Article(id=1217836023514583047, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1217836019408360416, articleNumber=null, orderNo=null, doi=10.19666/j.rlfd.202501046, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1736179200000, receivedDateStr=2025-01-07, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1768284334304, onlineDateStr=2026-01-13, pubDate=1764000000000, pubDateStr=2025-11-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1768284334304, onlineIssueDateStr=2026-01-13, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1768284334304, creator=13701087609, updateTime=1768284334304, updator=13701087609, issue=Issue{id=1217836019408360416, tenantId=1146029695717560320, journalId=1210938733613449225, year='2025', volume='54', issue='11', pageStart='1', pageEnd='168', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1768284333326, creator=13701087609, updateTime=1768284453982, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1217836525543408117, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1217836019408360416, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1217836525543408118, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1217836019408360416, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=58, endPage=67, ext={EN=ArticleExt(id=1217836023753658381, articleId=1217836023514583047, tenantId=1146029695717560320, journalId=1210938733613449225, language=EN, title=Healthy state monitoring method for offshore booster station platforms based on memory unit autoencoder method, columnId=1217836020515652407, journalTitle=Thermal Power Generation, columnName=Renewable energy power generation technology, runingTitle=null, highlight=null, articleAbstract=

A novel healthy state monitoring method for offshore booster station platforms is proposed to enhance the damage detection capabilities under complex operating conditions. Using a deep learning framework based on memory unit autoencoders, the method magnifies fault-relevant features via denoising and angular domain resampling high-frequency vibration data from offshore boosting stations. The model employs a deep convolutional neural network to learn historical data patterns, constructs a hidden state memory bank, and achieves sparse matching between sample encoded features and the memory bank. Finally, a Gaussian mixture probability model is employed to model the generated membership scores to assess the health status of the booster station. A case study of the offshore booster station in Rudong, Jiangsu, validates the approach, achieving an anomaly recall rate and accuracy of over 98%, outperforming other comparison algorithms.

, 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=Ruigang ZHANG, Dapeng WANG, Hang LEI, Jialiang WANG, Nan GUO, Jianqiang REN), CN=ArticleExt(id=1217836025628512362, articleId=1217836023514583047, tenantId=1146029695717560320, journalId=1210938733613449225, language=CN, title=基于记忆单元自编码的海上升压站平台健康监测方法, columnId=1217836020662453050, journalTitle=热力发电, columnName=新能源发电技术, runingTitle=null, highlight=null, articleAbstract=

提出一种新型海上升压站平台健康监测方法,以增强其在复杂工况下的损伤检测能力。采用基于记忆单元自编码器的深度学习框架,通过对海上升压站的高频振动数据进行降噪和角域重采样来放大故障相关特征。模型利用深度卷积神经网络学习历史数据模式,构建隐藏状态记忆库,并实现样本编码特征与记忆库的稀疏匹配。最后,采用高斯混合概率模型对生成的从属分数进行建模,以评估升压站的健康状态。以江苏如东县的海上升压站为案例进行验证,实现了98%以上的异常召回率及准确率,优于其他对比算法。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
王嘉良(1997),男,硕士,工程师,主要研究方向为海上风电安全监测技术,
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=smJrzNoDHb1VwHc/pwOiQA==, magXml=L6YnnrCcZHM2x/rYxzkyAQ==, pdfUrl=null, pdf=KfGhRs4ux1vTbS6p3fYQOg==, pdfFileSize=1469000, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=0AXGtrf9Ps/1LsRbqZjLOA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=ramA0CWYAZfxZaym2GnisQ==, mapNumber=null, authorCompany=null, fund=null, authors=

张瑞刚(1982),男,硕士,正高级工程师,主要研究方向为新能源发电设备选型、风力发电安全监测技术,

, authorsList=张瑞刚, 王大鹏, 雷航, 王嘉良, 郭楠, 任建强)}, authors=[Author(id=1217836026022776964, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhangruigang@tpri.com.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1217836026077302919, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, authorId=1217836026022776964, language=EN, stringName=Ruigang ZHANG, firstName=Ruigang, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Xi’an Thermal Power Research Institute Co., Ltd., Xi’an 710054, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836027398508686, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, authorId=1217836026022776964, language=CN, stringName=张瑞刚, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.西安热工研究院有限公司,陕西 西安 710054, bio={"content":"

张瑞刚(1982),男,硕士,正高级工程师,主要研究方向为新能源发电设备选型、风力发电安全监测技术,

"}, bioImg=null, bioContent=

张瑞刚(1982),男,硕士,正高级工程师,主要研究方向为新能源发电设备选型、风力发电安全监测技术,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836025829838963, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, xref=1., ext=[AuthorCompanyExt(id=1217836025834033268, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025829838963, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Xi’an Thermal Power Research Institute Co., Ltd., Xi’an 710054, China), AuthorCompanyExt(id=1217836025838227573, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025829838963, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安热工研究院有限公司,陕西 西安 710054)])]), Author(id=1217836027507560596, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, 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=1217836027612418205, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, authorId=1217836027507560596, language=EN, stringName=Dapeng WANG, firstName=Dapeng, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Huaneng Longdong Energy Co., Ltd., Qingyang 745100, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836027692109987, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, authorId=1217836027507560596, language=CN, stringName=王大鹏, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.华能陇东能源有限责任公司,甘肃 庆阳 745100, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836025922113660, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, xref=2., ext=[AuthorCompanyExt(id=1217836025930502269, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025922113660, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Huaneng Longdong Energy Co., Ltd., Qingyang 745100, China), AuthorCompanyExt(id=1217836025934696574, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025922113660, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.华能陇东能源有限责任公司,甘肃 庆阳 745100)])]), Author(id=1217836027780190379, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, 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=1217836027889242290, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, authorId=1217836027780190379, language=EN, stringName=Hang LEI, firstName=Hang, middleName=null, lastName=LEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Xi’an Thermal Power Research Institute Co., Ltd., Xi’an 710054, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836028031848639, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, authorId=1217836027780190379, language=CN, stringName=雷航, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.西安热工研究院有限公司,陕西 西安 710054, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836025829838963, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, xref=1., ext=[AuthorCompanyExt(id=1217836025834033268, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025829838963, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Xi’an Thermal Power Research Institute Co., Ltd., Xi’an 710054, China), AuthorCompanyExt(id=1217836025838227573, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025829838963, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安热工研究院有限公司,陕西 西安 710054)])]), Author(id=1217836028149289157, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=wangjialiang@tpri.com.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1217836028266729677, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, authorId=1217836028149289157, language=EN, stringName=Jialiang WANG, firstName=Jialiang, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Xi’an Thermal Power Research Institute Co., Ltd., Xi’an 710054, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836028384170195, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, authorId=1217836028149289157, language=CN, stringName=王嘉良, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.西安热工研究院有限公司,陕西 西安 710054, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836025829838963, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, xref=1., ext=[AuthorCompanyExt(id=1217836025834033268, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025829838963, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Xi’an Thermal Power Research Institute Co., Ltd., Xi’an 710054, China), AuthorCompanyExt(id=1217836025838227573, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025829838963, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安热工研究院有限公司,陕西 西安 710054)])]), Author(id=1217836028459667673, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, 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=1217836028610662627, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, authorId=1217836028459667673, language=EN, stringName=Nan GUO, firstName=Nan, middleName=null, lastName=GUO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Huaneng Longdong Energy Co., Ltd., Qingyang 745100, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836028728103148, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, authorId=1217836028459667673, language=CN, stringName=郭楠, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.华能陇东能源有限责任公司,甘肃 庆阳 745100, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836025922113660, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, xref=2., ext=[AuthorCompanyExt(id=1217836025930502269, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025922113660, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Huaneng Longdong Energy Co., Ltd., Qingyang 745100, China), AuthorCompanyExt(id=1217836025934696574, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025922113660, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.华能陇东能源有限责任公司,甘肃 庆阳 745100)])]), Author(id=1217836028879098099, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, orderNo=5, 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=1217836029000732924, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, authorId=1217836028879098099, language=EN, stringName=Jianqiang REN, firstName=Jianqiang, middleName=null, lastName=REN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Huaneng Longdong Energy Co., Ltd., Qingyang 745100, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836029231419653, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, authorId=1217836028879098099, language=CN, stringName=任建强, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.华能陇东能源有限责任公司,甘肃 庆阳 745100, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836025922113660, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, xref=2., ext=[AuthorCompanyExt(id=1217836025930502269, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025922113660, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Huaneng Longdong Energy Co., Ltd., Qingyang 745100, China), AuthorCompanyExt(id=1217836025934696574, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025922113660, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.华能陇东能源有限责任公司,甘肃 庆阳 745100)])])], keywords=[Keyword(id=1217836029340471565, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=EN, orderNo=1, keyword=offshore booster station platform), Keyword(id=1217836029441134868, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=EN, orderNo=2, keyword=health monitoring), Keyword(id=1217836029537603869, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=EN, orderNo=3, keyword=angular domain resampling), Keyword(id=1217836029638267175, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=EN, orderNo=4, keyword=memory unit), Keyword(id=1217836029738930476, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=EN, orderNo=5, keyword=deep autoencoder), Keyword(id=1217836029831205169, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=CN, orderNo=1, keyword=海上升压站平台), Keyword(id=1217836029948645688, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=CN, orderNo=2, keyword=健康监测), Keyword(id=1217836030036726082, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=CN, orderNo=3, keyword=角域重采样), Keyword(id=1217836030154166601, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=CN, orderNo=4, keyword=记忆单元), Keyword(id=1217836030393241936, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=CN, orderNo=5, keyword=深度自编码器)], refs=[Reference(id=1217836033941623282, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=ZHENG T, XIE W, YAO Z, journalName=null, refType=null, unstructuredReference=ZHENG T, XIE W, YAO Z, et al. Online monitoring and analysis system for steel structure safety of offshore wind farm booster station based on multi-source data[C]. IET Conference Proceedings CP843, 2023., articleTitle=Online monitoring and analysis system for steel structure safety of offshore wind farm booster station based on multi-source data, refAbstract=null), Reference(id=1217836034042286583, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2022, volume=10, issue=8, pageStart=1074, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=AMAECHI C V, REDA A, BUTLER H O, journalName=Journal of Marine Science and Engineering, refType=null, unstructuredReference=AMAECHI C V, REDA A, BUTLER H O, et al. Review on fixed and floating offshore structures. Part I: types of platforms with some applications[J]. Journal of Marine Science and Engineering, 2022, 10(8): 1074., articleTitle=Review on fixed and floating offshore structures. Part I: types of platforms with some applications, refAbstract=null), Reference(id=1217836034222641660, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=1031, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=CENTENARO E, LANY M, MEYER T, journalName=null, refType=null, unstructuredReference=CENTENARO E, LANY M, MEYER T, et al. Structural health monitoring solutions for offshore platforms[C]. Offshore Mediterranean Conference and Exhibition. OMC, 2019: 1031., articleTitle=Structural health monitoring solutions for offshore platforms, refAbstract=null), Reference(id=1217836034323304962, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=89, pageEnd=108, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=PEZESHKI H, ADELI H, PAVLOU D, journalName=null, refType=null, unstructuredReference=PEZESHKI H, ADELI H, PAVLOU D, et al. State of the art in structural health monitoring of offshore and marine structures[C]. Proceedings of the Institution of Civil Engineers-Maritime Engineering. Thomas Telford Ltd., 2023: 89-108., articleTitle=State of the art in structural health monitoring of offshore and marine structures, refAbstract=null), Reference(id=1217836034444939780, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2020, volume=264, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=LIANG T, WANG S, LU C, journalName=Journal of Cleaner Production, refType=null, unstructuredReference=LIANG T, WANG S, LU C, et al. Environmental impact evaluation of an iron and steel plant in China: normalized data and direct/indirect contribution[J]. Journal of Cleaner Production, 2020, 264: 121697., articleTitle=Environmental impact evaluation of an iron and steel plant in China: normalized data and direct/indirect contribution, refAbstract=null), Reference(id=1217836034562380297, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2016, volume=45, issue=5, pageStart=739, pageEnd=756, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=DONG Y, FRANGOPOL D M, journalName=Earthquake Engineering & Structural Dynamics, refType=null, unstructuredReference=DONG Y, FRANGOPOL D M. Performance-based seismic assessment of conventional and base-isolated steel buildings including environmental impact and resilience[J]. Earthquake Engineering & Structural Dynamics, 2016, 45(5): 739-756., articleTitle=Performance-based seismic assessment of conventional and base-isolated steel buildings including environmental impact and resilience, refAbstract=null), Reference(id=1217836034663043595, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2024, volume=53, issue=12, pageStart=77, pageEnd=85, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=司广全, 赵勇, 童博, journalName=热力发电, refType=null, unstructuredReference=司广全, 赵勇, 童博, 等. 海上风电水下资产质量缺陷及检测方法[J]. 热力发电, 2024, 53(12): 77-85., articleTitle=海上风电水下资产质量缺陷及检测方法, refAbstract=null), Reference(id=1217836034772095506, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2024, volume=53, issue=12, pageStart=77, pageEnd=85, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=SI Guangquan, ZHAO Yong, TONG Bo, journalName=Thermal Power Generation, refType=null, unstructuredReference=SI Guangquan, ZHAO Yong, TONG Bo, et al. Quality defects of underwater assets in offshore wind power and the detecting methods[J]. Thermal Power Generation, 2024, 53(12): 77-85., articleTitle=Quality defects of underwater assets in offshore wind power and the detecting methods, refAbstract=null), Reference(id=1217836034839204376, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2019, volume=48, issue=7, pageStart=137, pageEnd=141, url=null, language=null, rfNumber=[8], rfOrder=8, authorNames=张宝锋, 赵勇, 韩斌, journalName=热力发电, refType=null, unstructuredReference=张宝锋, 赵勇, 韩斌. 海上升压站建造阶段质量控制[J]. 热力发电, 2019, 48(7): 137-141., articleTitle=海上升压站建造阶段质量控制, refAbstract=null), Reference(id=1217836034910507548, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2019, volume=48, issue=7, pageStart=137, pageEnd=141, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=ZHANG Baofeng, ZHAO Yong, HAN Bin, journalName=Thermal Power Generation, refType=null, unstructuredReference=ZHANG Baofeng, ZHAO Yong, HAN Bin. Quality control of offshore substation construction in construction stage[J]. Thermal Power Generation, 2019, 48(7): 137-141., articleTitle=Quality control of offshore substation construction in construction stage, refAbstract=null), Reference(id=1217836034994393633, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2019, volume=11, issue=2, pageStart=494, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=10, authorNames=LIAN J, CAI O, DONG X, journalName=Sustainability, refType=null, unstructuredReference=LIAN J, CAI O, DONG X, et al. Health monitoring and safety evaluation of the offshore wind turbine structure: a review and discussion of future development[J]. Sustainability, 2019, 11(2): 494., articleTitle=Health monitoring and safety evaluation of the offshore wind turbine structure: a review and discussion of future development, refAbstract=null), Reference(id=1217836035124417060, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2015, volume=2, issue=4/5, pageStart=3419, pageEnd=3428, url=null, language=null, rfNumber=[10], rfOrder=11, authorNames=AMBHORE N, KAMBLE D, CHINCHANIKAR S, journalName=Materials Today: Proceedings, refType=null, unstructuredReference=AMBHORE N, KAMBLE D, CHINCHANIKAR S, et al. Tool condition monitoring system: a review[J]. Materials Today: Proceedings, 2015, 2(4/5): 3419-3428., articleTitle=Tool condition monitoring system: a review, refAbstract=null), Reference(id=1217836036395291177, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2003, volume=18, issue=1, pageStart=4, pageEnd=13, url=null, language=null, rfNumber=[11], rfOrder=12, authorNames=HAN Y, SONG Y H, journalName=IEEE Transactions on Power delivery, refType=null, unstructuredReference=HAN Y, SONG Y H. Condition monitoring techniques for electrical equipment-a literature survey[J]. IEEE Transactions on Power delivery, 2003, 18(1): 4-13., articleTitle=Condition monitoring techniques for electrical equipment-a literature survey, refAbstract=null), Reference(id=1217836036487565869, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2020, volume=19, issue=null, pageStart=725, pageEnd=737, url=null, language=null, rfNumber=[12], rfOrder=13, authorNames=KHAN M A, AKHTAR K, AHMAD N, journalName=Earthquake Engineering and Engineering Vibration, refType=null, unstructuredReference=KHAN M A, AKHTAR K, AHMAD N, et al. Vibration analysis of damaged and undamaged steel structure systems: cantilever column and frame[J]. Earthquake Engineering and Engineering Vibration, 2020, 19: 725-737., articleTitle=Vibration analysis of damaged and undamaged steel structure systems: cantilever column and frame, refAbstract=null), Reference(id=1217836036575646258, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2022, volume=349, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=14, authorNames=VERSTRYNGE E, VAN STEEN C, VANDECRUYS E, journalName=Construction and Building Materials, refType=null, unstructuredReference=VERSTRYNGE E, VAN STEEN C, VANDECRUYS E, et al. Steel corrosion damage monitoring in reinforced concrete structures with the acoustic emission technique: a review[J]. Construction and Building Materials, 2022, 349: 128732., articleTitle=Steel corrosion damage monitoring in reinforced concrete structures with the acoustic emission technique: a review, refAbstract=null), Reference(id=1217836036659532344, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=15, authorNames=贾丹桐, journalName=null, refType=null, unstructuredReference=贾丹桐. 基于无监督学习的海上风电支撑结构损伤识别研究[D]. 青岛: 青岛理工大学, 2022: 1., articleTitle=基于无监督学习的海上风电支撑结构损伤识别研究, refAbstract=null), Reference(id=1217836036751807035, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=16, authorNames=JIA Dantong, journalName=null, refType=null, unstructuredReference=JIA Dantong. Study on the damage identification of offshore wind turbine support structure based on unsupervised learning[D]. Qingdao: Qingdao University of Technology, 2022: 1., articleTitle=Study on the damage identification of offshore wind turbine support structure based on unsupervised learning, refAbstract=null), Reference(id=1217836036831498815, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=增刊1, pageStart=47, pageEnd=50, url=null, language=null, rfNumber=[15], rfOrder=17, authorNames=陈韬, 杨三元, journalName=船舶工程, refType=null, unstructuredReference=陈韬, 杨三元. 海上风电基础健康监测技术[J]. 船舶工程, 2022, 44(增刊1): 47-50., articleTitle=海上风电基础健康监测技术, refAbstract=null), Reference(id=1217836036927967811, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=Suppl.1, pageStart=47, pageEnd=50, url=null, language=null, rfNumber=[15], rfOrder=18, authorNames=CHEN Tao, YANG Sanyuan, journalName=Ship Engineering, refType=null, unstructuredReference=CHEN Tao, YANG Sanyuan. Offshore wind turbine foundation health monitoring technology[J]. Ship Engineering, 2022, 44(Suppl.1): 47-50., articleTitle=Offshore wind turbine foundation health monitoring technology, refAbstract=null), Reference(id=1217836037037019721, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2024, volume=37, issue=7, pageStart=94, pageEnd=96, url=null, language=null, rfNumber=[16], rfOrder=19, authorNames=魏君, journalName=长江信息通信, refType=null, unstructuredReference=魏君. 基于无线传感器网络的机械异常振动信号采集方法[J]. 长江信息通信, 2024, 37(7): 94-96., articleTitle=基于无线传感器网络的机械异常振动信号采集方法, refAbstract=null), Reference(id=1217836037141877328, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2024, volume=37, issue=7, pageStart=94, pageEnd=96, url=null, language=null, rfNumber=[16], rfOrder=20, authorNames=WEI Jun, journalName=Changjiang Information & Communications, refType=null, unstructuredReference=WEI Jun. Mechanical abnormal vibration signal acquisition method based on wireless sensor network[J]. Changjiang Information & Communications, 2024, 37(7): 94-96., articleTitle=Mechanical abnormal vibration signal acquisition method based on wireless sensor network, refAbstract=null), Reference(id=1217836037229957718, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2022, volume=12, issue=23, pageStart=12021, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=21, authorNames=YE H, JIANG C, ZU F, journalName=Applied Sciences, refType=null, unstructuredReference=YE H, JIANG C, ZU F, et al. Design of a structural health monitoring system and performance evaluation for a jacket offshore platform in east china sea[J]. Applied Sciences, 2022, 12(23): 12021., articleTitle=Design of a structural health monitoring system and performance evaluation for a jacket offshore platform in east china sea, refAbstract=null), Reference(id=1217836037305455190, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2024, volume=301, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=22, authorNames=WANG M, INCECIK A, TIAN Z, journalName=Ocean Engineering, refType=null, unstructuredReference=WANG M, INCECIK A, TIAN Z, et al. Structural health monitoring on offshore jacket platforms using a novel ensemble deep learning model[J]. Ocean Engineering, 2024, 301: 117510., articleTitle=Structural health monitoring on offshore jacket platforms using a novel ensemble deep learning model, refAbstract=null), Reference(id=1217836037431284316, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2021, volume=154, issue=null, pageStart=249, pageEnd=261, url=null, language=null, rfNumber=[19], rfOrder=23, authorNames=BAO X, FAN T, SHI C, journalName=Process Safety and Environmental Protection, refType=null, unstructuredReference=BAO X, FAN T, SHI C, et al. Deep learning methods for damage detection of jacket-type offshore platforms[J]. Process Safety and Environmental Protection, 2021, 154: 249-261., articleTitle=Deep learning methods for damage detection of jacket-type offshore platforms, refAbstract=null), Reference(id=1217836037519364706, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2024, volume=303, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=24, authorNames=XIN S, QI Z, YANG L, journalName=Ocean Engineering, refType=null, unstructuredReference=XIN S, QI Z, YANG L, et al. Deep-learning approach based on multi-data fusion for damage recognition of marine platforms under complex loads[J]. Ocean Engineering, 2024, 303: 116604., articleTitle=Deep-learning approach based on multi-data fusion for damage recognition of marine platforms under complex loads, refAbstract=null), Reference(id=1217836037620028008, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=增刊1, pageStart=166, pageEnd=171, url=null, language=null, rfNumber=[21], rfOrder=25, authorNames=刘占领, 黄远远, journalName=船舶工程, refType=null, unstructuredReference=刘占领, 黄远远. 基于海上风电结构安全监测系统的研究[J]. 船舶工程, 2024, 46(增刊1): 166-171., articleTitle=基于海上风电结构安全监测系统的研究, refAbstract=null), Reference(id=1217836037724885612, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2024, volume=46, issue=Suppl.1, pageStart=166, pageEnd=171, url=null, language=null, rfNumber=[21], rfOrder=26, authorNames=LIU Zhanling, HUANG Yuanyuan, journalName=Ship Engineering, refType=null, unstructuredReference=LIU Zhanling, HUANG Yuanyuan. Research on safety monitoring system for offshore wind power structures[J]. Ship Engineering, 2024, 46(Suppl.1): 166-171., articleTitle=Research on safety monitoring system for offshore wind power structures, refAbstract=null), Reference(id=1217836037842326129, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2023, volume=52, issue=2, pageStart=157, pageEnd=164, url=null, language=null, rfNumber=[22], rfOrder=27, authorNames=王火平, 陈道毅, journalName=石油与天然气化工, refType=null, unstructuredReference=王火平, 陈道毅. 海上导管架平台结构健康监测技术研究及应用[J]. 石油与天然气化工, 2023, 52(2): 157-164., articleTitle=海上导管架平台结构健康监测技术研究及应用, refAbstract=null), Reference(id=1217836037938795125, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2023, volume=52, issue=2, pageStart=157, pageEnd=164, url=null, language=null, rfNumber=[22], rfOrder=28, authorNames=WANG Huoping, CHEN Daoyi, journalName=Chemical Engineering of Oil and Gas, refType=null, unstructuredReference=WANG Huoping, CHEN Daoyi. Research and application of jacket platform structure health monitoring technology in offshore[J]. Chemical Engineering of Oil and Gas, 2023, 52(2): 157-164., articleTitle=Research and application of jacket platform structure health monitoring technology in offshore, refAbstract=null), Reference(id=1217836038026875512, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=29, authorNames=刘亚森, journalName=null, refType=null, unstructuredReference=刘亚森. 基于振动信号的统计时域阻尼参数研究[D]. 哈尔滨: 哈尔滨工业大学, 2023: 1., articleTitle=基于振动信号的统计时域阻尼参数研究, refAbstract=null), Reference(id=1217836038148510331, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=30, authorNames=LIU Yasen, journalName=null, refType=null, unstructuredReference=LIU Yasen. Research on statistical time-domain damping parameters based on vibration signals[D]. Harbin: Harbin Institute of Technology, 2023: 1., articleTitle=Research on statistical time-domain damping parameters based on vibration signals, refAbstract=null), Reference(id=1217836038249173632, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2020, volume=157, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=31, authorNames=FAN G, LI J, HAO H, journalName=Measurement, refType=null, unstructuredReference=FAN G, LI J, HAO H. Vibration signal denoising for structural health monitoring by residual convolutional neural networks[J]. Measurement, 2020, 157: 107651., articleTitle=Vibration signal denoising for structural health monitoring by residual convolutional neural networks, refAbstract=null), Reference(id=1217836038362419842, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2022, volume=41, issue=2, pageStart=637, pageEnd=645, url=null, language=null, rfNumber=[25], rfOrder=32, authorNames=MIAO F, ZHAO R, journalName=Journal of Low Frequency Noise, Vibration and Active Control, refType=null, unstructuredReference=MIAO F, ZHAO R. A new method of vibration signal denoising based on improved wavelet[J]. Journal of Low Frequency Noise, Vibration and Active Control, 2022, 41(2): 637-645., articleTitle=A new method of vibration signal denoising based on improved wavelet, refAbstract=null), Reference(id=1217836038467277446, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=1989, volume=1, issue=4, pageStart=541, pageEnd=551, url=null, language=null, rfNumber=[26], rfOrder=33, authorNames=LECUN Y, BOSER B, DENKER J S, journalName=Neural Computation, refType=null, unstructuredReference=LECUN Y, BOSER B, DENKER J S, et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989, 1(4): 541-551., articleTitle=Backpropagation applied to handwritten zip code recognition, refAbstract=null), Reference(id=1217836038576329355, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=3431, pageEnd=3440, url=null, language=null, rfNumber=[27], rfOrder=34, authorNames=LONG J, SHELHAMER E, DARRELL T, journalName=null, refType=null, unstructuredReference=LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]. Proceedings of the IEEE Conference on Computer vision and Pattern Recognition, 2015: 3431-3440., articleTitle=Fully convolutional networks for semantic segmentation, refAbstract=null), Reference(id=1217836038685381265, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=770, pageEnd=778, url=null, language=null, rfNumber=[28], rfOrder=35, authorNames=HE K, ZHANG X, REN S, journalName=null, refType=null, unstructuredReference=HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778., articleTitle=Deep residual learning for image recognition, refAbstract=null), Reference(id=1217836038790238871, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2019, volume=42, issue=5, pageStart=1218, pageEnd=1227, url=null, language=null, rfNumber=[29], rfOrder=36, authorNames=GAO H, YUAN H, WANG Z, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=GAO H, YUAN H, WANG Z, et al. Pixel transposed convolutional networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 42(5): 1218-1227., articleTitle=Pixel transposed convolutional networks, refAbstract=null), Reference(id=1217836038920262298, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2021, volume=452, issue=null, pageStart=48, pageEnd=62, url=null, language=null, rfNumber=[30], rfOrder=37, authorNames=NIU Z, ZHONG G, YU H, journalName=Neurocomputing, refType=null, unstructuredReference=NIU Z, ZHONG G, YU H. A review on the attention mechanism of deep learning[J]. Neurocomputing, 2021, 452: 48-62., articleTitle=A review on the attention mechanism of deep learning, refAbstract=null), Reference(id=1217836038995759773, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2009, volume=741, issue=null, pageStart=659, pageEnd=663, url=null, language=null, rfNumber=[31], rfOrder=38, authorNames=REYNOLDS D A, journalName=Encyclopedia of Biometrics, refType=null, unstructuredReference=REYNOLDS D A. Gaussian mixture models[J]. Encyclopedia of Biometrics, 2009, 741: 659-663., articleTitle=Gaussian mixture models, refAbstract=null), Reference(id=1217836039079645856, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=1977, volume=39, issue=1, pageStart=1, pageEnd=22, url=null, language=null, rfNumber=[32], rfOrder=39, authorNames=DEMPSTER A P, LAIRD N M, RUBIN D B, journalName=Journal of the Royal Statistical Society: Series B (methodological), refType=null, unstructuredReference=DEMPSTER A P, LAIRD N M, RUBIN D B. Maximum likelihood from incomplete data via the EM algorithm[J]. Journal of the Royal Statistical Society: Series B (methodological), 1977, 39(1): 1-22., articleTitle=Maximum likelihood from incomplete data via the EM algorithm, refAbstract=null), Reference(id=1217836039197086371, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2008, volume=9, issue=11, pageStart=2579, pageEnd=2605, url=null, language=null, rfNumber=[33], rfOrder=40, authorNames=DER MAATEN L V, HINTON G E, journalName=Journal of Machine Learning Research, refType=null, unstructuredReference=DER MAATEN L V, HINTON G E. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9(11): 2579-2605., articleTitle=Visualizing data using t-SNE, refAbstract=null), Reference(id=1217836039297749670, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2001, volume=13, issue=7, pageStart=1443, pageEnd=1471, url=null, language=null, rfNumber=[34], rfOrder=41, authorNames=SCHÖLKOPF B, PLATT J C, SHAWE-TAYLOR J, journalName=Neural Computation, refType=null, unstructuredReference=SCHÖLKOPF B, PLATT J C, SHAWE-TAYLOR J, et al. Estimating the support of a high-dimensional distribution[J]. Neural Computation, 2001, 13(7): 1443-1471., articleTitle=Estimating the support of a high-dimensional distribution, refAbstract=null), Reference(id=1217836039390024360, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, doi=null, pmid=null, pmcid=null, year=2008, volume=null, issue=null, pageStart=413, pageEnd=422, url=null, language=null, rfNumber=[35], rfOrder=42, authorNames=LIU F T, TING K M, ZHOU Z H, journalName=null, refType=null, unstructuredReference=LIU F T, TING K M, ZHOU Z H. Isolation forest[C]. IEEE International Conference on Data Mining, 2008: 413-422., articleTitle=Isolation forest, refAbstract=null)], funds=[Fund(id=1217836033710936547, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, awardId=HNKJ24-HF72, language=EN, fundingSource=Science and Technology Project of China Huaneng Group Co., Ltd.(HNKJ24-HF72), fundOrder=null, country=null), Fund(id=1217836033807405544, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, awardId=HNKJ24-HF72, language=CN, fundingSource=中国华能集团有限公司总部科技项目(HNKJ24-HF72), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1217836025829838963, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, xref=1., ext=[AuthorCompanyExt(id=1217836025834033268, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025829838963, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Xi’an Thermal Power Research Institute Co., Ltd., Xi’an 710054, China), AuthorCompanyExt(id=1217836025838227573, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025829838963, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.西安热工研究院有限公司,陕西 西安 710054)]), AuthorCompany(id=1217836025922113660, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, xref=2., ext=[AuthorCompanyExt(id=1217836025930502269, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025922113660, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Huaneng Longdong Energy Co., Ltd., Qingyang 745100, China), AuthorCompanyExt(id=1217836025934696574, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, companyId=1217836025922113660, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.华能陇东能源有限责任公司,甘肃 庆阳 745100)])], figs=[ArticleFig(id=1217836030531653973, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=EN, label=Fig.1, caption=Schematic diagram of the deep convolutional memory-based auto-encoder, figureFileSmall=V+BTU5OMWfIfbyp9q2tJeA==, figureFileBig=0AXGtrf9Ps/1LsRbqZjLOA==, tableContent=null), ArticleFig(id=1217836030611345756, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=CN, label=图1, caption=深度卷积记忆自编码器示意, figureFileSmall=V+BTU5OMWfIfbyp9q2tJeA==, figureFileBig=0AXGtrf9Ps/1LsRbqZjLOA==, tableContent=null), ArticleFig(id=1217836032049992046, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=EN, label=Fig.2, caption=The accelerometer installation, figureFileSmall=F2X0yIVYem+JyCgeueCuDg==, figureFileBig=a9es5OatdsrEAoix2SAp5Q==, tableContent=null), ArticleFig(id=1217836032159043957, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=CN, label=图2, caption=加速度计安装, figureFileSmall=F2X0yIVYem+JyCgeueCuDg==, figureFileBig=a9es5OatdsrEAoix2SAp5Q==, tableContent=null), ArticleFig(id=1217836032293261693, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=EN, label=Fig.3, caption=The model training residuals, figureFileSmall=zaJafagdAKRS6/UJHeWAQw==, figureFileBig=l7RckF8ldtNSMpDabX9LRQ==, tableContent=null), ArticleFig(id=1217836032381342084, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=CN, label=图3, caption=模型训练残差, figureFileSmall=zaJafagdAKRS6/UJHeWAQw==, figureFileBig=l7RckF8ldtNSMpDabX9LRQ==, tableContent=null), ArticleFig(id=1217836032477811082, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=EN, label=Fig.4, caption=Allocation scoring visualization, figureFileSmall=o5QQqK1mKazOwjmN0B2gow==, figureFileBig=VTaGA91minleHfEwhiEpPA==, tableContent=null), ArticleFig(id=1217836032586862996, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=CN, label=图4, caption=从属分数, figureFileSmall=o5QQqK1mKazOwjmN0B2gow==, figureFileBig=VTaGA91minleHfEwhiEpPA==, tableContent=null), ArticleFig(id=1217836032687526302, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=EN, label=Fig.5, caption=GMM probability modeling visualization, figureFileSmall=Gi0E8q1Uz49xQZ9D7iTo2g==, figureFileBig=v+awzm7zwyeZobTZk/gvNw==, tableContent=null), ArticleFig(id=1217836032788189606, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=CN, label=图5, caption=GMM概率建模可视化, figureFileSmall=Gi0E8q1Uz49xQZ9D7iTo2g==, figureFileBig=v+awzm7zwyeZobTZk/gvNw==, tableContent=null), ArticleFig(id=1217836032905630126, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=EN, label=Fig.6, caption=Health assessment of degradation process of the booster station platform, figureFileSmall=r7YFgTU9ypEhouu4HXcbwA==, figureFileBig=sMtca+Kx3mkvv0t3nAw0sQ==, tableContent=null), ArticleFig(id=1217836033002099128, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=CN, label=图6, caption=升压站平台劣化过程健康评估, figureFileSmall=r7YFgTU9ypEhouu4HXcbwA==, figureFileBig=sMtca+Kx3mkvv0t3nAw0sQ==, tableContent=null), ArticleFig(id=1217836033073402302, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=EN, label=Tab.1, caption=

Encoder structure detail

, figureFileSmall=null, figureFileBig=null, tableContent=
层数卷积核大小步长输入通道数输出通道数输出特征图大小跳层连接
13×3+5×5+7×741616128×1281连接3
23×3+5×5+7×74163232×322连接4
33×3+5×52326416×163连接5
43×3+5×52641288×8
53×321282564×4
64×422565121×1
), ArticleFig(id=1217836033178259909, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=CN, label=表1, caption=

编码器结构表

, figureFileSmall=null, figureFileBig=null, tableContent=
层数卷积核大小步长输入通道数输出通道数输出特征图大小跳层连接
13×3+5×5+7×741616128×1281连接3
23×3+5×5+7×74163232×322连接4
33×3+5×52326416×163连接5
43×3+5×52641288×8
53×321282564×4
64×422565121×1
), ArticleFig(id=1217836033278923212, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=EN, label=Tab.2, caption=

Decoder structure detail

, figureFileSmall=null, figureFileBig=null, tableContent=
层数卷积核大小步长输入通道数输出通道数输出特征图大小跳层连接
14×425122561×11连接3
23×322561284×42连接4
33×3+5×52128648×83连接5
43×3+5×52643216×16
53×3+5×5+7×74321632×32
63×3+5×5+7×741616128×128
), ArticleFig(id=1217836033371197905, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=CN, label=表2, caption=

解码器结构表

, figureFileSmall=null, figureFileBig=null, tableContent=
层数卷积核大小步长输入通道数输出通道数输出特征图大小跳层连接
14×425122561×11连接3
23×322561284×42连接4
33×3+5×52128648×83连接5
43×3+5×52643216×16
53×3+5×5+7×74321632×32
63×3+5×5+7×741616128×128
), ArticleFig(id=1217836033480249812, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=EN, label=Tab.3, caption=

Performance comparison between and among different anomaly detection algorithms

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称召回率/%精确率/%准确率/%
OC-SVM66.5463.8777.16
IF59.8862.4262.98
LSTM+CNN86.5488.7385.16
FusionCNN93.4795.6896.32
本文模型99.7298.6498.93
), ArticleFig(id=1217836033580913116, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836023514583047, language=CN, label=表3, caption=

不同异常检测算法性能对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型名称召回率/%精确率/%准确率/%
OC-SVM66.5463.8777.16
IF59.8862.4262.98
LSTM+CNN86.5488.7385.16
FusionCNN93.4795.6896.32
本文模型99.7298.6498.93
)], attaches=null, journal=Journal(id=1210938006006558725, delFlag=0, nameCn=热力发电, nameEn=Thermal Power Generation, nameHistory1=null, nameHistory2=null, issn=1002-3364, eissn=null, cn=61-1111/TM, 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=YWgAUXbKXZzTw3c+kJbAIA==, journalPrice=null, startedYear=null, abbrevIsoEn=Thermal Power Generation, journalRemark=null, publicationField=null, createdTime=1766639718774, updatedTime=1766640759031, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=T, firstLetterEn=T, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=YWgAUXbKXZzTw3c+kJbAIA==, picEn=jfJjUlYAGfUZwuOMQZ6AHQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1210942369256575009, language=CN, name=热力发电, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1766640759052, updatedTime=1766640759052, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=1, submissionEditorUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=3, submissionReviewUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1210942369315295266, language=EN, name=Thermal Power Generation, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1766640759066, updatedTime=1766640759066, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=1, submissionEditorUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=3, submissionReviewUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1210938733613449225, websiteList=[Website(id=1210941118787744741, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1210938733613449225, 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/rlfd/CN, language=CN, createTime=1766640460918, createBy=18614031015, updateTime=1766640511525, updateBy=18614031015, name=热力发电-中文, tplId=1146099689490845704, title=热力发电, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1210944690380214659, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=articleTextType, value=kx, createTime=1766641312451, updateTime=1766641312451, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690359243136, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=banner, value=null, createTime=1766641312446, updateTime=1766641312446, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690401186182, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=grayFlag, value=0, createTime=1766641312456, updateTime=1766641312456, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690346660223, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=logo, value=https://castjournals.cast.org.cn/joweb/rlfd/CN/file/pic?fileId=ToFA0Lu4b/CNocENDvNjHA==, createTime=1766641312443, updateTime=1766641312443, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690409574792, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=minRunFlag, value=0, createTime=1766641312458, updateTime=1766641312458, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690371826050, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/rlfd/CN/file/pic, createTime=1766641312449, updateTime=1766641312449, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690405380487, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=silenceFlag, value=0, createTime=1766641312457, updateTime=1766641312457, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690367631745, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1766641312448, updateTime=1766641312448, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690388603268, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=themeColor, value=null, createTime=1766641312453, updateTime=1766641312453, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690392797573, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=themeStyle, value=null, createTime=1766641312454, updateTime=1766641312454, creator=18614031015, updator=18614031015)]), Website(id=1210941118926156777, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1210938733613449225, 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/rlfd/EN, language=EN, createTime=1766640460950, createBy=18614031015, updateTime=1766640598724, updateBy=18614031015, name=热力发电-英文, tplId=1146101810881728533, title=Thermal Power Generation, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1210944709317489283, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=articleTextType, value=kx, createTime=1766641316966, updateTime=1766641316966, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709296517760, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=banner, value=null, createTime=1766641316961, updateTime=1766641316961, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709334266502, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=grayFlag, value=0, createTime=1766641316970, updateTime=1766641316970, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709288129151, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=logo, value=https://castjournals.cast.org.cn/joweb/rlfd/CN/file/pic?fileId=ToFA0Lu4b/CNocENDvNjHA==, createTime=1766641316959, updateTime=1766641316959, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709346849416, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=minRunFlag, value=0, createTime=1766641316973, updateTime=1766641316973, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709309100674, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/rlfd/EN/file/pic, createTime=1766641316964, updateTime=1766641316964, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709338460807, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=silenceFlag, value=0, createTime=1766641316971, updateTime=1766641316971, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709300712065, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1766641316962, updateTime=1766641316962, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709321683588, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=themeColor, value=null, createTime=1766641316967, updateTime=1766641316967, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709330072197, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=themeStyle, value=null, createTime=1766641316969, updateTime=1766641316969, creator=18614031015, updator=18614031015)])], journalTitle=热力发电, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=Thermal Power Generation, journalPhotoCn=YWgAUXbKXZzTw3c+kJbAIA==, journalPhotoEn=jfJjUlYAGfUZwuOMQZ6AHQ==, journalFirstLetter=T, 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/rlfd/CN/10.19666/j.rlfd.202501046, detailUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/10.19666/j.rlfd.202501046, pdfUrlCn=https://castjournals.cast.org.cn/joweb/rlfd/CN/PDF/10.19666/j.rlfd.202501046, pdfUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/PDF/10.19666/j.rlfd.202501046, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于记忆单元自编码的海上升压站平台健康监测方法
收藏切换
PDF下载
张瑞刚 1 , 王大鹏 2 , 雷航 1 , 王嘉良 1 , 郭楠 2 , 任建强 2
热力发电 | 新能源发电技术 2025,54(11): 58-67
收起
收藏切换
热力发电 | 新能源发电技术 2025, 54(11): 58-67
基于记忆单元自编码的海上升压站平台健康监测方法
全屏
张瑞刚1 , 王大鹏2, 雷航1, 王嘉良1 , 郭楠2, 任建强2
作者信息
  • 1.西安热工研究院有限公司,陕西 西安 710054
  • 2.华能陇东能源有限责任公司,甘肃 庆阳 745100
  • 张瑞刚(1982),男,硕士,正高级工程师,主要研究方向为新能源发电设备选型、风力发电安全监测技术,

通讯作者:

王嘉良(1997),男,硕士,工程师,主要研究方向为海上风电安全监测技术,
Healthy state monitoring method for offshore booster station platforms based on memory unit autoencoder method
Ruigang ZHANG1 , Dapeng WANG2, Hang LEI1, Jialiang WANG1 , Nan GUO2, Jianqiang REN2
Affiliations
  • 1.Xi’an Thermal Power Research Institute Co., Ltd., Xi’an 710054, China
  • 2.Huaneng Longdong Energy Co., Ltd., Qingyang 745100, China
出版时间: 2025-11-25 doi: 10.19666/j.rlfd.202501046
文章导航
收藏切换

提出一种新型海上升压站平台健康监测方法,以增强其在复杂工况下的损伤检测能力。采用基于记忆单元自编码器的深度学习框架,通过对海上升压站的高频振动数据进行降噪和角域重采样来放大故障相关特征。模型利用深度卷积神经网络学习历史数据模式,构建隐藏状态记忆库,并实现样本编码特征与记忆库的稀疏匹配。最后,采用高斯混合概率模型对生成的从属分数进行建模,以评估升压站的健康状态。以江苏如东县的海上升压站为案例进行验证,实现了98%以上的异常召回率及准确率,优于其他对比算法。

海上升压站平台  /  健康监测  /  角域重采样  /  记忆单元  /  深度自编码器

A novel healthy state monitoring method for offshore booster station platforms is proposed to enhance the damage detection capabilities under complex operating conditions. Using a deep learning framework based on memory unit autoencoders, the method magnifies fault-relevant features via denoising and angular domain resampling high-frequency vibration data from offshore boosting stations. The model employs a deep convolutional neural network to learn historical data patterns, constructs a hidden state memory bank, and achieves sparse matching between sample encoded features and the memory bank. Finally, a Gaussian mixture probability model is employed to model the generated membership scores to assess the health status of the booster station. A case study of the offshore booster station in Rudong, Jiangsu, validates the approach, achieving an anomaly recall rate and accuracy of over 98%, outperforming other comparison algorithms.

offshore booster station platform  /  health monitoring  /  angular domain resampling  /  memory unit  /  deep autoencoder
张瑞刚, 王大鹏, 雷航, 王嘉良, 郭楠, 任建强. 基于记忆单元自编码的海上升压站平台健康监测方法. 热力发电, 2025 , 54 (11) : 58 -67 . DOI: 10.19666/j.rlfd.202501046
Ruigang ZHANG, Dapeng WANG, Hang LEI, Jialiang WANG, Nan GUO, Jianqiang REN. Healthy state monitoring method for offshore booster station platforms based on memory unit autoencoder method[J]. Thermal Power Generation, 2025 , 54 (11) : 58 -67 . DOI: 10.19666/j.rlfd.202501046
海上升压站平台在海上风电等清洁能源的开发中具有关键作用[1]。此类平台一方面承担能量转换与输送的核心任务,另一方面也是运行维护人员的重要作业场所。由于海洋环境复杂多变,平台钢结构易遭受海水、高湿、高盐雾等多重因素的腐蚀作用,进而使整体结构的安全性与可靠性面临严峻考验[2-3]。钢结构一旦发生破损,不仅会造成巨大的经济损失和人员安全风险,也可能引发严重的环境污染问题,对企业和社会造成负面影响[4-5]。为保障海上能源产业的持续稳定运行,业界对海上升压站平台的实时监测与安全评估技术给予了高度重视,并通过持续优化传感器、检测仪器和计算机系统软硬件设备等,实现对海上升压站平台运行状态的高效感知与评价[6-8]
在实际应用中,海上升压站平台的健康状况主要借助状态监测系统(condition monitoring system,CMS)进行监控[9-11]。平台钢结构通常布设加速度传感器与应变传感器,这些高频测点数据可实时捕获结构的动力学特征,以识别影响安全性与稳定性的腐蚀损伤以及疲劳累积效应[12-15]。随着海量传感数据的获取与深度学习技术的蓬勃发展,基于CMS的海上升压站平台健康状态检测与评估精度不断提升[16]。Ye等人[17]构建了导管架平台完整的结构健康监测体系架构,并基于静态测量与应变模态相结合的方法实现了安全预警与整体性能评估。Wang等人[18]提出了一种融合循环神经网络(CNN)、双向长短时(LSTM)神经网络与注意力机制的新型深度学习方法,用于精准识别海上导管架平台的结构损伤模式。Bao等人[19]通过深度学习方法,结合随机衰减技术,解决了在噪声环境中有效检测外海结构损伤的问题。文献[20]提出了一种基于深度学习和多数据融合技术的方法,旨在解决复杂载荷下对海洋导管架平台结构损伤的识别问题,有效提高了损伤检测的准确性。
然而,海上升压站平台所处工况依然异常复杂,不同气候、海况及载荷条件下的振动与加速度响应差异显著,传统基于机理的统一建模方法普遍面临精度不足的问题[21-22]。此外,原始高频测点信号往往呈现低信噪比、非平稳特征,如何从复杂多变的噪声环境中提取并重构结构特征仍是业界共同关注的难题[23-25]。因此,有必要针对海上升压站平台CMS数据特征开展进一步的理论与方法创新。
基于以上背景,本文提出一种基于记忆单元自编码器的海上升压站平台健康监测方法。首先,对平台多测点高频振动数据进行角域重采样和初步降噪处理,获取低噪高特征的阶次图谱;随后,将阶次图谱输入记忆自编码器(memory auto-encoder,DCMem-AE)进行训练,通过深度卷积神经网络与隐藏记忆库相结合的方式,对历史数据模式进行刻画,并利用稀疏匹配机制实现对复杂工况的精确建模;最后,基于高斯混合概率模型对编码层输出的隐藏状态从属分数进行统计分析,并通过设定置信区间阈值来判定海上升压站平台的健康状态。本文以江苏省如东县某海上升压站平台为案例开展验证试验,结果表明所提方法能够有效应对高频振动信号特征提取与平台健康状况评估中的挑战,为海上升压站平台的安全运行与维护提供可行的技术支撑。
由于海上环境多变,海上升压站平台的频率响应会随着海浪、海风的不断变化,其受外部环境频率的影响极大,而这种影响会干扰对升压站损伤相关频率响应的识别。为了排除环境带来主频变化的影响,本文提出一种针对海上升压站平台的CMS中收集的原始振动信号的角域重采样技术。这种处理技术确保经过处理信号中相邻数据点在角域上是等间隔的,从而排除了信号主频变化的干扰,使得信号更加凸显与结构健康状态相关的频域特征。
假设原始振动信号定义为x(t),其中t为时间。由于原始信号中高频噪声较为明显,为了有效降噪并使得信号转化为平稳信号,采用差分滤波的方法,消除原始信号中的趋势和常数项,并抑制信号的突然变化,初步降低高频噪声干扰,其表达式为:
xdiff(t)=x(t)λ×x(t1)
式中:λ为差分系数。
然后,采取一阶低通滤波进一步消除高频噪声的影响,去噪后的信号xde(t)可表示为:
xde(t)=γ×xde(t1)+(1γ)×xdiff(t)
式中:γ为加权系数。
在降噪处理完成后,本文采用以下策略实现对降噪信号在角域上的均匀采样:首先,依据降噪信号的上下包络线计算出信号的参考曲线;随后通过希尔伯特变换求解参考曲线的解析信号;进一步地,根据解析信号的相位,计算出每个采样点对应的瞬时频率;最后,依据这些瞬时频率计算累计相位,并在角域上进行均匀重采样,此过程借助插值技术来获取角域重采样后的预处理信号。
参考信号的获取首先要找到降噪后信号xde(t)的所有局部极大值和局部极小值,将它们分别表示为Xmax=xmaxti, i=1, …, NmaxXmin=xmintj, j=1, …, Nmin,其中titj分别表示局部极大值和局部极小值所对应的时间点位置,NmaxNmin分别代表局部极大值和极小值的个数。
进一步将上下包络线分别用局部极大值和极小值的三次样条插值曲线表示为:
{xupper(t)=cubicspline(Xmax)xlower(t)=cubicspline(Xmin)
式中:上包络线xupper(t)使用局部极大值点进行拟合;下包络线xlower(t)使用局部极小值点进行拟合。
最后,将拟合后的上下包络线的均值曲线,作为参考信号曲线,其表达式为:
xenv(t)=xupper(t)+xlower(t)2
计算解析信号时,首先使用希尔伯特变换来求解参考信号曲线的复部信号,其表达式为:
x^env(t)=Hilbert[xenv(t)]=1πxenv(τ)tτ dτ
参考信号的复数信号计算公式为:
xenv(t)=xenv(t)+jx^env(t)
最终,瞬时频率finst(t)的计算公式为:
finst(t)=12πdϕ(t)dt
式中:ϕ(t)为xenv(t)的幅角。
根据瞬时频率对降噪后的信号xde(t)进行重采样,将原本时域上的均匀采样信号转换为角域上的均匀采样信号。假设θ(t)为累积相位,则其计算方法可表示为:
θ(t)=2π0tfinst(t)dτ
然后,通过线性插值方法,可从原始振动信号x(t)中获得在角域上均匀采样的信号x*(θ):
x(θ)=x(t(θ))
进一步对角域信号进行短时傅里叶变换,可以得到去除主频变换干扰以及外部噪声的角域重采样后的阶次图谱,可表示为:
Sin=STFT(x(θ))
式中:Sin表示处理后的降噪阶次图谱,该参数将在下一节中作为深度卷积记忆自编码器的模型输入参数。
本文构建了一个深度卷积记忆自编码器(deep convolutional memory-based auto-encoder,DCMem-AE)模型。该模型采用自编码结构,将海上升压站平台的多测点振动数据的阶次图谱作为输入,由编码器对其进行统一编码,并生成隐藏特征。随后,解码器可以利用这些隐藏特征还原出原始输入的阶次图谱。解码器能够结合训练残差解码出重构图谱和输入图谱之间的平均平方误差。
在DCMem-AE模型中,自编码器设计为一种端到端的深度神经网络,通过全卷积神经网络[26-27]构建编码器,旨在将原始阶次图谱转化为高通道低像素图谱。该编码过程逐层提取特征,特征图的尺寸呈现“沙漏式”形状,这也表明随着层级的加深,特征图的长宽逐渐缩小,而通道数则适度增加,从而在局部与整体之间实现有效的信息提取与分散。
为了增强特征提取的能力,编码器中引入了“跳层”连接的残差结构。这一设计不仅融合了浅层的局部特征与深层的全局特征,还有效缓解了梯度消失的问题[28],促使梯度反向传播顺畅。解码器部分与编码器结构对称,采用全卷积神经网络展开,负责将隐藏特征逐层还原为原始的阶次图谱。该过程需要将高通道、低尺寸的隐藏特征转换为低通道、大尺寸的阶次图谱,因此解码器中采用了3×3卷积核、零填充转置卷积[29]方式,以确保信息的有效重构。这样的设计有效提高了模型对特征的表达与恢复能力,进而提升了对海上升压站平台健康状态的监测效率。
与传统自编码结构不同之处在于上文提到的位于编码器和解码器之间的“记忆单元”。记忆单元的任务是将编码器得到的输入激活特征与记忆单元中存储的所有记忆条目进行比较,并为每一个条目进行从属关系打分,直到根据分数构建出最终的隐藏特征。DCMem-AE模型假设每一个阶次图谱都可以用一个高通道的隐藏特征hhs有效表征,并且其可以被一个可学习的记忆库MNs×hs稀疏线性表示,其中Ns是记忆库的大小,并且记忆库中的单条记忆特征和编码器编码出的隐藏特征共享相同的特征数hs
通过将编码器输出的激活特征h与记忆库M中的所有记忆条目进行注意力相似度[30]计算,得到从属分数向量α,并通过Softmax函数对其进行归一化,以保证所有记忆条目的权重之和为1。最终,样本的编码特征zα和记忆库的每个记忆条目线性加权得到。具体的计算公式为:
αi=miTtanh(Whh+Wmmi)
αi=eαjj=1Nseαj
z=i=1Nsαimi
式中:mihs, i=1, 2, …, Ns为第i个记忆条目;WhWmhs×hs分别为计算注意力相似度时分配给隐藏特征h和每个记忆条目mi的待训练参数,αi为从属分数向量中第i个值。
DCMem-AE模型旨在实现每个样本隐藏特征在记忆库中从属关系的稀疏化表示。这是因为记忆库涵盖了所有可能的历史运行状态,而每个样本所代表的运行状态通常仅对应于全部运行状态中的一个或少数几个的叠加。因此,DCMem-AE模型引入信息熵作为衡量从属关系向量α稀疏性的标准。当信息熵较大时,说明激活特征h对记忆库中每个条目的从属关系较为平均;相反,信息熵较小时,表明h对记忆库中特定条目的响应较为剧烈,而与其他条目不产生联系。综上,DCMem-AE模型期望信息熵具有极小值,从而使得从属关系评分具有稀疏性。信息熵的计算公式为:
Lentrpy=i=1Nsαilnαi
综合重构误差和记忆单元中信息熵,最终神经网络的训练残差可表示为:
Ltotal=xx^22i=1Nsαilnαi
式中:x为原始输入的阶次图谱;x^为DCMem-AE模型输出的重构图谱。
最终,本文采用梯度下降的方式对编码器、解码器以及记忆库中所有记忆条目进行参数学习。整体的模型结构如图1所示,详细的编码器结构表和解码器参数分别如表1表2所示。由图1表1表2可见,本文参数的配置规律为:随着编码器的层数加深,卷积核大小逐渐缩小,步长减小,输出通道数和特征图大小分别呈现指数增长和减小趋势。这样的参数配置能够实现从局部到整体特征的逐层提取与抽象,促进高效的信息传递与特征融合,符合前文所述“沙漏式”结构,使得特征图在逐层处理过程中逐渐缩小,从而集中高频特征,增强模型捕捉细微差异的能力。同时,引入跳层连接的残差结构不仅有助于缓解梯度消失问题,还增强了浅层与深层特征的融合,为后续的解码过程打下了坚实的基础。
解码器的结构设计则通过与编码器对称的方式,结合转置卷积,将高通道、低尺寸的隐藏特征有效还原为低通道、大尺寸的原始图谱,这一过程确保了信息的完整保留与重构质量。因此,这些参数的选择充分优化了模型的表达能力与学习效率。
在DCMem-AE模型的自编码编码器负责将阶次图谱转换为激活特征向量,并将此向量与记忆库中的记忆条目逐一对比,以计算出每个条目对特征向量的评分。故而在自编码训练完成后,可认为每个阶次图谱的隐藏特征可以使用记忆库中的记忆条目稀疏地表示。这种表示不是随机的,而是存在一定客观规律。当海上升压站平台的结构处于稳定的健康状态时,其振动模式在相似的外部条件下,虽然不是完全一致,但也具有一定程度上的一致性。例如,在南北风向5 m/s风速的工况下,阶次图谱应表现出相似的特征,而在东西风向7 m/s风速的工况下,阶次图谱应该表现出另外的特征,这样的表征方式也会同样体现在稀疏从属分数向量α上。
因此,在DCMem-AE模型训练完成后,对所有历史数据生成阶次图谱,并输入DCMem-AE的编码器中,获取隐藏特征在记忆单元中的稀疏从属分数向量α。然后采用概率建模的方法,对所有运行情况进行统计分析,旨在揭示海上升压站平台在健康状态下,面对不同外部环境时其振动数据的特征分布规律。
本节采用高斯混合模型(Gaussian mixture model,GMM)[31]α的分布形式进行建模。GMM模型具有聚类特性,能够使得符合该分布的样本以一定的概率分布在多个高斯分布的中心点周围。这一特性与研究对不同外部环境进行细致描绘的需求相吻合。假设一共选取K个高斯核,πk是第k个高斯分布的混合权重,μk和Σk分别是第k个高斯分布的均值和协方差矩阵,则GMM概率模型可以表示为:
p(x)=k=1KπkN(x|μk,Σk)
对于其中待学习的参数πkμk和Σk,可通过期望最大化算法(expectation maximization,EM)[32]对其进行求解。首先初始化参数πk0,μk0Σk0,而后通过文献[32]中E步骤和M步骤的不断迭代,对参数进行优化,具体计算公式如下。
1)在第j次迭代的E步骤中,计算每个从属分数αi属于每个混合成分的后验概率γ(j)(zik),计算公式为:
γ(j)(zik)=πk(j1)N(αi|μk(j1),Σk(j1))l=1Kπl(j1)N(αi|μl(j1),Σl(j1))
2)在第j次迭代的M步骤中,使用从E步骤得到的后验概率γ(j)(zik)来更新参数πkμk和Σk。更新公式为:
πk(j)=1Ni=1Nγ(j)(zik)
μk(j)=i=1Nγ(j)(zik)αii=1Nγ(j)(zik)
Σk(j)=i=1Nγ(j)(zik)(αiμk(j))(αiμk(j))Ti=1Nγ(j)(zik)
3)重复E步骤和M步骤,直到参数的变化极小时(在实际操作中,本文将阈值设定为10–4),停止对GMM参数的更新。
在求取GMM模型中的参数后,对历史数据进行遍历,计算每个振动数据样本的阶次图谱从属分数向量α的概率密度,计算训练集中所有健康样本α的概率密度95分位数作为健康状态置信度阈值。最终本文根据以上阈值构建异常检出策略,当实时数据样本的概率密度低于此阈值时,检出策略将其视为异常;当概率密度大于此阈值时,检出策略认为所监测实时样本处于正常状态。
本文选取江苏省如东县某个海上风电场海上升压站作为案例,开展了海上升压站的健康评估工作,该升压站为一座110 kV海上升压站,离岸距离约25 km。下面将详细介绍本案例中传感器的部署方法及数据清洗、模型训练、案例分析等重要过程。
本案例中采用的传感器是振动加速度计,加速度计的基座直接焊接在海上升压站平台的主立柱上,并确保其测量主轴对准主峰方向,以便获取到准确的振动信号。图2展示了海上升压站平台加速度计的安装情况,在海上升压站平台顶部及二层平台的4个主立柱上各安装1台加速度计,共计8台加速度计,16个测点,这样的布局设计能够使所有测点数据综合反映海上钢结构平台的主要振动状态信息。
该案例的数据采集工作自2022年开始,持续到2024年,期间收集了加速度振动监测数据,采集频率为3 000 Hz,每次采集时间为15 s,每天的24个整点时间进行定时采集。在数据预处理阶段,首先对历史加速度振动数据进行清洗,包括消除超出加速度计测量范围的异常值和插补由设备故障、外部干扰、通信问题导致的数据缺失,鉴于加速度数值呈现出病态分布的特性,对加速度进行了对数变换处理,通过对数变换可使数据分布较为平缓并有助于去除高频噪声。
由于海洋环境的严苛性,2023年6月19日巡检员在巡检过程中发现升压站东南角第2层钢结构存在小部分腐蚀,2023年7月3日进行了紧急维护。2023年2月26日,巡检员在海上巡检时,发现海上升压站平台东南角外侧,出现严重腐蚀,腐蚀问题在2024年3月7日进行了紧急修复。
在使用数据进行模型训练之前,首先要对所有历史数据进行数据划分。将2022年6月至2023年5月共1年的收集数据用作训练集,此期间在巡检过程中未发现存在异常现象,因此这段时期的数据能够较好地代表海上平台的结构健康状态。训练集样本数为5 368。
测试数据集包括2023年6月直至2024年3月修复后的数据。这部分数据既包括了升压站钢结构腐蚀初期的数据,随着时间的深入,腐蚀程度缓慢加深,并最终在2024年3月进行修复后,腐蚀现象彻底消失,这一时期的数据涵盖了升压站平台健康状态从初步良好直至恶劣的全过程。测试集数据样本数为4 329。因此本文期望在升压站平台的健康劣化期间,使用本文提出的模型与策略呈现这种劣化过程,并在彻底劣化之前根据本文策略做出预警。
本节对模型训练的结果进行深入讨论。由于训练DCMem-AE模型时使用了两部分残差,分别是AE重构残差和信息熵残差,故而在案例分析中,需对2种残差的优化情况分别进行分析。图3为模型训练残差,图3a)展示了训练过程中的重构误差曲线,图3b)展示了训练过程中的信息熵残差曲线。由图3可见,2类残差在训练过程中的变化趋势是相同的,但是重构残差的下降速度要比信息熵残差的下降速度快。这也从侧面说明了在深度神经网络中,模型对于数据的表征能力是极为强大的,在隐藏特征不确定的情况下,解码器依旧可以较好地完成重构任务。这也进一步说明了引入信息熵残差的必要性:如果不对隐藏变量的行为模式加以约束,模型并不能保证获得质量足够好的隐藏特征。
为了进一步验证信息熵残差在本模型中起到的作用,分别选取海上风速为15、10、8、5、3 m/s这几种环境下的振动数据样本,将其对应的阶次图谱输入训练好的DCMem-AE模型中,从而获得其对应于记忆单元记忆库中每个条目的从属分数,图4为模型从属分数。图4a)为可视化后的不同外部环境热力图。从图4a)中可以清晰看出,这5类不同风速条件下的振动数据样本,分别在不同的记忆条目上有明显的响应,并且仅有少数位置存在显著响应,满足DCMem-AE模型中隐藏特征可以被记忆库稀疏表示的假设,这从结果层面印证本文所提出记忆单元的作用。同时,图4b)表示的风速为5 m/s的5个不同样本对应于记忆库中每个条目的从属分数,虽然不完全一致,但不难发现,其在记忆条目中响应具有极高的相似性,这也从侧面证明了记忆条目的鲁棒性和有效性,可以代表在不同外部环境下海上升压站平台的运行模式。
在DCMem-AE模型训练完成后,根据本文提出的技术路线,需对全部训练样本的从属分数进行概率建模。在本案例中,对高斯混合分布建模的高斯核个数K进行了最优参数筛选。分别使用K=4,8,,28对从属分数进行概率建模,并对每种情况下每个高斯核的权重πk进行统计。理想的高斯核个数应该满足每个高斯核的权重不应过小(至少维持在2个数量级之内),这是因为过小的高斯核权重表明这部分数据点属于噪声部分,属于无效建模,且在高斯核数量逐渐增加的过程中,高斯核权重也随之变化。当本案例中K增加到20时,高斯核权重开始出现过小值,故而最终采用K=20。
同时,为了更好地对本文建模的高斯分布可视化,本案例采用了t-分布随机近邻嵌入(T-distributed stochastic neighbor embedding,t-SNE)[33]对从属分数降维为平面二维数据,而后根据拟合后的高斯混合分布标明每一个数据点的对数概率,结果如图5所示。图5a)显示了所有样本在进行了GMM建模后,每一个隐藏特征对应的对数概率密度,图5b)显示了每一个数据点分属于不同高斯类别的情况。
图5a)中可以看出,相似状态的从属分数向量被分配到集中的区域,从视觉效果上呈现聚类状态。进一步来说,多数不同的GMM聚类类别具有明显的边界,这也侧面说明了海上升压站存在多种明显可分的工作状态,进而验证了本文所提出方法的有效性,即实验结果符合DCMem-AE模型对隐藏特征和记忆库条目之间稀疏匹配关系的假设。
同理,图5b)中可以看出样本概率密度和样本所处位置呈现紧密关联。当样本处于明显可分的工作状态时,样本的概率密度较大,主要体现在11、12、13、15、16、17、18、19等类别的中心区域。这是符合预期的,因为处于充分可识别的状态时,样本的可信程度较高,故而样本的概率密度较大。同时,可以观察到聚类边缘的样本和处于混叠状态的样本的概率密度较低,而这些样本在实际中相比于处于稳定、可识别状态的样本更倾向于故障或异常。
最后,本案例基于测试集对劣化过程中的升压站数据进行健康度评估。从2023年6月1日至2024年5月31日每天抽取1个样本,DCMem-AE模型获取的从属分数在GMM模型中的对数概率密度值,画出概率密度值随着时间变化的曲线(图6)。
图6中可以看出,升压站平台在2023年6月出现过一次健康指标的明显下降,但是由于当月运维人员对其进行了紧急处理,故而状态迅速恢复了正常。2023年12月初,升压站平台再次出现显著的健康劣化,在2023年12月24日时,健康指标首次降到了阈值之下。从图6中同样可以看出,虽然在2024年1月中旬到2月中旬,其健康状态有所回升,但是2月13日之后,本文所提出的健康评估策略处于持续报出异常状态。同时,查看了2024年1月中旬到2月中旬的风速情况,当时的风速较小,这可能是健康度回升的主要原因。而在2024年2月18日之后,升压站平台的健康程度迅速劣化,直至2024年3月7日运维人员对升压站平台进行整修。
综上所述,本文所提出的基于记忆单元的自编码器和后续健康指标制定策略综合评估效果良好,在升压站平台健康受损期间展现了较强的异常捕获能力,能够给出持续的异常报警。
为了综合验证本文提出基于记忆单元自编码的异常检测框架的优越性,使用其他异常检测模型与本文框架模型进行对比。在对比模型方面,选取以下4种成熟机器学习或海上升压站异常检测算法:单类支持向量机[34](one-class support vector machine,OC-SVM)、孤立森林算法[35](isolation forest,IF)、LSTM+CNN[19]、FusionCNN[20]
所有方法皆采用2022年6月至2023年4月共11个月的数据用作训练集进行训练,使用2023年5月以及确认故障的2024年2月13日至3月8日的数据进行测试。模型的输入同样采用与本模型相同的降噪时频图特征。
本文分别从精确率(precision)、召回率(recall)以及准确率(accuracy)3类指标进行比较,不同异常检测算法性能对比见表3
通过表3对比可以发现,本文提出的模型框架拥有相对最优的异常检出指标。
本文开发了一种基于记忆单元自编码器的海上升压站平台健康监测方法,通过对高频振动数据的有效处理和记忆学习,显著提高了复杂工况下海上升压站平台健康状况的诊断精度。通过江苏如东县海上升压站的案例分析,验证了该方法在实际应用中的有效性和可靠性,其监测精确率在98%以上,为海上升压站平台的健康监测提供了一种新的技术路径和理论基础。
该方法在实际应用中也存在一定局限性,主要体现在3个方面:
1)数据依赖性与环境适应性
该方法的有效性高度依赖高质量的振动数据,数据采集过程中若存在噪声或缺失,将可能影响模型的训练效果和健康评估的准确性。尽管本研究针对特定海上升压站进行了验证,但不同海洋环境和平台结构的差异可能会影响模型的普适性和适应性,需在不同场景下进行进一步验证。
2)模型复杂性
深度学习模型的复杂性使得其训练和调优过程需要大量的计算资源和时间,尤其是在处理大规模数据时,可能导致效率低下。
3)异常检测阈值设定
本文采用的健康状态置信度阈值是基于历史数据统计得出的,可能无法适应未来环境变化或突发事件,因此需进一步研究动态阈值的设定方法。
针对上述局限性,未来的研究将包括3个主要方向:
1)开发多源数据融合与实时监测系统
未来研究可以考虑将多种传感器数据(如温度、湿度、压力等)与振动数据结合,利用多模态学习方法提高健康监测的准确性和鲁棒性,同时开发基于云计算和边缘计算的实时监测系统,实现对海上升压站的在线健康监测和预警,提升运维效率。
2)模型优化与简化
针对模型的复杂性,未来研究可以探索模型压缩和加速技术,以降低计算成本,提高实时性。
3)自适应学习机制与长时间序列分析的研究
探索如何使模型能够根据新的数据动态调整参数和结构,以适应环境变化和设备老化带来的影响,并进一步研究如何处理长时间序列数据,探索时间序列预测模型,以便更好地捕捉设备健康状态的变化趋势。
  • 中国华能集团有限公司总部科技项目(HNKJ24-HF72)
参考文献 引证文献
排序方式:
[1]
ZHENG T, XIE W, YAO Z, et al. Online monitoring and analysis system for steel structure safety of offshore wind farm booster station based on multi-source data[C]. IET Conference Proceedings CP843, 2023.
[2]
AMAECHI C V, REDA A, BUTLER H O, et al. Review on fixed and floating offshore structures. Part I: types of platforms with some applications[J]. Journal of Marine Science and Engineering, 2022, 10(8): 1074.
[3]
CENTENARO E, LANY M, MEYER T, et al. Structural health monitoring solutions for offshore platforms[C]. Offshore Mediterranean Conference and Exhibition. OMC, 2019: 1031.
[4]
PEZESHKI H, ADELI H, PAVLOU D, et al. State of the art in structural health monitoring of offshore and marine structures[C]. Proceedings of the Institution of Civil Engineers-Maritime Engineering. Thomas Telford Ltd., 2023: 89-108.
[5]
LIANG T, WANG S, LU C, et al. Environmental impact evaluation of an iron and steel plant in China: normalized data and direct/indirect contribution[J]. Journal of Cleaner Production, 2020, 264: 121697.
[6]
DONG Y, FRANGOPOL D M. Performance-based seismic assessment of conventional and base-isolated steel buildings including environmental impact and resilience[J]. Earthquake Engineering & Structural Dynamics, 2016, 45(5): 739-756.
[7]
司广全, 赵勇, 童博, 等. 海上风电水下资产质量缺陷及检测方法[J]. 热力发电, 2024, 53(12): 77-85.
SI Guangquan, ZHAO Yong, TONG Bo, et al. Quality defects of underwater assets in offshore wind power and the detecting methods[J]. Thermal Power Generation, 2024, 53(12): 77-85.
[8]
张宝锋, 赵勇, 韩斌. 海上升压站建造阶段质量控制[J]. 热力发电, 2019, 48(7): 137-141.
ZHANG Baofeng, ZHAO Yong, HAN Bin. Quality control of offshore substation construction in construction stage[J]. Thermal Power Generation, 2019, 48(7): 137-141.
[9]
LIAN J, CAI O, DONG X, et al. Health monitoring and safety evaluation of the offshore wind turbine structure: a review and discussion of future development[J]. Sustainability, 2019, 11(2): 494.
[10]
AMBHORE N, KAMBLE D, CHINCHANIKAR S, et al. Tool condition monitoring system: a review[J]. Materials Today: Proceedings, 2015, 2(4/5): 3419-3428.
[11]
HAN Y, SONG Y H. Condition monitoring techniques for electrical equipment-a literature survey[J]. IEEE Transactions on Power delivery, 2003, 18(1): 4-13.
[12]
KHAN M A, AKHTAR K, AHMAD N, et al. Vibration analysis of damaged and undamaged steel structure systems: cantilever column and frame[J]. Earthquake Engineering and Engineering Vibration, 2020, 19: 725-737.
[13]
VERSTRYNGE E, VAN STEEN C, VANDECRUYS E, et al. Steel corrosion damage monitoring in reinforced concrete structures with the acoustic emission technique: a review[J]. Construction and Building Materials, 2022, 349: 128732.
[14]
贾丹桐. 基于无监督学习的海上风电支撑结构损伤识别研究[D]. 青岛: 青岛理工大学, 2022: 1.
JIA Dantong. Study on the damage identification of offshore wind turbine support structure based on unsupervised learning[D]. Qingdao: Qingdao University of Technology, 2022: 1.
[15]
陈韬, 杨三元. 海上风电基础健康监测技术[J]. 船舶工程, 2022, 44(增刊1): 47-50.
CHEN Tao, YANG Sanyuan. Offshore wind turbine foundation health monitoring technology[J]. Ship Engineering, 2022, 44(Suppl.1): 47-50.
[16]
魏君. 基于无线传感器网络的机械异常振动信号采集方法[J]. 长江信息通信, 2024, 37(7): 94-96.
WEI Jun. Mechanical abnormal vibration signal acquisition method based on wireless sensor network[J]. Changjiang Information & Communications, 2024, 37(7): 94-96.
[17]
YE H, JIANG C, ZU F, et al. Design of a structural health monitoring system and performance evaluation for a jacket offshore platform in east china sea[J]. Applied Sciences, 2022, 12(23): 12021.
[18]
WANG M, INCECIK A, TIAN Z, et al. Structural health monitoring on offshore jacket platforms using a novel ensemble deep learning model[J]. Ocean Engineering, 2024, 301: 117510.
[19]
BAO X, FAN T, SHI C, et al. Deep learning methods for damage detection of jacket-type offshore platforms[J]. Process Safety and Environmental Protection, 2021, 154: 249-261.
[20]
XIN S, QI Z, YANG L, et al. Deep-learning approach based on multi-data fusion for damage recognition of marine platforms under complex loads[J]. Ocean Engineering, 2024, 303: 116604.
[21]
刘占领, 黄远远. 基于海上风电结构安全监测系统的研究[J]. 船舶工程, 2024, 46(增刊1): 166-171.
LIU Zhanling, HUANG Yuanyuan. Research on safety monitoring system for offshore wind power structures[J]. Ship Engineering, 2024, 46(Suppl.1): 166-171.
[22]
王火平, 陈道毅. 海上导管架平台结构健康监测技术研究及应用[J]. 石油与天然气化工, 2023, 52(2): 157-164.
WANG Huoping, CHEN Daoyi. Research and application of jacket platform structure health monitoring technology in offshore[J]. Chemical Engineering of Oil and Gas, 2023, 52(2): 157-164.
[23]
刘亚森. 基于振动信号的统计时域阻尼参数研究[D]. 哈尔滨: 哈尔滨工业大学, 2023: 1.
LIU Yasen. Research on statistical time-domain damping parameters based on vibration signals[D]. Harbin: Harbin Institute of Technology, 2023: 1.
[24]
FAN G, LI J, HAO H. Vibration signal denoising for structural health monitoring by residual convolutional neural networks[J]. Measurement, 2020, 157: 107651.
[25]
MIAO F, ZHAO R. A new method of vibration signal denoising based on improved wavelet[J]. Journal of Low Frequency Noise, Vibration and Active Control, 2022, 41(2): 637-645.
[26]
LECUN Y, BOSER B, DENKER J S, et al. Backpropagation applied to handwritten zip code recognition[J]. Neural Computation, 1989, 1(4): 541-551.
[27]
LONG J, SHELHAMER E, DARRELL T. Fully convolutional networks for semantic segmentation[C]. Proceedings of the IEEE Conference on Computer vision and Pattern Recognition, 2015: 3431-3440.
[28]
HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]// Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.
[29]
GAO H, YUAN H, WANG Z, et al. Pixel transposed convolutional networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2019, 42(5): 1218-1227.
[30]
NIU Z, ZHONG G, YU H. A review on the attention mechanism of deep learning[J]. Neurocomputing, 2021, 452: 48-62.
[31]
REYNOLDS D A. Gaussian mixture models[J]. Encyclopedia of Biometrics, 2009, 741: 659-663.
[32]
DEMPSTER A P, LAIRD N M, RUBIN D B. Maximum likelihood from incomplete data via the EM algorithm[J]. Journal of the Royal Statistical Society: Series B (methodological), 1977, 39(1): 1-22.
[33]
DER MAATEN L V, HINTON G E. Visualizing data using t-SNE[J]. Journal of Machine Learning Research, 2008, 9(11): 2579-2605.
[34]
SCHÖLKOPF B, PLATT J C, SHAWE-TAYLOR J, et al. Estimating the support of a high-dimensional distribution[J]. Neural Computation, 2001, 13(7): 1443-1471.
[35]
LIU F T, TING K M, ZHOU Z H. Isolation forest[C]. IEEE International Conference on Data Mining, 2008: 413-422.
2025年第54卷第11期
PDF下载
84
34
引用本文
BibTeX
文章信息
doi: 10.19666/j.rlfd.202501046
  • 接收时间:2025-01-07
  • 首发时间:2026-01-13
  • 出版时间:2025-11-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-01-07
基金
Science and Technology Project of China Huaneng Group Co., Ltd.(HNKJ24-HF72)
中国华能集团有限公司总部科技项目(HNKJ24-HF72)
作者信息
    1.西安热工研究院有限公司,陕西 西安 710054
    2.华能陇东能源有限责任公司,甘肃 庆阳 745100

通讯作者:

王嘉良(1997),男,硕士,工程师,主要研究方向为海上风电安全监测技术,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202501046
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