Article(id=1149768948901654635, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149768937925165147, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2405970, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1723046400000, receivedDateStr=2024-08-08, revisedDate=1732377600000, revisedDateStr=2024-11-24, acceptedDate=null, acceptedDateStr=null, onlineDate=1752055879091, onlineDateStr=2025-07-09, pubDate=1748361600000, pubDateStr=2025-05-28, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752055879091, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752055879091, creator=13701087609, updateTime=1752055879091, updator=13701087609, issue=Issue{id=1149768937925165147, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='15', pageStart='6155', pageEnd='6586', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752055876475, creator=13701087609, updateTime=1768456822194, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1218559490207699090, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149768937925165147, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1218559490211893395, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149768937925165147, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=6360, endPage=6367, ext={EN=ArticleExt(id=1149768949178478708, articleId=1149768948901654635, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Lifespan Prediction of Rectifier Diodes Based on Improved Grey Wolf Optimization-simple Recurrent Unit Network, columnId=1156262733675876713, journalTitle=Science Technology and Engineering, columnName=Papers·Electrical Technology, runingTitle=null, highlight=null, articleAbstract=

As essential components in power conversion modules, rectifiers are extensively utilized in power supply systems such as inverters, where their operational reliability directly influences the overall system performance. In order to enhance the reliability of rectifiers, it is critical to conduct lifespan predictions for sensitive components, particularly rectifier diodes. A predictive model was proposed that employs an improved grey wolf optimization (GWO) algorithm to optimize the hyperparameters of a simple recurrent unit (SRU) network. Initially, a power cycling accelerated aging test was performed on the diode, followed by an analysis of its characteristic parameters, with forward voltage drop identified as the primary aging indicator. Subsequently, the improved GWO algorithm was applied to optimize SRU hyperparameters—such as learning rate, number of hidden layers, and iteration count—thereby establishing a hybrid predictive model. Finally, the model was trained and validated using aging test data, with predictive accuracy compared against alternative models. The results show that the proposed model achieves superior predictive accuracy, and the data-driven predictive approach enhances the precision of diode lifespan estimation compared to conventional analytical modeling methods, thereby contributing to enhanced operational reliability of rectifiers.

, correspAuthors=Lin CHAI, 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=Liang XIE, Lin CHAI, Hang DUAN, De FANG), CN=ArticleExt(id=1149768978899316807, articleId=1149768948901654635, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于改进灰狼优化-简单循环单元网络的整流二极管寿命预测, columnId=1156262734506353627, journalTitle=科学技术与工程, columnName=论文·电工技术, runingTitle=null, highlight=null, articleAbstract=

整流器作为电能变换功率模块的关键环节,广泛应用于变频器等供电系统设备中,其运行可靠性直接影响整个系统的运行状态。为提高整流器运行可靠性,需针对其中的敏感部件整流二极管进行寿命预测,提出一种由改进后的灰狼优化算法(grey wolf optimization,GWO)优化简单循环单元(simple recurrent unit, SRU)网络超参数的预测模型。首先对二极管进行功率循环加速老化试验,对其特征参数进行分析,选取正向导通压降作为主要老化特征,其次采用改良策略后的GWO对SRU网络的学习率、隐藏层个数、迭代次数等超参数进行寻优,建立组合预测模型,最后将老化试验所得数据输入模型中进行训练以及验证,得到预测结果与其他模型对比。结果表明:本文模型具有更高的准确性,基于数据驱动的预测方法较传统分析建模方法提高了二极管寿命预测精度,进而提高了整流器工作可靠性。

, correspAuthors=柴琳, authorNote=null, correspAuthorsNote=
* 柴琳(1979—),男,汉族,湖北黄冈人,博士,教授。研究方向:电力系统负荷预测、人工智能及其应用。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=ewXH09m/qmRllLw51GUhng==, magXml=rCSekcNW8BdWYtCzkz4tkw==, pdfUrl=null, pdf=AFbTKxNiDD4bFQHKexcFGg==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=7dKYpHAFLwud4jlAR5g6+A==, mapNumber=null, authorCompany=null, fund=null, authors=

谢亮(2001—),男,汉族,湖北洪湖人,硕士研究生。研究方向:高压变频器功率模块可靠性。E-mail:

, authorsList=谢亮, 柴琳, 段航, 方德)}, authors=[Author(id=1172924193239875860, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=553803853@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1172924193567031574, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, authorId=1172924193239875860, language=EN, stringName=Liang XIE, firstName=Liang, middleName=null, lastName=XIE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1172924193680277783, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, authorId=1172924193239875860, language=CN, stringName=谢亮, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 武汉科技大学信息科学与工程学院, 武汉 430081, bio={"content":"

谢亮(2001—),男,汉族,湖北洪湖人,硕士研究生。研究方向:高压变频器功率模块可靠性。E-mail:

"}, bioImg=null, bioContent=

谢亮(2001—),男,汉族,湖北洪湖人,硕士研究生。研究方向:高压变频器功率模块可靠性。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1172924192807862541, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, xref=1, ext=[AuthorCompanyExt(id=1172924192812056846, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, companyId=1172924192807862541, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China), AuthorCompanyExt(id=1172924192820445455, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, companyId=1172924192807862541, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 武汉科技大学信息科学与工程学院, 武汉 430081)])]), Author(id=1172924193785135385, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=chailin@wust.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1172924193869021467, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, authorId=1172924193785135385, language=EN, stringName=Lin CHAI, firstName=Lin, middleName=null, lastName=CHAI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1172924193940324636, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, authorId=1172924193785135385, language=CN, stringName=柴琳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, *, address=1 武汉科技大学信息科学与工程学院, 武汉 430081, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1172924192807862541, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, xref=1, ext=[AuthorCompanyExt(id=1172924192812056846, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, companyId=1172924192807862541, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China), AuthorCompanyExt(id=1172924192820445455, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, companyId=1172924192807862541, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 武汉科技大学信息科学与工程学院, 武汉 430081)])]), Author(id=1172924193994850590, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1172924194095513888, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, authorId=1172924193994850590, language=EN, stringName=Hang DUAN, firstName=Hang, middleName=null, lastName=DUAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 China Steel Group Safety and Environmental Protection Research Institute Co., Ltd., Wuhan 430081, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1172924194305229089, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, authorId=1172924193994850590, language=CN, stringName=段航, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 中钢集团安全环保研究院有限公司, 武汉 430081, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1172924192950468880, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, xref=2, ext=[AuthorCompanyExt(id=1172924192979829009, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, companyId=1172924192950468880, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 China Steel Group Safety and Environmental Protection Research Institute Co., Ltd., Wuhan 430081, China), AuthorCompanyExt(id=1172924193009189138, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, companyId=1172924192950468880, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中钢集团安全环保研究院有限公司, 武汉 430081)])]), Author(id=1172924194473001251, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1172924194615607589, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, authorId=1172924194473001251, language=EN, stringName=De FANG, firstName=De, middleName=null, lastName=FANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1172924194745631014, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, authorId=1172924194473001251, language=CN, stringName=方德, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 武汉科技大学信息科学与工程学院, 武汉 430081, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1172924192807862541, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, xref=1, ext=[AuthorCompanyExt(id=1172924192812056846, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, companyId=1172924192807862541, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China), AuthorCompanyExt(id=1172924192820445455, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, companyId=1172924192807862541, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 武汉科技大学信息科学与工程学院, 武汉 430081)])])], keywords=[Keyword(id=1172924194946957607, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, orderNo=1, keyword=rectifier diode), Keyword(id=1172924195030843688, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, orderNo=2, keyword=lifespan prediction), Keyword(id=1172924195160867113, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, orderNo=3, keyword=accelerated aging test), Keyword(id=1172924195404136746, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, orderNo=4, keyword=simple recurrent unit), Keyword(id=1172924195458662699, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, orderNo=5, keyword=improved grey wolf optimization), Keyword(id=1172924195668377900, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, orderNo=1, keyword=整流二极管), Keyword(id=1172924195869704493, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, orderNo=2, keyword=寿命预测), Keyword(id=1172924195999727918, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, orderNo=3, keyword=加速老化试验), Keyword(id=1172924196222026031, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, orderNo=4, keyword=简单循环单元), Keyword(id=1172924196373020976, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, orderNo=5, keyword=改进灰狼算法)], refs=[Reference(id=1172924200194031948, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2017, volume=1, issue=1, pageStart=3, pageEnd=14, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Boldea I, journalName=CES Transactions on Electrical Machines and Systems, refType=null, unstructuredReference=Boldea I. Electric generators and motors: an overview[J]. CES Transactions on Electrical Machines and Systems, 2017, 1(1): 3-14., articleTitle=Electric generators and motors: an overview, refAbstract=null), Reference(id=1172924200311472461, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2015, volume=30, issue=21, pageStart=1, pageEnd=12, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=徐殿国, 刘晓峰, 于泳, journalName=电工技术学报, refType=null, unstructuredReference=徐殿国, 刘晓峰, 于泳. 变频器故障诊断及容错控制研究综述[J]. 电工技术学报, 2015, 30(21): 1-12., articleTitle=变频器故障诊断及容错控制研究综述, refAbstract=null), Reference(id=1172924200407941454, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2015, volume=30, issue=21, pageStart=1, pageEnd=12, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=Xu Dianguo, Liu Xiaofeng, Yu Yong, journalName=Transactions of China Electrotechnical Society, refType=null, unstructuredReference=Xu Dianguo, Liu Xiaofeng, Yu Yong. A survey on fault diagnosis and tolerant control of inverters[J]. Transactions of China Electrotechnical Society, 2015, 30(21): 1-12., articleTitle=A survey on fault diagnosis and tolerant control of inverters, refAbstract=null), Reference(id=1172924200496021839, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2021, volume=36, issue=12, pageStart=2560, pageEnd=2575, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=张军, 张犁, 成瑜, journalName=电工技术学报, refType=null, unstructuredReference=张军, 张犁, 成瑜. IGBT模块寿命评估研究综述[J]. 电工技术学报, 2021, 36(12): 2560-2575., articleTitle=IGBT模块寿命评估研究综述, refAbstract=null), Reference(id=1172924200588296528, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2021, volume=36, issue=12, pageStart=2560, pageEnd=2575, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=Zhang Jun, Zhang Li, Cheng Yu, journalName=Transactions of China Electrotechnical Society, refType=null, unstructuredReference=Zhang Jun, Zhang Li, Cheng Yu. Review of the lifetime evaluation for the IGBT module[J]. Transactions of China Electrotechnical Society, 2021, 36(12): 2560-2575., articleTitle=Review of the lifetime evaluation for the IGBT module, refAbstract=null), Reference(id=1172924200697348433, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2020, volume=40, issue=18, pageStart=5796, pageEnd=5805, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=马铭遥, 郭伟生, 严雪松, journalName=中国电机工程学报, refType=null, unstructuredReference=马铭遥, 郭伟生, 严雪松, 等. 用于电动汽车功率模块热分析的紧凑型热网络模型[J]. 中国电机工程学报, 2020, 40(18): 5796-5805., articleTitle=用于电动汽车功率模块热分析的紧凑型热网络模型, refAbstract=null), Reference(id=1172924200789623122, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2020, volume=40, issue=18, pageStart=5796, pageEnd=5805, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=Ma Mingyao, Guo Weisheng, Yan Xuesong, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=Ma Mingyao, Guo Weisheng, Yan Xuesong, et al. Compact thermal network model for thermal analysis of power modules in electric vehicle[J]. Proceedings of the CSEE, 2020, 40(18): 5796-5805., articleTitle=Compact thermal network model for thermal analysis of power modules in electric vehicle, refAbstract=null), Reference(id=1172924200831566163, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2022, volume=17, issue=2, pageStart=19, pageEnd=26, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=许智亮, 葛兴来, 李金, journalName=电气工程学报, refType=null, unstructuredReference=许智亮, 葛兴来, 李金, 等. 计及流-热耦合热网络模型的IGBT结温计算[J]. 电气工程学报, 2022, 17(2): 19-26., articleTitle=计及流-热耦合热网络模型的IGBT结温计算, refAbstract=null), Reference(id=1172924200907063636, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2022, volume=17, issue=2, pageStart=19, pageEnd=26, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=Xu Zhiliang, Ge Xinglai, Li Jin, journalName=Journal of Electrical Engineering, refType=null, unstructuredReference=Xu Zhiliang, Ge Xinglai, Li Jin, et al. Calculation of IGBT junction temperature with thermal network model considering flow-thermal coupling[J]. Journal of Electrical Engineering, 2022, 17(2): 19-26., articleTitle=Calculation of IGBT junction temperature with thermal network model considering flow-thermal coupling, refAbstract=null), Reference(id=1172924200990949717, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=9, authorNames=黄宇剑, journalName=地铁整流器二极管故障诊断与剩余寿命预测方法研究, refType=null, unstructuredReference=黄宇剑. 地铁整流器二极管故障诊断与剩余寿命预测方法研究[D]. 成都: 西南交通大学, 2021., articleTitle=null, refAbstract=null), Reference(id=1172924201066447190, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=Huang Yujian, journalName=Research on fault diagnosis and remaining life prediction method of diode in metro rectifier, refType=null, unstructuredReference=Huang Yujian. Research on fault diagnosis and remaining life prediction method of diode in metro rectifier[D]. Chengdu: Southwest Jiaotong University, 2021., articleTitle=null, refAbstract=null), Reference(id=1172924201141944663, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2020, volume=13, issue=8, pageStart=1942, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=Plesca A, Mihet-Popa L, journalName=Energies, refType=null, unstructuredReference=Plesca A, Mihet-Popa L. Thermal analysis of power rectifiers in steady-state conditions[J]. Energies, 2020, 13(8): 1942., articleTitle=Thermal analysis of power rectifiers in steady-state conditions, refAbstract=null), Reference(id=1172924201242607960, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2023, volume=141, issue=null, pageStart=1, pageEnd=10, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=Zhao S H, Yang X, Wu X L, journalName=Microelectronics Reliability, refType=null, unstructuredReference=Zhao S H, Yang X, Wu X L, et al. Investigation on fatigue mechanism of solder layers in IGBT modules under high temperature gradients[J]. Microelectronics Reliability, 2023, 141: 1-10., articleTitle=Investigation on fatigue mechanism of solder layers in IGBT modules under high temperature gradients, refAbstract=null), Reference(id=1172924201410380121, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=1, pageEnd=6, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=Ren H, Du X, Yu Y, journalName=2022 IEEE Energy Conversion Congress and Exposition (ECCE), refType=null, unstructuredReference=Ren H, Du X, Yu Y, et al. Power MOSFET lifetime prediction method based on optimized long short-term memory neural network[C]// 2022 IEEE Energy Conversion Congress and Exposition (ECCE). New York: IEEE, 2022: 1-6., articleTitle=Power MOSFET lifetime prediction method based on optimized long short-term memory neural network, refAbstract=null), Reference(id=1172924201511043418, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2021, volume=52, issue=8, pageStart=7504, pageEnd=7512, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=Han Y, Qi W, Ding N, journalName=IEEE Transactions on Cybernetics, refType=null, unstructuredReference=Han Y, Qi W, Ding N, et al. Short-time wavelet entropy integrating improved LSTM for fault diagnosis of modular multilevel converter[J]. IEEE Transactions on Cybernetics, 2021, 52(8): 7504-7512., articleTitle=Short-time wavelet entropy integrating improved LSTM for fault diagnosis of modular multilevel converter, refAbstract=null), Reference(id=1172924201611706715, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2022, volume=37, issue=12, pageStart=3162, pageEnd=3171, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=于永进, 姜雅男, 李长云, journalName=电工技术学报, refType=null, unstructuredReference=于永进, 姜雅男, 李长云. 基于鲸鱼优化-长短期记忆网络模型的机-热老化绝缘纸剩余寿命预测方法[J]. 电工技术学报, 2022, 37(12): 3162-3171., articleTitle=基于鲸鱼优化-长短期记忆网络模型的机-热老化绝缘纸剩余寿命预测方法, refAbstract=null), Reference(id=1172924201712370012, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2022, volume=37, issue=12, pageStart=3162, pageEnd=3171, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=Yu Yongjin, Jiang Ya'nan, Li Changyun, journalName=Transactions of China Electrotechnical Society, refType=null, unstructuredReference=Yu Yongjin, Jiang Ya'nan, Li Changyun. Prediction method of insulation paper remaining life with mechanical-thermal synergy based on whale optimization algorithm-long-short term memory model[J]. Transactions of China Electrotechnical Society, 2022, 37(12): 3162-3171., articleTitle=Prediction method of insulation paper remaining life with mechanical-thermal synergy based on whale optimization algorithm-long-short term memory model, refAbstract=null), Reference(id=1172924201808839005, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2021, volume=17, issue=5, pageStart=3478, pageEnd=3487, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=Ren L, Dong J, Wang X, journalName=IEEE Transactions on Industrial Informatics, refType=null, unstructuredReference=Ren L, Dong J, Wang X, et al. A data-driven auto-CNN-LSTM prediction model for lithium-ion battery remaining useful life[J]. IEEE Transactions on Industrial Informatics, 2021, 17(5): 3478-3487., articleTitle=A data-driven auto-CNN-LSTM prediction model for lithium-ion battery remaining useful life, refAbstract=null), Reference(id=1172924201938862430, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2024, volume=39, issue=4, pageStart=1074, pageEnd=1086, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=任宏宇, 余瑶怡, 杜雄, journalName=电工技术学报, refType=null, unstructuredReference=任宏宇, 余瑶怡, 杜雄, 等. 基于优化长短期记忆神经网络的IGBT寿命预测模型[J]. 电工技术学报, 2024, 39(4): 1074-1086., articleTitle=基于优化长短期记忆神经网络的IGBT寿命预测模型, refAbstract=null), Reference(id=1172924202005971295, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2024, volume=39, issue=4, pageStart=1074, pageEnd=1086, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=Ren Hongyu, Yu Yaoyi, Du Xiong, journalName=Transactions of China Electrotechnical Society, refType=null, unstructuredReference=Ren Hongyu, Yu Yaoyi, Du Xiong, et al. IGBT lifetime prediction model based on optimized long short-term memory neural network[J]. Transactions of China Electrotechnical Society, 2024, 39(4): 1074-1086., articleTitle=IGBT lifetime prediction model based on optimized long short-term memory neural network, refAbstract=null), Reference(id=1172924202085663072, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2024, volume=49, issue=4, pageStart=373, pageEnd=379, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=张金萍, 薛治伦, 陈航, journalName=半导体技术, refType=null, unstructuredReference=张金萍, 薛治伦, 陈航, 等. 基于注意力机制的CNN-BiLSTM的IGBT剩余使用寿命预测[J]. 半导体技术, 2024, 49(4): 373-379., articleTitle=基于注意力机制的CNN-BiLSTM的IGBT剩余使用寿命预测, refAbstract=null), Reference(id=1172924202190520673, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2024, volume=49, issue=4, pageStart=373, pageEnd=379, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=Zhang Jinping, Xue Zhilun, Chen Hang, journalName=Semiconductor Technology, refType=null, unstructuredReference=Zhang Jinping, Xue Zhilun, Chen Hang, et al. CNN-BiLSTM based on attention mechanism for prediction of igbt remaining useful life[J]. Semiconductor Technology, 2024, 49(4): 373-379., articleTitle=CNN-BiLSTM based on attention mechanism for prediction of igbt remaining useful life, refAbstract=null), Reference(id=1172924202425401698, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2021, volume=175, issue=null, pageStart=109166, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=22, authorNames=Yao D, Li B, Liu H, journalName=Measurement, refType=null, unstructuredReference=Yao D, Li B, Liu H, et al. Remaining useful life prediction of roller bearings based on improved 1D-CNN and simple recurrent unit[J]. Measurement, 2021, 175: 109166., articleTitle=Remaining useful life prediction of roller bearings based on improved 1D-CNN and simple recurrent unit, refAbstract=null), Reference(id=1172924202488316259, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2024, volume=73, issue=2, pageStart=736, pageEnd=744, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=Ma H, Qiu J, Sheng G, journalName=IEEE Transactions on Microwave Theory and Techniques, refType=null, unstructuredReference=Ma H, Qiu J, Sheng G, et al. Deep simple recurrent unit-based transient modeling method for high-speed circuits[J]. IEEE Transactions on Microwave Theory and Techniques, 2024, 73(2): 736-744., articleTitle=Deep simple recurrent unit-based transient modeling method for high-speed circuits, refAbstract=null), Reference(id=1172924202614145380, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2021, volume=9, issue=null, pageStart=121944, pageEnd=121956, url=null, language=null, rfNumber=[17], rfOrder=24, authorNames=Liu J, Wei X, Huang H, journalName=IEEE Access, refType=null, unstructuredReference=Liu J, Wei X, Huang H. An improved grey wolf optimization algorithm and its application in path planning[J]. IEEE Access, 2021, 9: 121944-121956., articleTitle=An improved grey wolf optimization algorithm and its application in path planning, refAbstract=null), Reference(id=1172924202681254246, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=18, pageStart=7701, pageEnd=7709, url=null, language=null, rfNumber=[18], rfOrder=25, authorNames=陈晓梅, 周博, 蔡烨, journalName=科学技术与工程, refType=null, unstructuredReference=陈晓梅, 周博, 蔡烨. 基于改进灰狼算法的微网多主体主从博弈策略[J]. 科学技术与工程, 2024, 24(18): 7701-7709., articleTitle=基于改进灰狼算法的微网多主体主从博弈策略, refAbstract=null), Reference(id=1172924202773528936, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=18, pageStart=7701, pageEnd=7709, url=null, language=null, rfNumber=[18], rfOrder=26, authorNames=Chen Xiaomei, Zhou Bo, Cai Ye, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Chen Xiaomei, Zhou Bo, Cai Ye. Multi-agent master-slave game strategy of microgrid based on improved grey wolf algorithm[J]. Science Technology and Engineering, 2024, 24(18): 7701-7709., articleTitle=Multi-agent master-slave game strategy of microgrid based on improved grey wolf algorithm, refAbstract=null), Reference(id=1172924202836443498, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2017, volume=12, issue=10, pageStart=9, pageEnd=18, url=null, language=null, rfNumber=[19], rfOrder=27, authorNames=丁杰, 张平, journalName=电气工程学报, refType=null, unstructuredReference=丁杰, 张平. 地铁车辆牵引逆变器IGBT模块的结温与疲劳寿命计算[J]. 电气工程学报, 2017, 12(10): 9-18., articleTitle=地铁车辆牵引逆变器IGBT模块的结温与疲劳寿命计算, refAbstract=null), Reference(id=1172924202903552364, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2017, volume=12, issue=10, pageStart=9, pageEnd=18, url=null, language=null, rfNumber=[19], rfOrder=28, authorNames=Ding Jie, Zhang Ping, journalName=Journal of Electrical Engineering, refType=null, unstructuredReference=Ding Jie, Zhang Ping. Junction temperature and fatigue life calculation of IGBT module for metro vehicle traction inverter[J]. Journal of Electrical Engineering, 2017, 12(10): 9-18., articleTitle=Junction temperature and fatigue life calculation of IGBT module for metro vehicle traction inverter, refAbstract=null), Reference(id=1172924203016798575, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=11, pageStart=4654, pageEnd=4659, url=null, language=null, rfNumber=[20], rfOrder=29, authorNames=张明宇, 王琦, 于洋, journalName=科学技术与工程, refType=null, unstructuredReference=张明宇, 王琦, 于洋. 基于GRU与PCA-TL的热应力下IGBT故障预测[J]. 科学技术与工程, 2023, 23(11): 4654-4659., articleTitle=基于GRU与PCA-TL的热应力下IGBT故障预测, refAbstract=null), Reference(id=1172924203264262514, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=11, pageStart=4654, pageEnd=4659, url=null, language=null, rfNumber=[20], rfOrder=30, authorNames=Zhang Mingyu, Wang Qi, Yu Yang, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Zhang Mingyu, Wang Qi, Yu Yang. Fault prediction of IGBT under thermal stress based on GRU and PCA-TL[J]. Science Technology and Engineering, 2023, 23(11): 4654-4659., articleTitle=Fault prediction of IGBT under thermal stress based on GRU and PCA-TL, refAbstract=null)], funds=[Fund(id=1172924199980122443, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, awardId=51877161, language=CN, fundingSource=国家自然科学基金(51877161), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1172924192807862541, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, xref=1, ext=[AuthorCompanyExt(id=1172924192812056846, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, companyId=1172924192807862541, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China), AuthorCompanyExt(id=1172924192820445455, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, companyId=1172924192807862541, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 武汉科技大学信息科学与工程学院, 武汉 430081)]), AuthorCompany(id=1172924192950468880, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, xref=2, ext=[AuthorCompanyExt(id=1172924192979829009, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, companyId=1172924192950468880, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 China Steel Group Safety and Environmental Protection Research Institute Co., Ltd., Wuhan 430081, China), AuthorCompanyExt(id=1172924193009189138, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, companyId=1172924192950468880, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 中钢集团安全环保研究院有限公司, 武汉 430081)])], figs=[ArticleFig(id=1172924196687593777, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, label=Fig.1, caption=Cyclic structure of SRU, figureFileSmall=k6EWdL1WrhoVvR/HfZB1uQ==, figureFileBig=v0Ivg1dUCBwz10WLTCdU+g==, tableContent=null), ArticleFig(id=1172924196905697586, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, label=图1, caption=SRU网络循环结构

Xt为当前时刻输入;WL为线性权重矩阵;ct为单元当前时刻状态;ht为单元当前时刻输出;ft为遗忘门输出; rt为重置门输出;σfσr为遗忘门、重置门的sigmoid激活函数

, figureFileSmall=k6EWdL1WrhoVvR/HfZB1uQ==, figureFileBig=v0Ivg1dUCBwz10WLTCdU+g==, tableContent=null), ArticleFig(id=1172924197119607091, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, label=Fig.2, caption=Diagram of grey wolf position update in GWO, figureFileSmall=76BuI0QIp0sL6hhYr3M7Ag==, figureFileBig=LBteDtpUhDAEnjrmwflI5A==, tableContent=null), ArticleFig(id=1172924197220270388, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, label=图2, caption=GWO算法中灰狼位置更新示意图, figureFileSmall=76BuI0QIp0sL6hhYr3M7Ag==, figureFileBig=LBteDtpUhDAEnjrmwflI5A==, tableContent=null), ArticleFig(id=1172924197354488117, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, label=Fig.3, caption=Flowchart of improved GWO, figureFileSmall=GDBoNOTqFd2er0v2a3ZTVA==, figureFileBig=i9nFkb3M0X2fQJkCfwKHDQ==, tableContent=null), ArticleFig(id=1172924197476122934, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, label=图3, caption=改进GWO流程图, figureFileSmall=GDBoNOTqFd2er0v2a3ZTVA==, figureFileBig=i9nFkb3M0X2fQJkCfwKHDQ==, tableContent=null), ArticleFig(id=1172924197593563447, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, label=Fig.4, caption=Flowchart of improved GWO-SRU prediction, figureFileSmall=lZM6Upqxe8G4O7Y9zNz2/Q==, figureFileBig=FZaob94muoBi/VuadVxl5g==, tableContent=null), ArticleFig(id=1172924197702615352, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, label=图4, caption=改进GWO-SRU预测流程图, figureFileSmall=lZM6Upqxe8G4O7Y9zNz2/Q==, figureFileBig=FZaob94muoBi/VuadVxl5g==, tableContent=null), ArticleFig(id=1172924197861998905, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, label=Fig.5, caption=Platform of aging test, figureFileSmall=kl01IF9nqBY50Bb1JIYWdA==, figureFileBig=FnOlRdgHBakhak5t4hwlGg==, tableContent=null), ArticleFig(id=1172924198050742586, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, label=图5, caption=老化试验平台, figureFileSmall=kl01IF9nqBY50Bb1JIYWdA==, figureFileBig=FnOlRdgHBakhak5t4hwlGg==, tableContent=null), ArticleFig(id=1172924198151405883, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, label=Fig.6, caption=Convergence curve of fitness value, figureFileSmall=+TaghYJz0pW92T+Uos/oZQ==, figureFileBig=oGwLFK5UB2DrkZRSsJveFg==, tableContent=null), ArticleFig(id=1172924198302400828, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, label=图6, caption=适应度值收敛曲线, figureFileSmall=+TaghYJz0pW92T+Uos/oZQ==, figureFileBig=oGwLFK5UB2DrkZRSsJveFg==, tableContent=null), ArticleFig(id=1172924198361121085, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, label=Fig.7, caption=Comparison between model predicted values and actual values, figureFileSmall=z80QNVoeqiE+x1EIkX1d4w==, figureFileBig=O/wZe+pt6x+c5Narn4H/+g==, tableContent=null), ArticleFig(id=1172924198474367294, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, label=图7, caption=模型预测值与实际值对比, figureFileSmall=z80QNVoeqiE+x1EIkX1d4w==, figureFileBig=O/wZe+pt6x+c5Narn4H/+g==, tableContent=null), ArticleFig(id=1172924198541476159, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, label=Fig.8, caption=Comparison of prediction results of various lifespan prediction models, figureFileSmall=DqxlPqkmgrgBlED7NYkAJw==, figureFileBig=DP5eKeoNaZ+X74849Rs2vQ==, tableContent=null), ArticleFig(id=1172924198642139456, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, label=图8, caption=各寿命预测模型预测结果对比, figureFileSmall=DqxlPqkmgrgBlED7NYkAJw==, figureFileBig=DP5eKeoNaZ+X74849Rs2vQ==, tableContent=null), ArticleFig(id=1172924198721831233, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, label=Fig.9, caption=Comparison of mean absolute percentage error, figureFileSmall=lT/UJnJo6Pvt/WOXX3sLSw==, figureFileBig=YNoZBpzfR1+nIngfGXYsqg==, tableContent=null), ArticleFig(id=1172924198835077442, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, label=图9, caption=平均绝对百分比误差对比, figureFileSmall=lT/UJnJo6Pvt/WOXX3sLSw==, figureFileBig=YNoZBpzfR1+nIngfGXYsqg==, tableContent=null), ArticleFig(id=1172924198969295171, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, label=Table 1, caption=

Aging data of rectifier diodes

, figureFileSmall=null, figureFileBig=null, tableContent=
二极管 设置温度/℃ 起始压降/V 失效压降/V 失效周期/次
VD1 90 0.765 0.691 537
VD2 90 0.758 0.681 544
VD3 100 0.749 0.693 312
VD4 100 0.772 0.701 334
VD5 110 0.776 0.689 202
VD6 110 0.759 0.675 197
VD7 120 0.768 0.673 128
VD8 120 0.782 0.675 134
), ArticleFig(id=1172924199074152772, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, label=表1, caption=

整流二极管老化数据

, figureFileSmall=null, figureFileBig=null, tableContent=
二极管 设置温度/℃ 起始压降/V 失效压降/V 失效周期/次
VD1 90 0.765 0.691 537
VD2 90 0.758 0.681 544
VD3 100 0.749 0.693 312
VD4 100 0.772 0.701 334
VD5 110 0.776 0.689 202
VD6 110 0.759 0.675 197
VD7 120 0.768 0.673 128
VD8 120 0.782 0.675 134
), ArticleFig(id=1172924199237730629, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, label=Table 2, caption=

Optimal hyperparameter values

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 取值
学习率 0.013
隐藏层神经元个数 15
迭代次数 231
), ArticleFig(id=1172924199325811014, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, label=表2, caption=

最优超参数值

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 取值
学习率 0.013
隐藏层神经元个数 15
迭代次数 231
), ArticleFig(id=1172924199455834439, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, label=Table 3, caption=

Comparison of prediction results for rectifier diodes

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 设置温度/℃ 失效压降/V 失效周期/次
实际值 90 0.692 529
预测值 0.689 529
实际值 100 0.688 311
预测值 0.687 316
实际值 110 0.679 205
预测值 0.681 207
实际值 120 0.672 125
预测值 0.674 122
), ArticleFig(id=1172924199564886344, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, label=表3, caption=

整流二极管预测结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 设置温度/℃ 失效压降/V 失效周期/次
实际值 90 0.692 529
预测值 0.689 529
实际值 100 0.688 311
预测值 0.687 316
实际值 110 0.679 205
预测值 0.681 207
实际值 120 0.672 125
预测值 0.674 122
), ArticleFig(id=1172924199673938249, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=EN, label=Table 4, caption=

Comparison of evaluation indicators

, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型 MAPE RMSE R2
LSTM 0.070 7 0.077 4 0.815 4
BO-LSTM 0.041 5 0.048 7 0.896 3
SRU 0.076 9 0.086 5 0.798 9
GWO-SRU 0.039 5 0.045 3 0.904 7
本文模型 0.026 4 0.020 6 0.966 4
), ArticleFig(id=1172924199812350282, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149768948901654635, language=CN, label=表4, caption=

评价指标对比

, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型 MAPE RMSE R2
LSTM 0.070 7 0.077 4 0.815 4
BO-LSTM 0.041 5 0.048 7 0.896 3
SRU 0.076 9 0.086 5 0.798 9
GWO-SRU 0.039 5 0.045 3 0.904 7
本文模型 0.026 4 0.020 6 0.966 4
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, 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=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, 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.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, 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.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, 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/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, 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/kxjsygc/CN/10.12404/j.issn.1671-1815.2405970, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2405970, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2405970, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2405970, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于改进灰狼优化-简单循环单元网络的整流二极管寿命预测
收藏切换
PDF下载
谢亮 1 , 柴琳 1, * , 段航 2 , 方德 1
科学技术与工程 | 论文·电工技术 2025,25(15): 6360-6367
收起
收藏切换
科学技术与工程 | 论文·电工技术 2025, 25(15): 6360-6367
基于改进灰狼优化-简单循环单元网络的整流二极管寿命预测
全屏
谢亮1 , 柴琳1, * , 段航2, 方德1
作者信息
  • 1 武汉科技大学信息科学与工程学院, 武汉 430081
  • 2 中钢集团安全环保研究院有限公司, 武汉 430081
  • 谢亮(2001—),男,汉族,湖北洪湖人,硕士研究生。研究方向:高压变频器功率模块可靠性。E-mail:

通讯作者:

* 柴琳(1979—),男,汉族,湖北黄冈人,博士,教授。研究方向:电力系统负荷预测、人工智能及其应用。E-mail:
Lifespan Prediction of Rectifier Diodes Based on Improved Grey Wolf Optimization-simple Recurrent Unit Network
Liang XIE1 , Lin CHAI1, * , Hang DUAN2, De FANG1
Affiliations
  • 1 School of Information Science and Engineering, Wuhan University of Science and Technology, Wuhan 430081, China
  • 2 China Steel Group Safety and Environmental Protection Research Institute Co., Ltd., Wuhan 430081, China
出版时间: 2025-05-28 doi: 10.12404/j.issn.1671-1815.2405970
文章导航
收藏切换

整流器作为电能变换功率模块的关键环节,广泛应用于变频器等供电系统设备中,其运行可靠性直接影响整个系统的运行状态。为提高整流器运行可靠性,需针对其中的敏感部件整流二极管进行寿命预测,提出一种由改进后的灰狼优化算法(grey wolf optimization,GWO)优化简单循环单元(simple recurrent unit, SRU)网络超参数的预测模型。首先对二极管进行功率循环加速老化试验,对其特征参数进行分析,选取正向导通压降作为主要老化特征,其次采用改良策略后的GWO对SRU网络的学习率、隐藏层个数、迭代次数等超参数进行寻优,建立组合预测模型,最后将老化试验所得数据输入模型中进行训练以及验证,得到预测结果与其他模型对比。结果表明:本文模型具有更高的准确性,基于数据驱动的预测方法较传统分析建模方法提高了二极管寿命预测精度,进而提高了整流器工作可靠性。

整流二极管  /  寿命预测  /  加速老化试验  /  简单循环单元  /  改进灰狼算法

As essential components in power conversion modules, rectifiers are extensively utilized in power supply systems such as inverters, where their operational reliability directly influences the overall system performance. In order to enhance the reliability of rectifiers, it is critical to conduct lifespan predictions for sensitive components, particularly rectifier diodes. A predictive model was proposed that employs an improved grey wolf optimization (GWO) algorithm to optimize the hyperparameters of a simple recurrent unit (SRU) network. Initially, a power cycling accelerated aging test was performed on the diode, followed by an analysis of its characteristic parameters, with forward voltage drop identified as the primary aging indicator. Subsequently, the improved GWO algorithm was applied to optimize SRU hyperparameters—such as learning rate, number of hidden layers, and iteration count—thereby establishing a hybrid predictive model. Finally, the model was trained and validated using aging test data, with predictive accuracy compared against alternative models. The results show that the proposed model achieves superior predictive accuracy, and the data-driven predictive approach enhances the precision of diode lifespan estimation compared to conventional analytical modeling methods, thereby contributing to enhanced operational reliability of rectifiers.

rectifier diode  /  lifespan prediction  /  accelerated aging test  /  simple recurrent unit  /  improved grey wolf optimization
谢亮, 柴琳, 段航, 方德. 基于改进灰狼优化-简单循环单元网络的整流二极管寿命预测. 科学技术与工程, 2025 , 25 (15) : 6360 -6367 . DOI: 10.12404/j.issn.1671-1815.2405970
Liang XIE, Lin CHAI, Hang DUAN, De FANG. Lifespan Prediction of Rectifier Diodes Based on Improved Grey Wolf Optimization-simple Recurrent Unit Network[J]. Science Technology and Engineering, 2025 , 25 (15) : 6360 -6367 . DOI: 10.12404/j.issn.1671-1815.2405970
随着电气传动技术的发展和更高的工艺要求,变频调速技术以其低谐波含量和优异调速性能被广泛应用于实际工程中[1]。高压变频器在运行过程中仅靠空气自然对流散热,内部温度长期保持在较高范围,易引起敏感功率器件的疲劳损伤甚至失效。若其中一个模块出现故障失效,则将导致系统整体输出谐波含量上升、波形发生失真,难以实现变频调速功能[2]。若能对其中功率模块的敏感器件如整流二极管进行准确寿命预测,便于及时进行维护,有利于提高系统可靠性,在实际生产中具有重要意义。
关于整流二极管的寿命预测方法,传统解析建模一般选取结温为主要影响因素[3],利用温度循环建立对应寿命损伤模型,其中非接触式且精度较高的热网络模型主要被应用于进行功率器件的结温提取[4-5]。黄宇剑[6]利用实际工况计算二极管损耗来构建局部热网络模型,随后通过PLECS与MATLAB /Simulink联合仿真得到结温波动曲线,最后使用Coffin-Mason模型进行寿命预测,结果与实际数据相吻合。仅考虑结温影响可能导致模型与实际出现偏差,Plesca等[7]提出了一种结合紧固扭矩、气流速度、电流和负载参数的整流二极管三维热网络模型,采用了Pro/Engineering软件进行3D建模和热模拟,对比只考虑功耗温升的传统热网络模型提升了精确度。Shihan等[8]从材料物理性质方面入手,采用有限元分析法建立焊料层裂纹扩展路径与温度之间关联性,进而提出一种基于Darveaux模型的寿命预测模型。但基于物理模型的预测方法所采用的参数拟合无法应对实际中复杂的工况,往往难以建立足够精确的寿命模型。
基于试验数据的预测方法通过分析老化参数与寿命之间关系来训练模型,以达到更高的稳定性和预测精度[9]。由于老化数据一般为时间上的周期序列,可利用循环神经网络来实现预测。Han等[10]使用LSTM(long-short term memory)神经网络对IGBT(insulated gate bipolar transistor)进行寿命预测,并采用MATLAB仿真进行验证,但基本LSTM网络的预测精度较低。为改善预测精度问题,当前的预测模型一般加入优化算法对神经网络超参数进行寻优[11]或采用不同神经网络加权组合模型[12]。任宏宇等[13]提出一种经贝叶斯算法优化的LSTM网络来对IGBT进行寿命预测,首先采用逐次变分模态分解将老化数据分解为多个模块提取特征,随后通过高斯过程与期望改进对LSTM进行优化,最后训练结果证明了模型的优越性。张金萍等[14]提出一种基于注意力机制的卷积神经网络和双向长短期记忆网络融合的剩余使用寿命模型,其中采用CNN(convolutional neural networks)提取NASA(National Aeronautics and Space Administration)老化试验数据的特征参数,Bi-LSTM(bi-directional long short-term memory)获取时序信息,最后经注意力机制加权,与其他4种模型相比该模型性能最优。优化算法的加入与组合模型的使用使得模型整体结构复杂,Yao等[15]提出一种应用简单循环单元的预测模型,该模型减少了对过去时刻输出的依赖以及状态的更新,从而简化计算和训练难度。
综上,针对整流二极管提出一种改进GWO-SRU(grey wolf optimization-simple recurrent unit)的组合预测模型对其进行寿命预测,首先对GWO的缺点进行改进,随后利用改进GWO对SRU网络超参数进行全局寻优,并通过老化试验利用试验数据进行验证,证明本文方法优良性,最后将所得数据输入组合模型训练,实现二极管剩余寿命预测,为提高变频器功率模块可靠性提供理论支撑。
传统循环神经网络如LSTM超参数较多,训练过程中计算复杂,不宜调试。简单循环单元(SRU)是一种特殊的循环神经网络,由Ma等[16]在LSTM的基础上提出,优化了状态更新过程,内部结构可独立于各输入处理每个步骤,实现了并行处理,大大提高了计算效率并减少了超参数使用,同时能有效减小梯度消失和梯度爆炸风险。SRU的单层基本门控结构如图1所示,与LSTM相比不再需要前一时刻输出。
当前时刻输入经过线性变换进入网络中,表达式为
X ~ t=WLXt
同时输入进入遗忘门和重置门,进行线性变换后,输出一个0~1的值来分别决定遗忘历史信息和控制信息更新的程度,表达式为
ft=σ(WfXt+bf)
rt=σ(WrXt+br)
σ(x)= 1 1 + e - x
式中: WfWr为遗忘权重矩阵和重置权重矩阵;bfbr为遗忘门偏置和重置门偏置;σ为sigmoid激活函数。
随后单元进行状态更新,当前时刻状态只与输入、遗忘门输出和上一时刻状态有关,其表达式为
ct=ftct-1+(1-ft) X ~ t
最后得到该层单元的输出,表达式为
ht=rttanh(ct)+(1-rt)Xt
tanh(x)= 1 - e - 2 x 1 + e - 2 x
式中:tanh(x)为激活函数。
从循环过程可以看出,SRU只依赖当前时刻状态与输入来完成更新,实现了信息的高效并行化传输。
初始相关阈值参数的选择对后续的预测精度至关重要,故在此使用具有较强全局搜索能力的灰狼优化算法(grey wolf optimization,GWO)对SRU网络超参数进行优化。GWO由于采用自适应收敛因子和最优领导者使用最好的三只灰狼来更新其他灰狼的位置,使其他灰狼能够快速地与种群中的高级灰狼同步,并在有限的迭代次数内获得相对较好的优化结果,具有结构明晰、所需参数少、局部搜索能力强的特点[17]
在GWO中,灰狼个体被划分为αβδω水平。α狼为最优解,βδ狼依次是两个次优解,ω狼为剩余的解决方案。首先进行灰狼种群初始化,按式(8)生成种群初始位置Xi(0)(i=1,2,…,n)。
X i j(0)=Lj+rand(Uj-Lj)
式(8)中:j=1,2,…,N为向量维数;UjLj为搜索空间上下限;rand为[0,1]内的任意数。
随后定义用于表示距离目标位置远近的适应度值函数f,分别计算各灰狼位置的适应度值来划分αβδω水平。在接近目标的过程中灰狼的位置更新公式为
D= C X p ( t ) - X ( t )
X(t+1)=Xp(t)-AD
式中: D为灰狼个体与目标猎物之间距离; t为当前迭代次数; Xp为目标猎物位置,X为当前灰狼个体位置;AC为系数向量,其更新公式如下
A = 2 a r 1 - a N C = 2 r 2
a=2-2 t T
式中:r1r2为[0,1]上均匀分布的随机向量;T为设置总迭代次数;a为收敛因子,迭代过程中数值从2到0线性递减;N为单位向量。当|A|>1和|A|<1时,灰狼种群分别进行全局范围寻优和局部精确定位。
在逼近目标猎物阶段,灰狼个体的位置代表一个可行解,根据最优与次优的αβδ狼所在位置来进行全局优化,更新ω狼的位置。
X 1 = X α - A 1 D α X 2 = X β - A 2 D β X 3 = X δ - A 3 D δ
D α = C 1 X α ( t ) - X ( t ) D β = C 2 X β ( t ) - X ( t ) D δ = C 3 X δ ( t ) - X ( t )
X(t+1)= X 1 + X 2 + X 3 3
式中: XαXβXδ为种群最优解α狼、次优解β狼和第三优解δ狼的位置;X为当前解的位置; DαDβDδ为当前解与前三优解之间距离;X1X2X3为当前解受其他解影响需要调整的位置。
二维搜索空间中灰狼位置更新示意如图2所示,目标猎物被α狼、β狼和δ狼围绕,最后锁定在一个圆形随机位置内,每次迭代时灰狼个体更新它们的位置,向目标逼近。
然而在实际使用中,GWO存在种群多样性差、求解精度低、易陷入局部最优和难以协调全局搜索与局部搜索等缺点[18],于是在此利用混沌映射代替随机产生初始种群,引入动态权重策略并采用基于余弦规律变化的收敛因子代替线性收敛因子,最后加入多项式导优变异机制避免算法陷入局部极值,以达到更快的收敛速度以及获得更准确的结果。
混沌序列为包含了某种随机性且有序的序列,利用混沌序列使用恰当的混沌映射来代替随机变量,所生成的解具有更优的灵活性和多样性。在此采用遍历均匀和收敛较快的ICMIC(iterative chaotic map with infinite collapses)混沌映射来生成种群初始位置,其映射方程为
xk+1=sin λ x k
式(16)中:λ为控制参数,λ∈(0,+∞),其混沌轨道状态值范围为(-1,1)。
原始GWO算法中灰狼个体更新位置直接采用α狼、β狼和δ狼位置的等同权重平均值,忽略了不同解之间适应度值的差距,在此采用一种基于步长欧氏距离的比例权重策略,以加快算法收敛速度,表达式为
Wi= X i X 1 + X 2 + X 3
X(t+1)= W 1 X 1 + W 2 X 2 + W 3 X 3 3
式中:W1W2W3分别表示灰狼个体对α狼、β狼、δ狼的学习率,i=1,2,3。
原始GWO算法中的收敛因子a线性递减变化,但在实际中保持线性变化可能导致搜索效率不足以及结果精度不高的问题,在此提出一种基于余弦规律变化的收敛因子来对原收敛因子进行修正。即
a= Δ a 1 + { c o s [ π ( t - 1 ) / ( T - 1 ) ] } n 2 , t T 2 Δ a 1 - c o s [ π ( t - 1 ) / ( T - 1 ) ] n 2 , T 2 < t T
式(19)中: Δa为收敛因子初始值与最终值之差;n为递减指数,0<n≤1。
改进后的收敛因子随迭代次数变化图像是一条基于余弦规律变化的曲线,在迭代前期减小较慢,利于提高效率,在迭代后期减小较快,利于提高结果精度。
当算法陷入局部极值时,可利用变异来对可行解进行随机扰动,以提高算法活跃性,跳出局部最优解。在此利用多项式变异机制对灰狼更新后位置进行判断:若第i只灰狼位置更新后的目标函数值劣于第i-1只灰狼,则对第i只灰狼进行多项式变异重新进行位置更新,随后比较原位置与重新更新后位置目标函数值,若结果更优则采用新位置,反之则保留原来的位置。多项式变异公式为
Xi(t+1)=Xi(t)+ξ(U-L)
式(20)中:Xi(t)为第i只灰狼在第t次迭代时位置;UL为位置区间的上界和下界;ξ为扰动因子,计算式为
ξ= [ 2 u + ( 1 - 2 u ) ( 1 - ξ 1 ) η + 1 ] 1 / ( η + 1 ) - 1 ,     u 0.5 1 - [ 2 ( 1 - u ) + 2 ( u - 0.5 ) ( 1 - ξ 2 ) η + 1 ] 1 / ( η + 1 ) ,     u > 0.5
式(21)中:u为0~1的随机分布的随机数;ξ1=[Xbest(t)-L]/(U-L),ξ2=[U-Xbest(t)]/(U-L);η为分布指数,η=ηmaxt/T,ηmax一般取30~50。
根据上述改进GWO的策略,可以总结得出其执行流程框图如图3所示。
利用改进后GWO对SRU网络学习率、隐藏神经元个数、迭代次数进行寻优,最终利用优化后组合模型实现对老化数据时序特征的挖掘,得出寿命预测结果。寿命预测流程框图如图4所示。
现采用如下评价指标对预测结果进行准确性判定。
计算式为
MAPE= i = 1 N 1 N y i - y i y i×100%
式(22)中:N为样本总量; y i为第i个样本的预测值; yi为第i个样本的实际值。
方均根误差(root mean square error,RMSE)计算式为
RMSE= 1 N i = 1 N ( y i - y i ) 2
决定系数用来衡量实际值与回归模型的拟合程度,值越接近1则模型拟合效果越好。计算式为
R2=1- i = 1 N ( y i - y i ) 2 i = 1 N ( y - i - y i ) 2
式(24)中: y - i为样本平均值。
整流器中二极管长时间处于高温环境下工作,在结温波动和交变电流影响下易发生老化,致使焊料层开裂、键合线脱落,无法正常工作[19-20]。为分析老化过程中二极管结温、正向导通压降等特征参数变化状况,有必要进行功率循环试验。
功率循环是研究功率器件老化状态下可靠性的有效方法,在此设计高温条件下功率循环加速老化试验平台,其实物如图5所示。二极管型号采用C4D15120D,电源采用AC6803B型号交流源,器件置于型号401B的空气热老化实验箱中,通过对二极管进行重复的导通和关断来模拟实际中负荷波动状况。二极管在导通时温度迅速升高,关断后通过快速冷却加快循环进程,设置不同环境温度进行对照,以12 h为周期采集并记录二极管正向导通压降与结温数据。
在此筛选出8个二极管的起始与失效数据进行分析,如表1所示。
表1可知,二极管的失效周期与温度具有强相关性,且随着循环进行,二极管压降逐渐减小,原因是老化导致PN结正负离子层浓度变小,从而导致势垒电压变小,与实际情况相符。
在此将随周期变化的压降值作为二极管性能退化特征指标,输入组合预测模型中进行训练。
首先将数据集划分为数据集与测试集,在训练之前对数据进行归一化预处理,其表达式为
x'i= x i - x m i n x m a x - x m i n
式(25)中: xmaxxmin分别为数据中最大和最小值。
设置改进GWO的种群数量为30,维数为3,最大迭代次数为50,学习率为0.001,控制参数λ=70,递减指数n=0.7,分布指数ηmax=35,选取相同种群数量、维数和最大迭代次数,同时采用PSO(particle swarm optimization)、GWO、SSA(sparrow search algorithm)、AO(aquila optimizer)和改进GWO对网络进行优化,得到算法收敛曲线如图6所示。相比于其余优化算法,改进后GWO的收敛速度更快,最小方均根误差更低,寻优效果更好。
SRU网络采用Adam优化器,激活函数采用sigmoid和tanh,初始设置学习率为0.001,隐藏层神经元个数为10,迭代次数为800次,利用改进后GWO对SRU超参数进行寻优,得到参数如表2所示。
模型训练完成后,利用测试集进行寿命预测结果的分析。
将测试集的正向导通压降数据输入组合预测模型中,得到导通压降随周期变化的预测结果,110 ℃条件下基于改进GWO-SRU模型的二极管老化特征趋势如图7所示。
根据图7可以明显看出,本文中所用组合预测模型具有良好的准确度。表3展示了不同温度条件下的最终预测结果,与老化试验所得数据基本吻合。
为进一步体现本文模型的性能,在此分别与LSTM、SRU、BO-LSTM、GWO-SRU模型的预测结果作对比,在此以间隔10个周期为采样点,得到模型预测结果如图8所示。
不同预测模型的评价指标对比如表4所示,平均绝对百分比误差的对比如图9所示。
可以明显观察出,本文提出的模型具有更高的决定系数,更低的相对预测误差,平均值为0.026 4,最低可达0.016 6,均方根误差同样也为最低,证明了该模型具有更优的精确性和稳定性,提升了寿命预测精度。
由于变频器中功率模块在运行时长期处于较高温度,使得内部敏感功率器件易发生老化失效,且传统物理建模预测方法精度不能满足实际需求,提出了一种改进GWO-SRU的寿命预测模型,利用改进寻优策略后的GWO对SRU网络超参数进行全局寻优,并对整流二极管开展老化试验,最后对其剩余寿命进行预测,得到以下结论。
(1)针对LSTM智能串行运算的不足,采用可以并行运算且参数更少的SRU进行预测,提高训练时效性;利用改进策略后的GWO对SRU网络初始学习率、隐藏层神经元个数、迭代次数进行全局寻优,提高了寿命预测模型精度。
(2)对整流二极管进行加速热老化试验,根据测得数据的变化趋势分析其老化特征量,选用正向导通压降作为指标和数据集进行模型的训练和测试。
(3)所提出的模型能够在有限周期内预测出精确的结果,对比其他模型拥有更好的性能,为评估变频器功率模块可靠性提供了理论支撑,并为系统器件维修从“定时修”转变为“按需修”提供依据。
综上所述,本文中所提出的预测方法拥有符合预期的准确性与可靠性,实现了高压变频器固定工况下整流二极管寿命准确预测,便于降低高压变频器运维成本,提升经济效益。
  • 国家自然科学基金(51877161)
参考文献 引证文献
排序方式:
[1]
Boldea I. Electric generators and motors: an overview[J]. CES Transactions on Electrical Machines and Systems, 2017, 1(1): 3-14.
[2]
徐殿国, 刘晓峰, 于泳. 变频器故障诊断及容错控制研究综述[J]. 电工技术学报, 2015, 30(21): 1-12.
Xu Dianguo, Liu Xiaofeng, Yu Yong. A survey on fault diagnosis and tolerant control of inverters[J]. Transactions of China Electrotechnical Society, 2015, 30(21): 1-12.
[3]
张军, 张犁, 成瑜. IGBT模块寿命评估研究综述[J]. 电工技术学报, 2021, 36(12): 2560-2575.
Zhang Jun, Zhang Li, Cheng Yu. Review of the lifetime evaluation for the IGBT module[J]. Transactions of China Electrotechnical Society, 2021, 36(12): 2560-2575.
[4]
马铭遥, 郭伟生, 严雪松, 等. 用于电动汽车功率模块热分析的紧凑型热网络模型[J]. 中国电机工程学报, 2020, 40(18): 5796-5805.
Ma Mingyao, Guo Weisheng, Yan Xuesong, et al. Compact thermal network model for thermal analysis of power modules in electric vehicle[J]. Proceedings of the CSEE, 2020, 40(18): 5796-5805.
[5]
许智亮, 葛兴来, 李金, 等. 计及流-热耦合热网络模型的IGBT结温计算[J]. 电气工程学报, 2022, 17(2): 19-26.
Xu Zhiliang, Ge Xinglai, Li Jin, et al. Calculation of IGBT junction temperature with thermal network model considering flow-thermal coupling[J]. Journal of Electrical Engineering, 2022, 17(2): 19-26.
[6]
黄宇剑. 地铁整流器二极管故障诊断与剩余寿命预测方法研究[D]. 成都: 西南交通大学, 2021.
Huang Yujian. Research on fault diagnosis and remaining life prediction method of diode in metro rectifier[D]. Chengdu: Southwest Jiaotong University, 2021.
[7]
Plesca A, Mihet-Popa L. Thermal analysis of power rectifiers in steady-state conditions[J]. Energies, 2020, 13(8): 1942.
[8]
Zhao S H, Yang X, Wu X L, et al. Investigation on fatigue mechanism of solder layers in IGBT modules under high temperature gradients[J]. Microelectronics Reliability, 2023, 141: 1-10.
[9]
Ren H, Du X, Yu Y, et al. Power MOSFET lifetime prediction method based on optimized long short-term memory neural network[C]// 2022 IEEE Energy Conversion Congress and Exposition (ECCE). New York: IEEE, 2022: 1-6.
[10]
Han Y, Qi W, Ding N, et al. Short-time wavelet entropy integrating improved LSTM for fault diagnosis of modular multilevel converter[J]. IEEE Transactions on Cybernetics, 2021, 52(8): 7504-7512.
[11]
于永进, 姜雅男, 李长云. 基于鲸鱼优化-长短期记忆网络模型的机-热老化绝缘纸剩余寿命预测方法[J]. 电工技术学报, 2022, 37(12): 3162-3171.
Yu Yongjin, Jiang Ya'nan, Li Changyun. Prediction method of insulation paper remaining life with mechanical-thermal synergy based on whale optimization algorithm-long-short term memory model[J]. Transactions of China Electrotechnical Society, 2022, 37(12): 3162-3171.
[12]
Ren L, Dong J, Wang X, et al. A data-driven auto-CNN-LSTM prediction model for lithium-ion battery remaining useful life[J]. IEEE Transactions on Industrial Informatics, 2021, 17(5): 3478-3487.
[13]
任宏宇, 余瑶怡, 杜雄, 等. 基于优化长短期记忆神经网络的IGBT寿命预测模型[J]. 电工技术学报, 2024, 39(4): 1074-1086.
Ren Hongyu, Yu Yaoyi, Du Xiong, et al. IGBT lifetime prediction model based on optimized long short-term memory neural network[J]. Transactions of China Electrotechnical Society, 2024, 39(4): 1074-1086.
[14]
张金萍, 薛治伦, 陈航, 等. 基于注意力机制的CNN-BiLSTM的IGBT剩余使用寿命预测[J]. 半导体技术, 2024, 49(4): 373-379.
Zhang Jinping, Xue Zhilun, Chen Hang, et al. CNN-BiLSTM based on attention mechanism for prediction of igbt remaining useful life[J]. Semiconductor Technology, 2024, 49(4): 373-379.
[15]
Yao D, Li B, Liu H, et al. Remaining useful life prediction of roller bearings based on improved 1D-CNN and simple recurrent unit[J]. Measurement, 2021, 175: 109166.
[16]
Ma H, Qiu J, Sheng G, et al. Deep simple recurrent unit-based transient modeling method for high-speed circuits[J]. IEEE Transactions on Microwave Theory and Techniques, 2024, 73(2): 736-744.
[17]
Liu J, Wei X, Huang H. An improved grey wolf optimization algorithm and its application in path planning[J]. IEEE Access, 2021, 9: 121944-121956.
[18]
陈晓梅, 周博, 蔡烨. 基于改进灰狼算法的微网多主体主从博弈策略[J]. 科学技术与工程, 2024, 24(18): 7701-7709.
Chen Xiaomei, Zhou Bo, Cai Ye. Multi-agent master-slave game strategy of microgrid based on improved grey wolf algorithm[J]. Science Technology and Engineering, 2024, 24(18): 7701-7709.
[19]
丁杰, 张平. 地铁车辆牵引逆变器IGBT模块的结温与疲劳寿命计算[J]. 电气工程学报, 2017, 12(10): 9-18.
Ding Jie, Zhang Ping. Junction temperature and fatigue life calculation of IGBT module for metro vehicle traction inverter[J]. Journal of Electrical Engineering, 2017, 12(10): 9-18.
[20]
张明宇, 王琦, 于洋. 基于GRU与PCA-TL的热应力下IGBT故障预测[J]. 科学技术与工程, 2023, 23(11): 4654-4659.
Zhang Mingyu, Wang Qi, Yu Yang. Fault prediction of IGBT under thermal stress based on GRU and PCA-TL[J]. Science Technology and Engineering, 2023, 23(11): 4654-4659.
2025年第25卷第15期
PDF下载
619
394
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2405970
  • 接收时间:2024-08-08
  • 首发时间:2025-07-09
  • 出版时间:2025-05-28
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-08-08
  • 修回日期:2024-11-24
基金
国家自然科学基金(51877161)
作者信息
    1 武汉科技大学信息科学与工程学院, 武汉 430081
    2 中钢集团安全环保研究院有限公司, 武汉 430081

通讯作者:

* 柴琳(1979—),男,汉族,湖北黄冈人,博士,教授。研究方向:电力系统负荷预测、人工智能及其应用。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2405970
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