract=null), Reference(id=1205931315807974212, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=26, authorNames=Yin Jiapeng, journalName=Research on kernel function and key par-ameter selection of support vector machine, refType=null, unstructuredReference=Yin Jiapeng. Research on kernel function and key par-ameter selection of support vector machine[D]. Harbin: Harbin Institute of Technology, 2016. (in Chinese), articleTitle=null, refAbstract=null), Reference(id=1205931315900248902, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2019, volume=165, issue=null, pageStart=169, pageEnd=196, url=null, language=null, rfNumber=[16], rfOrder=27, authorNames=Dhiman G, Kumar V, journalName=Knowledge-Based Systems, refType=null, unstructuredReference=Dhiman G, Kumar V. Seagull optimization algorithm: Theory and its applications for large-scale industrial engineering problems[J]. Knowledge-Based Systems, 2019, 165: 169-196., articleTitle=Seagull optimization algorithm: Theory and its applications for large-scale industrial engineering problems, refAbstract=null), Reference(id=1205931315992523591, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=35, issue=3, pageStart=123, pageEnd=129, url=null, language=null, rfNumber=[17], rfOrder=28, authorNames=李黄曼, 张勇, 张瑶, journalName=电子测量与仪器学报, refType=null, unstructuredReference=李黄曼, 张勇, 张瑶. 基于ISSA优化SVM的变压器故障诊断研究[J]. 电子测量与仪器学报, 2021, 35(3): 123-129., articleTitle=基于ISSA优化SVM的变压器故障诊断研究, refAbstract=null), Reference(id=1205931316097381194, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, doi=null, pmid=null, pmcid=null, year=2021, volume=35, issue=3, pageStart=123, pageEnd=129, url=null, language=null, rfNumber=[17], rfOrder=29, authorNames=Li Huangman, Zhang Yong, Zhang Yao, journalName=Journal of Electronic Measurement and Instrumentation, refType=null, unstructuredReference=Li Huangman, Zhang Yong, Zhang Yao. Study of trans-former fault diagnosis based on improved sparrow search algorithm optimized support vector machine[J]. Journal of Electronic Measurement and Instrumentation, 2021, 35(3): 123-129. (in Chinese), articleTitle=Study of trans-former fault diagnosis based on improved sparrow search algorithm optimized support vector machine, refAbstract=null)], funds=[Fund(id=1205931311517201086, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, awardId=61603212, language=EN, fundingSource=National Natural Science Foundation of China(61603212), fundOrder=null, country=null), Fund(id=1205931311613670080, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, awardId=61603212, language=CN, fundingSource=国家自然科学基金资助项目(61603212), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1205931304005202230, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, xref=null, ext=[AuthorCompanyExt(id=1205931304017785142, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, companyId=1205931304005202230, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China), AuthorCompanyExt(id=1205931304026173752, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, companyId=1205931304005202230, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=三峡大学电气与新能源学院,宜昌 443002)])], figs=[ArticleFig(id=1205931307687801371, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, label=Fig. 1, caption=Classification of linear separable data, figureFileSmall=SFRzL881g0zO85YKiycYYg==, figureFileBig=x2PyhzfI5krVPnSCXMPNyA==, tableContent=null), ArticleFig(id=1205931307780076066, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, label=图1, caption=线性可分数据分类, figureFileSmall=SFRzL881g0zO85YKiycYYg==, figureFileBig=x2PyhzfI5krVPnSCXMPNyA==, tableContent=null), ArticleFig(id=1205931308082065972, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, label=Fig. 2, caption=Classification of nonlinear separable data, figureFileSmall=a1ovG6Eezqo64mHw5kuNBA==, figureFileBig=SyQvRJaSHmd7TMo/6Bbaig==, tableContent=null), ArticleFig(id=1205931308191117881, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, label=图2, caption=非线性可分数据分类, figureFileSmall=a1ovG6Eezqo64mHw5kuNBA==, figureFileBig=SyQvRJaSHmd7TMo/6Bbaig==, tableContent=null), ArticleFig(id=1205931308287586883, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, label=Fig. 3, caption=Simulation model of photovoltaic array, figureFileSmall=JHC/62YQGgw5HBGdOVdhcw==, figureFileBig=txeYCVTiFlMjPBgE3g2gXw==, tableContent=null), ArticleFig(id=1205931308354695750, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, label=图3, caption=光伏阵列仿真模型, figureFileSmall=JHC/62YQGgw5HBGdOVdhcw==, figureFileBig=txeYCVTiFlMjPBgE3g2gXw==, tableContent=null), ArticleFig(id=1205931308476330574, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, label=Fig. 4, caption=I-U characteristic curves in different running states, figureFileSmall=2KiAikeV98VfUAfXx19I3Q==, figureFileBig=Eziw8dburogcgOxG/j0Nog==, tableContent=null), ArticleFig(id=1205931308585382482, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, label=图4, caption=不同运行状态的I-U特性曲线, figureFileSmall=2KiAikeV98VfUAfXx19I3Q==, figureFileBig=Eziw8dburogcgOxG/j0Nog==, tableContent=null), ArticleFig(id=1205931308694434392, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, label=Fig. 5, caption=P-U characteristic curves in different running states, figureFileSmall=dcB7jAxZGc0HKpx3QWoBrA==, figureFileBig=h9EEmMV26fsD28iMCf7Reg==, tableContent=null), ArticleFig(id=1205931308816069215, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, label=图5, caption=不同运行状态的P-U特性曲线, figureFileSmall=dcB7jAxZGc0HKpx3QWoBrA==, figureFileBig=h9EEmMV26fsD28iMCf7Reg==, tableContent=null), ArticleFig(id=1205931308925121125, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, label=Fig. 6, caption=Process of SVM optimized by SOA, figureFileSmall=lhr3ksz810vxEF2oUQoKKg==, figureFileBig=jqRTJv4uwyfDLFTJIeoXrw==, tableContent=null), ArticleFig(id=1205931309004812906, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, label=图6, caption=SOA算法优化SVM流程, figureFileSmall=lhr3ksz810vxEF2oUQoKKg==, figureFileBig=jqRTJv4uwyfDLFTJIeoXrw==, tableContent=null), ArticleFig(id=1205931310208578161, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, label=Fig. 7, caption=Comparison of diagnosis results under different random value times of unoptimized SVM, figureFileSmall=DJOl8bfZqT56o9TWte+X/w==, figureFileBig=UTpUCWwD55m21VyGcauIfA==, tableContent=null), ArticleFig(id=1205931310300852857, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, label=图7, caption=未优化SVM不同随机取值次数下诊断结果对比, figureFileSmall=DJOl8bfZqT56o9TWte+X/w==, figureFileBig=UTpUCWwD55m21VyGcauIfA==, tableContent=null), ArticleFig(id=1205931310418293372, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, label=Fig. 8, caption=Diagnostic result of unoptimized SVM model, figureFileSmall=6+7Whz8vjRLWTdHcSrZCmw==, figureFileBig=RzPtRRYA3WXJIaEbN2As3g==, tableContent=null), ArticleFig(id=1205931310523150980, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, label=图8, caption=未优化SVM模型诊断结果, figureFileSmall=6+7Whz8vjRLWTdHcSrZCmw==, figureFileBig=RzPtRRYA3WXJIaEbN2As3g==, tableContent=null), ArticleFig(id=1205931310619619979, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, label=Fig. 9, caption=Diagnostic result of SVM optimized by SOA, figureFileSmall=XsdVRtiwTjFV55CVWrpVoQ==, figureFileBig=aac/LewStFlf582sOsqDCA==, tableContent=null), ArticleFig(id=1205931310724477584, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, label=图9, caption=SOA-SVM诊断结果, figureFileSmall=XsdVRtiwTjFV55CVWrpVoQ==, figureFileBig=aac/LewStFlf582sOsqDCA==, tableContent=null), ArticleFig(id=1205931310825140885, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, label=Fig. 10, caption=Fitness curves of different algorithm models, figureFileSmall=TsztAq2TrnWxIRyu7vXNOA==, figureFileBig=j2OJjczlQHSb3uBc70hozw==, tableContent=null), ArticleFig(id=1205931310913221275, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, label=图10, caption=不同算法模型适应度曲线, figureFileSmall=TsztAq2TrnWxIRyu7vXNOA==, figureFileBig=j2OJjczlQHSb3uBc70hozw==, tableContent=null), ArticleFig(id=1205931311013884579, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, label=Tab. 1, caption=

Typical data in different running states

, figureFileSmall=null, figureFileBig=null, tableContent=
系统参数 运行状态
正常 短路 老化 开路 阴影
短路电流Isc/A 55.41 55.41 55.39 46.20 55.41
开路电压Uoc/V 205.48 191.61 208.20 205.50 207.30
最大功率点电流Ipm/A 51.03 51.48 47.84 42.52 51.30
最大功率点电压Upm/V 170.48 156.61 169.40 170.48 147.34
), ArticleFig(id=1205931311118742183, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, label=表1, caption=

不同运行状态典型数据

, figureFileSmall=null, figureFileBig=null, tableContent=
系统参数 运行状态
正常 短路 老化 开路 阴影
短路电流Isc/A 55.41 55.41 55.39 46.20 55.41
开路电压Uoc/V 205.48 191.61 208.20 205.50 207.30
最大功率点电流Ipm/A 51.03 51.48 47.84 42.52 51.30
最大功率点电压Upm/V 170.48 156.61 169.40 170.48 147.34
), ArticleFig(id=1205931311190045356, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=EN, label=Tab. 2, caption=

Diagnostic results of different algorithm models

, figureFileSmall=null, figureFileBig=null, tableContent=
算法模型 训练准确
率/%
测试准确
率/%
收敛迭代次数 最优
适应度
ABC-SVM 90.54 94.55 10 0.149 1
PSO-SVM 92.12 96.36 30 0.115 2
SOA-SVM 90.77 98.18 30 0.110 5
), ArticleFig(id=1205931311286514353, tenantId=1146029695717560320, journalId=1146031654075715584, articleId=1146828030355308578, language=CN, label=表2, caption=

不同算法模型诊断结果

, figureFileSmall=null, figureFileBig=null, tableContent=
算法模型 训练准确
率/%
测试准确
率/%
收敛迭代次数 最优
适应度
ABC-SVM 90.54 94.55 10 0.149 1
PSO-SVM 92.12 96.36 30 0.115 2
SOA-SVM 90.77 98.18 30 0.110 5
)], attaches=null, journal=Journal(id=1046111678587809797, delFlag=0, nameCn=电源学报, nameEn=Journal of Power Supply, nameHistory1=null, nameHistory2=null, issn=2095-2805, eissn=, cn=12-1420/TM, coden=null, periodic=bio-monthly, language=CN, oaType=是, 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=Mx+A2dn+ULnPHuEAI1LruQ==, journalPrice=null, startedYear=null, abbrevIsoEn=J Power Supp, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1759802942253, createdBy=null, updatedBy=18614031015, firstLetterCn=J, firstLetterEn=J, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=Mx+A2dn+ULnPHuEAI1LruQ==, picEn=yHt2vwjzkDgqh+JDCfJKoQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1162453073839375337, language=CN, name=电源学报, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.jops.cn/EN/home, createdTime=1755080010137, updatedTime=1755080010137, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.jops.cn/CN/column/column7.shtml, submissionAuthorUrl=https://mc03.manuscriptcentral.com/jops, submissionEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionReviewUrl=https://mc03.manuscriptcentral.com/jops, submissionCeEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionAeEditorUrl=https://mc03.manuscriptcentral.com/jops, option={"copyright":""}), JournalExt(id=1162453073902289898, language=EN, name=Journal of Power Supply, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.jops.cn/CN/home, createdTime=1755080010152, updatedTime=1755080010152, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.jops.cn/EN/column/column7.shtml, submissionAuthorUrl=https://mc03.manuscriptcentral.com/jops, submissionEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionReviewUrl=https://mc03.manuscriptcentral.com/jops, submissionCeEditorUrl=https://mc03.manuscriptcentral.com/jops, submissionAeEditorUrl=https://mc03.manuscriptcentral.com/jops, option={"copyright":""})], databaseList=null, tenantJournalId=1146031654075715584, websiteList=[Website(id=1146832214672683008, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031654075715584, 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/dyxb/EN, language=EN, createTime=1751355707101, createBy=18614031015, updateTime=1753435268747, updateBy=18614031015, name=电源学报-英文站点, tplId=1146101810881728533, title=电源学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155559379819679852, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=articleTextType, value=kx, createTime=1753436425404, updateTime=1753436425404, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379798708329, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=banner, value=null, createTime=1753436425399, updateTime=1753436425399, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379781931112, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=efYTu4aDDzS8GgTA1MjEKw==, createTime=1753436425396, updateTime=1753436425396, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379811291243, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753436425402, updateTime=1753436425402, creator=18614031015, updator=18614031015), WebsiteProps(id=1155559379802902634, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1146832214672683008, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753436425400, updateTime=1753436425400, creator=18614031015, updator=18614031015)]), Website(id=1148243202240405915, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146031654075715584, 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/dyxb/CN, language=CN, createTime=1751692112741, createBy=18614031015, updateTime=1753435242839, updateBy=18614031015, name=电源学报-中文站点, tplId=1146099689490845704, title=电源学报, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148618015060553758, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=articleTextType, value=kx, createTime=1751781475081, updateTime=1751781475081, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015035387931, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=banner, value=null, createTime=1751781475075, updateTime=1751781475075, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015022805018, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=efYTu4aDDzS8GgTA1MjEKw==, createTime=1751781475072, updateTime=1751781475072, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015052165149, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751781475079, updateTime=1751781475079, creator=18614031015, updator=18614031015), WebsiteProps(id=1148618015043776540, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202240405915, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751781475077, updateTime=1751781475077, creator=18614031015, updator=18614031015)])], journalTitle=电源学报, weixinUrl=null, journalUrl=http://www.jops.cn/CN/home, iacademicId=null, status=0, seqNo=null, journalTitleEn=Journal of Power Supply, journalPhotoCn=Mx+A2dn+ULnPHuEAI1LruQ==, journalPhotoEn=yHt2vwjzkDgqh+JDCfJKoQ==, journalFirstLetter=J, 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=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2025.1.143, detailUrlEn=https://castjournals.cast.org.cn/joweb/dyxb/EN/10.13234/j.issn.2095-2805.2025.1.143, pdfUrlCn=https://castjournals.cast.org.cn/joweb/dyxb/CN/PDF/10.13234/j.issn.2095-2805.2025.1.143, pdfUrlEn=https://castjournals.cast.org.cn/joweb/dyxb/EN/PDF/10.13234/j.issn.2095-2805.2025.1.143, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于SOA-SVM模型的光伏阵列故障诊断研究
收藏切换
PDF下载
孙培胜 , 陈堂贤 , 程陈 , 李正
电源学报 | 新能源系统 2025,23(1): 143-150
收起
收藏切换
电源学报 | 新能源系统 2025, 23(1): 143-150
基于SOA-SVM模型的光伏阵列故障诊断研究
全屏
孙培胜 , 陈堂贤 , 程陈 , 李正
作者信息
  • 三峡大学电气与新能源学院,宜昌 443002
  • 陈堂贤(1965— ),男,学士副教授。研究方向:柔性电力系统、风能及新能源发电技术。E-mail:

    程陈(1998— ),男,硕士研究生。研究方向:光伏发电技术。E-mail:

    李正(1997— ),男,硕士研究生。研究方向:柔性直流输电技术。E-mail:

通讯作者:

孙培胜(1996— ),男,硕士研究生。研究方向:光伏发电故障诊断技术。E-mail:
Research on Fault Diagnosis of Photovoltaic Array Based on SOA-SVM Model
Peisheng SUN , Tangxian CHEN , Chen CHENG , Zheng LI
Affiliations
  • College of Electrical Engineering and New Energy, China Three Gorges University, Yichang 443002, China
出版时间: 2025-01-30 doi: 10.13234/j.issn.2095-2805.2025.1.143
文章导航
收藏切换

针对支持向量机SVM(support vector machine)用于光伏阵列故障诊断时准确率不高、且易受核函数与惩罚因子参数影响的问题,提出1种基于海鸥优化算法SOA(seagull optimization algorithm)支持向量机的光伏阵列故障诊断方法。引入海鸥优化算法对SVM模型进行参数寻优,建立基于最优参数的SOA-SVM故障诊断模型;利用MATLAB软件搭建光伏阵列仿真模型,提取不同故障类型下的特征参数并输入到SOA-SVM模型进行故障诊断。实验结果表明:经SOA优化后的SVM模型故障诊断准确率显著提高,且相比于基于人工蜂群ABC(artificial bee colony)算法的ABC-SVM模型和基于粒子群优化PSO(particle swarm optimization)算法的PSO-SVM模型,SOA-SVM模型具有更快的寻优收敛迭代速度和更高的故障诊断准确率。

光伏阵列  /  故障诊断  /  海鸥优化算法  /  支持向量机

Aimed at the problem that the accuracy of photovoltaic array fault diagnosis based on support vector machine (SVM) is not high and it is easily affected by the kernel function and penalty factor parameters, a photovoltaic array fault diagnosis method based on SVM optimized by the seagull optimization algorithm (SOA) is proposed. The SOA is introduced to optimize the parameters of the SVM model, and an SOA-SVM fault diagnosis model based on the optimal parameters is established. MATLAB software is used to build a photovoltaic array simulation model, and the characteristic parameters under different fault types are extracted and further inputted into the SOA-SVM model for fault diagnosis. Experimental results show that the fault diagnosis accuracy of the SVM model optimized by SOA is significantly improved. Compared with the ABC-SVM and PSO-SVM models, the SOA-SVM model converges faster in the optimization process and has a higher fault diagnosis accuracy.

Photovoltaic array  /  fault diagnosis  /  seagull optimization algorithm (SOA)  /  support vector machine (SVM)
孙培胜, 陈堂贤, 程陈, 李正. 基于SOA-SVM模型的光伏阵列故障诊断研究. 电源学报, 2025 , 23 (1) : 143 -150 . DOI: 10.13234/j.issn.2095-2805.2025.1.143
Peisheng SUN, Tangxian CHEN, Chen CHENG, Zheng LI. Research on Fault Diagnosis of Photovoltaic Array Based on SOA-SVM Model[J]. Journal of Power Supply, 2025 , 23 (1) : 143 -150 . DOI: 10.13234/j.issn.2095-2805.2025.1.143
在“双碳”目标下,新能源发电技术呈现高速发展态势。光伏发电因地域限制小、规模灵活、清洁安全等优点,正成为我国新能源发展的关键力量[1]。但由于光伏阵列工作环境复杂,容易发生光伏组件老化、短路、开路、局部遮阴等故障,降低光伏发电效率,缩短光伏阵列使用寿命[2]。因此,进行快速准确的故障诊断对于光伏发电系统具有重要意义。
目前,机器学习技术被大量运用于故障诊断研究,如神经网络[3]、极限学习机[4]和支持向量机[5]等。文献[6]利用遗传算法对反向传播BP (back propagation)神经网络进行优化,解决其易陷入局部最优的问题,准确完成对光伏阵列的故障诊断;文献[7]利用布谷鸟算法优化神经网络对光伏组件进行故障诊断,提升了预测精度;文献[8]利用K均值聚类算法优化径向基函数RBF(radial basis function)神经网络的参数选取过程进行光伏组件故障诊断,获得较高的故障诊断准确率;文献[9]建立基于高斯核函数的支持向量机SVM(support vector machine)模型,可较为精准地判别光伏阵列各类型故障。
SVM模型用于故障诊断能获得较高的准确率[10],但仍存在一些不足:SVM部分参数的设置对整体诊断精确度影响较大;部分改进模型中使用的优化算法,如人工蜂群ABC(artificial bee colony)算法、粒子群优化PSO(particle swarm optimization)算法,存在收敛速度慢、陷入局部最优等问题[11-12]。为此,本文提出1种基于海鸥优化算法SOA(seagull optimization algorithm)优化支持向量机的方法。针对惩罚因子与核函数参数对支持向量机辨识结果影响大的问题,引入海鸥优化算法进行参数寻优,进而建立1种基于SOA-SVM的故障诊断模型。通过仿真实验与ABC-SVM、PSO-SVM模型进行对比,结果表明SOA-SVM模型具有更快的收敛迭代速度和更高的故障诊断准确率,可有效进行光伏阵列故障诊断。
支持向量机具有样本需求低、训练时间短、分类识别效果好、泛化能力强等优点[13],因此常被用于故障诊断。SVM的核心概念在于构建1个最优超平面[14]将不同数据分类,并使分类间隔最大。如图1所示,H为超平面,H1H2是相对H平行且距离相等的分类面,当H1H2的间距M达到最大,若待分类的数据样本线性可分,则此超平面H为最优超平面。
对于非线性可分的数据,如图2所示,可通过核函数将样本数据映射到更高维度的空间,将最优分类超平面由低维不可建变为高维可建,进而对数据分类,使得高维数据能使用线性分类方法,从而提高分类的泛化能力和置信度。
SVM的最优超平面分类函数为
$f(x)=\mathrm{sgn}\left[{\displaystyle \sum }_{i=1}^{n}{\alpha }_{i}{y}_{i}K({x}_{i}\cdot x)+b\right]$
式中:${\alpha }_{i}$为拉格朗日乘子,且$0\le {\alpha }_{i}\le C$,其中C为非负的惩罚因子,调节训练错误数与泛化能力之间的折中关系,能确保分类准确率,C值越大训练错误分类越少,C值越小训练错误分类越多;xiyi分别为样本集T中的特征向量与样本标签,T = $\{({x}_{1},{y}_{1}),\text{ }({x}_{2},{y}_{2}),\cdots,({x}_{i},{y}_{i})\}$$K({x}_{i}\cdot x)$为核函数;b为训练样本确定的分类阈值。
选取不同核函数将影响SVM的分类能力和应用范围,常用核函数有线性核函数、多项式核函数、高斯核函数、Sigmoid核函数等[15]。线性核函数主要用于低维度线性可分的数据样本;多项式核函数参数较多,计算复杂;高斯核函数具有参数少、非线性映射和收敛速度快等优点。因此,本文选择高斯核函数,其大小可表示为
$K({x}_{i}\cdot {x}_{j})=\mathrm{exp}\left(-\frac{{‖{x}_{i}-{x}_{j}‖}^{2}}{2{g}^{2}}\right)$
式中:g为核函数参数;xj为样本集T中的不同样本的特征向量。
SOA算法是Dhiman等[16]提出的1种基于种群的新型搜索算法,可用于解决各领域优化问题。该算法通过模拟海鸥种群的迁徙与觅食行为分别实现全局搜索与局部搜索的功能,全局搜索用于快速定位最优解范围,局部搜索用于找到最优解。
1)海鸥迁徙行为分析
为避免迁徙过程中不同海鸥个体之间的碰撞,以及所有海鸥朝最佳位置靠近,需要更新海鸥的位置,即有
$\left\{\begin{array}{l}{C}_{\text{s}}(t)=A{P}_{\text{s}}(t)\hfill \\ {M}_{\text{s}}(t)=B[{P}_{\text{best}}(t)-{P}_{\text{s}}(t)]\hfill \\ {D}_{\text{s}}(t)=\left|{C}_{\text{s}}(t)+{M}_{\text{s}}(t)\right|\hfill \end{array}\right.$
式中:${C}_{\text{s}}(t)$为海鸥不发生碰撞的新位置;${M}_{\text{s}}(t)$为海鸥最佳位置所在方向;${D}_{\text{s}}(t)$为海鸥更新后的新位置;${P}_{\text{s}}(t)$为海鸥当前位置;$ {P}_{\text{best}}(t)$为最佳海鸥位置;$ t$为迭代次数;$A$为附加变量,用于模拟海鸥在搜索空间的运动;$B$为平衡算法局部与全局搜索的随机参数。AB的大小可表示为
$A={f}_{\text{c}}-t\frac{{f}_{\text{c}}}{{t}_{\text{max}}}$
$B=2{A}^{2}\cdot rd$
式中:${f}_{\text{c}}$为根据迭代次数变化的变量,由2线性下降至0;${t}_{\text{max}}$为最大迭代次数;rd为[0,1]内的随机数。
2)海鸥觅食行为分析
海鸥在觅食时产生攻击行为,会不断改变攻击角度与飞行螺旋半径,其在三维空间中的位置更新可表示为
$\left\{\begin{array}{l}{P}_{\text{s}}(t+1)={D}_{\text{s}}(t)xyz+{P}_{\text{best}}(t)\hfill \\ x=r\mathrm{cos}\text{ }k\hfill \\ y=r\mathrm{sin}\text{ }k\hfill \\ z=rk\hfill \end{array}\right.$
式中:$k$$\left[0,2\text{π}\right]$范围内的随机角度;$r$为海鸥的螺旋半径,$r=u{\text{e}}^{kv}$,其中$u$$v$为与螺旋形状相关的参数。
通过MATLAB/Simulink软件搭建如图3所示的6行6列光伏阵列,模拟其在不同运行条件下的故障并获取样本数据。仿真模拟光伏阵列5种运行状态:正常运行;光伏组件短路故障,通过短接单个电气模块来模拟;内部组件开路故障,通过断开某组件支路来模拟;局部阴影故障,通过减小部分光伏组件的光照强度模拟;光伏组件老化故障,通过在支路中串联小电阻来模拟。
每个光伏组件的电气参数相同:最大功率点电流为8.1 A,最大功率点电压为30.2 V,开路电压为37.2 V,短路电流为8.62 A,光照强度范围为600~1 000 W/m2,温度范围为25~40 ℃。仿真得到的电流-电压(I-U)特性曲线与功率-电压(P-U)特性曲线分别如图4图5所示。
图4图5可见,相较于正常运行状态,短路故障时,光伏阵列的开路电压明显减小,最大功率点的电压与电流减小;老化故障时,最大功率点的电流与电压变化明显,短路电流与开路电压无明显变化;开路故障时,短路电流明显减小;局部阴影故障时,P-U特性曲线出现“多峰”现象,I-U特性曲线呈阶梯性变化。光伏阵列仿真所得典型运行数据见表1
综上可知,光伏阵列发生故障时,短路电流、开路电压、最大功率点电流与最大功率点电压中,至少存在1项系统参数与正常运行时产生明显变化。因此,选择此4种数据作为故障诊断的输入变量,进而进行不同类型的故障识别。
作为2个重要参数,惩罚因子C与核函数参数g直接影响支持向量机的故障诊断精度[17],因此如何快速有效寻找最优参数是优化算法的关键。引入SOA算法来优化支持向量机,保证了搜索优化参数的准确性与速度,使该分类诊断模型能快速、准确地得到最优参数,进而进行故障诊断。
将2.1节仿真所得数据作为训练集与测试集,通过SOA-SVM故障诊断模型进行分类诊断,用适应度来判断分类诊断的准确率。适应度fitness的大小可表示为
$\text{fitness}=\frac{{\text{train}}_{\text{w}}}{{\text{train}}_{\text{all}}}+\frac{{\text{test}}_{\text{w}}}{{\text{test}}_{\text{all}}}$
式中:${\text{train}}_{\text{w}}$${\text{test}}_{\text{w}}$分别为训练集和测试集的错误诊断数量;${\text{train}}_{\text{all}}$${\text{test}}_{\text{all}}$分别为训练集和测试集的样本总数。适应度$\text{fitness}$越小则表示诊断准确率越高。
SOA优化SVM的故障诊断流程如图6所示,其基本步骤如下。
步骤1 输入正常运行及不同故障下的光伏阵列样本数据,设置训练集与测试集,并对数据归一化处理。
步骤2 初始化SVM模型及SOA算法的参数,并设置海鸥种群数量、最大迭代次数、自变量上、下限及维度大小。
步骤3 随机生成海鸥种群,每只海鸥位置都由对应参数Cg决定。
步骤4 根据式(3)~式(7)对海鸥位置不断更新,计算新位置的适应度,并与更新前的适应度做比较,保存更小的适应度作为当前最优值。
步骤5 若更新到最优适应度或达到最大迭代次数,则保存最优适应度;否则,返回步骤4。
步骤6 根据最优适应度保存对应的SVM参数组合(C, g)。
步骤7 由式(1)和式(2)对SVM模型进行训练与测试。
将2.1节仿真所得运行数据代入2.2节SOA-SVM故障诊断模型进行训练与测试。共计使用500组含故障状态标签的样本数据集,其中正常(类别1)运行状态200组,老化(类别2)状态75组,阴影(类别3)状态75组,开路(类别4)状态75组,短路(类别5)状态75组。随机选定55组数据作为测试集,其他数据作为训练集。
惩罚因子C与核函数参数g的取值直接影响SVM的故障分类精度。对于未经参数优化的SVM模型,在(0, 100]范围内分别对Cg进行随机取值,每对(C, g)能得到相应的诊断准确率,不同取值次数下所得分类诊断结果如图7所示。由图7可见,(C, g)随机取值的次数越多,诊断准确率在80%以上的越多,但多数情况诊断准确率保持在较低水平。因此,采用未经参数优化的(C, g)将使SVM模型所得诊断准确率较低且随机变化。
随机选取1组参数(C=19.4,g=1.6),所得未经参数优化的SVM模型诊断结果如图8所示,预测结果显示,该方法所得诊断准确率仅为83.64%。其中,4组正常样本被诊断为组件开路,1组局部阴影样本被诊断为正常,4组组件开路样本被诊断为正常。由此可见,未经参数优化的SVM模型对数据分类诊断效果存在不足,有待优化。
使用SOA算法对SVM的惩罚因子C与核函数参数g进行参数寻优。设定SOA-SVM的参数如下:种群规模N=8,最大迭代次数为100,惩罚因子C的范围为(0, 100],核函数参数g的范围为(0, 100]。故障诊断可视化结果如图9所示,且寻优所得惩罚因子C=24.56,核函数参数g=0.121 2。
图9可见,SOA-SVM模型诊断结果中仅有1组老化故障数据被错误诊断为局部阴影故障,分类预测准确率达到了98.18%,相比于未优化的SVM模型其准确率提升了14.54%。结果表明SOA-SVM模型对光伏阵列的故障诊断较优化前更具可靠性。
为验证所提SOA-SVM分类模型的有效性,参考文献[12-13]建立基于人工蜂群算法优化的SVM模型ABC-SVM与基于粒子群算法优化的SVM模型PSO-SVM,采用同一训练集数据与测试集数据进行诊断实验,并与SOA-SVM模型所得结果进行对比,不同迭代次数下的适应度曲线如图10所示。
图10可见,ABC算法与PSO算法对于参数寻优过程的收敛迭代次数均大于SOA算法,种群在搜索空间会更易陷入局部最优;SOA-SVM算法模型的适应度最小,表明诊断错误率最小。证明SOA算法可缓解传统算法在寻优过程中易陷入局部最优的问题。不同算法模型所得诊断分类准确率结果见表2,结果表明SOA-SVM模型具有最高的测试准确率98.18%,相比于ABC-SVM模型、PSO-SVM模型分别提高了3.63%、1.82%。综合寻优收敛迭代速度和诊断分类准确率可见,SOA-SVM算法模型性能最好,适用于本文中光伏阵列的故障诊断。
本文提出1种基于海鸥算法优化支持向量机的光伏阵列故障诊断方法,通过引入海鸥算法进行参数优化,建立了SOA-SVM故障诊断模型。SOA算法优异的全局搜索和局部搜索能力解决了传统算法模型存在的收敛迭代慢和易陷入局部最优的问题,提高了SVM模型对光伏阵列的故障分类精度。与ABC-SVM、PSO-SVM模型相比,SOA-SVM模型在分类诊断准确率、收敛迭代速度方面具有综合最优性能,可将该模型用于其他类型的故障诊断。
  • 国家自然科学基金资助项目(61603212)
参考文献 引证文献
排序方式:
[1]
高伟, 黄俊铭. 基于SSELM的光伏组件故障智能诊断方法[J]. 太阳能学报, 2021, 42(12): 465-470.
Gao Wei, Huang Junming. Intelligent fault diagnosis method of photovoltaic module via SSELM[J]. Acta Energiae Solaris Sinica, 2021, 42(12): 465-470. (in Chinese)
[2]
余玲珍, 覃涛, 龙道银, 等. TGBA优化核极限学习机的光伏阵列故障诊断[J]. 激光杂志, 2021, 42(12): 140-148.
Yu Lingzhen, Qin Tao, Long Daoyin, et al. Fault diagnosis of PV array based on TGBA optimized kernel extreme learning machine[J]. Laser Journal, 2021, 42(12): 140-148. (in Chinese)
[3]
宋文海, 李田泽, 田晖, 等. 基于概率神经网络的光伏阵列故障诊断研究[J]. 电源技术, 2019, 43(9): 1525-1527, 1567.
Song Wenhai, Li Tianze, Tian Hui, et al. Research on fault diagnosis of PV array based on PNN[J]. Chinese Journal of Power Sources, 2019, 43(9): 1525-1527, 1567. (in Chinese)
[4]
陈世群, 高伟, 陈孝琪, 等. 一种基于极限学习机和皮尔逊相关系数的光伏阵列故障快速诊断方法[J]. 电气技术, 2021, 22(10): 57-64.
Chen Shiqun, Gao Wei, Chen Xiaoqi, et al. A fast fault diagnosis method for photovoltaic array via extreme learning machine and Pearson’s correlation coefficient[J]. Electrical Engineering, 2021, 22(10): 57-64. (in Chinese)
[5]
梅恒荣, 殷礼胜, 刘冬梅, 等. 改进粒子群算法优化的SVM模拟电路故障诊断[J]. 电子测量与仪器学报, 2017, 31(8): 1239-1246.
Mei Hengrong, Yin Lisheng, Liu Dongmei, et al. Ana-logue circuit fault diagnosis based on SVM optimized by IPSO[J]. Journal of Electronic Measurement and Instru-mentation, 2017, 31(8): 1239-1246. (in Chinese)
[6]
刘东, 李田泽, 刘开石, 等. GA-BP神经网络在光伏阵列故障检测中的应用研究[J]. 电源技术, 2021, 45(3): 370-373.
Liu Dong, Li Tianze, Liu Kaishi, et al. Research on GA-BP neural network in photovoltaic array fault detection[J]. Chinese Journal of Power Sources, 2021, 45(3): 370-373. (in Chinese)
[7]
张杰, 易辉, 张霞, 等. 基于布谷鸟算法的光伏组件故障诊断模型优化[J]. 电源技术, 2020, 44(1): 76-79.
Zhang Jie, Yi Hui, Zhang Xia, et al. Optimization of fault diagnosis model for photovoltaic module based on cuckoo algorithm[J]. Chinese Journal of Power Sources, 2020, 44(1): 76-79. (in Chinese)
[8]
马纪梅, 张志耀, 张启然. 基于改进RBF神经网络的光伏组件故障诊断[J]. 电测与仪表, 2021, 58(2): 118-124.
Ma Jimei, Zhang Zhiyao, Zhang Qiran. Fault diagnosis of photovoltaic modules based on improved RBF neural network[J]. Electrical Measurement & Instrumentation, 2021, 58(2): 118-124. (in Chinese)
[9]
张晓鹏, 张兴忠. 基于高斯核函数的支持向量机光伏故障诊断研究[J]. 可再生能源, 2021, 39(6): 760-765.
Zhang Xiaopeng, Zhang Xingzhong. Research on photov-oltaic fault diagnosis based on time domain characteristics[J]. Renewable Energy Resources, 2021, 39(6): 760-765. (in Chinese)
[10]
Wang Junjie, Gao Dedong, Zhu Shaokang, et al. Fault diagnosis method of photovoltaic array based on support vector machine[J]. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 2023, 45(2): 5380-5395.
[11]
刘开石, 李田泽, 刘东, 等. 基于ABC-SVM算法的光伏阵列故障诊断[J]. 电源技术, 2021, 45(9): 1171-1174.
Liu Kaishi, Li Tianze, Liu Dong, et al. Fault diagnosis of PV array based on ABC-SVM algorithm[J]. Chinese Journal of Power Sources, 2021, 45(9): 1171-1174. (in Chinese)
[12]
林培杰, 陈志聪, 吴丽君, 等. 一种PSO-SVM的光伏阵列故障检测与分类[J]. 福州大学学报(自然科学版), 2017, 45(5): 652-658.
Lin Peijie, Chen Zhicong, Wu Lijun, et al. Fault detection and classification for photovoltaic arrays based on PSO-SVM[J]. Journal of Fuzhou University (Natural Science Edition), 2017, 45(5): 652-658. (in Chinese)
[13]
Tuerxun W, Xu Chang, Guo Hongyu, et al. Fault diagn-osis of wind turbines based on a support vector machine optimized by the sparrow search algorithm[J]. IEEE Access, 2021, 9: 69307-69315.
[14]
Yin Zuyu, Hou Jian. Recent advances on SVM based fault diagnosis and process monitoring in complicated industrial processes[J]. Neurocomputing, 2016, 174: 643-650.
[15]
尹嘉鹏. 支持向量机核函数及关键参数选择研究[D]. 哈尔滨: 哈尔滨工业大学, 2016.
Yin Jiapeng. Research on kernel function and key par-ameter selection of support vector machine[D]. Harbin: Harbin Institute of Technology, 2016. (in Chinese)
[16]
Dhiman G, Kumar V. Seagull optimization algorithm: Theory and its applications for large-scale industrial engineering problems[J]. Knowledge-Based Systems, 2019, 165: 169-196.
[17]
李黄曼, 张勇, 张瑶. 基于ISSA优化SVM的变压器故障诊断研究[J]. 电子测量与仪器学报, 2021, 35(3): 123-129.
Li Huangman, Zhang Yong, Zhang Yao. Study of trans-former fault diagnosis based on improved sparrow search algorithm optimized support vector machine[J]. Journal of Electronic Measurement and Instrumentation, 2021, 35(3): 123-129. (in Chinese)
2025年第23卷第1期
PDF下载
341
132
引用本文
BibTeX
文章信息
doi: 10.13234/j.issn.2095-2805.2025.1.143
  • 接收时间:2022-05-12
  • 首发时间:2025-07-01
  • 出版时间:2025-01-30
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2022-05-12
  • 修回日期:2022-06-26
  • 录用日期:2022-07-07
基金
National Natural Science Foundation of China(61603212)
国家自然科学基金资助项目(61603212)
作者信息
    三峡大学电气与新能源学院,宜昌 443002

通讯作者:

孙培胜(1996— ),男,硕士研究生。研究方向:光伏发电故障诊断技术。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/dyxb/CN/10.13234/j.issn.2095-2805.2025.1.143
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