Article(id=1217836020607927097, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1217836019408360416, articleNumber=null, orderNo=null, doi=10.19666/j.rlfd.202501029, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1737907200000, receivedDateStr=2025-01-27, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1768284333612, onlineDateStr=2026-01-13, pubDate=1764000000000, pubDateStr=2025-11-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1768284333612, onlineIssueDateStr=2026-01-13, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1768284333612, creator=13701087609, updateTime=1768284333612, 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=107, endPage=116, ext={EN=ArticleExt(id=1217836020830225213, articleId=1217836020607927097, tenantId=1146029695717560320, journalId=1210938733613449225, language=EN, title=Modeling method for characterizing condenser system based on multi-fidelity data and transfer learning, columnId=1211002405299294959, journalTitle=Thermal Power Generation, columnName=Thermal energy science research, runingTitle=null, highlight=null, articleAbstract=

The effectiveness of a data-driven model relies on the completeness of its training samples. For operating conditions beyond the scope of the training samples, the model’s generalization ability is compromised. Therefore, to develop a condenser model that can adapt to the wide load variation of the unit, it is essential for the training samples to involve a diverse range of power generation loads and ambient temperatures. However, achieving this complete dataset is difficult for newly-commissioned units because of their short operation time. To address these challenges, a method for characterizing condensing units using multi-fidelity data and transfer learning is proposed, even with incomplete data. In this method, a pre-trained model is firstly built based on the comprehensive operational dataset collected from a similar unit. On the basis of the pre-trained model, additional linear and nonlinear calibration networks are introduced. The calibration networks are updated through the incomplete data of newly constructed units, enabling the transfer of the pre-training model to the feature space that is adapted to the incomplete dataset. The effectiveness of this method is validated through the condenser of a 1 000 MW supercritical unit. The results indicate that, even with limited training samples, the method accurately predicts parameters such as condenser pressure and circulating water outlet temperature, with an average R2 of 0.95, significantly outperforming the conventional data-driven model based on a single data set, of which the average R2 is only 0.81.

, 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=Yijia ZHANG, Shaojun REN, Baoyu ZHU, Qihang WENG, Zihan WEI, Fengqi SI), CN=ArticleExt(id=1217836023204201318, articleId=1217836020607927097, tenantId=1146029695717560320, journalId=1210938733613449225, language=CN, title=基于多保真度数据和迁移学习的凝汽器系统特性建模方法, columnId=1211002405437706993, journalTitle=热力发电, columnName=热能科学研究, runingTitle=null, highlight=null, articleAbstract=

数据驱动模型有效性取决于训练样本是否完备,对于样本覆盖范围外的工况,模型泛化能力较差。为构建适应机组宽负荷变化的凝汽器系统特性模型,训练样本需包括较大变化范围的发电负荷和环境温度。然而,新建机组因投运时间短,无法提供完备数据集。因此,针对不完备数据集提出了一种基于多保真度数据和迁移学习的凝汽器系统特性建模方法。该方法首先采用同类型系统的完备数据集构建预训练模型,在预训练模型上,新增线性和非线性校准网络,通过新建机组的不完备数据对校准网络进行更新,使预训练模型迁移适配不完备数据集的特征空间。最后通过某1 000 MW超临界机组凝汽器系统验证该方法有效性,验证结果表明,在训练样本不充分的情况下,该方法能准确预测凝汽器压力和循环水出口温度等参数,决定系数R2平均值为0.95,明显优于传统单一数据集数据驱动模型的R2平均值0.81。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
司风琪(1973),男,教授,博士生导师,主要研究方向为大型火电机组运行特性、性能优化及故障诊断,
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=BAGSZDOwaVjt86uMNapkHg==, magXml=AVCn83pR17ZyXwZRbeMs7Q==, pdfUrl=null, pdf=Uf5aU53/CU0Mgb9VkA/d7Q==, pdfFileSize=2331603, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=SJvftjORquruCbnXl7VXNw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=lPGIAuhp44Z5kMYT3Bx05A==, mapNumber=null, authorCompany=null, fund=null, authors=

张逸佳(2001),男,硕士研究生,主要研究方向为凝汽器系统特性建模,

, authorsList=张逸佳, 任少君, 朱保宇, 翁琪航, 卫子涵, 司风琪)}, authors=[Author(id=1217836023485219698, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=220234970@seu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1217836023552328565, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, authorId=1217836023485219698, language=EN, stringName=Yijia ZHANG, firstName=Yijia, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing 210096, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836023627826043, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, authorId=1217836023485219698, language=CN, stringName=张逸佳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=东南大学能源热转换及过程测控教育部重点实验室,江苏 南京 210096, bio={"content":"

张逸佳(2001),男,硕士研究生,主要研究方向为凝汽器系统特性建模,

"}, bioImg=null, bioContent=

张逸佳(2001),男,硕士研究生,主要研究方向为凝汽器系统特性建模,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836023401333613, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, xref=null, ext=[AuthorCompanyExt(id=1217836023409722222, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, companyId=1217836023401333613, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing 210096, China), AuthorCompanyExt(id=1217836023418110831, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, companyId=1217836023401333613, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=东南大学能源热转换及过程测控教育部重点实验室,江苏 南京 210096)])]), Author(id=1217836023728489345, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, 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=1217836023820764041, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, authorId=1217836023728489345, language=EN, stringName=Shaojun REN, firstName=Shaojun, middleName=null, lastName=REN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing 210096, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836023934010254, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, authorId=1217836023728489345, language=CN, stringName=任少君, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=东南大学能源热转换及过程测控教育部重点实验室,江苏 南京 210096, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836023401333613, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, xref=null, ext=[AuthorCompanyExt(id=1217836023409722222, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, companyId=1217836023401333613, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing 210096, China), AuthorCompanyExt(id=1217836023418110831, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, companyId=1217836023401333613, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=东南大学能源热转换及过程测控教育部重点实验室,江苏 南京 210096)])]), Author(id=1217836024005313427, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, 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=1217836024093393817, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, authorId=1217836024005313427, language=EN, stringName=Baoyu ZHU, firstName=Baoyu, middleName=null, lastName=ZHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing 210096, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836024194057120, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, authorId=1217836024005313427, language=CN, stringName=朱保宇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=东南大学能源热转换及过程测控教育部重点实验室,江苏 南京 210096, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836023401333613, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, xref=null, ext=[AuthorCompanyExt(id=1217836023409722222, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, companyId=1217836023401333613, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing 210096, China), AuthorCompanyExt(id=1217836023418110831, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, companyId=1217836023401333613, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=东南大学能源热转换及过程测控教育部重点实验室,江苏 南京 210096)])]), Author(id=1217836024277943203, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, 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=1217836024366023592, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, authorId=1217836024277943203, language=EN, stringName=Qihang WENG, firstName=Qihang, middleName=null, lastName=WENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing 210096, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836024454103981, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, authorId=1217836024277943203, language=CN, stringName=翁琪航, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=东南大学能源热转换及过程测控教育部重点实验室,江苏 南京 210096, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836023401333613, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, xref=null, ext=[AuthorCompanyExt(id=1217836023409722222, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, companyId=1217836023401333613, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing 210096, China), AuthorCompanyExt(id=1217836023418110831, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, companyId=1217836023401333613, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=东南大学能源热转换及过程测控教育部重点实验室,江苏 南京 210096)])]), Author(id=1217836024537990070, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, 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=1217836024638653370, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, authorId=1217836024537990070, language=EN, stringName=Zihan WEI, firstName=Zihan, middleName=null, lastName=WEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing 210096, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836024718345152, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, authorId=1217836024537990070, language=CN, stringName=卫子涵, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=东南大学能源热转换及过程测控教育部重点实验室,江苏 南京 210096, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836023401333613, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, xref=null, ext=[AuthorCompanyExt(id=1217836023409722222, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, companyId=1217836023401333613, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing 210096, China), AuthorCompanyExt(id=1217836023418110831, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, companyId=1217836023401333613, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=东南大学能源热转换及过程测控教育部重点实验室,江苏 南京 210096)])]), Author(id=1217836024777065415, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, orderNo=5, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=fqsi@seu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1217836024890311630, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, authorId=1217836024777065415, language=EN, stringName=Fengqi SI, firstName=Fengqi, middleName=null, lastName=SI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing 210096, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836024957420501, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, authorId=1217836024777065415, language=CN, stringName=司风琪, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=东南大学能源热转换及过程测控教育部重点实验室,江苏 南京 210096, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836023401333613, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, xref=null, ext=[AuthorCompanyExt(id=1217836023409722222, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, companyId=1217836023401333613, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing 210096, China), AuthorCompanyExt(id=1217836023418110831, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, companyId=1217836023401333613, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=东南大学能源热转换及过程测控教育部重点实验室,江苏 南京 210096)])])], keywords=[Keyword(id=1217836025171330020, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=EN, orderNo=1, keyword=transfer learning), Keyword(id=1217836025271993325, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=EN, orderNo=2, keyword=multi-fidelity data), Keyword(id=1217836025418793974, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=EN, orderNo=3, keyword=deep neural network), Keyword(id=1217836025515262976, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=EN, orderNo=4, keyword=condenser), Keyword(id=1217836025590759428, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=EN, orderNo=5, keyword=power plant), Keyword(id=1217836025678839816, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=CN, orderNo=1, keyword=迁移学习), Keyword(id=1217836025783697425, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=CN, orderNo=2, keyword=多保真度数据), Keyword(id=1217836025871777816, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=CN, orderNo=3, keyword=深度神经网络), Keyword(id=1217836025964052513, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=CN, orderNo=4, keyword=凝汽器), Keyword(id=1217836026043744294, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=CN, orderNo=5, keyword=发电机组)], refs=[Reference(id=1217836029604708587, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2009, volume=30, issue=1, pageStart=99, pageEnd=101, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=杜小泽, 金衍胜, 姜剑波, journalName=工程热物理学报, refType=null, unstructuredReference=杜小泽, 金衍胜, 姜剑波, 等. 火电厂直接空冷凝汽器传热性能实验研究[J]. 工程热物理学报, 2009, 30(1): 99-101., articleTitle=火电厂直接空冷凝汽器传热性能实验研究, refAbstract=null), Reference(id=1217836029680206066, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2009, volume=30, issue=1, pageStart=99, pageEnd=101, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=DU Xiaoze, JIN Yansheng, JIANG Jianbo, journalName=Journal of Engineering Thermophysics, refType=null, unstructuredReference=DU Xiaoze, JIN Yansheng, JIANG Jianbo, et al. Experimental study on heat transfer performance of direct air-cooled condenser in power plant[J]. Journal of Engineering Thermophysics, 2009, 30(1): 99-101., articleTitle=Experimental study on heat transfer performance of direct air-cooled condenser in power plant, refAbstract=null), Reference(id=1217836029755703546, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2010, volume=13, issue=4, pageStart=104, pageEnd=107, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=JIANG J, journalName=Industrial Engineering Journal, refType=null, unstructuredReference=JIANG J. Fault diagnosis of condenser based on wavelet neural network[J]. Industrial Engineering Journal, 2010, 13(4): 104-107., articleTitle=Fault diagnosis of condenser based on wavelet neural network, refAbstract=null), Reference(id=1217836029877338372, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2014, volume=35, issue=1, pageStart=123, pageEnd=127, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=ZHONG D, ZENG H, MENG J, journalName=Journal of Engineering Thermophysics, refType=null, unstructuredReference=ZHONG D, ZENG H, MENG J, et al. Numerical simulation of power plant condenser performance and roles for tube arrangement[J]. Journal of Engineering Thermophysics, 2014, 35(1): 123-127., articleTitle=Numerical simulation of power plant condenser performance and roles for tube arrangement, refAbstract=null), Reference(id=1217836029998973195, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2020, volume=49, issue=9, pageStart=2037, pageEnd=2040, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=薛倩, journalName=当代化工, refType=null, unstructuredReference=薛倩. 凝汽器强化传热研究[J]. 当代化工, 2020, 49(9): 2037-2040., articleTitle=凝汽器强化传热研究, refAbstract=null), Reference(id=1217836030120608024, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2020, volume=49, issue=9, pageStart=2037, pageEnd=2040, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=XUE Qian, journalName=Contemporary Chemical Industry, refType=null, unstructuredReference=XUE Qian. Study on enhanced heat transfer of condenser in power plant[J]. Contemporary Chemical Industry, 2020, 49(9): 2037-2040., articleTitle=Study on enhanced heat transfer of condenser in power plant, refAbstract=null), Reference(id=1217836030292574494, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2011, volume=31, issue=10, pageStart=74, pageEnd=77, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=WANG J, WANG H, BI W, journalName=Cryogenics & Superconductivity, refType=null, unstructuredReference=WANG J, WANG H, BI W. Research of energy consumption of evaporative condenser in ammonia refrigeration system[J]. Cryogenics & Superconductivity, 2011, 31(10): 74-77., articleTitle=Research of energy consumption of evaporative condenser in ammonia refrigeration system, refAbstract=null), Reference(id=1217836030439375142, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2014, volume=null, issue=5, pageStart=58, pageEnd=62, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=WANG Q, LIU B, DONG X, journalName=Cryogenics, refType=null, unstructuredReference=WANG Q, LIU B, DONG X, et al. Performance characteristics of microchannel condenser under different heat loads[J]. Cryogenics, 2014(5): 58-62., articleTitle=Performance characteristics of microchannel condenser under different heat loads, refAbstract=null), Reference(id=1217836030569398573, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2010, volume=33, issue=5, pageStart=982, pageEnd=988, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=HAJIDAVALLOO E, EGHTEDARI H, journalName=International Journal of Refrigeration, refType=null, unstructuredReference=HAJIDAVALLOO E, EGHTEDARI H. Performance improvement of air-cooled refrigeration system by using evaporatively cooled air condenser[J]. International Journal of Refrigeration, 2010, 33(5): 982-988., articleTitle=Performance improvement of air-cooled refrigeration system by using evaporatively cooled air condenser, refAbstract=null), Reference(id=1217836030636507444, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=张远绪, journalName=null, refType=null, unstructuredReference=张远绪. 基于PSO-DDSAEN的凝汽器故障诊断研究[D]. 青岛: 青岛科技大学, 2019: 1., articleTitle=基于PSO-DDSAEN的凝汽器故障诊断研究, refAbstract=null), Reference(id=1217836031978684733, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=ZHANG Yuanxu, journalName=null, refType=null, unstructuredReference=ZHANG Yuanxu. Research on condenser fault diagnosis based on PSO-DDSAEN[D]. Qingdao: Qingdao University of Science and Technology, 2019: 1., articleTitle=Research on condenser fault diagnosis based on PSO-DDSAEN, refAbstract=null), Reference(id=1217836032075153731, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=21, pageStart=198, pageEnd=204, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=冯金金, 章颢, 李健平, journalName=科技和产业, refType=null, unstructuredReference=冯金金, 章颢, 李健平, 等. 1 000 MW燃煤机组双压凝汽器冷端系统运行优化[J]. 科技和产业, 2024, 24(21): 198-204., articleTitle=1 000 MW燃煤机组双压凝汽器冷端系统运行优化, refAbstract=null), Reference(id=1217836032175817035, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=21, pageStart=198, pageEnd=204, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=FENG Jinjin, ZHANG Hao, LI Jianping, journalName=Science Technology and Industry, refType=null, unstructuredReference=FENG Jinjin, ZHANG Hao, LI Jianping, et al. Operation optimization of the cold end system with dual-pressure condenser of 1 000 MW coal-fired unit[J]. Science Technology and Industry, 2024, 24(21): 198-204., articleTitle=Operation optimization of the cold end system with dual-pressure condenser of 1 000 MW coal-fired unit, refAbstract=null), Reference(id=1217836032305840468, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2020, volume=19, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=HAFFEJEE R A, LAUBSCHER R, journalName=Thermal Science and Engineering Progress, refType=null, unstructuredReference=HAFFEJEE R A, LAUBSCHER R. Development of a thermofluid network modeling methodology for double-row air-cooled condensers[J]. Thermal Science and Engineering Progress, 2020, 19: 100646., articleTitle=Development of a thermofluid network modeling methodology for double-row air-cooled condensers, refAbstract=null), Reference(id=1217836032419086682, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=朱自强, journalName=null, refType=null, unstructuredReference=朱自强. 不同凝汽器冷却方式的燃气蒸汽联合循环系统热经济性研究[D]. 北京: 华北电力大学, 2022: 1., articleTitle=不同凝汽器冷却方式的燃气蒸汽联合循环系统热经济性研究, refAbstract=null), Reference(id=1217836032507167074, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=ZHU Ziqiang, journalName=null, refType=null, unstructuredReference=ZHU Ziqiang. Study on thermoeconomic performance of gas-steam combined cycle system with different condenser cooling modes[D]. Beijing: North China Electric Power University, 2022: 1., articleTitle=Study on thermoeconomic performance of gas-steam combined cycle system with different condenser cooling modes, refAbstract=null), Reference(id=1217836032578470248, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=代雨辰, journalName=null, refType=null, unstructuredReference=代雨辰. 基于机器学习的凝汽器设备故障分类方法研究[D]. 南京: 东南大学, 2022: 1., articleTitle=基于机器学习的凝汽器设备故障分类方法研究, refAbstract=null), Reference(id=1217836032729465201, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=DAI Yuchen, journalName=null, refType=null, unstructuredReference=DAI Yuchen. Research on fault classification method of condenser based on machine learning[D]. Nanjing: Southeast University, 2022: 1., articleTitle=Research on fault classification method of condenser based on machine learning, refAbstract=null), Reference(id=1217836032834322809, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2020, volume=136, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=WU D, ZHOU D, ZHANG J, journalName=Computers & Chemical Engineering, refType=null, unstructuredReference=WU D, ZHOU D, ZHANG J, et al. Multimode process monitoring based on fault dependent variable selection and moving window-negative log likelihood probability[J]. Computers & Chemical Engineering, 2020, 136: 106787., articleTitle=Multimode process monitoring based on fault dependent variable selection and moving window-negative log likelihood probability, refAbstract=null), Reference(id=1217836032922403196, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2020, volume=141, issue=20, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=WU H, ZHAO J, journalName=Computers & Chemical Engineering, refType=null, unstructuredReference=WU H, ZHAO J. Self-adaptive deep learning for multimode process monitoring[J]. Computers & Chemical Engineering, 2020, 141(20): 107024., articleTitle=Self-adaptive deep learning for multimode process monitoring, refAbstract=null), Reference(id=1217836033023066498, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2019, volume=34, issue=6, pageStart=4796, pageEnd=4805, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=ZAMZAM A S, FU X, SIDIROPOULOS N D, journalName=IEEE Transactions on Power Systems, refType=null, unstructuredReference=ZAMZAM A S, FU X, SIDIROPOULOS N D. Data-driven learning-based optimization for distribution system state estimation[J]. IEEE Transactions on Power Systems, 2019, 34(6): 4796-4805., articleTitle=Data-driven learning-based optimization for distribution system state estimation, refAbstract=null), Reference(id=1217836033136312712, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2013, volume=33, issue=6, pageStart=443, pageEnd=447, url=null, language=null, rfNumber=[16], rfOrder=21, authorNames=高建强, 王艳, journalName=动力工程学报, refType=null, unstructuredReference=高建强, 王艳. 基于BP神经网络的直接空冷凝汽器换热性能预测[J]. 动力工程学报, 2013, 33(6): 443-447., articleTitle=基于BP神经网络的直接空冷凝汽器换热性能预测, refAbstract=null), Reference(id=1217836033245364625, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2013, volume=33, issue=6, pageStart=443, pageEnd=447, url=null, language=null, rfNumber=[16], rfOrder=22, authorNames=GAO Jianqiang, WANG Yan, journalName=Journal of Chinese Society of Power Engineering, refType=null, unstructuredReference=GAO Jianqiang, WANG Yan. BP neural network prediction on heat-transfer performance of direct air-cooled condensers[J]. Journal of Chinese Society of Power Engineering, 2013, 33(6): 443-447., articleTitle=BP neural network prediction on heat-transfer performance of direct air-cooled condensers, refAbstract=null), Reference(id=1217836033320862100, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2018, volume=129, issue=null, pageStart=1496, pageEnd=1507, url=null, language=null, rfNumber=[17], rfOrder=23, authorNames=LI X, WANG N, WANG L, journalName=Applied Thermal Engineering Design Processes Equipment Economics, refType=null, unstructuredReference=LI X, WANG N, WANG L, et al. A data-driven model for the air-cooling condenser of thermal power plants based on data reconciliation and support vector regression[J]. Applied Thermal Engineering Design Processes Equipment Economics, 2018, 129: 1496-1507., articleTitle=A data-driven model for the air-cooling condenser of thermal power plants based on data reconciliation and support vector regression, refAbstract=null), Reference(id=1217836033392165272, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2024, volume=215, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=24, authorNames=LAI C, BARALDI P, ZIO E, journalName=Mechanical Systems & Signal Processing, refType=null, unstructuredReference=LAI C, BARALDI P, ZIO E. Physics-informed deep autoencoder for fault detection in new-design systems[J]. Mechanical Systems & Signal Processing, 2024, 215: 111420., articleTitle=Physics-informed deep autoencoder for fault detection in new-design systems, refAbstract=null), Reference(id=1217836033564131741, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2021, volume=35, issue=6, pageStart=420, pageEnd=425, url=null, language=null, rfNumber=[19], rfOrder=25, authorNames=王力光, 贠勇博, 朱保宇, journalName=发电设备, refType=null, unstructuredReference=王力光, 贠勇博, 朱保宇, 等. 基于迁移学习的湿法烟气脱硫系统出口SO2浓度预测研究[J]. 发电设备, 2021, 35(6): 420-425., articleTitle=基于迁移学习的湿法烟气脱硫系统出口SO2浓度预测研究, refAbstract=null), Reference(id=1217836033677377956, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2021, volume=35, issue=6, pageStart=420, pageEnd=425, url=null, language=null, rfNumber=[19], rfOrder=26, authorNames=WANG Liguang, YUN Yongbo, ZHU Baoyu, journalName=Power Equipment, refType=null, unstructuredReference=WANG Liguang, YUN Yongbo, ZHU Baoyu, et al. Research on the prediction of SO2 concentration at the outlet of wet flue gas desulfurization system based on transfer learning[J]. Power Equipment, 2021, 35(6): 420-425., articleTitle=Research on the prediction of SO2 concentration at the outlet of wet flue gas desulfurization system based on transfer learning, refAbstract=null), Reference(id=1217836033794818472, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2018, volume=60, issue=3, pageStart=550, pageEnd=591, url=null, language=null, rfNumber=[20], rfOrder=27, authorNames=BENJAMIN P, KAREN W, MAX G, journalName=SIAM Review, refType=null, unstructuredReference=BENJAMIN P, KAREN W, MAX G. Survey of multifidelity methods in uncertainty propagation, inference, and optimization[J]. SIAM Review, 2018, 60(3): 550-591., articleTitle=Survey of multifidelity methods in uncertainty propagation, inference, and optimization, refAbstract=null), Reference(id=1217836033924841905, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2023, volume=197, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=28, authorNames=TORZONI G, MANZONI R, MARIANI S, journalName=Mechanical Systems and Signal Processing, refType=null, unstructuredReference=TORZONI G, MANZONI R, MARIANI S. A multi-fidelity surrogate model for structural health monitoring exploiting model order reduction and artificial neural networks[J]. Mechanical Systems and Signal Processing, 2023, 197: 110376., articleTitle=A multi-fidelity surrogate model for structural health monitoring exploiting model order reduction and artificial neural networks, refAbstract=null), Reference(id=1217836034025505205, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=18, pageStart=7309, pageEnd=7321, url=null, language=null, rfNumber=[22], rfOrder=29, authorNames=任少君, 朱保宇, 翁琪航, journalName=中国电机工程学报, refType=null, unstructuredReference=任少君, 朱保宇, 翁琪航, 等. 基于数据增强和模型迁移的生物质气化产物分布预测方法[J]. 中国电机工程学报, 2024, 44(18): 7309-7321., articleTitle=基于数据增强和模型迁移的生物质气化产物分布预测方法, refAbstract=null), Reference(id=1217836034138751414, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2024, volume=44, issue=18, pageStart=7309, pageEnd=7321, url=null, language=null, rfNumber=[22], rfOrder=30, authorNames=REN Shaojun, ZHU Baoyu, WENG Qihang, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=REN Shaojun, ZHU Baoyu, WENG Qihang, et al. Prediction method of biomass gasification product distribution based on data augmentation and model migration[J]. Proceedings of the CSEE, 2024, 44(18): 7309-7321., articleTitle=Prediction method of biomass gasification product distribution based on data augmentation and model migration, refAbstract=null), Reference(id=1217836034247803325, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2023, volume=137, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=31, authorNames=GENG X, LIU P, HU T, journalName=Aerospace Science and Technology, refType=null, unstructuredReference=GENG X, LIU P, HU T, et al. Multi-fidelity optimization of a quiet propeller based on deep deterministic policy gradient and transfer learning[J]. Aerospace Science and Technology, 2023, 137: 108288., articleTitle=Multi-fidelity optimization of a quiet propeller based on deep deterministic policy gradient and transfer learning, refAbstract=null), Reference(id=1217836034327495110, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2022, volume=180, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=32, authorNames=YE X, NI Y Q, SAJJADI M, journalName=Mechanical Systems & Signal Processing, refType=null, unstructuredReference=YE X, NI Y Q, SAJJADI M, et al. Physics-guided, data-refined modeling of granular material-filled particle dampers by deep transfer learning[J]. Mechanical Systems & Signal Processing, 2022, 180: 109437., articleTitle=Physics-guided, data-refined modeling of granular material-filled particle dampers by deep transfer learning, refAbstract=null), Reference(id=1217836034457518537, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, doi=null, pmid=null, pmcid=null, year=2017, volume=1, issue=4, pageStart=351, pageEnd=400, url=null, language=null, rfNumber=[25], rfOrder=33, authorNames=GISELLE M, PARK C, KIM N H, journalName=Advances in Computational Science and Engineering, refType=null, unstructuredReference=GISELLE M, PARK C, KIM N H, et al. Review of multi-fidelity models[J]. Advances in Computational Science and Engineering, 2017, 1(4): 351-400., articleTitle=Review of multi-fidelity models, refAbstract=null)], funds=[Fund(id=1217836029223026890, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, awardId=52306230, language=EN, fundingSource=National Natural Science Foundation of China(52306230), fundOrder=null, country=null), Fund(id=1217836029327884498, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, awardId=52306230, language=CN, fundingSource=国家自然科学基金项目(52306230), fundOrder=null, country=null), Fund(id=1217836029411770584, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, awardId=2022YFB4100700, language=EN, fundingSource=National Key Research & Development Program(2022YFB4100700), fundOrder=null, country=null), Fund(id=1217836029491462368, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, awardId=2022YFB4100700, language=CN, fundingSource=国家重点研发计划项目(2022YFB4100700), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1217836023401333613, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, xref=null, ext=[AuthorCompanyExt(id=1217836023409722222, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, companyId=1217836023401333613, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing 210096, China), AuthorCompanyExt(id=1217836023418110831, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, companyId=1217836023401333613, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=东南大学能源热转换及过程测控教育部重点实验室,江苏 南京 210096)])], figs=[ArticleFig(id=1217836026165379122, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=EN, label=Fig.1, caption=The modeling method based on multi-fidelity data and transfer learning, figureFileSmall=oxebvIvfRR+diOi9EeTs5w==, figureFileBig=SJvftjORquruCbnXl7VXNw==, tableContent=null), ArticleFig(id=1217836027436253244, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=CN, label=图1, caption=基于多保真度数据和迁移学习的建模方法, figureFileSmall=oxebvIvfRR+diOi9EeTs5w==, figureFileBig=SJvftjORquruCbnXl7VXNw==, tableContent=null), ArticleFig(id=1217836027633385544, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=EN, label=Fig.2, caption=Distributions of the dataset samples, figureFileSmall=4765fAZGRtLEZVZEaAShFw==, figureFileBig=aLkAjvEkmB/f9FB0Hir43A==, tableContent=null), ArticleFig(id=1217836027729854543, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=CN, label=图2, caption=数据集样本分布, figureFileSmall=4765fAZGRtLEZVZEaAShFw==, figureFileBig=aLkAjvEkmB/f9FB0Hir43A==, tableContent=null), ArticleFig(id=1217836027809546324, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=EN, label=Fig.3, caption=The model prediction performance based on limited high-fidelity data, figureFileSmall=bI3/8XIWmzqn+7bA30MuhQ==, figureFileBig=6smHUru2RrosjjJ/L2tYPA==, tableContent=null), ArticleFig(id=1217836027893432415, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=CN, label=图3, caption=基于有限高保真数据的模型预测效果, figureFileSmall=bI3/8XIWmzqn+7bA30MuhQ==, figureFileBig=6smHUru2RrosjjJ/L2tYPA==, tableContent=null), ArticleFig(id=1217836027994095720, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=EN, label=Fig.4, caption=The model prediction performance based on sufficient low-fidelity data, figureFileSmall=u2ELMQt9d+8V2FfGt6+Pjg==, figureFileBig=PxK0s39iZCDtGswdQgCdSw==, tableContent=null), ArticleFig(id=1217836028065398891, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=CN, label=图4, caption=基于充分低保真数据的模型预测效果, figureFileSmall=u2ELMQt9d+8V2FfGt6+Pjg==, figureFileBig=PxK0s39iZCDtGswdQgCdSw==, tableContent=null), ArticleFig(id=1217836028140896371, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=EN, label=Fig.5, caption=The prediction performance of multi-fidelity model, figureFileSmall=s1iCSL0SD6ZR1WM8KDI3Mg==, figureFileBig=sp0ui2DWLrwhLhErpBjcHg==, tableContent=null), ArticleFig(id=1217836028228976764, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=CN, label=图5, caption=多保真模型预测效果, figureFileSmall=s1iCSL0SD6ZR1WM8KDI3Mg==, figureFileBig=sp0ui2DWLrwhLhErpBjcHg==, tableContent=null), ArticleFig(id=1217836028317057156, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=EN, label=Fig.6, caption=Performance comparison between different models, figureFileSmall=aa1ciN1xH0khdrLcB3NPmQ==, figureFileBig=5J8P2CeeqWhDrerHh7r/KQ==, tableContent=null), ArticleFig(id=1217836028459663495, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=CN, label=图6, caption=不同模型预测性能比较, figureFileSmall=aa1ciN1xH0khdrLcB3NPmQ==, figureFileBig=5J8P2CeeqWhDrerHh7r/KQ==, tableContent=null), ArticleFig(id=1217836028556132494, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=EN, label=Fig.7, caption=Prediction values of different synthetic samples, figureFileSmall=qR0vmSPiW6h846gso5fIJQ==, figureFileBig=kksNSFTrt/0G+EEFDUrGlw==, tableContent=null), ArticleFig(id=1217836028665184409, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=CN, label=图7, caption=合成样本预测值对比, figureFileSmall=qR0vmSPiW6h846gso5fIJQ==, figureFileBig=kksNSFTrt/0G+EEFDUrGlw==, tableContent=null), ArticleFig(id=1217836028757459102, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=EN, label=Fig.8, caption=Comparison of error distributions, figureFileSmall=n8JW9lN7LAJQFpOsmoqjrw==, figureFileBig=IkU12bd5sYydFHPe0N6dbQ==, tableContent=null), ArticleFig(id=1217836028887482531, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=CN, label=图8, caption=误差分布对比, figureFileSmall=n8JW9lN7LAJQFpOsmoqjrw==, figureFileBig=IkU12bd5sYydFHPe0N6dbQ==, tableContent=null), ArticleFig(id=1217836028967174317, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=EN, label=Tab.1, caption=

Input and output variables for modeling a condenser

, figureFileSmall=null, figureFileBig=null, tableContent=
输入变量输出变量
机组负荷,MW凝汽器A真空压力,kPa
循环水进水温度,℃凝汽器B真空压力,kPa
循环水流量,kg/s凝汽器A温度,℃
循环水进水压力,MPa凝汽器B温度,℃
循环水出水压力,MPa循环水连接管温度,℃
LP汽缸A排气压力,kPa循环水出口温度,℃
LP汽缸B排气压力,kPa热井出口温度,℃
冷凝水流量,kg/s
热井水位,mm
), ArticleFig(id=1217836029093003450, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836020607927097, language=CN, label=表1, caption=

凝汽器建模输入变量、输出变量

, figureFileSmall=null, figureFileBig=null, tableContent=
输入变量输出变量
机组负荷,MW凝汽器A真空压力,kPa
循环水进水温度,℃凝汽器B真空压力,kPa
循环水流量,kg/s凝汽器A温度,℃
循环水进水压力,MPa凝汽器B温度,℃
循环水出水压力,MPa循环水连接管温度,℃
LP汽缸A排气压力,kPa循环水出口温度,℃
LP汽缸B排气压力,kPa热井出口温度,℃
冷凝水流量,kg/s
热井水位,mm
)], 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.202501029, detailUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/10.19666/j.rlfd.202501029, pdfUrlCn=https://castjournals.cast.org.cn/joweb/rlfd/CN/PDF/10.19666/j.rlfd.202501029, pdfUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/PDF/10.19666/j.rlfd.202501029, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于多保真度数据和迁移学习的凝汽器系统特性建模方法
收藏切换
PDF下载
张逸佳 , 任少君 , 朱保宇 , 翁琪航 , 卫子涵 , 司风琪
热力发电 | 热能科学研究 2025,54(11): 107-116
收起
收藏切换
热力发电 | 热能科学研究 2025, 54(11): 107-116
基于多保真度数据和迁移学习的凝汽器系统特性建模方法
全屏
张逸佳 , 任少君, 朱保宇, 翁琪航, 卫子涵, 司风琪
作者信息
  • 东南大学能源热转换及过程测控教育部重点实验室,江苏 南京 210096
  • 张逸佳(2001),男,硕士研究生,主要研究方向为凝汽器系统特性建模,

通讯作者:

司风琪(1973),男,教授,博士生导师,主要研究方向为大型火电机组运行特性、性能优化及故障诊断,
Modeling method for characterizing condenser system based on multi-fidelity data and transfer learning
Yijia ZHANG , Shaojun REN, Baoyu ZHU, Qihang WENG, Zihan WEI, Fengqi SI
Affiliations
  • Laboratory of Energy Thermal Conversion and Control of Ministry of Education, Southeast University, Nanjing 210096, China
出版时间: 2025-11-25 doi: 10.19666/j.rlfd.202501029
文章导航
收藏切换

数据驱动模型有效性取决于训练样本是否完备,对于样本覆盖范围外的工况,模型泛化能力较差。为构建适应机组宽负荷变化的凝汽器系统特性模型,训练样本需包括较大变化范围的发电负荷和环境温度。然而,新建机组因投运时间短,无法提供完备数据集。因此,针对不完备数据集提出了一种基于多保真度数据和迁移学习的凝汽器系统特性建模方法。该方法首先采用同类型系统的完备数据集构建预训练模型,在预训练模型上,新增线性和非线性校准网络,通过新建机组的不完备数据对校准网络进行更新,使预训练模型迁移适配不完备数据集的特征空间。最后通过某1 000 MW超临界机组凝汽器系统验证该方法有效性,验证结果表明,在训练样本不充分的情况下,该方法能准确预测凝汽器压力和循环水出口温度等参数,决定系数R2平均值为0.95,明显优于传统单一数据集数据驱动模型的R2平均值0.81。

迁移学习  /  多保真度数据  /  深度神经网络  /  凝汽器  /  发电机组

The effectiveness of a data-driven model relies on the completeness of its training samples. For operating conditions beyond the scope of the training samples, the model’s generalization ability is compromised. Therefore, to develop a condenser model that can adapt to the wide load variation of the unit, it is essential for the training samples to involve a diverse range of power generation loads and ambient temperatures. However, achieving this complete dataset is difficult for newly-commissioned units because of their short operation time. To address these challenges, a method for characterizing condensing units using multi-fidelity data and transfer learning is proposed, even with incomplete data. In this method, a pre-trained model is firstly built based on the comprehensive operational dataset collected from a similar unit. On the basis of the pre-trained model, additional linear and nonlinear calibration networks are introduced. The calibration networks are updated through the incomplete data of newly constructed units, enabling the transfer of the pre-training model to the feature space that is adapted to the incomplete dataset. The effectiveness of this method is validated through the condenser of a 1 000 MW supercritical unit. The results indicate that, even with limited training samples, the method accurately predicts parameters such as condenser pressure and circulating water outlet temperature, with an average R2 of 0.95, significantly outperforming the conventional data-driven model based on a single data set, of which the average R2 is only 0.81.

transfer learning  /  multi-fidelity data  /  deep neural network  /  condenser  /  power plant
张逸佳, 任少君, 朱保宇, 翁琪航, 卫子涵, 司风琪. 基于多保真度数据和迁移学习的凝汽器系统特性建模方法. 热力发电, 2025 , 54 (11) : 107 -116 . DOI: 10.19666/j.rlfd.202501029
Yijia ZHANG, Shaojun REN, Baoyu ZHU, Qihang WENG, Zihan WEI, Fengqi SI. Modeling method for characterizing condenser system based on multi-fidelity data and transfer learning[J]. Thermal Power Generation, 2025 , 54 (11) : 107 -116 . DOI: 10.19666/j.rlfd.202501029
凝汽器是燃煤电厂的关键设备,主要通过为机组提供稳定的低温环境,从而凝结低压缸排汽并维持汽轮机排汽口真空。为了保障凝汽器高效稳定运行,对其运行参数进行监测和优化至关重要[1-4]。由于凝汽器的运行环境复杂且受冷却水温度、热电负荷及外界气象条件等多种因素的影响,仅通过人工调整难以满足复杂的工况变化需求[5-7]。为此,研究者常常通过建立凝汽器的系统特性模型来预测其真空度、循环水出口温度等关键参数。一方面,模型预测结果可以与实际值进行对比,通过预测偏差来判断凝汽器的运行状况,从而及时发现潜在问题并采取相应措施[8]。另一方面,高保真的凝汽器系统特性模型能够表征运行参数在不同工况下的变化特性,为汽轮机组冷端优化提供理论依据[9]
目前,针对凝汽器系统特性建模的方法主要分为机理建模和数据驱动建模两大类。机理建模通过能量守恒和质量守恒等理化规律进行模型构建,也采用计算流体动力学(computational fluid dynamics,CFD)软件Fluent或系统级仿真平台Apros和Eplison等软件进行流动、换热等复杂过程的精细模拟[10-12]。随着人工智能和大数据技术的快速发展,数据驱动建模方法已广泛应用于燃煤发电机组凝汽器系统建模,因其计算效率高和拟合精度良好成为研究热点[13-15]。然而,该类模型的有效性依赖于训练数据的准确性和完整性,对于训练样本未覆盖的运行工况往往预测性能不佳。由于凝汽器换热量受多因素影响,数据驱动模型需要训练样本覆盖较广的发电负荷和环境温度变化范围,当面向新建机组或系统内设备维护(清洁、修理、更换)等情况时,训练样本覆盖的运行工况则不够完备[16-17]
面向不完备数据集的建模方法已成为数据驱动建模领域一个公认的难点[18]。迁移学习通过将源任务的知识迁移到目标任务中,能够在目标任务数据不足时提高模型的泛化能力,特别适用于数据不完备的情况[19-20]。Torzoni等人[21]通过简化模型生成大量低保真仿真数据,再采用迁移学习将低保真仿真数据与高精度有限元模型获得的高保真数据相结合,成功构建了结构健康监测的代理模型,结果表明该策略能够提供比单一保真度方法更准确的预测结果。任少君等[22]则通过模型迁移学习将Aspen Plus仿真数据与实验数据融合,建立了一种高精度的生物质气化产物预测模型。此外,Geng等人[23]将BEMT模型生成的低保真数据和CFD模拟得到的高保真数据相融合,进一步建立了螺旋桨叶片空气动力学和气动声学性能的优化代理模型。
在凝汽器建模场景中,除目标凝汽器运行数据外,也存在着多种不同保真度的数据来源。如通过机理模型可以生成大量仿真数据,目标凝汽器在检修前存储了长时周期的运行数据,或不同机组同类型凝汽器也可提供海量运行数据。虽然这些数据不能直接用于目标凝汽器的特性建模,但与目标凝汽器运行数据存在着一定的共性关系。为此,本文通过迁移学习的思想来有效利用低保真数据的广度与高保真数据的精度,弥补样本量不足的问题,进而在凝汽器建模中构建更稳定和准确的特性模型。
以某新建百万机组为例,由于机组运行时间短,因此已存储的运行数据不足以构建准确的凝汽器特性模型。为此,本文充分考虑了同类型机组的长时段运行数据与目标机组少量运行数据的相似性和差异性,提出了一种基于多保真度数据和迁移学习(multi-fidelity data and transfer learning,MF-TL)的凝汽器系统特性建模方法,从而解决不完备数据集场景下的凝汽器系统特性建模问题。对于目标新建机组而言,同类型机组的长时段运行数据为低保真数据,目标机组本身的少量运行数据为高保真数据。该方法首先利用同类型机组大量低保真运行数据对凝汽器系统模型进行训练,得到预训练模型。然后,利用新建机组少量高保真运行数据对预训练模型进行更新,实现模型迁移。最后,通过工程实例验证所提出的MF-TL方法的有效性。
深度神经网络(deep neural network,DNN)通过引入多层结构,能够捕捉复杂数据特征并处理非线性、高维问题。本文基于给定源域数据集DS={xS, yS},采用深度神经网络建立凝汽器系统特性模型。该DNN模型包含n个输入层节点、m个输出层节点以及L个隐含层。模型输入记为x=[x1, x2,…, xn]T,第l层隐含层的输出为:
Al=g(WlAl1+bl),l=1,2,...,L
式中:Wl为连接第l-1层与第l层的权重矩阵;bl为偏置项;g(τ)=max(0, τ)为RELU激活函数。
因此,DNN模型的输出可表示为:
y^=f(x)=g(WlAl+bl)
式中:y^为模型输出。
为了评估模型的性能,将模型输出值与真实测试值进行对比,并通过计算损失函数来量化误差。这里采用均方误差(mean square error,δMSE)作为损失函数,其计算公式为:
δMSE=1Ni=1N(y^y)2
式中:N为训练样本数量;y为训练样本真实值。
本文采用反向传播(back propagation,BP)算法来进行DNN网络的参数优化,BP算法通过最小化损失函数来更新权重与偏置,该优化过程为:
dWl=δMSEWl,dbl=δMSEbl
Wl=WllrdWl,bl=bllrdbl
式中:dWl和dbl分别为损失函数对第l层隐含层权重和偏置的偏导数;lr为学习率。
在训练过程中,选取合适的超参数,主要包括隐含层层数、每层神经元个数、学习率lr和训练次数Ne。考虑到源域数据量较大,在预训练过程中以较大的学习率lr和训练次数Ne来迭代更新网络权重。基于源域数据集预训练出的DNN模型只是一个近似模型,称为低保真模型。
本文在预训练模型的基础上,通过模型迁移的方式将预训练模型调整至与目标域数据集DT={xT, yT}相匹配的特征空间[24]。模型迁移的关键点是发现和利用预训练模型和目标域数据集之间的关联[25],实现对目标任务的有效适配。其关联式可表示为:
yH=F(x,yL)
式中:x为模型输入;yHyL分别为目标域数据集和对应预训练模型的输出值。
F(·)可以分解为线性和非线性两部分,用于自适应地挖掘目标域数据与源域数据之间线性和非线性关联,即为:
F=Fl+Fnl=αFl(x,yL)+(1α)Fnl(x,yL)
式中:F1Fnl分别为F(·)中线性项和非线性项;αF(·)中线性项的权重因子。
综上,模型迁移的具体流程如图1所示。本文所提出的多保真模型由1个预训练的神经网络(NNL)和2个校准网络(NNH1和NNH2)共3个神经网络组成。NNL是源域数据集建立的神经网络预训练模型,NNH1和NNH2分别表征式(7)中的线性项F1和非线性项Fn1
多保真模型采用BP算法进行模型训练,包括预训练和模型迁移2个步骤。首先使用源域数据集预训练NNL模型,其损失函数为:
δMSE,L=1NLi=1NL(y^LyL)2
式中:y^L为预训练网络的预测输出值。
之后进行模型迁移,冻结预训练模型NNL的网络参数,通过训练NNH1和NNH2校准网络,对预训练模型NNL进行调整,从而最小化多保真模型在目标域数据集样本上的预测误差。其损失函数为:
δMSE,H=1NHi=1NH(y^HyH)2
式中:y^H为多保真模型的预测输出值。
在迁移过程中目标域数据量有限的情况下,模型性能对超参数设置尤为敏感。学习率直接影响收敛性和泛化能力,网络结构决定特征提取与过拟合的平衡,而训练次数则影响模型收敛程度和计算效率。因此,本文通过网格搜索、隐含层结构设计以及训练次数控制的方式进行超参数优化。为实现模型在有限数据条件下的稳定训练,采用较低的学习率lr2和训练次数Ne2进行训练,在保证训练速度的同时减小波动。构造多保真模型算法流程的详细步骤如下。
阶段1:预训练模型NNL阶段
1)输入:源域数据集,目标域数据集;
2)随机初始化网络参数;
3)使用源域数据集训练模型NNL,根据式(8)最小化损失函数;
4)BP算法参数更新,直到损失函数收敛结束迭代,训练完成。
阶段2:基于多保真度数据的模型迁移阶段
1)冻结预训练NNL模型的网络参数;
2)随机初始化网络参数NNH1和NNH2校准网络参数;
3)使用目标域数据集训练NNH1和NNH2 2个校准网络,根据式(9)最小化损失函数;
4)BP算法参数更新,直到损失函数收敛结束迭代,训练完成;
5)输出:模型预测值。
模型相关的输入和输出参数信息见表1
本文研究对象为1 000 MW新建机组,以该同类机组为源域机组。先从源域机组的监控信息系统(supervisory information system,SIS)中以1 min采样频率采集84 960个连续样本DL。从目标域机组的SIS中以同样参数和采样频率,采集43 200个连续样本DH。作为预处理步骤,对所有的输入变量进行了高斯标准化处理,确保所有变量的数据分布一致。
为分析不同模型的预测效果,建立3种模型:
1)模型1,基于有限高保真数据建立的模型 将数据集DH前14 400条样本记为训练集TrH,将数据集DH中剩余的28 800条样本记为测试集TeH。基于训练集TrH构建DNN模型进行训练,对测试集TeH进行模型测试,观察模型1的预测精度。
2)模型2,基于充分低保真数据建立的模型 以数据集DL为训练集建立DNN模型,以数据集DH为测试集进行模型测试,观察模型2预测结果。
3)模型3,结合有限高保真数据和充分低保真数据建立的多保真模型 该模型采用模型1作为预训练模型。预训练完成后冻结模型1的网络结构参数并在此基础上新增线性和非线性校准网络。基于训练集TrH的数据对校准网络进行更新,得到模型3,以测试集TeH对模型进行测试,将模型3的性能与模型1和模型2的性能进行对比。
图2给出了目标域机组不完备数据集TrH和源域机组完备数据集DL的数据分布。图2中框内数字表示对应工况所含数据样本的数量大小,颜色为所取数据集覆盖的工况范围。由图2可见,DL中机组负荷和循环水进水温度的覆盖区间分别为[440, 1 000] MW和[21, 35] ℃,而TrH中机组负荷和循环水进水温度的覆盖区间分别为[520, 1 000] MW和[27, 32] ℃。由于源域机组运行时间较长,DL覆盖的机组负荷与循环水进水温度范围较大。相对而言,目标机组投运时间较短,TrH工况覆盖率较低。
为了比较不同模型的精度,3个模型的深度神经网络部分具有相同的网络结构和参数配置,均采用5层神经网络结构,第一层输入层,中间三层为隐含层,神经元个数均为10个,最后一层为输出层。模型1、模型2和模型3的学习率lr1和循环次数Ne1均设定为10–3和10 000。本文算法在Python 3.8以及PyTorch-2.0.1版本的开发环境下通过Visual Studio Code 1.89.1编辑器编程实现。
图3给出了基于有限高保真数据的模型1的预测结果。
图3可以看出,模型预测值与真实值较为吻合,但在样本数18 000~20 000以及36 000~40 000这2段预测的结果都较差,即该模型在测试数据集的部分工况(如循环水进水温度23~25 ℃)表现不佳。具体来说,图3a)中低背压凝汽器压力的预测值与实际测量值在绿色圈内有较大的偏差,均方根误差为1.62 kPa,决定系数R2低至-3.88。这是由于训练集TrH中样本的循环水进水温度所覆盖的区间为[27, 32]℃,而圈内包含的测试集样本循环水进水温度覆盖的区间为[23, 25]℃,即该部分样本处在训练样本覆盖范围以外的工况。因此模型表现出泛化能力不足的特性,无法准确预测出低背压凝汽器压力。
图4给出了基于充分低保真数据的模型2的预测结果。值得注意的是,该模型是以同类型机组充分低保真数据为训练样本,以目标新建机组的运行数据为测试样本。从图4可以看出,模型预测结果与测试数据的变化趋势保持一致,但存在明显偏移。这说明源域机组与目标域机组凝汽器系统具有共性特征,但由于测点安装位置和凝汽器本身特性存在差异,所以在相似工况下其参数预测值存在一定的偏差。如图4a)所示,低背压凝汽器压力的2条曲线存在约1 kPa的偏离。这表明2台机组数据之间存在相关性,在近似运行条件下目标域机组低背压凝汽器压力比源域机组整体偏高。由此可见,直接用源域模型对目标域系统进行预测会带来较大的预测误差。
图5给出了多保真模型的预测效果。由图5可以看出,与单一保真度模型相比,多保真模型的预测值更接近真实值,低背压和高背压凝汽器压力的均方根误差分别降低至0.10 kPa和0.15 kPa,低背压凝汽器温度、高背压凝汽器温度、循环水出口温度和热井出口温度的均方根误差分别降低至0.45、0.34、0.43、0.48 ℃,R2值也均提升至0.9以上。
图6比较了3种模型的预测性能。由图6可见,就R2值而言,基于多保真度数据的模型3明显优于基于有限高保真数据的模型1和基于充分低保真数据的模型2,模型3所有参数的R2值均接近1,均值为0.95,远高于模型2(R2=0.81)和模型1(R2=–1.53)。这表明多保真模型能够准确预测在目标域机组中凝汽器系统的关键参数的趋势。通过根据测量值偏差设置适当的阈值,可以在模态变化后监测凝汽器的特性。
为了进一步评估3种模型的可解释性。本文以某一测试样本为基础,设定负荷为650 MW,循环水入口温度范围为20~36 ℃,步长为1 ℃,其他输入参数保持不变,共得到16组合成样本。
图7比较了3种模型对合成样本的预测结果。由图7可以看出,由于训练样本有限,基于有限高保真数据的模型1未能捕捉到低温范围内的凝汽器压力特性,导致曲线趋势出现偏差。基于充分低保真数据的模型2的预测曲线几乎是一条直线,有效地反映了随着循环水进水温度升高,凝汽器整体换热量减少,进而导致凝汽器压力增加的线性关系。然而,在循环水入口温度较高的范围内,曲线垂直偏离基于有限高保真数据的模型1。这一偏差主要源于源域与目标域机组数据的差异,进而导致基于低保真数据的模型出现预测偏差,影响预测精度。基于多保真度数据的模型3在保留基于充分低保真数据的模型参数关系的同时,增强了泛化能力,对目标域机组凝汽器的预测更加准确。
采用平方预测误差(squared prediction error,δSPE)指标来评估模型的可解释性。该指标是用来衡量模型预测值与真实值之间偏差的平方和,数值越小,表示模型的性能越好。δSPE计算公式为:
δSPE=i=1N(yiy^i)2
式中:N为样本数量;yiy^i分别为第i个样本真实值及其模型预测值。
分别计算基于有限高保真数据的模型1与基于多保真度数据的模型3针对目标域机组数据集DHδSPE指标,将δSPE根据样本的机组负荷与循环水进水温度分为不同工况后求和取平均,绘制δSPE根据样本工况的分布对比图(图8)。由图8可以看出,基于有限高保真数据的模型1在训练集的表现很好,当样本的循环水进水温度偏低时,δSPE值明显增加。温度偏离训练集覆盖范围越远,δSPE越高。而基于多保真度数据的模型3通过学习完备数据集中的规律,能够在未被训练集覆盖的较低循环水进水温度区间也表现出很高的精度。可见,多保真模型能够在包括无样本区域在内的较大工况范围内,保持机理规律的一致性,得到的预测结果比单一模态数据更具有可解释性。
1)本文提出了面向不完备数据集的MF-TL凝汽器系统特性建模方法,该方法通过采集同类型机组凝汽器系统运行数据构建预训练模型,并利用新建机组有限的高保真数据对预训练模型进行迁移优化。
2)本文MF-TL模型在预测精度和泛化能力方面均优于传统的单一保真度模型,低背压凝汽器压力和高背压凝汽器压力的均方根误差分别降低至0.10 kPa和0.15 kPa,低背压凝汽器温度、高背压凝汽器温度、循环水出口温度和热井出口温度的均方根误差分别降低至0.45、0.34、0.43、0.48 ℃,R2均值为0.95,满足高精度预测需求。
3)本文方法在运行数据不完备的情况下,也能够在宽工况范围内给出符合机理规律的预测结果,具有较高的物理可解释性。
  • 国家自然科学基金项目(52306230)
  • 国家重点研发计划项目(2022YFB4100700)
参考文献 引证文献
排序方式:
[1]
杜小泽, 金衍胜, 姜剑波, 等. 火电厂直接空冷凝汽器传热性能实验研究[J]. 工程热物理学报, 2009, 30(1): 99-101.
DU Xiaoze, JIN Yansheng, JIANG Jianbo, et al. Experimental study on heat transfer performance of direct air-cooled condenser in power plant[J]. Journal of Engineering Thermophysics, 2009, 30(1): 99-101.
[2]
JIANG J. Fault diagnosis of condenser based on wavelet neural network[J]. Industrial Engineering Journal, 2010, 13(4): 104-107.
[3]
ZHONG D, ZENG H, MENG J, et al. Numerical simulation of power plant condenser performance and roles for tube arrangement[J]. Journal of Engineering Thermophysics, 2014, 35(1): 123-127.
[4]
薛倩. 凝汽器强化传热研究[J]. 当代化工, 2020, 49(9): 2037-2040.
XUE Qian. Study on enhanced heat transfer of condenser in power plant[J]. Contemporary Chemical Industry, 2020, 49(9): 2037-2040.
[5]
WANG J, WANG H, BI W. Research of energy consumption of evaporative condenser in ammonia refrigeration system[J]. Cryogenics & Superconductivity, 2011, 31(10): 74-77.
[6]
WANG Q, LIU B, DONG X, et al. Performance characteristics of microchannel condenser under different heat loads[J]. Cryogenics, 2014(5): 58-62.
[7]
HAJIDAVALLOO E, EGHTEDARI H. Performance improvement of air-cooled refrigeration system by using evaporatively cooled air condenser[J]. International Journal of Refrigeration, 2010, 33(5): 982-988.
[8]
张远绪. 基于PSO-DDSAEN的凝汽器故障诊断研究[D]. 青岛: 青岛科技大学, 2019: 1.
ZHANG Yuanxu. Research on condenser fault diagnosis based on PSO-DDSAEN[D]. Qingdao: Qingdao University of Science and Technology, 2019: 1.
[9]
冯金金, 章颢, 李健平, 等. 1 000 MW燃煤机组双压凝汽器冷端系统运行优化[J]. 科技和产业, 2024, 24(21): 198-204.
FENG Jinjin, ZHANG Hao, LI Jianping, et al. Operation optimization of the cold end system with dual-pressure condenser of 1 000 MW coal-fired unit[J]. Science Technology and Industry, 2024, 24(21): 198-204.
[10]
HAFFEJEE R A, LAUBSCHER R. Development of a thermofluid network modeling methodology for double-row air-cooled condensers[J]. Thermal Science and Engineering Progress, 2020, 19: 100646.
[11]
朱自强. 不同凝汽器冷却方式的燃气蒸汽联合循环系统热经济性研究[D]. 北京: 华北电力大学, 2022: 1.
ZHU Ziqiang. Study on thermoeconomic performance of gas-steam combined cycle system with different condenser cooling modes[D]. Beijing: North China Electric Power University, 2022: 1.
[12]
代雨辰. 基于机器学习的凝汽器设备故障分类方法研究[D]. 南京: 东南大学, 2022: 1.
DAI Yuchen. Research on fault classification method of condenser based on machine learning[D]. Nanjing: Southeast University, 2022: 1.
[13]
WU D, ZHOU D, ZHANG J, et al. Multimode process monitoring based on fault dependent variable selection and moving window-negative log likelihood probability[J]. Computers & Chemical Engineering, 2020, 136: 106787.
[14]
WU H, ZHAO J. Self-adaptive deep learning for multimode process monitoring[J]. Computers & Chemical Engineering, 2020, 141(20): 107024.
[15]
ZAMZAM A S, FU X, SIDIROPOULOS N D. Data-driven learning-based optimization for distribution system state estimation[J]. IEEE Transactions on Power Systems, 2019, 34(6): 4796-4805.
[16]
高建强, 王艳. 基于BP神经网络的直接空冷凝汽器换热性能预测[J]. 动力工程学报, 2013, 33(6): 443-447.
GAO Jianqiang, WANG Yan. BP neural network prediction on heat-transfer performance of direct air-cooled condensers[J]. Journal of Chinese Society of Power Engineering, 2013, 33(6): 443-447.
[17]
LI X, WANG N, WANG L, et al. A data-driven model for the air-cooling condenser of thermal power plants based on data reconciliation and support vector regression[J]. Applied Thermal Engineering Design Processes Equipment Economics, 2018, 129: 1496-1507.
[18]
LAI C, BARALDI P, ZIO E. Physics-informed deep autoencoder for fault detection in new-design systems[J]. Mechanical Systems & Signal Processing, 2024, 215: 111420.
[19]
王力光, 贠勇博, 朱保宇, 等. 基于迁移学习的湿法烟气脱硫系统出口SO2浓度预测研究[J]. 发电设备, 2021, 35(6): 420-425.
WANG Liguang, YUN Yongbo, ZHU Baoyu, et al. Research on the prediction of SO2 concentration at the outlet of wet flue gas desulfurization system based on transfer learning[J]. Power Equipment, 2021, 35(6): 420-425.
[20]
BENJAMIN P, KAREN W, MAX G. Survey of multifidelity methods in uncertainty propagation, inference, and optimization[J]. SIAM Review, 2018, 60(3): 550-591.
[21]
TORZONI G, MANZONI R, MARIANI S. A multi-fidelity surrogate model for structural health monitoring exploiting model order reduction and artificial neural networks[J]. Mechanical Systems and Signal Processing, 2023, 197: 110376.
[22]
任少君, 朱保宇, 翁琪航, 等. 基于数据增强和模型迁移的生物质气化产物分布预测方法[J]. 中国电机工程学报, 2024, 44(18): 7309-7321.
REN Shaojun, ZHU Baoyu, WENG Qihang, et al. Prediction method of biomass gasification product distribution based on data augmentation and model migration[J]. Proceedings of the CSEE, 2024, 44(18): 7309-7321.
[23]
GENG X, LIU P, HU T, et al. Multi-fidelity optimization of a quiet propeller based on deep deterministic policy gradient and transfer learning[J]. Aerospace Science and Technology, 2023, 137: 108288.
[24]
YE X, NI Y Q, SAJJADI M, et al. Physics-guided, data-refined modeling of granular material-filled particle dampers by deep transfer learning[J]. Mechanical Systems & Signal Processing, 2022, 180: 109437.
[25]
GISELLE M, PARK C, KIM N H, et al. Review of multi-fidelity models[J]. Advances in Computational Science and Engineering, 2017, 1(4): 351-400.
2025年第54卷第11期
PDF下载
92
40
引用本文
BibTeX
文章信息
doi: 10.19666/j.rlfd.202501029
  • 接收时间:2025-01-27
  • 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:2025-01-27
基金
National Natural Science Foundation of China(52306230)
国家自然科学基金项目(52306230)
National Key Research & Development Program(2022YFB4100700)
国家重点研发计划项目(2022YFB4100700)
作者信息
    东南大学能源热转换及过程测控教育部重点实验室,江苏 南京 210096

通讯作者:

司风琪(1973),男,教授,博士生导师,主要研究方向为大型火电机组运行特性、性能优化及故障诊断,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202501029
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