Article(id=1154428867923136599, tenantId=1146029695717560320, journalId=1146119893612605453, issueId=1154428861249998924, articleNumber=null, orderNo=null, doi=10.1109/ICASSP.2011.5947265, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1718640000000, receivedDateStr=2024-06-18, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1753166890364, onlineDateStr=2025-07-22, pubDate=1729353600000, pubDateStr=2024-10-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753166890364, onlineIssueDateStr=2025-07-22, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753166890364, creator=13701087609, updateTime=1753166890364, updator=13701087609, issue=Issue{id=1154428861249998924, tenantId=1146029695717560320, journalId=1146119893612605453, year='2024', volume='42', issue='10', pageStart='1278', pageEnd='1420', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1753166888773, creator=13701087609, updateTime=1753694543506, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1156642005640930141, tenantId=1146029695717560320, journalId=1146119893612605453, issueId=1154428861249998924, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1156642005640930142, tenantId=1146029695717560320, journalId=1146119893612605453, issueId=1154428861249998924, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1332, endPage=1340, ext={EN=ArticleExt(id=1154428868598419546, articleId=1154428867923136599, tenantId=1146029695717560320, journalId=1146119893612605453, language=EN, title=CEEMDAN joint adaptive wavelet thresholding algorithm for GA-BP wind turbine fault prediction, columnId=null, journalTitle=Renewable Energy Resources, columnName=null, runingTitle=null, highlight=null, articleAbstract=

Generator is an important core component in wind power system, in order to improve the stable and efficient operation of wind turbine, the fault prediction of wind turbine generator is necessary. Focusing on the problem of generator machineside bearing temperature overrun fault prediction in wind power system, this paper takes into account that the collected fault characteristic signal is characterized by large noise, introduces CEEMDAN joint adaptive wavelet threshold denoising method to realize effective denoising of the signal, and at the same time establishes a fault prediction model by combining GABP neural network. By comparing the prediction indexes, error indexes and prediction effect graphs with BP neural network and GABP neural network, it is verified that the proposed algorithm can obtain better prediction effect. The error index and prediction effect are improved, and the accuracy of the prediction of generator failure of wind power system 15 days in advance reaches 92.98%.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Cheng Xiao, Wanpeng Cao, Yueqiang Chu, Zhengkun Yang, Jiaxing Wang), CN=ArticleExt(id=1154428921387930049, articleId=1154428867923136599, tenantId=1146029695717560320, journalId=1146119893612605453, language=CN, title=CEEMDAN 联合自适应小波阈值算法的 GA-BP 风电发电机故障预测, columnId=null, journalTitle=可再生能源, columnName=null, runingTitle=null, highlight=null, articleAbstract=

发电机是风电系统中重要的核心部件,为了提高风电机组的稳定、高效运行,对风电机组发电机的故障预测十分必要。文章围绕风电系统发电机机侧轴承温度超限故障预测的问题,考虑到所采集的故障特征信号具有较大噪声的特点,引入自适应完备噪声经验模态分解(CEEMDAN)联合自适应小波阈值去噪的方法实现信号有效去噪,同时结合 GABP神经网络建立故障预测模型。通过与BP神经网络、GABP神经网络对比预测指标、误差指标和预测效果图形,验证了所提算法可以获得较好的预测效果。误差指标和预测效果均有提升,对提前15 d风电系统发电机故障预测的准确率达到了92.98%。

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=TSaW7qq1BQ5S4lU5zK0pdw==, magXml=1hAxzVAPOlH4Kv6jDb7gyw==, pdfUrl=null, pdf=XcFLSr1PonWEUqK3Mpkd0Q==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=ZRGnUB01LUYFFLX4xk93eg==, mapNumber=null, authorCompany=null, fund=null, authors=

肖成(1983-),女,博士,副教授,研究方向为风电系统故障预测、智能控制。E-mail:

, authorsList=肖成, 曹万鹏, 褚越强, 杨政琨, 王佳兴)}, authors=[Author(id=1154428924051313118, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xiaocheng1130@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154428924172947940, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, authorId=1154428924051313118, language=EN, stringName=Cheng Xiao, firstName=Cheng, middleName=null, lastName=Xiao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Electronics and Control Engineering North China Institute of Aerospace Engineering Langfang 065000 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154428924248445415, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, authorId=1154428924051313118, language=CN, stringName=肖成, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 北华航天工业学院 电子与控制工程学院 河北 廊坊 065000, bio={"content":"

肖成(1983-),女,博士,副教授,研究方向为风电系统故障预测、智能控制。E-mail:

"}, bioImg=null, bioContent=

肖成(1983-),女,博士,副教授,研究方向为风电系统故障预测、智能控制。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154428922415534542, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, xref=1, ext=[AuthorCompanyExt(id=1154428922457477583, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, companyId=1154428922415534542, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Electronics and Control Engineering North China Institute of Aerospace Engineering Langfang 065000 China), AuthorCompanyExt(id=1154428922465866192, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, companyId=1154428922415534542, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北华航天工业学院 电子与控制工程学院 河北 廊坊 065000)])]), Author(id=1154428924332331502, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154428924424606196, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, authorId=1154428924332331502, language=EN, stringName=Wanpeng Cao, firstName=Wanpeng, middleName=null, lastName=Cao, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 China Suntien Green Energy Corporation Limited Huaian 223001 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154428924504297976, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, authorId=1154428924332331502, language=CN, stringName=曹万鹏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 新天绿色能源股份有限公司 江苏 淮安 223001, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154428923946455509, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, xref=2, ext=[AuthorCompanyExt(id=1154428923954844119, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, companyId=1154428923946455509, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 China Suntien Green Energy Corporation Limited Huaian 223001 China), AuthorCompanyExt(id=1154428923959038424, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, companyId=1154428923946455509, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 新天绿色能源股份有限公司 江苏 淮安 223001)])]), Author(id=1154428924588184062, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, 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=1154428924655292930, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, authorId=1154428924588184062, language=EN, stringName=Yueqiang Chu, firstName=Yueqiang, middleName=null, lastName=Chu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Electronics and Control Engineering North China Institute of Aerospace Engineering Langfang 065000 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154428924714013189, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, authorId=1154428924588184062, language=CN, stringName=褚越强, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 北华航天工业学院 电子与控制工程学院 河北 廊坊 065000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154428922415534542, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, xref=1, ext=[AuthorCompanyExt(id=1154428922457477583, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, companyId=1154428922415534542, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Electronics and Control Engineering North China Institute of Aerospace Engineering Langfang 065000 China), AuthorCompanyExt(id=1154428922465866192, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, companyId=1154428922415534542, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北华航天工业学院 电子与控制工程学院 河北 廊坊 065000)])]), Author(id=1154428924785316362, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, 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=1154428924856619534, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, authorId=1154428924785316362, language=EN, stringName=Zhengkun Yang, firstName=Zhengkun, middleName=null, lastName=Yang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Electronics and Control Engineering North China Institute of Aerospace Engineering Langfang 065000 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154428924940505617, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, authorId=1154428924785316362, language=CN, stringName=杨政琨, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 北华航天工业学院 电子与控制工程学院 河北 廊坊 065000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154428922415534542, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, xref=1, ext=[AuthorCompanyExt(id=1154428922457477583, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, companyId=1154428922415534542, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Electronics and Control Engineering North China Institute of Aerospace Engineering Langfang 065000 China), AuthorCompanyExt(id=1154428922465866192, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, companyId=1154428922415534542, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北华航天工业学院 电子与控制工程学院 河北 廊坊 065000)])]), Author(id=1154428925003420179, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, orderNo=4, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154428925078917655, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, authorId=1154428925003420179, language=EN, stringName=Jiaxing Wang, firstName=Jiaxing, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 School of Electronics and Control Engineering North China Institute of Aerospace Engineering Langfang 065000 China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154428925166998039, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, authorId=1154428925003420179, language=CN, stringName=王佳兴, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 北华航天工业学院 电子与控制工程学院 河北 廊坊 065000, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1154428922415534542, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, xref=1, ext=[AuthorCompanyExt(id=1154428922457477583, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, companyId=1154428922415534542, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Electronics and Control Engineering North China Institute of Aerospace Engineering Langfang 065000 China), AuthorCompanyExt(id=1154428922465866192, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, companyId=1154428922415534542, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北华航天工业学院 电子与控制工程学院 河北 廊坊 065000)])])], keywords=[Keyword(id=1154428927561945639, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, orderNo=1, keyword=wind energy system), Keyword(id=1154428927645831724, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, orderNo=2, keyword=generator failure), Keyword(id=1154428927729717810, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, orderNo=3, keyword=fault prediction), Keyword(id=1154428927801020980, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, orderNo=4, keyword=CEEMDAN), Keyword(id=1154428927868129845, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, orderNo=5, keyword=GA-BP neural network), Keyword(id=1154428927922655799, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, orderNo=1, keyword=风电系统), Keyword(id=1154428927993958968, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, orderNo=2, keyword=发电机故障), Keyword(id=1154428928065262137, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, orderNo=3, keyword=故障预测), Keyword(id=1154428928140759613, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, orderNo=4, keyword=CEEMDAN), Keyword(id=1154428928233034302, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, orderNo=5, keyword=GA-BP神经网络)], refs=[Reference(id=1154428932058239698, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, doi=null, pmid=null, pmcid=null, year=2021, volume=47, issue=9, pageStart=3036, pageEnd=3046, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=韩肖清, 李廷钧, 张东霞, journalName=高电压技术, refType=null, unstructuredReference=韩肖清, 李廷钧, 张东霞, 等. 双碳目标下的新型电力系统规划新问题及关键技术[J]. 高电压技术, 2021, 47(9): 3036-3046., articleTitle=双碳目标下的新型电力系统规划新问题及关键技术, refAbstract=null), Reference(id=1154428932121154266, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=吕致为, journalName=null, refType=null, unstructuredReference=吕致为. 基于深度迁移学习的风电机组发电机轴承故障诊断方法研究[D]. 北京: 华北电力大学, 2023., articleTitle=基于深度迁移学习的风电机组发电机轴承故障诊断方法研究, refAbstract=null), Reference(id=1154428932192457437, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, doi=null, pmid=null, pmcid=null, year=2021, volume=39, issue=4, pageStart=521, pageEnd=526, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=米志伟, 常彬, journalName=可再生能源, refType=null, unstructuredReference=米志伟, 常彬. 考虑变流器容错特性的海上双馈风电机组绕组短路故障辨识[J]. 可再生能源, 2021, 39(4): 521-526., articleTitle=考虑变流器容错特性的海上双馈风电机组绕组短路故障辨识, refAbstract=null), Reference(id=1154428932267954908, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=龙泉, 鲁志平, 张羽, journalName=2016年中国电机工程学会年会论文集, refType=null, unstructuredReference=龙泉, 鲁志平, 张羽. 基于BP神经网络的多变量风力发电机绕组温度预测[A]. 2016年中国电机工程学会年会论文集[C].南京:中国电机工程学会, 2016., articleTitle=基于BP神经网络的多变量风力发电机绕组温度预测, refAbstract=null), Reference(id=1154428932351840992, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, doi=null, pmid=null, pmcid=null, year=2021, volume=54, issue=6, pageStart=95, pageEnd=103, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=滕伟, 黄乙珂, 吴仕明, journalName=中国电力, refType=null, unstructuredReference=滕伟, 黄乙珂, 吴仕明, 等. 基于 XGBoost 与 LSTM 的风力发电机绕组温度预测[J]. 中国电力, 2021, 54(6): 95-103., articleTitle=基于 XGBoost 与 LSTM 的风力发电机绕组温度预测, refAbstract=null), Reference(id=1154428932427338468, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, doi=null, pmid=null, pmcid=null, year=2023, volume=34, issue=12, pageStart=1476, pageEnd=1485, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=蒙康, 滕伟, journalName=中国机械工程, refType=null, unstructuredReference=蒙康, 滕伟. 运行机理与数据双驱动的风电齿轮箱系统故障预警[J]. 中国机械工程, 2023, 34(12): 1476-1485., articleTitle=运行机理与数据双驱动的风电齿轮箱系统故障预警, refAbstract=null), Reference(id=1154428932511224554, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=3, pageStart=15, pageEnd=19, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=刘红艳, 刘华新, 朱霄珣, journalName=自动化仪表, refType=null, unstructuredReference=刘红艳, 刘华新, 朱霄珣. 基于胶囊网络的风电机组主轴承故障诊断研究[J]. 自动化仪表, 2022, 43(3): 15-19., articleTitle=基于胶囊网络的风电机组主轴承故障诊断研究, refAbstract=null), Reference(id=1154428932607693550, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, doi=null, pmid=null, pmcid=null, year=2023, volume=72, issue=22, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=樊超阳, 李朝锋, journalName=物理学报, refType=null, unstructuredReference=樊超阳, 李朝锋. CEEMDAN 联合小波阈值算法在水下激光雷达中抑制散射杂波的应用[J]. 物理学报, 2023, 72(22): 1-8., articleTitle=CEEMDAN 联合小波阈值算法在水下激光雷达中抑制散射杂波的应用, refAbstract=null), Reference(id=1154428932746105589, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, doi=null, pmid=null, pmcid=null, year=2023, volume=38, issue=11, pageStart=141, pageEnd=150, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=贾文哲, 闻麒, journalName=热能动力工程, refType=null, unstructuredReference=贾文哲, 闻麒. 改进 CEEMDAN 算法与 CNN 融合的深度学习系泊故障研究[J]. 热能动力工程, 2023, 38(11): 141-150., articleTitle=改进 CEEMDAN 算法与 CNN 融合的深度学习系泊故障研究, refAbstract=null), Reference(id=1154428932800631549, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://link.cnki.net/urlid/11.1864.TB.20240416.1517.004, language=null, rfNumber=[10], rfOrder=9, authorNames=金宇强, 李春辉, 黄震威, journalName=计量学报, refType=null, unstructuredReference=金宇强, 李春辉, 黄震威, 等. 基于特征工程和 GA-BP 神经网络的气体超声流量计使用中检验方法的研究[J/OL]. 计量学报, https://link.cnki.net/urlid/11.1864.TB.20240416.1517.004, articleTitle=基于特征工程和 GA-BP 神经网络的气体超声流量计使用中检验方法的研究, refAbstract=null), Reference(id=1154428932859351807, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://doi.org/10.16085/j.issn.1000-6613.2023-0961, language=null, rfNumber=[11], rfOrder=10, authorNames=李凯, 魏鹤琳, 尹志凡, journalName=化工进展, refType=null, unstructuredReference=李凯, 魏鹤琳, 尹志凡, 等. 基于 GA-BP 神经网络模型预测水基炭黑-胶原蛋白纳米流体热导率和黏度[J/OL]. 化工进展, https://doi.org/10.16085/j.issn.1000-6613.2023-0961, articleTitle=基于 GA-BP 神经网络模型预测水基炭黑-胶原蛋白纳米流体热导率和黏度, refAbstract=null), Reference(id=1154428932939043586, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, doi=null, pmid=null, pmcid=null, year=2011, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=Torres M E, Colominas M A, Schlotthauer G, journalName=IEEE, refType=null, unstructuredReference=Torres M E, Colominas M A, Schlotthauer G, et al. A complete ensemble empirical mode decomposition with adaptive noise[J]. IEEE, 2011. Doi:10.1109/ICASSP.2011.5947265., articleTitle=A complete ensemble empirical mode decomposition with adaptive noise, refAbstract=null), Reference(id=1154428933010346759, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://link.cnki.net/urlid/11.5946.TP.20231023.0900.002, language=null, rfNumber=[13], rfOrder=12, authorNames=江莉, 向世召, journalName=计算机集成制造系统, refType=null, unstructuredReference=江莉, 向世召. 基于 CEEMDAN-VSSLMS 的滚动轴承故障诊断[J/OL]. 计算机集成制造系统, https://link.cnki.net/urlid/11.5946.TP.20231023.0900.002, articleTitle=基于 CEEMDAN-VSSLMS 的滚动轴承故障诊断, refAbstract=null), Reference(id=1154428933090038540, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, doi=null, pmid=null, pmcid=null, year=2010, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=王念彬, journalName=null, refType=null, unstructuredReference=王念彬. 基于小波神经网络的小电流接地系统故障选线方法的研究[D]. 北京: 中国矿业大学, 2010., articleTitle=基于小波神经网络的小电流接地系统故障选线方法的研究, refAbstract=null), Reference(id=1154428933157147407, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, doi=null, pmid=null, pmcid=null, year=2020, volume=38, issue=6, pageStart=846, pageEnd=852, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=周强, 蔡嘉炜, journalName=可再生能源, refType=null, unstructuredReference=周强, 蔡嘉炜. 基于指数平滑与CEEMDAN 的混合储能控制策略研究[J]. 可再生能源, 2020, 38(6): 846-852., articleTitle=基于指数平滑与CEEMDAN 的混合储能控制策略研究, refAbstract=null)], funds=[Fund(id=1154428931806581445, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, awardId=ZD2022089, language=CN, fundingSource=河北省教育厅重点项目(ZD2022089), fundOrder=null, country=null), Fund(id=1154428931877884618, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, awardId=BKY-2023-03, language=CN, fundingSource=北华航天工业学院博士基金项目(BKY-2023-03), fundOrder=null, country=null), Fund(id=1154428931965965004, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, awardId=ZD-2022-03, language=CN, fundingSource=北华航天工业学院校重点项目(ZD-2022-03), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1154428922415534542, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, xref=1, ext=[AuthorCompanyExt(id=1154428922457477583, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, companyId=1154428922415534542, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Electronics and Control Engineering North China Institute of Aerospace Engineering Langfang 065000 China), AuthorCompanyExt(id=1154428922465866192, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, companyId=1154428922415534542, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 北华航天工业学院 电子与控制工程学院 河北 廊坊 065000)]), AuthorCompany(id=1154428923946455509, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, xref=2, ext=[AuthorCompanyExt(id=1154428923954844119, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, companyId=1154428923946455509, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 China Suntien Green Energy Corporation Limited Huaian 223001 China), AuthorCompanyExt(id=1154428923959038424, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, companyId=1154428923946455509, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 新天绿色能源股份有限公司 江苏 淮安 223001)])], figs=[ArticleFig(id=1154428929294193255, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Fig. 1, caption=Flowchart of CEEMDAN combined with adaptive wavelet thresholding denoising algorithm, figureFileSmall=ZXS/SVf3Ms+wjq1SA4A6qw==, figureFileBig=LHqpHdVFqco814Ac+2qBdA==, tableContent=null), ArticleFig(id=1154428929373885034, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=图 1, caption=CEEMDAN 结合自适应小波阈值去噪算法流程, figureFileSmall=ZXS/SVf3Ms+wjq1SA4A6qw==, figureFileBig=LHqpHdVFqco814Ac+2qBdA==, tableContent=null), ArticleFig(id=1154428929432605294, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Fig. 2, caption=IMF waveform obtained from generator fault indicator signal decomposition, figureFileSmall=K+0BysVDH2SQShJh0N0NCw==, figureFileBig=R7FPOGsV/sGxNzpGNz7kpA==, tableContent=null), ArticleFig(id=1154428929495519856, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=图 2, caption=发电机故障指标信号分解得到的 IMF 波形, figureFileSmall=K+0BysVDH2SQShJh0N0NCw==, figureFileBig=R7FPOGsV/sGxNzpGNz7kpA==, tableContent=null), ArticleFig(id=1154428929541657203, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Fig. 3, caption=IMF’s decomposition order and correlation coefficient charts, figureFileSmall=1nIBxDUbU3UausDhiyi8SA==, figureFileBig=2dzfLpyLKUW9DEDAi+foPA==, tableContent=null), ArticleFig(id=1154428929671680630, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=图 3, caption=IMF 的分解阶次和相关系数, figureFileSmall=1nIBxDUbU3UausDhiyi8SA==, figureFileBig=2dzfLpyLKUW9DEDAi+foPA==, tableContent=null), ArticleFig(id=1154428929747178104, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Fig. 4, caption=Comparison of time-domain waveforms of denoised signals, figureFileSmall=NMr7AE9aHnbmMM7Ck8ga4Q==, figureFileBig=asGhxpQMY3vTUYrxtqQbCA==, tableContent=null), ArticleFig(id=1154428929805898362, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=图 4, caption=去噪信号时域波形对比, figureFileSmall=NMr7AE9aHnbmMM7Ck8ga4Q==, figureFileBig=asGhxpQMY3vTUYrxtqQbCA==, tableContent=null), ArticleFig(id=1154428929868812924, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Fig. 5, caption=Three-layer BP neural network model, figureFileSmall=wHkDQ7fUo35uIeRoV9Gr6w==, figureFileBig=R1RgnVQOPk2vlG2wbNBrGw==, tableContent=null), ArticleFig(id=1154428929923338878, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=图 5, caption=三层 BP 神经网络模型, figureFileSmall=wHkDQ7fUo35uIeRoV9Gr6w==, figureFileBig=R1RgnVQOPk2vlG2wbNBrGw==, tableContent=null), ArticleFig(id=1154428929986253440, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Fig. 6, caption=Neural network flowchart of GA-BP, figureFileSmall=WbjBr8igs9kX4Hu25bSmcw==, figureFileBig=9LUgh4/ojtEHVDD9jICLeg==, tableContent=null), ArticleFig(id=1154428930040779394, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=图 6, caption=GA-BP 神经网络流程, figureFileSmall=WbjBr8igs9kX4Hu25bSmcw==, figureFileBig=9LUgh4/ojtEHVDD9jICLeg==, tableContent=null), ArticleFig(id=1154428930107888258, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Fig. 7, caption=Adaptation change graph, figureFileSmall=DYhQfyo7Jjh39VZS5QQZAg==, figureFileBig=Xj5HhWE6BwS0TMuw+82z1g==, tableContent=null), ArticleFig(id=1154428930170802820, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=图 7, caption=适应度变化曲线, figureFileSmall=DYhQfyo7Jjh39VZS5QQZAg==, figureFileBig=Xj5HhWE6BwS0TMuw+82z1g==, tableContent=null), ArticleFig(id=1154428930242105989, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Fig. 8, caption=Normal training set prediction results, figureFileSmall=eo1YGNN/IBFv3Ey2TWTImQ==, figureFileBig=dF7Y03/jWmEZY9t8vU9vrg==, tableContent=null), ArticleFig(id=1154428930300826247, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=图 8, caption=正常训练集预测结果, figureFileSmall=eo1YGNN/IBFv3Ey2TWTImQ==, figureFileBig=dF7Y03/jWmEZY9t8vU9vrg==, tableContent=null), ArticleFig(id=1154428930367935113, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Fig. 9, caption=Faulty training set prediction results, figureFileSmall=CnBjjDFPMRfzLcZ3dXnj7g==, figureFileBig=pkWvpQ+dPoGqkLZwxCmBzg==, tableContent=null), ArticleFig(id=1154428930439238285, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=图 9, caption=故障训练集预测结果, figureFileSmall=CnBjjDFPMRfzLcZ3dXnj7g==, figureFileBig=pkWvpQ+dPoGqkLZwxCmBzg==, tableContent=null), ArticleFig(id=1154428930531512977, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Fig. 10, caption=Normal test set prediction results, figureFileSmall=qZ8nnY745/f40oR8mXRc2Q==, figureFileBig=a7OaQIZSgSdJlwBvtai2uQ==, tableContent=null), ArticleFig(id=1154428930607010452, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=图 10, caption=正常测试集预测结果, figureFileSmall=qZ8nnY745/f40oR8mXRc2Q==, figureFileBig=a7OaQIZSgSdJlwBvtai2uQ==, tableContent=null), ArticleFig(id=1154428930695090837, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Fig. 11, caption=Failure test set prediction results, figureFileSmall=7LWH+2FKcLBsHgXbLg/gpA==, figureFileBig=3qfLUn78Ur0PO+rY+aGk4Q==, tableContent=null), ArticleFig(id=1154428930766394007, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=图 11, caption=故障测试集预测结果, figureFileSmall=7LWH+2FKcLBsHgXbLg/gpA==, figureFileBig=3qfLUn78Ur0PO+rY+aGk4Q==, tableContent=null), ArticleFig(id=1154428930854474395, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Table 1, caption=Results of generator forecasts for wind power systems, figureFileSmall=null, figureFileBig=null, tableContent=
检测 指标 BP 神经 网络 GA-BP 神经网络 CEEMDAN-GA-BP 神经网络
TP 3 840 4 628 6 206
${FN}$ 2 640 1 825 274
${FP}$ 757 428 635
${TN}$ 5 723 6052 5 845
), ArticleFig(id=1154428930938360478, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=表 1, caption=风电系统发电机预测结果, figureFileSmall=null, figureFileBig=null, tableContent=
检测 指标 BP 神经 网络 GA-BP 神经网络 CEEMDAN-GA-BP 神经网络
TP 3 840 4 628 6 206
${FN}$ 2 640 1 825 274
${FP}$ 757 428 635
${TN}$ 5 723 6052 5 845
), ArticleFig(id=1154428931005469346, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Table 2, caption=Predictive performance indicators for wind power, figureFileSmall=null, figureFileBig=null, tableContent=
system generators %
性能 指标 BP 神经 网络 GA-BP 神经网络 CEEMDAN-GA-BP 神经网络
准确率 73.78 82.41 92.98
精确率 83.49 91.53 90.72
召回率 60.00 71.42 95.77
诊断能力评价 88.31 93.39 90.20
), ArticleFig(id=1154428931076772516, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=表 2, caption=风电系统发电机预测性能指标, figureFileSmall=null, figureFileBig=null, tableContent=
system generators %
性能 指标 BP 神经 网络 GA-BP 神经网络 CEEMDAN-GA-BP 神经网络
准确率 73.78 82.41 92.98
精确率 83.49 91.53 90.72
召回率 60.00 71.42 95.77
诊断能力评价 88.31 93.39 90.20
), ArticleFig(id=1154428931164852906, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Table 3, caption=Normal training data error indicators, figureFileSmall=null, figureFileBig=null, tableContent=
误差 指标 BP 神经 网络 GA-BP 神经网络 CEEMDAN-GA-BP 神经网络
RMSE 7.775 9 5.928 1 4.880 5
MBE 0.726 2 $- {0.725}\;9$ $- {1.520}\;0$
MAE 6.075 3 4.677 7 3.484 3
), ArticleFig(id=1154428931261321902, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=表 3, caption=正常训练数据误差指标, figureFileSmall=null, figureFileBig=null, tableContent=
误差 指标 BP 神经 网络 GA-BP 神经网络 CEEMDAN-GA-BP 神经网络
RMSE 7.775 9 5.928 1 4.880 5
MBE 0.726 2 $- {0.725}\;9$ $- {1.520}\;0$
MAE 6.075 3 4.677 7 3.484 3
), ArticleFig(id=1154428931328430767, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Table 4, caption=Failure training data error indicators, figureFileSmall=null, figureFileBig=null, tableContent=
误差 指标 BP 神经 网络 GA-BP 神经网络 CEEMDAN-GA-BP 神经网络
RMSE 7.852 1 7.320 8 5.392 4
MBE 1.238 1 $- {3.812}\;9$ -1.1176
MAE 6.602 1 6.149 7 4.900 4
), ArticleFig(id=1154428931387151027, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=表 4, caption=故障训练数据误差指标, figureFileSmall=null, figureFileBig=null, tableContent=
误差 指标 BP 神经 网络 GA-BP 神经网络 CEEMDAN-GA-BP 神经网络
RMSE 7.852 1 7.320 8 5.392 4
MBE 1.238 1 $- {3.812}\;9$ -1.1176
MAE 6.602 1 6.149 7 4.900 4
), ArticleFig(id=1154428931450065591, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Table 5, caption=Normal test data error indicator, figureFileSmall=null, figureFileBig=null, tableContent=
误差 指标 BP 神经 网络 GA-BP 神经网络 CEEMDAN-GA-BP 神经网络
RMSE 7.363 6 6.537 9 5.7796
MBE -0.1475 -3.2170 $- {1.372}\;3$
MAE 6.056 9 5.407 1 5.020 9
), ArticleFig(id=1154428931517174458, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=表 5, caption=正常测试数据误差指标, figureFileSmall=null, figureFileBig=null, tableContent=
误差 指标 BP 神经 网络 GA-BP 神经网络 CEEMDAN-GA-BP 神经网络
RMSE 7.363 6 6.537 9 5.7796
MBE -0.1475 -3.2170 $- {1.372}\;3$
MAE 6.056 9 5.407 1 5.020 9
), ArticleFig(id=1154428931596866238, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=EN, label=Table 6, caption=Failure test data error indicator, figureFileSmall=null, figureFileBig=null, tableContent=
误差 指标 BP 神经 网络 GA-BP 神经网络 CEEMDAN-GA-BP 神经网络
RMSE 9.884 7 8.595 9 7.244 7
MBE 4.2721 -1.0491 $- {2.327}\;6$
MAE 8.8895 7.407 0 5.911 8
), ArticleFig(id=1154428931672363713, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428867923136599, language=CN, label=表 6, caption=故障测试数据误差指标, figureFileSmall=null, figureFileBig=null, tableContent=
误差 指标 BP 神经 网络 GA-BP 神经网络 CEEMDAN-GA-BP 神经网络
RMSE 9.884 7 8.595 9 7.244 7
MBE 4.2721 -1.0491 $- {2.327}\;6$
MAE 8.8895 7.407 0 5.911 8
)], attaches=null, journal=Journal(id=1146118781765529606, delFlag=0, nameCn=可再生能源, nameEn=Renewable Energy Resources, nameHistory1=null, nameHistory2=null, issn=1671-5292, eissn=, cn=21-1469/TK, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=JwZjzvOuLF6gg7XdYa5wzg==, journalPrice=null, startedYear=null, abbrevIsoEn=Renew Energy Res, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1755588886026, createdBy=null, updatedBy=15831073675, firstLetterCn=R, firstLetterEn=R, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=JwZjzvOuLF6gg7XdYa5wzg==, picEn=JbD+CPZ3qeyTMjY1NLqExg==, jcr=null, cjcr=null, exts=[JournalExt(id=1164587454112678277, language=CN, name=可再生能源, 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://kzsny.com/, createdTime=1755588886049, updatedTime=1755588886049, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=https://ncny.cbpt.cnki.net/EditorEN/PromptPageInfo.aspx?t=v&c=1, submissionAuthorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=1, submissionEditorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=3, submissionReviewUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=2, submissionCeEditorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=3, submissionAeEditorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=3, option={"copyright":""}), JournalExt(id=1164587454167204230, language=EN, name=Renewable Energy Resources, 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=, createdTime=1755588886062, updatedTime=1755588886062, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=, submissionAuthorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=1, submissionEditorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=3, submissionReviewUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=2, submissionCeEditorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=3, submissionAeEditorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=3, option={"copyright":""})], databaseList=null, tenantJournalId=1146119893612605453, websiteList=[Website(id=1148243202370429360, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146119893612605453, 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/kzsny/CN, language=CN, createTime=1751692112772, createBy=18614031015, updateTime=1753519535151, updateBy=18614031015, name=《可再生能源》-中文站点, tplId=1146099689490845704, title=可再生能源, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148619523667816493, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202370429360, code=articleTextType, value=kx, createTime=1751781834761, updateTime=1751781834761, creator=18614031015, updator=18614031015), WebsiteProps(id=1148619523642650666, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202370429360, code=banner, value=null, createTime=1751781834755, updateTime=1751781834755, creator=18614031015, updator=18614031015), WebsiteProps(id=1148619523634262057, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202370429360, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=y1rtJt0tFAqUB4W3g4tlSw==, createTime=1751781834753, updateTime=1751781834753, creator=18614031015, updator=18614031015), WebsiteProps(id=1148619523659427884, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202370429360, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751781834759, updateTime=1751781834759, creator=18614031015, updator=18614031015), WebsiteProps(id=1148619523651039275, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202370429360, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751781834757, updateTime=1751781834757, creator=18614031015, updator=18614031015)]), Website(id=1155908164001353748, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146119893612605453, 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/kzsny/EN, language=EN, createTime=1753519582037, createBy=18614031015, updateTime=1753519582037, updateBy=18614031015, name=《可再生能源》-英文站点, tplId=1146101810881728533, title=Renewable Energy Resources, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155908456914739359, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155908164001353748, code=articleTextType, value=kx, createTime=1753519651869, updateTime=1753519651869, creator=18614031015, updator=18614031015), WebsiteProps(id=1155908456893767836, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155908164001353748, code=banner, value=null, createTime=1753519651864, updateTime=1753519651864, creator=18614031015, updator=18614031015), WebsiteProps(id=1155908456885379227, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155908164001353748, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=y1rtJt0tFAqUB4W3g4tlSw==, createTime=1753519651862, updateTime=1753519651862, creator=18614031015, updator=18614031015), WebsiteProps(id=1155908456906350750, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155908164001353748, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753519651867, updateTime=1753519651867, creator=18614031015, updator=18614031015), WebsiteProps(id=1155908456902156445, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155908164001353748, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753519651866, updateTime=1753519651866, creator=18614031015, updator=18614031015)])], journalTitle=可再生能源, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Renewable Energy Resources, journalPhotoCn=JwZjzvOuLF6gg7XdYa5wzg==, journalPhotoEn=JbD+CPZ3qeyTMjY1NLqExg==, journalFirstLetter=R, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kzsny/CN/10.1109/ICASSP.2011.5947265, detailUrlEn=https://castjournals.cast.org.cn/joweb/kzsny/EN/10.1109/ICASSP.2011.5947265, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kzsny/CN/PDF/10.1109/ICASSP.2011.5947265, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kzsny/EN/PDF/10.1109/ICASSP.2011.5947265, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
CEEMDAN 联合自适应小波阈值算法的 GA-BP 风电发电机故障预测
收藏切换
PDF下载
肖成 1 , 曹万鹏 2 , 褚越强 1 , 杨政琨 1 , 王佳兴 1
可再生能源 | 2024,42(10): 1332-1340
收起
收藏切换
可再生能源 | 2024, 42(10): 1332-1340
CEEMDAN 联合自适应小波阈值算法的 GA-BP 风电发电机故障预测
全屏
肖成1 , 曹万鹏2, 褚越强1, 杨政琨1, 王佳兴1
作者信息
  • 1 北华航天工业学院 电子与控制工程学院 河北 廊坊 065000
  • 2 新天绿色能源股份有限公司 江苏 淮安 223001
  • 肖成(1983-),女,博士,副教授,研究方向为风电系统故障预测、智能控制。E-mail:

CEEMDAN joint adaptive wavelet thresholding algorithm for GA-BP wind turbine fault prediction
Cheng Xiao1 , Wanpeng Cao2, Yueqiang Chu1, Zhengkun Yang1, Jiaxing Wang1
Affiliations
  • 1 School of Electronics and Control Engineering North China Institute of Aerospace Engineering Langfang 065000 China
  • 2 China Suntien Green Energy Corporation Limited Huaian 223001 China
出版时间: 2024-10-20 doi: 10.1109/ICASSP.2011.5947265
文章导航
收藏切换

发电机是风电系统中重要的核心部件,为了提高风电机组的稳定、高效运行,对风电机组发电机的故障预测十分必要。文章围绕风电系统发电机机侧轴承温度超限故障预测的问题,考虑到所采集的故障特征信号具有较大噪声的特点,引入自适应完备噪声经验模态分解(CEEMDAN)联合自适应小波阈值去噪的方法实现信号有效去噪,同时结合 GABP神经网络建立故障预测模型。通过与BP神经网络、GABP神经网络对比预测指标、误差指标和预测效果图形,验证了所提算法可以获得较好的预测效果。误差指标和预测效果均有提升,对提前15 d风电系统发电机故障预测的准确率达到了92.98%。

风电系统  /  发电机故障  /  故障预测  /  CEEMDAN  /  GA-BP神经网络

Generator is an important core component in wind power system, in order to improve the stable and efficient operation of wind turbine, the fault prediction of wind turbine generator is necessary. Focusing on the problem of generator machineside bearing temperature overrun fault prediction in wind power system, this paper takes into account that the collected fault characteristic signal is characterized by large noise, introduces CEEMDAN joint adaptive wavelet threshold denoising method to realize effective denoising of the signal, and at the same time establishes a fault prediction model by combining GABP neural network. By comparing the prediction indexes, error indexes and prediction effect graphs with BP neural network and GABP neural network, it is verified that the proposed algorithm can obtain better prediction effect. The error index and prediction effect are improved, and the accuracy of the prediction of generator failure of wind power system 15 days in advance reaches 92.98%.

wind energy system  /  generator failure  /  fault prediction  /  CEEMDAN  /  GA-BP neural network
肖成, 曹万鹏, 褚越强, 杨政琨, 王佳兴. CEEMDAN 联合自适应小波阈值算法的 GA-BP 风电发电机故障预测. 可再生能源, 2024 , 42 (10) : 1332 -1340 . DOI: 10.1109/ICASSP.2011.5947265
Cheng Xiao, Wanpeng Cao, Yueqiang Chu, Zhengkun Yang, Jiaxing Wang. CEEMDAN joint adaptive wavelet thresholding algorithm for GA-BP wind turbine fault prediction[J]. Renewable Energy Resources, 2024 , 42 (10) : 1332 -1340 . DOI: 10.1109/ICASSP.2011.5947265
中共中央、国务院印发的《关于完整准确全面贯彻新发展理念做好碳达峰碳中和工作的意见》 提出了碳达峰-碳中和的战略目标,作为绿色能源,风力发电装机容量不断增大 [ 1 ] 。风电系统发电机是风电机组性能、效率和供电质量的核心,发电机轴承故障占所有故障的 70%~80% [ 2 ] 。轴承常见失效模式包括疲劳、摸索、断裂和电腐蚀等。经统计, 机侧轴承温度超限故障是风电场中发生次数最多的发电机故障。对风电机组发电机进行故障预测, 能够提前预警潜在问题。文献[ 3 ]提出了一种结合 $\mathrm{K}$ 均值聚类与 one-class $\mathrm{{KNN}}$ 单分类算法的预警方法, 可有效预警其绕组故障。文献[ 4 , 5 ]利用发电机定子绕组温度的预测模型与实际温度的对比分析,综合评估发电机定子的健康状况。文献[ 6 ]基于风电齿轮箱结构与运行控制,建立了基于单分类支持向量机的风电齿轮箱故障预警模型。文献[ 7 ]利用传热学构建发电机轴承温度动态模型,实现了对风电机组发电机轴承的故障诊断。 目前, 有关风电机组故障诊断的研究多集中于齿轮箱、发电机绕组以及轴承,对风电场中发电机机侧轴承温度超限故障预测的研究较少。
自适应完备噪声经验模态分解(CEEMDAN) 是一种对非线性或者非平稳信号分解的有效方法, 克服了端点效应和模态混叠现象。文献[ 8 ]提出了一种结合完全 CEEMDAN 与小波阈值技术的创新算法。文献 [ 9 ] 将集合经验模态分解 (CEEMD)与卷积神经网络(CNN)结合并应用于海上漂浮式风力机系泊系统的健康监测。
BP 神经网络神经元的传递函数具有非线性特性, 但是收敛速度相对较慢, 易陷入局部最优解。遗传算法(GA)是全局搜索的寻优算法,算法通过不断迭代, 生成最适应环境的个体。将两者结合,可以高效地搜索全局最优解。文献[ 10 ]提出了一种基于特征工程和遗传算法优化的 BP 神经网络方法。文献[ 11 ]基于实验数据建立了三输入两输出的 BP 神经网络预测模型,利用 GA 对 BP 模型进行优化。
针对发电机信号中显著的噪声干扰问题,本文提出了一种综合应用 CEEMDAN 与自适应小波阈值去噪的方法。该方法首先利用 CEEMDAN 技术对信号进行分解, 有效分离出信号中的固有模态函数, 从而降低噪声干扰; 然后, 通过自适应小波阈值处理,优化了去噪过程,解决了传统硬阈值和软阈值在信号重构上的局限性。这种结合方案不仅提高了信号重构的平滑度, 而且减小了与真实信号之间的差距;最后,与 GA-BP 神经网络联合进行风电系统发电机机侧轴承温度超限的故障预测。
CEEMDAN 算法显著提高了信号分解的准确性和可靠性 [ 12 ] ,为复杂信号的分析提供了一种有效工具。
CEEMDAN 算法具体实现步骤如下 [ 8 , 13 ]
① 假设 $x\left( t\right)$ 为发电机采集的原始信号, ${\omega }^{i}\left( t\right)$ 为第 $i$ 次添加的高斯白噪声,且白噪声服从 $N\left({0,1}\right)$ 分布。
${x}_{i}\left( t\right)= x\left( t\right)+ {\sigma }_{0}{\omega }^{i}\left( t\right), i = 1,2,\cdots , N $
式中: ${x}_{i}\left( t\right)$ 为加入白噪声后的第 $i$ 个信号; ${\sigma }_{0}$ 为噪声的标准偏差; $i$ 为添加噪声的次数。
${\mathrm{{IMF}}}_{i}^{1}$$x\left( i\right)$ 进行 $\mathrm{{EMD}}$ 分解得到的一阶模态分量, 第一个本征模态分量为
${\mathrm{{IMF}}}_{1}= \frac{1}{N}\mathop{\sum }\limits_{{i = 1}}^{N}{\mathrm{{IMF}}}_{i}^{1}$
去除第一个本征模态分量后的残差分量 ${r}_{1}$
${r}_{1}= x\left( t\right)- {\mathrm{{IMF}}}_{1}$
③基于 EMD 分解获取了第 $k$ 阶模态分量 ${E}_{k}\left(\cdot \right)$ , 将高斯白噪声加入残差分量中以生成新序列 ${r}_{1}\left( i\right)= {r}_{1}+ {\delta }_{1}{E}_{1}\left\lbrack {{\omega }^{i}\left( t\right)}\right\rbrack$ ; 然后,对信号 ${r}_{1}\left( i\right)$ 实施 EMD 分解, 从而提取出第二个本征模态分量。
${\mathrm{{IMF}}}_{2}= \frac{1}{N}\mathop{\sum }\limits_{{i = 1}}^{N}{E}_{1}\left\{{{r}_{1}+ {\delta }_{1}{E}_{1}\left\lbrack {{\omega }^{i}\left( t\right)}\right\rbrack }\right\}$
式中: ${\delta }_{1}$ 为添加的白噪声信号。
去除第二个本征模态分量后的残差分量 ${r}_{2}$
${r}_{2}= {r}_{1}- {\mathrm{{IMF}}}_{2}$
④重复步骤③,可以求得第 $k$ 个本征模态分量 ${\mathrm{{IMF}}}_{k}$ 和第 $k$ 个残差分量 ${r}_{k}$
${\mathrm{{IMF}}}_{k}= \frac{1}{N}\mathop{\sum }\limits_{{i = 1}}^{N}{E}_{1}\left\{{{r}_{k - 1}+ {\delta }_{k - 1}{E}_{k - 1}\left\lbrack {{\omega }^{i}\left( t\right)}\right\rbrack }\right\}$
${r}_{k}= {r}_{k - 1}- {\mathrm{{IMF}}}_{k}$
在 CEEMDAN 的分解过程中,需要对余量 ${r}_{k}$ 的极值点数量进行评估。如果 ${r}_{k}$ 的极值点少于 2 个,说明对原始信号 $x\left( t\right)$ 的 CEEMDAN 分解终止; 如果 ${r}_{k}$ 的极值点超过 2 个,则继续执行步骤 ③以完成进一步的分解。
得到 $k$ 个本征模态分量和一个残差余量。
$ x\left( t\right)= \mathop{\sum }\limits_{{k = 1}}^{K}{\mathrm{{IMF}}}_{k}+ {r}_{k}$
$\psi \left( t\right)\in {L}^{2}\left( R\right)$ ,在傅里叶变换中,当函数 $\widehat{\psi }\left(\omega \right)$ 满足特定的重构条件 ${C}_{\psi }= {\int }_{R}\frac{{\left|\psi \left(\omega \right)\right|}^{2}}{\left|\omega \right|}\mathrm{d}\omega <$ $+\infty$ 时, $\psi \left( t\right)$ 被称为基本小波函数。通过对 $\psi \left( t\right)$ 执行尺度伸缩和平移操作, 可以构造出一个函数集合 $\left\{{{\psi }_{a, b}\left( t\right)}\right\}$
${\psi }_{a, b}\left( t\right)= \frac{1}{\sqrt{\left| a\right|}}\psi \left(\frac{t - b}{a}\right)\;a, b \in R;a \neq 0 $
式中: 参数 $a$ 为伸缩因子,调控小波函数的伸缩程度,从而影响其频率特性; 参数 $b$ 为平移因子,控制小波函数沿时间轴的移动, 以适应信号在不同时间点的分析需求。
任意信号 $f\left( t\right)\in {L}^{2}\left( R\right)$ 的连续小波变换为
${W}_{f}\left({a, b}\right)= < f,{\psi }_{a, b}> =\frac{1}{{\left| a\right|}^{2}}{\int }_{R}f\left( t\right)\psi \left(\frac{t - b}{a}\right)\mathrm{d} t$
风电系统发电机故障指标采集信号为离散数据,对应的离散小波函数表示为
${\psi }_{j, k}\left( t\right)= {a}_{0}^{-\frac{j}{2}}\psi \left(\frac{t - k{a}_{0}^{j}{b}_{0}}{{a}_{0}^{j}}\right)= {a}_{0}^{-\frac{j}{2}}\psi \left({{a}_{0}^{-j}t - k{b}_{0}}\right)$
式中: $j, k \in {Z}_{\circ }$
离散小波变换系数为
${C}_{j, k}= {\int }_{-\infty }^{+\infty }f\left( t\right){\psi }_{j, k}\left( t\right)\mathrm{d}t $
小波重构如下所示:
$ f\left( t\right)= C\mathop{\sum }\limits_{{-\infty }}^{{+\infty }}\mathop{\sum }\limits_{{-\infty }}^{{+\infty }}{C}_{j, k}{\psi }_{j, k}\left( t\right)$
本文采用三层小波分解技术, 成功将信号分解为一个低频近似系数和 3 个高频细节系数,实现了信号在多个尺度上的特征提取。
小波阈值去噪法简单易行、计算量小,阈值函数通过设定特定的阈值来调整和优化小波系数, 其中硬阈值函数和软阈值函数是两种常见的处理方法 [ 14 ]
硬阈值函数为
${\widehat{w}}_{j, k}= \left\{\begin{array}{ll}{w}_{j, k}& \left|{w}_{j, k}\right|\geq \lambda \\ 0 &\left|{w}_{j, k}\right|< \lambda \end{array}\right.$
软阈值函数为
${\widehat{w}}_{j, k}= \left\{\begin{array}{ll}\operatorname{sgn}\left({w}_{j, k}\right)\left(\left|{{w}_{j, k}- \lambda }\right|\right)& \left|{w}_{j, k}\right|\geq \lambda \\ 0 &\left|{w}_{j, k}\right|< \lambda \end{array}\right.$
式中: ${w}_{jk}$ 为原始的小波系数; $\lambda$ 为设定的阈值; ${\widehat{w}}_{jk}$ 为经过阈值处理函数后得到的小波系数; $\mathrm{{sgn}}\left(\right)$ 为一个符号函数, 用于确定处理后的系数符号。
在信号处理领域, 硬阈值函数可能导致重构信号与原始信号之间出现显著偏差。在模大于阈值时,软阈值操作会有恒定的偏差存在。
为了进一步提升去噪性能,本文构造了阈值函数, 该函数在硬阈值和软阈值之间取得平衡。 式(16)为自适应阈值处理函数。
$\eta \left({{w}_{j, k},\lambda ,{m}_{j}}\right)= \\\left\{\begin{array}{ll}{w}_{j, k}- {0.5}\operatorname{sign}\left({w}_{j, k}\right)\frac{{\lambda }^{{m}_{j}}}{{\left|{w}_{j, k}\right|}^{{m}_{j}- 1}}& \left|{w}_{j, k}\right|\geq \lambda \\{0.5}\operatorname{sign}\left({w}_{j, k}\right)\frac{{\left|{w}_{j, k}\right|}^{{m}_{j, k}}}{{\lambda }^{{m}_{j}}}& \left|{w}_{j, k}\right|< \lambda \end{array}\right.$
在自适应阈值处理函数的设计中,参数 ${m}_{j}$ 可以取大于 1 的任意连续实数, 对小波系数的去噪行为产生决定性影响。当参数 ${m}_{j}= 1$ 时,所采用的阈值函数在功能上与软阈值函数极为相似;随着 ${m}_{j}$ 的增加,当 ${m}_{j}> {10}$ 时,阈值函数的表现则趋近于硬阈值函数。通过这种基于参数 ${m}_{j}$ 的自适应调整, 实现在降低噪声和保留信号特征之间的优化平衡。
${m}_{j}= 1 +{10}\frac{{E}_{nj}}{{E}_{dj}}$
式中: ${m}_{j}\in (1,{22}\rbrack$ ,当 $j = 1$ 时, ${m}_{j}= {11}$ ,随着参数 $j$ 的持续增加, ${m}_{j}$ 呈现逐渐减小的趋势; $d$ 为高频信号部分的能量分量。
${E}_{n1}\approx \mathop{\sum }\limits_{{k = 0}}^{{N - 1}}{d}_{1, k}^{2},{E}_{n}\approx 2{E}_{{n}_{1}}\approx 2\mathop{\sum }\limits_{{k = 0}}^{{N - 1}}{d}_{1, k}^{2}$ ,则 ${E}_{{n}_{j}}\approx \frac{1}{{2}^{j}}$ .
${E}_{n}\approx \frac{1}{{2}^{j - 1}}\mathop{\sum }\limits_{{k = 0}}^{{N - 1}}{d}_{1, k}^{2},{E}_{dj}= \mathop{\sum }\limits_{{k = 0}}^{{N - 1}}{d}_{1, k}^{2}\circ $
在风电系统发电机故障信号分析中, 通过 CEEMDAN 分解获得的 IMF 分量按瞬时频率递减排序, 然后利用高相关系数 IMF 分量的叠加重构,可有效实现低通、高通和带通滤波器的功能 [ 15 ] 。 本文通过分析确定了相关系数超过 0.2 的固有模态分量 (IMF) 作为关键特征, 并采用自适应小波阈值去噪算法对这些选定的 IMF 进行精细化处理。最后, 对选取的 IMF 去噪后分量和未选取处理的 IMF 分量实现信号重构。
IMF 分量与原始信号的相关系数 $\rho$
$\rho =\frac{\mathop{\sum }\limits_{{t = 1}}^{n}\left\lbrack {x\left( t\right)- \bar{x}}\right\rbrack \left\lbrack {{f}_{{\mathrm{{IMF}}}_{k}}\left( t\right)- {\bar{f}}_{{\mathrm{{IMF}}}_{k}}}\right\rbrack }{\sqrt{\mathop{\sum }\limits_{{t = 1}}^{n}{\left\lbrack x\left( t\right)- \bar{x}\right\rbrack }^{2}}\sqrt{\mathop{\sum }\limits_{{t = 1}}^{n}{\left\lbrack {f}_{{\mathrm{{IMF}}}_{k}}\left( t\right)- {\bar{f}}_{{\mathrm{{IMF}}}_{k}}\right\rbrack }^{2}}}$
式中: $x$$x\left( t\right)$ 的平均值; ${f}_{{\mathrm{{IMF}}}_{k}}$${f}_{{\mathrm{{IMF}}}_{k}}\left( t\right)$ 的平均值。
CEEMDAN 结合自适应小波阈值去噪算法实现了对风电发电机系统故障指标信号的处理,其流程如 图 1 所示。
发电机故障指标信号分解得到的 IMF 波形如 图 2 所示。
得到的 IMF 分解阶次和相关系数如 图 3 所示。
在时域中,信号去噪前后对比效果见 图 4
BP 网络是由信号正向传播以及误差信号反向传播的多层前向反馈神经网络,本文选用三层 BP 神经网络, 模型结构如 图 5 所示。
图中: ${X}_{l}= \left({{x}_{1}^{l},{x}_{2}^{l},\cdots ,{x}_{m}^{l}}\right)$ 为输入变量; ${Y}_{l}= {y}_{l}^{n}$ 为输出的期望变量; ${w}_{ih}$ 为输入层第 $i$ 个神经元和隐含层第 $h$ 个神经元之间的连接权重; ${v}_{hk}$ 为隐含层第 $h$ 个神经元和输出层第 $k$ 个神经元之间的连接权重; ${a}_{h}$ 为第 $h$ 个神经元的阈值; ${b}_{k}$ 为输出层第 $k$ 个神经元的阈值。
BP 神经网络易出现局部最优解, GA 可以进一步优化 BP 神经网络的权重和阈值,优化过程如下。
①种群的权重、阈值初始化。
神经网络输入层与隐含层连接权重、隐含层阈值、隐含层与输出层连接权重、输出层阈值生成种群个体。输入层节点数为 $m$ ,隐含层节点数为 $h$ ,输出层节点数为 $n$ 。输入层节点数种群中权重或阈值使用 $l$ 位二进制数进行编码,于是种群个体编码长度 $L$ 定义为
$ L = l \cdot \left({{mh}+ {hn}+ h + n}\right)$
②计算种群个体的适应度。
个体适应度函数 $F$
$ F =\mathop{\sum }\limits_{{i = 1}}^{n}\left|{{y}_{i}- {\widehat{y}}_{i}}\right|$
式中: $n$ 为测试样本数量; ${y}_{i}$ 为输出的真实值; ${\widehat{y}}_{i}$ 为预测值。
③遗传操作。
遗传操作包括选择操作、交叉操作和变异操作。
选择操作:适应度越小,误差越小。选择操作过程为
${p}_{i}= {f}_{i}/\mathop{\sum }\limits_{{i = 1}}^{N}{f}_{i}$
${f}_{i}= k/{F}_{i}$
式中: ${p}_{i}$ 为个体被选中的概率; ${f}_{i}$ 为第 $i$ 个个体的适应度; $N$ 为种群个体数目; $k$ 为系数; ${F}_{i}$ 为个体 $i$ 的排名。
交叉操作:染色体 ${c}_{t}$ 和染色体 ${c}_{v}$ 在位置 $k$ 进行交叉操作。
$\left\{\begin{array}{l}{c}_{tk}= {c}_{tk}\left({1 - a}\right)+ {c}_{vk}a \\{c}_{vk}= {c}_{vk}\left({1 - a}\right)+ {c}_{tk}a \end{array}\right.$
式中: ${c}_{tk},{c}_{vk}$ 分别为 ${c}_{t},{c}_{v}$ 在位置 $k$ 进行交叉操作后的染色体; $a$ 为随机数且位于 $\left\lbrack {0,1}\right\rbrack$
变异操作: 第 $t$ 个染色体中第 $i$ 个基因进行变异。
$\left\{\begin{array}{ll}{c}_{ti}= {c}_{ti}+ \left({{c}_{ti}- {a}_{\max }}\right)\cdot f\left( g\right)& r > 0 \\{c}_{ti}= {c}_{ti}+ \left({{a}_{\min }- {c}_{ti}}\right)\cdot f\left( g\right)& r \leq 0 \end{array}\right.$
$ f\left( g\right)= {r}^{\prime }{\left( 1 - g/{G}_{\max }\right)}^{2}$
式中: ${c}_{ti}$ 为变异基因; ${a}_{\max },{a}_{\min }$ 分别为变异基因的上、下界限; $f\left( g\right)$ 为调整的变异率; $g$ 为迭代次数; ${G}_{\max }$ 为最大进化次数; $r,{r}^{\prime }$ 为随机数。
④产生下一代种群。
⑤重复以上操作,获取输出最优权重和阈值。
GA-BP 神经网络流程如 图 6 所示。
经前期分析,选取发电机机侧轴承温度、电网频率、轴电流、发电机冷却温度、无功功率和风速作为发电机故障预测模型的输入, 叶轮转速作为输出。提取风电系统发电机故障发生前第 15 天的数据, 同时采集了与故障数据数量相等的正常运行数据,这些数据在未发生故障时收集,故障和正常数据具有相同的特征维度 ${21600}\times 7$ 。在数据预处理阶段,数据被划分为训练集和测试集,作为训练的数据,其维数为 ${15120}\times 7$ ; 测试的数据,维数为 ${6480}\times 7$ 。选用 GA-BP 神经网络,神经网络的输入层节点数为 6 , 输出层节点数为 1 , 隐含层节点数为 13。
隐含层输入可以表示为
${I}_{h}= \mathop{\sum }\limits_{{h = 1}}^{6}{W}_{ih}{x}_{i}+ {a}_{h}$
式中: ${I}_{h}$ 为第 $h$ 层神经元输入; ${W}_{ih}$ 为输入层第 $i$ 个神经元和隐含层第 $h$ 个神经元之间的权重; ${x}_{i}$ 为输入变量; ${a}_{h}$ 为第 $h$ 个神经元的阈值。
选用 Sigmoid 函数作为激活函数。
$ f\left( x\right)= \frac{1}{1 +{\mathrm{e}}^{-x}}$
隐含层输出可以表示为
${O}_{h}= f\left({\mathop{\sum }\limits_{{h = 1}}^{6}{W}_{ih}{x}_{i}+ {a}_{h}}\right)$
式中: $f\left( x\right)$ 为输入层与隐含层之间的激活函数。
输出层输出可以表示为
${O}_{k}= g\left({\mathop{\sum }\limits_{{h = 1}}^{M}{V}_{hk}{O}_{h}+ {b}_{k}}\right)$
式中: $g\left( x\right)$ 为隐含层与输出层之间的激活函数; ${V}_{hk}$ 为隐含层第 $h$ 个神经元和输出层第 $k$ 个神经元之间的权重; ${b}_{k}$ 为输出层第 $k$ 个神经元的阈值; $M$ 为隐含层神经元个数。
选取性能指标和误差指标共同作为性能评估指标。选取准确率(ACC)、精确率(Precision)、召回率(Recall)和诊断能力评价(Specificity)作为性能指标。
$\mathrm{{ACC}}= \frac{{TP}+ {TN}}{{TP}+ {FN}+ {FP}+ {TN}}$
$\text{Precision}= \frac{TP}{{TP}+ {FP}}$
$\text{Recall}= \frac{TP}{{TP}+ {FN}}$
$\text{Specificity}= \frac{TN}{{TN}+ {FP}}$
式中: ${TP}$ 为检测正确,发电机系统正常运行; ${FN}$ 为检测错误,发电机系统故障运行; ${FP}$ 为检测错误,发电机系统正常运行; ${TN}$ 为检测正确,发电机系统故障运行。
选取均方根误差 RMSE、平均绝对误差 MAE 和平均误差 MBE 作为误差指标。
$\text{ RMSE=}\sqrt{\frac{1}{n}\mathop{\sum }\limits_{{i = 1}}^{n}{\left({y}_{i}- {\widehat{y}}_{i}\right)}^{2}}$
$\mathrm{{MAE}}= \frac{1}{n}\mathop{\sum }\limits_{{i = 1}}^{n}\left|{{y}_{i}- {\widehat{y}}_{i}}\right|$
$\mathrm{{MBE}}= \frac{1}{n}\mathop{\sum }\limits_{{i = 1}}^{n}\left({{y}_{i}- {\widehat{y}}_{i}}\right)$
式中: ${y}_{i}$ 为真实值; ${\widehat{y}}_{i}$ 为模型对第 $i$ 个数据点的预测值; $n$ 为数据点个数。
比较 BP 神经网络模型、GA-BP 神经网络模型和 CEEMDAN-GA-BP 神经网络模型的预测效果, 得到的预测结果如 表 1 所示。
对比以上 3 种预测模型, 得到的预测结果如 表 2 所示。
表 2 可知,与 BP 神经网络和 GA-BP 神经网络模型相比, CEEMDAN-GA-BP 神经网络模型不仅将预测准确率提升了 19.2% 和 10.57%, 在精确率、召回率以及诊断能力等多个关键指标上均实现了显著增强。
本文选取 RMSE, MBE 和 MAE 来分析实验效果, 将叶轮转速作为训练模型的输出指标, 结果如 表 3 ~6 所示。
表 3 ~6 可知,与 BP 神经网络和 GA-BP 神经网络模型相比, CEEMDAN-GA-BP 神经网络模型的误差指标均有下降, 说明该模型的拟合效果更好。
CEEMDAN-GA-BP 神经网络模型的适应度变化曲线如 图 7 所示。
BP 神经网络模型、GA-BP 神经网络模型和 CEEMDAN-GA-BP 神经网络模型的正常训练集预测结果、故障训练集预测结果、正常测试预测结果和故障测试预测结果曲线如 图 8 ~11 所示。
图 8 ~11 可知,与 BP 神经网络和 GA-BP 神经网络模型相比, CEEMDAN-GA-BP 神经网络模型输出信号可以更好地拟合原数据, 具有更小的误差,更适用于风电机组发电机的故障预测。
本文分析了风电系统发电机故障, 讨论了故障预测方法。对于发电机采集数据存在较大噪声的情况, 采用 CEEMDAN 联合自适应小波阈值去噪的方法处理发电机数据。同时,结合 GA-BP 神经网络进行风电机组发电机机侧轴承温度超限故障的故障预测。通过与 $\mathrm{{BP}}$ 神经网络和 $\mathrm{{GA}}- \mathrm{{BP}}$ 神经网络进行误差指标、预测效果的对比,基于 CEEMDAN 联合自适应小波阈值的 GA-BP 神经网络在风电系统发电机故障预测领域展现出显著的优势,实现了预测准确率的明显提升。
  • 河北省教育厅重点项目(ZD2022089)
  • 北华航天工业学院博士基金项目(BKY-2023-03)
  • 北华航天工业学院校重点项目(ZD-2022-03)
参考文献 引证文献
排序方式:
[1]
韩肖清, 李廷钧, 张东霞, 等. 双碳目标下的新型电力系统规划新问题及关键技术[J]. 高电压技术, 2021, 47(9): 3036-3046.
[2]
吕致为. 基于深度迁移学习的风电机组发电机轴承故障诊断方法研究[D]. 北京: 华北电力大学, 2023.
[3]
米志伟, 常彬. 考虑变流器容错特性的海上双馈风电机组绕组短路故障辨识[J]. 可再生能源, 2021, 39(4): 521-526.
[4]
龙泉, 鲁志平, 张羽. 基于BP神经网络的多变量风力发电机绕组温度预测[A]. 2016年中国电机工程学会年会论文集[C].南京:中国电机工程学会, 2016.
[5]
滕伟, 黄乙珂, 吴仕明, 等. 基于 XGBoost 与 LSTM 的风力发电机绕组温度预测[J]. 中国电力, 2021, 54(6): 95-103.
[6]
蒙康, 滕伟. 运行机理与数据双驱动的风电齿轮箱系统故障预警[J]. 中国机械工程, 2023, 34(12): 1476-1485.
[7]
刘红艳, 刘华新, 朱霄珣. 基于胶囊网络的风电机组主轴承故障诊断研究[J]. 自动化仪表, 2022, 43(3): 15-19.
[8]
樊超阳, 李朝锋. CEEMDAN 联合小波阈值算法在水下激光雷达中抑制散射杂波的应用[J]. 物理学报, 2023, 72(22): 1-8.
[9]
贾文哲, 闻麒. 改进 CEEMDAN 算法与 CNN 融合的深度学习系泊故障研究[J]. 热能动力工程, 2023, 38(11): 141-150.
[10]
金宇强, 李春辉, 黄震威, 等. 基于特征工程和 GA-BP 神经网络的气体超声流量计使用中检验方法的研究[J/OL]. 计量学报, https://link.cnki.net/urlid/11.1864.TB.20240416.1517.004 https://link.cnki.net/urlid/11.1864.TB.20240416.1517.004
[11]
李凯, 魏鹤琳, 尹志凡, 等. 基于 GA-BP 神经网络模型预测水基炭黑-胶原蛋白纳米流体热导率和黏度[J/OL]. 化工进展, https://doi.org/10.16085/j.issn.1000-6613.2023-0961 https://doi.org/10.16085/j.issn.1000-6613.2023-0961
[12]
Torres M E, Colominas M A, Schlotthauer G, et al. A complete ensemble empirical mode decomposition with adaptive noise[J]. IEEE, 2011. Doi:10.1109/ICASSP.2011.5947265.
[13]
江莉, 向世召. 基于 CEEMDAN-VSSLMS 的滚动轴承故障诊断[J/OL]. 计算机集成制造系统, https://link.cnki.net/urlid/11.5946.TP.20231023.0900.002 https://link.cnki.net/urlid/11.5946.TP.20231023.0900.002
[14]
王念彬. 基于小波神经网络的小电流接地系统故障选线方法的研究[D]. 北京: 中国矿业大学, 2010.
[15]
周强, 蔡嘉炜. 基于指数平滑与CEEMDAN 的混合储能控制策略研究[J]. 可再生能源, 2020, 38(6): 846-852.
2024年第42卷第10期
PDF下载
338
136
引用本文
BibTeX
文章信息
doi: 10.1109/ICASSP.2011.5947265
  • 接收时间:2024-06-18
  • 首发时间:2025-07-22
  • 出版时间:2024-10-20
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-06-18
基金
河北省教育厅重点项目(ZD2022089)
北华航天工业学院博士基金项目(BKY-2023-03)
北华航天工业学院校重点项目(ZD-2022-03)
作者信息
    1 北华航天工业学院 电子与控制工程学院 河北 廊坊 065000
    2 新天绿色能源股份有限公司 江苏 淮安 223001
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kzsny/CN/10.1109/ICASSP.2011.5947265
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