Article(id=1149773874100925241, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149773869357167407, articleNumber=null, orderNo=null, doi=10.12404/j.issn.1671-1815.2404698, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1719158400000, receivedDateStr=2024-06-24, revisedDate=1738771200000, revisedDateStr=2025-02-06, acceptedDate=null, acceptedDateStr=null, onlineDate=1752057053349, onlineDateStr=2025-07-09, pubDate=1746633600000, pubDateStr=2025-05-08, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1752057053349, onlineIssueDateStr=2025-07-09, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1752057053349, creator=13701087609, updateTime=1752057053349, updator=13701087609, issue=Issue{id=1149773869357167407, tenantId=1146029695717560320, journalId=1146123166801305609, year='2025', volume='25', issue='13', pageStart='5273', pageEnd='5704', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=0, createTime=1752057052207, creator=13701087609, updateTime=1768456769392, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1218559268744253990, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149773869357167407, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1218559268744253991, tenantId=1146029695717560320, journalId=1146123166801305609, issueId=1149773869357167407, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=5589, endPage=5601, ext={EN=ArticleExt(id=1149773874344194875, articleId=1149773874100925241, tenantId=1146029695717560320, journalId=1146123166801305609, language=EN, title=Leakage Fault Diagnosis of Heating Network Based on CNN-Transformer, columnId=1156262729917780302, journalTitle=Science Technology and Engineering, columnName=Papers·Architectural Science, runingTitle=null, highlight=null, articleAbstract=

On-line and efficient monitoring of leakage faults in district heating network can effectively increase the quality of heat transmission and reduce energy consumption. However, the data feature extraction ability of conventional leakage fault diagnosis method is limited, and it is difficult to deal with the high dimensional nonlinear pressure flow monitoring data for complex heating network, which makes its diagnostic performance weak. Therefore, a fault diagnosis model of heating network leakage based on convolutional neural network (CNN) and Transformer was proposed. The proposed CNN-Transformer diagnostic model combines CNN and Transformer network to realize joint learning of different time scales and spatial features. The CNN network was used to extract local features, and the Transformer network was used to capture global features. The validity of the model was verified by simulating the fault data set of the annular heating pipe network system. The results show that the proposed CNN-Transformer diagnosis model based on multi-stage feature extraction and fusion mechanism of fault features significantly improves the accuracy of leak diagnosis. The CNN-Transformer method has the highest accuracy on the test set, with an accuracy increase of 13.21%, 7.49%, 6.1% and 4.62%, respectively, compared to other fault diagnosis methods including long short-term memory network, gate recurrent network, CNN and Transformer.

, correspAuthors=Xian-yang MENG, 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=Xiao-long LIANG, Jin-gang LI, Ping-ping XU, Jia-long WANG, Jie-jie LIU, Tao CHEN, Xian-yang MENG), CN=ArticleExt(id=1149773905033917044, articleId=1149773874100925241, tenantId=1146029695717560320, journalId=1146123166801305609, language=CN, title=基于卷积神经网络和Transformer的供热管网泄漏故障诊断, columnId=1156262730517565784, journalTitle=科学技术与工程, columnName=论文·建筑科学, runingTitle=null, highlight=null, articleAbstract=

区域供热网络泄漏故障在线高效监测可以减少检修反映时间,保障居民的用热需求。然而,常规泄漏故障诊断方法的数据特征提取能力有限,难以处理复杂供热网络高维度非线性压力流量监测数据,使得其诊断性能较弱。因此,提出了一种基于卷积神经网络(convolutional neural networks, CNN)和Transformer的供热管网泄漏故障诊断模型。提出的CNN-Transformer诊断模型将CNN与Transformer网络相结合,实现了不同时间尺度和空间特征的联合学习。其中CNN网络用于提取局部特征,Transformer网络用于捕获全局特征。通过模拟环状供热管网系统得到的故障数据集验证了模型的有效性。结果表明,提出的基于故障特征的多级特征提取与融合机制的CNN-Transforme诊断模型,显著提升了泄漏诊断的准确率。CNN-Transformer方法在测试集上准确率最高,与其他故障诊断方法(长短期记忆循环网络、门控循环网络、CNN和Transformer)相比,在测试集上的准确率分别提高了13.21%、7.49%、6.1%和4.62%。

, correspAuthors=孟现阳, authorNote=null, correspAuthorsNote=
* 孟现阳(1978—),男,汉族,河南清丰人,博士,教授。研究方向:能源系统优化。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=bcUY633dlwjueKtMFd3FZw==, magXml=ZXkbp5qJM0ztwC+eGZPw1Q==, pdfUrl=null, pdf=yYfZvK9V9tJJOhSNh3/RyA==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=nDGw/uLDFszDvn9VHSmbNA==, mapNumber=null, authorCompany=null, fund=null, authors=

梁晓龙(1991—),男,汉族,宁夏银川人,工程师。研究方向:信息化与智慧化供热。E-mail:

, authorsList=梁晓龙, 李金刚, 徐平平, 王佳龙, 刘杰杰, 陈涛, 孟现阳)}, authors=[Author(id=1175387063575789682, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=12876150@ceic.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1175387063634509940, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, authorId=1175387063575789682, language=EN, stringName=Xiao-long LIANG, firstName=Xiao-long, middleName=null, lastName=LIANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 National energy Ningxia heating Co. , Ltd. , Yinchuan 750004, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1175387063684841589, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, authorId=1175387063575789682, language=CN, stringName=梁晓龙, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 国能宁夏供热有限公司, 银川 750004, bio={"content":"

梁晓龙(1991—),男,汉族,宁夏银川人,工程师。研究方向:信息化与智慧化供热。E-mail:

"}, bioImg=null, bioContent=

梁晓龙(1991—),男,汉族,宁夏银川人,工程师。研究方向:信息化与智慧化供热。E-mail:

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1175387063353491559, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, xref=1, ext=[AuthorCompanyExt(id=1175387063361880168, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063353491559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 National energy Ningxia heating Co. , Ltd. , Yinchuan 750004, China), AuthorCompanyExt(id=1175387063366074473, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063353491559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国能宁夏供热有限公司, 银川 750004)])]), Author(id=1175387063747756151, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, 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=1175387063810670713, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, authorId=1175387063747756151, language=EN, stringName=Jin-gang LI, firstName=Jin-gang, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 National energy Ningxia heating Co. , Ltd. , Yinchuan 750004, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1175387063873585274, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, authorId=1175387063747756151, language=CN, stringName=李金刚, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 国能宁夏供热有限公司, 银川 750004, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1175387063353491559, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, xref=1, ext=[AuthorCompanyExt(id=1175387063361880168, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063353491559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 National energy Ningxia heating Co. , Ltd. , Yinchuan 750004, China), AuthorCompanyExt(id=1175387063366074473, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063353491559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国能宁夏供热有限公司, 银川 750004)])]), Author(id=1175387063932305532, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, 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=1175387064007803006, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, authorId=1175387063932305532, language=EN, stringName=Ping-ping XU, firstName=Ping-ping, middleName=null, lastName=XU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 National energy Ningxia heating Co. , Ltd. , Yinchuan 750004, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1175387064074911871, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, authorId=1175387063932305532, language=CN, stringName=徐平平, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1 国能宁夏供热有限公司, 银川 750004, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1175387063353491559, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, xref=1, ext=[AuthorCompanyExt(id=1175387063361880168, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063353491559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 National energy Ningxia heating Co. , Ltd. , Yinchuan 750004, China), AuthorCompanyExt(id=1175387063366074473, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063353491559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国能宁夏供热有限公司, 银川 750004)])]), Author(id=1175387064129437825, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, 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=1175387064192352387, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, authorId=1175387064129437825, language=EN, stringName=Jia-long WANG, firstName=Jia-long, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 National Energy Digital Intelligence Technology Development (Beijing) Co. , Ltd. , Beijing 100040, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1175387064251072644, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, authorId=1175387064129437825, language=CN, stringName=王佳龙, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2 国能数智科技开发(北京)有限公司, 北京 100040, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1175387063428989034, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, xref=2, ext=[AuthorCompanyExt(id=1175387063433183339, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063428989034, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 National Energy Digital Intelligence Technology Development (Beijing) Co. , Ltd. , Beijing 100040, China), AuthorCompanyExt(id=1175387063441571948, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063428989034, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 国能数智科技开发(北京)有限公司, 北京 100040)])]), Author(id=1175387064305598598, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, 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=1175387064368513160, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, authorId=1175387064305598598, language=EN, stringName=Jie-jie LIU, firstName=Jie-jie, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 Key Laboratory of Heat Flow Science and Engineering, Ministry of Education, Xi'an Jiaotong University, Xi'an 710049, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1175387064431427721, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, authorId=1175387064305598598, language=CN, stringName=刘杰杰, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 西安交通大学热流科学与工程教育部重点实验室, 西安 710049, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1175387063496097902, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, xref=3, ext=[AuthorCompanyExt(id=1175387063500292206, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063496097902, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Key Laboratory of Heat Flow Science and Engineering, Ministry of Education, Xi'an Jiaotong University, Xi'an 710049, China), AuthorCompanyExt(id=1175387063504486511, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063496097902, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 西安交通大学热流科学与工程教育部重点实验室, 西安 710049)])]), Author(id=1175387064494342283, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, 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=1175387064548868237, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, authorId=1175387064494342283, language=EN, stringName=Tao CHEN, firstName=Tao, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 Key Laboratory of Heat Flow Science and Engineering, Ministry of Education, Xi'an Jiaotong University, Xi'an 710049, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1175387064615977102, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, authorId=1175387064494342283, language=CN, stringName=陈涛, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, address=3 西安交通大学热流科学与工程教育部重点实验室, 西安 710049, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1175387063496097902, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, xref=3, ext=[AuthorCompanyExt(id=1175387063500292206, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063496097902, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Key Laboratory of Heat Flow Science and Engineering, Ministry of Education, Xi'an Jiaotong University, Xi'an 710049, China), AuthorCompanyExt(id=1175387063504486511, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063496097902, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 西安交通大学热流科学与工程教育部重点实验室, 西安 710049)])]), Author(id=1175387064674697360, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, orderNo=6, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xymeng@mail.xjtu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1175387064741806226, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, authorId=1175387064674697360, language=EN, stringName=Xian-yang MENG, firstName=Xian-yang, middleName=null, lastName=MENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, *, address=3 Key Laboratory of Heat Flow Science and Engineering, Ministry of Education, Xi'an Jiaotong University, Xi'an 710049, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1175387064800526483, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, authorId=1175387064674697360, language=CN, stringName=孟现阳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, *, address=3 西安交通大学热流科学与工程教育部重点实验室, 西安 710049, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1175387063496097902, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, xref=3, ext=[AuthorCompanyExt(id=1175387063500292206, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063496097902, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Key Laboratory of Heat Flow Science and Engineering, Ministry of Education, Xi'an Jiaotong University, Xi'an 710049, China), AuthorCompanyExt(id=1175387063504486511, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063496097902, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 西安交通大学热流科学与工程教育部重点实验室, 西安 710049)])])], keywords=[Keyword(id=1175387064947327124, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, orderNo=1, keyword=district heating network), Keyword(id=1175387065006047381, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, orderNo=2, keyword=pipeline leakage), Keyword(id=1175387065064767638, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, orderNo=3, keyword=fault diagnosis), Keyword(id=1175387065152848023, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, orderNo=4, keyword=data-driven), Keyword(id=1175387065211568280, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, orderNo=5, keyword=deep learning), Keyword(id=1175387065282871449, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, orderNo=1, keyword=区域供热网络), Keyword(id=1175387065345786010, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, orderNo=2, keyword=管道泄漏), Keyword(id=1175387065408700571, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, orderNo=3, keyword=故障诊断), Keyword(id=1175387065463226524, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, orderNo=4, keyword=数据驱动), Keyword(id=1175387065530335389, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, orderNo=5, keyword=深度学习)], refs=[Reference(id=1175387067686207672, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2023, volume=283, issue=null, pageStart=128387, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=Vallee M, Wissocq T, Gaoua Y, journalName=Energy, refType=null, unstructuredReference=Vallee M, Wissocq T, Gaoua Y, et al. Generation and evaluation of a synthetic dataset to improve fault detection in district heating and cooling systems[J]. Energy, 2023, 283: 128387., articleTitle=Generation and evaluation of a synthetic dataset to improve fault detection in district heating and cooling systems, refAbstract=null), Reference(id=1175387067757510841, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2023, volume=296, issue=null, pageStart=113367, pageEnd=null, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Liu J, Li X, Zhang Q, journalName=Energy & Buildings, refType=null, unstructuredReference=Liu J, Li X, Zhang Q, et al. An efficient sensor and thermal coupling fault diagnosis methodology for building energy systems[J]. Energy & Buildings, 2023, 296: 113367., articleTitle=An efficient sensor and thermal coupling fault diagnosis methodology for building energy systems, refAbstract=null), Reference(id=1175387067824619706, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2023, volume=276, issue=null, pageStart=127569, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=Neumayer M, Stecher D, Grimm S, journalName=Energy, refType=null, unstructuredReference=Neumayer M, Stecher D, Grimm S, et al. Fault and anomaly detection in district heating substations: a survey on methodology and data sets[J]. Energy, 2023, 276: 127569., articleTitle=Fault and anomaly detection in district heating substations: a survey on methodology and data sets, refAbstract=null), Reference(id=1175387067883339963, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2015, volume=35, issue=null, pageStart=157, pageEnd=168, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=Zhang T, Tan Y, Zhang X, journalName=Journal of Loss Prevention in the Process Industries, refType=null, unstructuredReference=Zhang T, Tan Y, Zhang X, et al. A novel hybrid technique for leak detection and location in straight pipelines[J]. Journal of Loss Prevention in the Process Industries, 2015, 35: 157-168., articleTitle=A novel hybrid technique for leak detection and location in straight pipelines, refAbstract=null), Reference(id=1175387067950448828, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2000, volume=40, issue=2, pageStart=81, pageEnd=85, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=秦绪忠, 江亿, journalName=清华大学学报(自然科学版), refType=null, unstructuredReference=秦绪忠, 江亿. 区域热网管网阻力系数的在线辨识与故障诊断[J]. 清华大学学报(自然科学版), 2000, 40(2): 81-85., articleTitle=区域热网管网阻力系数的在线辨识与故障诊断, refAbstract=null), Reference(id=1175387068013363389, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2000, volume=40, issue=2, pageStart=81, pageEnd=85, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=Qin Xuzhong, Jiang Yi, journalName=Journal of Tsinghua University (Science and Technology), refType=null, unstructuredReference=Qin Xuzhong, Jiang Yi. Identification of flow resistance coefficient and fault diagnosis in district heating networks[J]. Journal of Tsinghua University (Science and Technology), 2000, 40(2): 81-85., articleTitle=Identification of flow resistance coefficient and fault diagnosis in district heating networks, refAbstract=null), Reference(id=1175387068088860862, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2016, volume=104, issue=null, pageStart=142, pageEnd=149, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=Lu W, Liang W, Zhang L, journalName=Process Safety and Environmental Protection, refType=null, unstructuredReference=Lu W, Liang W, Zhang L, et al. A novel noise reduction method applied in negative pressure wave for pipeline leakage localization[J]. Process Safety and Environmental Protection, 2016, 104: 142-149., articleTitle=A novel noise reduction method applied in negative pressure wave for pipeline leakage localization, refAbstract=null), Reference(id=1175387068172746943, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=7, authorNames=韩为明, journalName=热力管网泄漏的红外热像检测技术研究, refType=null, unstructuredReference=韩为明. 热力管网泄漏的红外热像检测技术研究[D]. 天津: 河北工业大学, 2017., articleTitle=null, refAbstract=null), Reference(id=1175387068252438720, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=Han Weiming, journalName=Research on the infrared thermographic technology of leakage in heating network, refType=null, unstructuredReference=Han Weiming. Research on the infrared thermographic technology of leakage in heating network[D]. Tianjin: Hebei University of Technology, 2017., articleTitle=null, refAbstract=null), Reference(id=1175387068319547585, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=任冠企, journalName=基于PSO-EM改进GMM的换热站故障诊断研究, refType=null, unstructuredReference=任冠企. 基于PSO-EM改进GMM的换热站故障诊断研究[D]. 大连: 大连海事大学, 2020., articleTitle=null, refAbstract=null), Reference(id=1175387068399239362, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=Ren Guanqi, journalName=Research on fault diagnosis of heat exchange station based on improved GMM of PSO-EM, refType=null, unstructuredReference=Ren Guanqi. Research on fault diagnosis of heat exchange station based on improved GMM of PSO-EM[D]. Dalian: Dalian Maritime University, 2020., articleTitle=null, refAbstract=null), Reference(id=1175387068512485571, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2020, volume=223, issue=null, pageStart=110161, pageEnd=null, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=Xue P, Jiang Y, Zhou Z, journalName=Energy & Buildings, refType=null, unstructuredReference=Xue P, Jiang Y, Zhou Z, et al. Machine learning-based leakage fault detection for district heating networks[J]. Energy & Buildings, 2020, 223: 110161., articleTitle=Machine learning-based leakage fault detection for district heating networks, refAbstract=null), Reference(id=1175387068592177348, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=12, authorNames=崔建敏, journalName=基于支持向量机的供暖系统智能诊断方法研究, refType=null, unstructuredReference=崔建敏. 基于支持向量机的供暖系统智能诊断方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2021., articleTitle=null, refAbstract=null), Reference(id=1175387068667674821, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=13, authorNames=Cui Jianmin, journalName=Research on the intelligent diagnosis method of heating system based on support vector machine, refType=null, unstructuredReference=Cui Jianmin. Research on the intelligent diagnosis method of heating system based on support vector machine[D]. Harbin: Harbin Institute of Technology, 2021., articleTitle=null, refAbstract=null), Reference(id=1175387068734783686, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2024, volume=55, issue=2, pageStart=338, pageEnd=347, url=null, language=null, rfNumber=[11], rfOrder=14, authorNames=郝江勇, 段鹏飞, 杜永峰, journalName=太原理工大学学报, refType=null, unstructuredReference=郝江勇, 段鹏飞, 杜永峰, 等. 一种GA-ACO-BP模型的热网泄漏故障诊断研究[J]. 太原理工大学学报, 2024, 55(2): 338-347., articleTitle=一种GA-ACO-BP模型的热网泄漏故障诊断研究, refAbstract=null), Reference(id=1175387068818669767, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2024, volume=55, issue=2, pageStart=338, pageEnd=347, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=Hao Jiangyong, Duan Pengfei, Du Yongfeng, journalName=Journal of Taiyuan University of Technology, refType=null, unstructuredReference=Hao Jiangyong, Duan Pengfei, Du Yongfeng, et al. A study on fault diagnosis of heat network leakage based on GA-ACO-BP model[J]. Journal of Taiyuan University of Technology, 2024, 55(2): 338-347., articleTitle=A study on fault diagnosis of heat network leakage based on GA-ACO-BP model, refAbstract=null), Reference(id=1175387068952887496, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2023, volume=48, issue=4, pageStart=835, pageEnd=846, url=null, language=null, rfNumber=[12], rfOrder=16, authorNames=杜永峰, 段鹏飞, 赵秉旭, journalName=广西大学学报(自然科学版), refType=null, unstructuredReference=杜永峰, 段鹏飞, 赵秉旭, 等. 基于CABC-BP模型的供热管网泄漏诊断研究[J]. 广西大学学报(自然科学版), 2023, 48(4): 835-846., articleTitle=基于CABC-BP模型的供热管网泄漏诊断研究, refAbstract=null), Reference(id=1175387069036773577, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2023, volume=48, issue=4, pageStart=835, pageEnd=846, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=Du Yongfeng, Duan Pengfei, Zhao Bingxu, journalName=Journal of Guangxi University (Natural Science Edition), refType=null, unstructuredReference=Du Yongfeng, Duan Pengfei, Zhao Bingxu, et al. Leakage diagnosis model of heating pipe network based on CABC optimization of BP neural network[J]. Journal of Guangxi University (Natural Science Edition), 2023, 48(4): 835-846., articleTitle=Leakage diagnosis model of heating pipe network based on CABC optimization of BP neural network, refAbstract=null), Reference(id=1175387069116465354, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2019, volume=7, issue=null, pageStart=182983, pageEnd=182992, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=Fan Q, Guo Y, Wu S, journalName=IEEE Access, refType=null, unstructuredReference=Fan Q, Guo Y, Wu S, et al. Two-level diagnosis of heating pipe network leakage based on deep belief network[J]. IEEE Access, 2019, 7: 182983-182992., articleTitle=Two-level diagnosis of heating pipe network leakage based on deep belief network, refAbstract=null), Reference(id=1175387069191962827, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=6, pageStart=1011, pageEnd=1019, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=张向宇, 王衍学, journalName=机电工程, refType=null, unstructuredReference=张向宇, 王衍学. 基于同步挤压小波变换和Transformer的轴承故障诊断模型[J]. 机电工程, 2024, 41(6): 1011-1019., articleTitle=基于同步挤压小波变换和Transformer的轴承故障诊断模型, refAbstract=null), Reference(id=1175387069254877388, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2024, volume=41, issue=6, pageStart=1011, pageEnd=1019, url=null, language=null, rfNumber=[14], rfOrder=20, authorNames=Zhang Xiangyu, Wang Yanxue, journalName=Journal of Mechanical & Electrical Engineering, refType=null, unstructuredReference=Zhang Xiangyu, Wang Yanxue. Fault diagnosis model of rolling bearing based on synchro squeezing wavelet transform (SST) and Transformer[J]. Journal of Mechanical & Electrical Engineering, 2024, 41(6): 1011-1019., articleTitle=Fault diagnosis model of rolling bearing based on synchro squeezing wavelet transform (SST) and Transformer, refAbstract=null), Reference(id=1175387069313597645, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=1, pageEnd=12, url=http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html, language=null, rfNumber=[15], rfOrder=21, authorNames=孟宏宇, 张建良, 蔡兆龙, journalName=中国电机工程学报, refType=null, unstructuredReference=孟宏宇, 张建良, 蔡兆龙, 等. 基于CNN-BiLSTM-Attention的直流微电网故障诊断研究[J/OL]. 中国电机工程学报, 1-12[2025-02-20]. http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html., articleTitle=基于CNN-BiLSTM-Attention的直流微电网故障诊断研究, refAbstract=null), Reference(id=1175387069389095118, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=1, pageEnd=12, url=http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html, language=null, rfNumber=[15], rfOrder=22, authorNames=Meng Hongyu, Zhang Jianliang, Cai Zhaolong, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=Meng Hongyu, Zhang Jianliang, Cai Zhaolong, et al. Research on DC microgrid fault diagnosis based on CNN-BiLSTM-Attention[J/OL]. Proceedings of the CSEE, 1-12[2025-02-20]. http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html., articleTitle=Research on DC microgrid fault diagnosis based on CNN-BiLSTM-Attention, refAbstract=null), Reference(id=1175387069460398287, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2024, volume=18, issue=11, pageStart=13, pageEnd=22, url=null, language=null, rfNumber=[16], rfOrder=23, authorNames=朱晋, 程启明, 程尹曼, journalName=南方电网技术, refType=null, unstructuredReference=朱晋, 程启明, 程尹曼. 基于CNN-GRU深度学习的模块化多电平矩阵变换器故障诊断[J]. 南方电网技术, 2024, 18(11): 13-22., articleTitle=基于CNN-GRU深度学习的模块化多电平矩阵变换器故障诊断, refAbstract=null), Reference(id=1175387069531701456, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2024, volume=18, issue=11, pageStart=13, pageEnd=22, url=null, language=null, rfNumber=[16], rfOrder=24, authorNames=Zhu Jin, Cheng Qiming, Cheng Yinman, journalName=Southern Power System Technology, refType=null, unstructuredReference=Zhu Jin, Cheng Qiming, Cheng Yinman. Fault diagnosis of modular multilevel matrix converter based on CNN-GRU deep learning[J]. Southern Power System Technology, 2024, 18(11): 13-22., articleTitle=Fault diagnosis of modular multilevel matrix converter based on CNN-GRU deep learning, refAbstract=null), Reference(id=1175387069594616017, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2014, volume=31, issue=2, pageStart=207, pageEnd=215, url=null, language=null, rfNumber=[17], rfOrder=25, authorNames=王晓霞, 赵立华, 邹平华, journalName=计算物理, refType=null, unstructuredReference=王晓霞, 赵立华, 邹平华, 等. 基于图论的空间热网拓扑结构[J]. 计算物理, 2014, 31(2): 207-215., articleTitle=基于图论的空间热网拓扑结构, refAbstract=null), Reference(id=1175387069657530578, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2014, volume=31, issue=2, pageStart=207, pageEnd=215, url=null, language=null, rfNumber=[17], rfOrder=26, authorNames=Wang Xiaoxia, Zhao Lihua, Zou Pinghua, journalName=Chinese Journal of Computational Physics, refType=null, unstructuredReference=Wang Xiaoxia, Zhao Lihua, Zou Pinghua, et al. Topology structure of spatial heat-supply network based on graph theory[J]. Chinese Journal of Computational Physics, 2014, 31(2): 207-215., articleTitle=Topology structure of spatial heat-supply network based on graph theory, refAbstract=null), Reference(id=1175387069716250835, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2010, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=27, authorNames=雷翠红, journalName=供热管网泄漏故障诊断的研究, refType=null, unstructuredReference=雷翠红. 供热管网泄漏故障诊断的研究[D]. 哈尔滨: 哈尔滨工业大学, 2010., articleTitle=null, refAbstract=null), Reference(id=1175387069779165396, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2010, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=28, authorNames=Lei Cuihong, journalName=Study on leakage fault diagnosis for heating supply network, refType=null, unstructuredReference=Lei Cuihong. Study on leakage fault diagnosis for heating supply network[D]. Harbin: Harbin Institute of Technology, 2010., articleTitle=null, refAbstract=null), Reference(id=1175387069854662869, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2009, volume=39, issue=2, pageStart=1, pageEnd=4, url=null, language=null, rfNumber=[19], rfOrder=29, authorNames=王晓霞, 邹平华, journalName=暖通空调, refType=null, unstructuredReference=王晓霞, 邹平华. 多热源环状空间热网拓扑结构研究[J]. 暖通空调, 2009, 39(2): 1-4., articleTitle=多热源环状空间热网拓扑结构研究, refAbstract=null), Reference(id=1175387069934354646, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2009, volume=39, issue=2, pageStart=1, pageEnd=4, url=null, language=null, rfNumber=[19], rfOrder=30, authorNames=Wang Xiaoxia, Zou Pinghua, journalName=Heating Ventilating & Air Conditioning, refType=null, unstructuredReference=Wang Xiaoxia, Zou Pinghua. Topological structure of multi-heat source ring-shaped heat-supply network[J]. Heating Ventilating & Air Conditioning, 2009, 39(2): 1-4., articleTitle=Topological structure of multi-heat source ring-shaped heat-supply network, refAbstract=null), Reference(id=1175387070014046423, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=14, pageStart=5653, pageEnd=5658, url=null, language=null, rfNumber=[20], rfOrder=31, authorNames=丁津津, 邵庆祝, 齐振兴, journalName=科学技术与工程, refType=null, unstructuredReference=丁津津, 邵庆祝, 齐振兴, 等. 基于迁移学习的卷积神经网络电网故障诊断[J]. 科学技术与工程, 2022, 22(14): 5653-5658., articleTitle=基于迁移学习的卷积神经网络电网故障诊断, refAbstract=null), Reference(id=1175387070148264152, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2022, volume=22, issue=14, pageStart=5653, pageEnd=5658, url=null, language=null, rfNumber=[20], rfOrder=32, authorNames=Ding Jinjin, Shao Qingzhu, Qi Zhenxing, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Ding Jinjin, Shao Qingzhu, Qi Zhenxing, et al. CNN distribution network fault diagnosis method based on Transfer learning[J]. Science Technology and Engineering, 2022, 22(14): 5653-5658., articleTitle=CNN distribution network fault diagnosis method based on Transfer learning, refAbstract=null), Reference(id=1175387070269898969, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=4, pageStart=165, pageEnd=171, url=null, language=null, rfNumber=[21], rfOrder=33, authorNames=孙祺淳, 李媛媛, journalName=噪声与振动控制, refType=null, unstructuredReference=孙祺淳, 李媛媛. DE算法优化CNN的滚动轴承故障诊断研究[J]. 噪声与振动控制, 2022, 42(4): 165-171., articleTitle=DE算法优化CNN的滚动轴承故障诊断研究, refAbstract=null), Reference(id=1175387070324424922, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=4, pageStart=165, pageEnd=171, url=null, language=null, rfNumber=[21], rfOrder=34, authorNames=Sun Qichun, Li Yuanyuan, journalName=Noise and Vibration Control, refType=null, unstructuredReference=Sun Qichun, Li Yuanyuan. Research on fault diagnosis of rolling bearings based on DE algorithm optimization of CNN[J]. Noise and Vibration Control, 2022, 42(4): 165-171., articleTitle=Research on fault diagnosis of rolling bearings based on DE algorithm optimization of CNN, refAbstract=null), Reference(id=1175387070433476827, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2020, volume=41, issue=5, pageStart=92, pageEnd=96, url=null, language=null, rfNumber=[22], rfOrder=35, authorNames=郝旺身, 陈耀, 孙浩, journalName=郑州大学学报(工学版), refType=null, unstructuredReference=郝旺身, 陈耀, 孙浩, 等. 基于全矢-CNN的轴承故障诊断研究[J]. 郑州大学学报(工学版), 2020, 41(5): 92-96., articleTitle=基于全矢-CNN的轴承故障诊断研究, refAbstract=null), Reference(id=1175387070563500252, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2020, volume=41, issue=5, pageStart=92, pageEnd=96, url=null, language=null, rfNumber=[22], rfOrder=36, authorNames=Hao Wangshen, Chen Yao, Sun Hao, journalName=Journal of Zhengzhou University (Engineering Science), refType=null, unstructuredReference=Hao Wangshen, Chen Yao, Sun Hao, et al. Bearing fault diagnosis based on full vector-CNN[J]. Journal of Zhengzhou University (Engineering Science), 2020, 41(5): 92-96., articleTitle=Bearing fault diagnosis based on full vector-CNN, refAbstract=null), Reference(id=1175387070626414813, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=16, pageStart=6974, pageEnd=6982, url=null, language=null, rfNumber=[23], rfOrder=37, authorNames=汤翔中, 高丙朋, journalName=科学技术与工程, refType=null, unstructuredReference=汤翔中, 高丙朋. 融合注意力空洞卷积和Transformer的矿石图像分割[J]. 科学技术与工程, 2023, 23(16): 6974-6982., articleTitle=融合注意力空洞卷积和Transformer的矿石图像分割, refAbstract=null), Reference(id=1175387070693523678, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=16, pageStart=6974, pageEnd=6982, url=null, language=null, rfNumber=[23], rfOrder=38, authorNames=Tang Xiangzhong, Gao Binpeng, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Tang Xiangzhong, Gao Binpeng. Ore image segmentation based on attention hole convolution and Transformer[J]. Science Technology and Engineering, 2023, 23(16): 6974-6982., articleTitle=Ore image segmentation based on attention hole convolution and Transformer, refAbstract=null), Reference(id=1175387070756438239, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2023, volume=278, issue=null, pageStart=127972, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=39, authorNames=Fan C, Lei Y, Sun Y, journalName=Energy, refType=null, unstructuredReference=Fan C, Lei Y, Sun Y, et al. Novel transformer-based self-supervised learning methods for improved HVAC fault diagnosis performance with limited labeled data[J]. Energy, 2023, 278: 127972., articleTitle=Novel transformer-based self-supervised learning methods for improved HVAC fault diagnosis performance with limited labeled data, refAbstract=null), Reference(id=1175387070831935712, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=5, pageStart=2044, pageEnd=2050, url=null, language=null, rfNumber=[25], rfOrder=40, authorNames=李赵春, 周永照, 冯卫奔, journalName=科学技术与工程, refType=null, unstructuredReference=李赵春, 周永照, 冯卫奔, 等. 基于Transformer模型的手势脑电信号分类识别[J]. 科学技术与工程, 2023, 23 (5): 2044-2050., articleTitle=基于Transformer模型的手势脑电信号分类识别, refAbstract=null), Reference(id=1175387070903238881, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2023, volume=23, issue=5, pageStart=2044, pageEnd=2050, url=null, language=null, rfNumber=[25], rfOrder=41, authorNames=Li Zhaochun, Zhou Yongzhao, Feng Weiben, journalName=Science Technology and Engineering, refType=null, unstructuredReference=Li Zhaochun, Zhou Yongzhao, Feng Weiben, et al. Gesture action electroencephalogram classification and recognition based on Transformer model[J]. Science Technology and Engineering, 2023, 23(5): 2044-2050., articleTitle=Gesture action electroencephalogram classification and recognition based on Transformer model, refAbstract=null), Reference(id=1175387070978736354, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2023, volume=51, issue=15, pageStart=209, pageEnd=215, url=null, language=null, rfNumber=[26], rfOrder=42, authorNames=杜康宁, 宁少慧, journalName=机床与液压, refType=null, unstructuredReference=杜康宁, 宁少慧. 基于ADASYN和Swin Transformer的滚动轴承故障诊断研究[J]. 机床与液压, 2023, 51(15): 209-215., articleTitle=基于ADASYN和Swin Transformer的滚动轴承故障诊断研究, refAbstract=null), Reference(id=1175387071054233827, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2023, volume=51, issue=15, pageStart=209, pageEnd=215, url=null, language=null, rfNumber=[26], rfOrder=43, authorNames=Du Kangning, Ning Shaohui, journalName=Machine Tool & Hydraulics, refType=null, unstructuredReference=Du Kangning, Ning Shaohui. Study of rolling bearing fault diagnosis based on ADASYN and Swin Transformer[J]. Machine Tool & Hydraulics, 2023, 51(15): 209-215., articleTitle=Study of rolling bearing fault diagnosis based on ADASYN and Swin Transformer, refAbstract=null), Reference(id=1175387071129731300, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=2023, volume=352, issue=null, pageStart=121949, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=44, authorNames=Zhao J, Feng X, Wang J, journalName=Applied Energy, refType=null, unstructuredReference=Zhao J, Feng X, Wang J, et al. Battery fault diagnosis and failure prognosis for electric vehicles using spatio-temporal transformer networks[J]. Applied Energy, 2023, 352: 121949., articleTitle=Battery fault diagnosis and failure prognosis for electric vehicles using spatio-temporal transformer networks, refAbstract=null), Reference(id=1175387071188451557, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=https://data.mendeley.com/datasets/sh72jwth68/1, language=null, rfNumber=[28], rfOrder=45, authorNames=Xue P, Jiang Y, Zhou Z, journalName=null, refType=null, unstructuredReference=Xue P, Jiang Y, Zhou Z, et al. Data for: machine learning-based leakage fault detection for district heating networks[DB/OL]. (2020-02-14) [2024-06-24]. https://data.mendeley.com/datasets/sh72jwth68/1., articleTitle=Data for: machine learning-based leakage fault detection for district heating networks, refAbstract=null)], funds=[Fund(id=1175387067484881078, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, awardId=51976164, language=CN, fundingSource=国家自然科学基金(51976164), fundOrder=null, country=null), Fund(id=1175387067539407031, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, awardId=2024JC-YBMS-257, language=CN, fundingSource=陕西省自然科学基础研究计划(2024JC-YBMS-257), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1175387063353491559, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, xref=1, ext=[AuthorCompanyExt(id=1175387063361880168, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063353491559, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 National energy Ningxia heating Co. , Ltd. , Yinchuan 750004, China), AuthorCompanyExt(id=1175387063366074473, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063353491559, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 国能宁夏供热有限公司, 银川 750004)]), AuthorCompany(id=1175387063428989034, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, xref=2, ext=[AuthorCompanyExt(id=1175387063433183339, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063428989034, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 National Energy Digital Intelligence Technology Development (Beijing) Co. , Ltd. , Beijing 100040, China), AuthorCompanyExt(id=1175387063441571948, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063428989034, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2 国能数智科技开发(北京)有限公司, 北京 100040)]), AuthorCompany(id=1175387063496097902, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, xref=3, ext=[AuthorCompanyExt(id=1175387063500292206, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063496097902, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 Key Laboratory of Heat Flow Science and Engineering, Ministry of Education, Xi'an Jiaotong University, Xi'an 710049, China), AuthorCompanyExt(id=1175387063504486511, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, companyId=1175387063496097902, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3 西安交通大学热流科学与工程教育部重点实验室, 西安 710049)])], figs=[ArticleFig(id=1175387065681330334, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, label=Fig.1, caption=Flow chart of solving hydraulic model of heating network, figureFileSmall=IfEpjip89XdwBuqExKt4pA==, figureFileBig=Ety9YLpAsmv3ivFGnojPZw==, tableContent=null), ArticleFig(id=1175387065748439199, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, label=图1, caption=供热网络的水力模型求解流程图, figureFileSmall=IfEpjip89XdwBuqExKt4pA==, figureFileBig=Ety9YLpAsmv3ivFGnojPZw==, tableContent=null), ArticleFig(id=1175387065832325280, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, label=Fig.2, caption=The model structure of developed CNN-Transformer, figureFileSmall=LzmWTbL6rib0nFn+s0IBeA==, figureFileBig=OkpAI7uquE+M3yyQR6ZGGA==, tableContent=null), ArticleFig(id=1175387065891045537, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, label=图2, caption=提出的CNN-Transformer的模型结构

n1~n37为供水管网的各个节点;u1~u15为不同的用户负荷

, figureFileSmall=LzmWTbL6rib0nFn+s0IBeA==, figureFileBig=OkpAI7uquE+M3yyQR6ZGGA==, tableContent=null), ArticleFig(id=1175387065945571490, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, label=Fig.3, caption=Leakage fault diagnosis model of heat supply network, figureFileSmall=zFE+glXWgJCbcQNZiUSrsA==, figureFileBig=7h4O5D59L+8CbojmLTvp/Q==, tableContent=null), ArticleFig(id=1175387066016874659, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, label=图3, caption=供热管网泄漏故障诊断模型流程图, figureFileSmall=zFE+glXWgJCbcQNZiUSrsA==, figureFileBig=7h4O5D59L+8CbojmLTvp/Q==, tableContent=null), ArticleFig(id=1175387066104955044, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, label=Fig.4, caption=Supply water network of ring heating pipe network, figureFileSmall=KogWf/1pk3fySCB1UxfFrQ==, figureFileBig=s2AicQiicJmaVVZ2gHwWYg==, tableContent=null), ArticleFig(id=1175387066243367077, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, label=图4, caption=环状供热管网系统的供水管网, figureFileSmall=KogWf/1pk3fySCB1UxfFrQ==, figureFileBig=s2AicQiicJmaVVZ2gHwWYg==, tableContent=null), ArticleFig(id=1175387066306281638, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, label=Fig.5, caption=Return water network of ring heating pipe network, figureFileSmall=8kZJxsqfYVuABgWDHD0BEw==, figureFileBig=Kw2EKyqNIaOA+qlMPlTg3w==, tableContent=null), ArticleFig(id=1175387066373390503, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, label=图5, caption=环状供热管网系统的回水管网

n1'~n37'为回水管网的各个节点

, figureFileSmall=8kZJxsqfYVuABgWDHD0BEw==, figureFileBig=Kw2EKyqNIaOA+qlMPlTg3w==, tableContent=null), ArticleFig(id=1175387066427916456, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, label=Fig.6, caption=Confusion matrix comparison of leakage fault diagnosis results of CNN-Transformer model, figureFileSmall=ZJzVjg/WDnLx5NVcqaMsjQ==, figureFileBig=rAQCyMIip9TXhIH+GjR+qw==, tableContent=null), ArticleFig(id=1175387066482442409, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, label=图6, caption=CNN-Transformer模型的泄漏故障诊断结果的混淆矩阵比较, figureFileSmall=ZJzVjg/WDnLx5NVcqaMsjQ==, figureFileBig=rAQCyMIip9TXhIH+GjR+qw==, tableContent=null), ArticleFig(id=1175387066545356970, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, label=Fig.7, caption=Confusion matrix comparison of leakage fault diagnosis results of CNN model, figureFileSmall=ikGnL7G0zOx4L44HHyPulw==, figureFileBig=yDnrfzCiZGBcz5j+oRkSKw==, tableContent=null), ArticleFig(id=1175387066608271531, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, label=图7, caption=CNN模型的泄漏故障诊断结果的混淆矩阵比较, figureFileSmall=ikGnL7G0zOx4L44HHyPulw==, figureFileBig=yDnrfzCiZGBcz5j+oRkSKw==, tableContent=null), ArticleFig(id=1175387066671186092, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, label=Fig.8, caption=Confusion matrix comparison of leakage fault diagnosis results of Transformer model, figureFileSmall=wsidIsG4H2e/FHqGWfkDpQ==, figureFileBig=KrlBYXrg7zCPK+dqRM0ZGQ==, tableContent=null), ArticleFig(id=1175387066734100653, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, label=图8, caption=Transformer模型的泄漏故障诊断结果的混淆矩阵比较, figureFileSmall=wsidIsG4H2e/FHqGWfkDpQ==, figureFileBig=KrlBYXrg7zCPK+dqRM0ZGQ==, tableContent=null), ArticleFig(id=1175387066822181038, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, label=Fig.9, caption=Confusion matrix comparison of leakage fault diagnosis results of GRU model, figureFileSmall=nra1QY7vq0KQ1upy7pOElg==, figureFileBig=nMnO5MGhoCjFfbqqUM42WA==, tableContent=null), ArticleFig(id=1175387066939621551, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, label=图9, caption=GRU模型的泄漏故障诊断结果的混淆矩阵比较, figureFileSmall=nra1QY7vq0KQ1upy7pOElg==, figureFileBig=nMnO5MGhoCjFfbqqUM42WA==, tableContent=null), ArticleFig(id=1175387067031896240, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, label=Fig.10, caption=Confusion matrix comparison of leakage fault diagnosis results of LSTM model, figureFileSmall=AWmF9T4dGDUqRKzX8stJeg==, figureFileBig=OT6RZi9f4P28mMavhYyCHg==, tableContent=null), ArticleFig(id=1175387067090616497, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, label=图10, caption=LSTM模型的泄漏故障诊断结果的混淆矩阵比较, figureFileSmall=AWmF9T4dGDUqRKzX8stJeg==, figureFileBig=OT6RZi9f4P28mMavhYyCHg==, tableContent=null), ArticleFig(id=1175387067149336754, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, label=Table 1, caption=

The hyperparameters of CNN-Transformer model

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 参数
编码器数量 4 输入维度 47
单序列长度 16 词嵌入维度 64
注意力层数 4 注意力头数 4
批次数 64 正则化值 0.1
激活函数 ReLU 学习率 0.000 03
卷积位置参数 3 卷积核步长 1
), ArticleFig(id=1175387067216445619, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, label=表1, caption=

CNN-Transformer模型超参数

, figureFileSmall=null, figureFileBig=null, tableContent=
参数 参数
编码器数量 4 输入维度 47
单序列长度 16 词嵌入维度 64
注意力层数 4 注意力头数 4
批次数 64 正则化值 0.1
激活函数 ReLU 学习率 0.000 03
卷积位置参数 3 卷积核步长 1
), ArticleFig(id=1175387067287748788, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=EN, label=Table 2, caption=

The comparison of accuracy of different leakage fault diagnosis methods

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 准确率/%
CNN-Transformer 90.30
CNN 85.68
Transformer 84.20
GRU 82.81
LSTM 77.09
), ArticleFig(id=1175387067350663349, tenantId=1146029695717560320, journalId=1146123166801305609, articleId=1149773874100925241, language=CN, label=表2, caption=

不同泄漏故障诊断方法准确率的对比

, figureFileSmall=null, figureFileBig=null, tableContent=
方法 准确率/%
CNN-Transformer 90.30
CNN 85.68
Transformer 84.20
GRU 82.81
LSTM 77.09
)], attaches=null, journal=Journal(id=1146119176004939786, delFlag=0, nameCn=科学技术与工程, nameEn=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, issn=1671-1815, eissn=, cn=11-4688/T, coden=null, periodic=4, language=CN, oaType=是, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=UKU/O7GSka5polgCTkbIIw==, journalPrice=null, startedYear=null, abbrevIsoEn=Sci Technol Eng, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1754445529766, createdBy=null, updatedBy=13701087609, firstLetterCn=S, firstLetterEn=S, subjectCode=Natural Sciences, subjectName=自然科学, subjectCodeEn=Natural Sciences, subjectNameEn=null, picCn=UKU/O7GSka5polgCTkbIIw==, picEn=5hwlULoNwcbj3xUmVi9MAQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1159791870395564357, language=CN, name=科学技术与工程, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529793, updatedTime=1754445529793, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=http://www.stae.com.cn/jsygc/site/menus/20090429150146001, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1159791870441701702, language=EN, name=Science Technology and Engineering, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://www.stae.com.cn/jsygc/home, createdTime=1754445529804, updatedTime=1754445529804, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=http://www.stae.com.cn/jsygc/author/login, submissionEditorUrl=http://www.stae.com.cn/jsygc/editor/login, submissionReviewUrl=http://www.stae.com.cn/jsygc/reviewer/login, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1146123166801305609, websiteList=[Website(id=1148243202391400884, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/CN, language=CN, createTime=1751692112777, createBy=18614031015, updateTime=1753520965431, updateBy=18614031015, name=科学技术与工程-中文站点, tplId=1146099689490845704, title=科学技术与工程, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148622798802673703, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=articleTextType, value=kx, createTime=1751782615614, updateTime=1751782615614, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798781702180, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=banner, value=null, createTime=1751782615609, updateTime=1751782615609, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798769119267, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1751782615606, updateTime=1751782615606, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798794285094, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751782615612, updateTime=1751782615612, creator=18614031015, updator=18614031015), WebsiteProps(id=1148622798790090789, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202391400884, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751782615611, updateTime=1751782615611, creator=18614031015, updator=18614031015)]), Website(id=1155914124811976731, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146123166801305609, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/kxjsygc/EN, language=EN, createTime=1753521003206, createBy=18614031015, updateTime=1753521003206, updateBy=18614031015, name=科学技术与工程-英文站点, tplId=1146101810881728533, title=Science Technology and Engineering, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155914371227308235, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=articleTextType, value=kx, createTime=1753521061952, updateTime=1753521061952, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371210531016, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=banner, value=null, createTime=1753521061947, updateTime=1753521061947, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371202142407, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=j86gbwi+p0Idkyl5SzIlmQ==, createTime=1753521061945, updateTime=1753521061945, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371223113930, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753521061950, updateTime=1753521061950, creator=18614031015, updator=18614031015), WebsiteProps(id=1155914371218919625, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155914124811976731, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753521061949, updateTime=1753521061949, creator=18614031015, updator=18614031015)])], journalTitle=科学技术与工程, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Science Technology and Engineering, journalPhotoCn=UKU/O7GSka5polgCTkbIIw==, journalPhotoEn=5hwlULoNwcbj3xUmVi9MAQ==, journalFirstLetter=S, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=null, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2404698, detailUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2404698, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kxjsygc/CN/PDF/10.12404/j.issn.1671-1815.2404698, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kxjsygc/EN/PDF/10.12404/j.issn.1671-1815.2404698, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于卷积神经网络和Transformer的供热管网泄漏故障诊断
收藏切换
PDF下载
梁晓龙 1 , 李金刚 1 , 徐平平 1 , 王佳龙 2 , 刘杰杰 3 , 陈涛 3 , 孟现阳 3, *
科学技术与工程 | 论文·建筑科学 2025,25(13): 5589-5601
收起
收藏切换
科学技术与工程 | 论文·建筑科学 2025, 25(13): 5589-5601
基于卷积神经网络和Transformer的供热管网泄漏故障诊断
全屏
梁晓龙1 , 李金刚1, 徐平平1, 王佳龙2, 刘杰杰3, 陈涛3, 孟现阳3, *
作者信息
  • 1 国能宁夏供热有限公司, 银川 750004
  • 2 国能数智科技开发(北京)有限公司, 北京 100040
  • 3 西安交通大学热流科学与工程教育部重点实验室, 西安 710049
  • 梁晓龙(1991—),男,汉族,宁夏银川人,工程师。研究方向:信息化与智慧化供热。E-mail:

通讯作者:

* 孟现阳(1978—),男,汉族,河南清丰人,博士,教授。研究方向:能源系统优化。E-mail:
Leakage Fault Diagnosis of Heating Network Based on CNN-Transformer
Xiao-long LIANG1 , Jin-gang LI1, Ping-ping XU1, Jia-long WANG2, Jie-jie LIU3, Tao CHEN3, Xian-yang MENG3, *
Affiliations
  • 1 National energy Ningxia heating Co. , Ltd. , Yinchuan 750004, China
  • 2 National Energy Digital Intelligence Technology Development (Beijing) Co. , Ltd. , Beijing 100040, China
  • 3 Key Laboratory of Heat Flow Science and Engineering, Ministry of Education, Xi'an Jiaotong University, Xi'an 710049, China
出版时间: 2025-05-08 doi: 10.12404/j.issn.1671-1815.2404698
文章导航
收藏切换

区域供热网络泄漏故障在线高效监测可以减少检修反映时间,保障居民的用热需求。然而,常规泄漏故障诊断方法的数据特征提取能力有限,难以处理复杂供热网络高维度非线性压力流量监测数据,使得其诊断性能较弱。因此,提出了一种基于卷积神经网络(convolutional neural networks, CNN)和Transformer的供热管网泄漏故障诊断模型。提出的CNN-Transformer诊断模型将CNN与Transformer网络相结合,实现了不同时间尺度和空间特征的联合学习。其中CNN网络用于提取局部特征,Transformer网络用于捕获全局特征。通过模拟环状供热管网系统得到的故障数据集验证了模型的有效性。结果表明,提出的基于故障特征的多级特征提取与融合机制的CNN-Transforme诊断模型,显著提升了泄漏诊断的准确率。CNN-Transformer方法在测试集上准确率最高,与其他故障诊断方法(长短期记忆循环网络、门控循环网络、CNN和Transformer)相比,在测试集上的准确率分别提高了13.21%、7.49%、6.1%和4.62%。

区域供热网络  /  管道泄漏  /  故障诊断  /  数据驱动  /  深度学习

On-line and efficient monitoring of leakage faults in district heating network can effectively increase the quality of heat transmission and reduce energy consumption. However, the data feature extraction ability of conventional leakage fault diagnosis method is limited, and it is difficult to deal with the high dimensional nonlinear pressure flow monitoring data for complex heating network, which makes its diagnostic performance weak. Therefore, a fault diagnosis model of heating network leakage based on convolutional neural network (CNN) and Transformer was proposed. The proposed CNN-Transformer diagnostic model combines CNN and Transformer network to realize joint learning of different time scales and spatial features. The CNN network was used to extract local features, and the Transformer network was used to capture global features. The validity of the model was verified by simulating the fault data set of the annular heating pipe network system. The results show that the proposed CNN-Transformer diagnosis model based on multi-stage feature extraction and fusion mechanism of fault features significantly improves the accuracy of leak diagnosis. The CNN-Transformer method has the highest accuracy on the test set, with an accuracy increase of 13.21%, 7.49%, 6.1% and 4.62%, respectively, compared to other fault diagnosis methods including long short-term memory network, gate recurrent network, CNN and Transformer.

district heating network  /  pipeline leakage  /  fault diagnosis  /  data-driven  /  deep learning
梁晓龙, 李金刚, 徐平平, 王佳龙, 刘杰杰, 陈涛, 孟现阳. 基于卷积神经网络和Transformer的供热管网泄漏故障诊断. 科学技术与工程, 2025 , 25 (13) : 5589 -5601 . DOI: 10.12404/j.issn.1671-1815.2404698
Xiao-long LIANG, Jin-gang LI, Ping-ping XU, Jia-long WANG, Jie-jie LIU, Tao CHEN, Xian-yang MENG. Leakage Fault Diagnosis of Heating Network Based on CNN-Transformer[J]. Science Technology and Engineering, 2025 , 25 (13) : 5589 -5601 . DOI: 10.12404/j.issn.1671-1815.2404698
区域供热系统是将不同品质的热能作为热源,在供热站集中制取热量,通过热力管网系统输送给区域中分散热用户的城镇集中供热设施[1]。其中,区域供热网络是连接热能供给侧与需求侧的重要枢纽。就当前第三代及第四代区域供热系统而言,区域供热网络主要通过直埋地下的方式部署[2]。使得管网的故障问题难以避免,而管道泄漏是发生最频繁的故障形式。区域供热系统的泄漏故障会严重降低热能传输质量,增加能耗,因此,如何及时准确地检测泄漏故障是区域供热系统的安全经济运行亟须解决的研究问题[3]
为了保障区域供热网络的正常运行,通常利用压力流量等传感器来监管系统的运行状态。当系统发生泄漏故障时,流量和压力等参数会发生变化以帮助研究人员定位泄漏故障。基于此,已有学者提出了一些泄漏故障检测方法。Zhang等[4]提出了一种基于实时瞬态建模方法和负压波方法的诊断模型,泄漏工况通过对比不同工况下的管道瞬态流动差异进行判别。秦绪忠等[5]设计了一种基于管网阻力特性系数的供热网络泄漏诊断方法,通过分析管网不同区域的实测参数与该管段的阻力特性系数之间的关系,实现故障诊断和参数辨识。Lu等[6]将经验模态分解的噪声降噪方法与负压波方法结合,对管道泄漏位置进行定位,结果表明该方法可以保留压力信号的突变以及去噪后信号的平滑,使得压降识别更精确,提高了泄漏位置诊断准确率。韩为明[7]提出了一种针对直埋供热管网的红外成像及土壤温湿度方法,可以通过管道周围温湿度场分布检测管网泄漏位置。任冠企[8]提出了一种耦合粒子群算法和高斯混合模型的换热站泄漏故障诊断方法,其可以改进常规异常检测算法的收敛性。
随着人工智能技术的快速发展,基于机器学习的泄漏故障智能检测方法凭借其高效快速、数据驱动和无模型的独特优势,受到了广泛的关注。Xue等[9]提出了一种基于极限梯度提升树的供热网络泄漏故障诊断方法,其可以通过各管段流量压力的变化情况识别泄漏管道。崔建敏[10]利用支持向量机算法实现了建筑供暖系统的故障诊断分类。郝江勇等[11]提出了一种基于改进反向传播(back propagation,BP)模型的供热管网泄漏故障诊断模型,通过遗传蚁群算法优化BP模型的超参数,提高模型的收敛速度。杜永峰等[12]采用混沌蜂群算法来优化BP模型的权重和阈值,并将其应用于供热网络的泄漏故障检测,结果显示改进的算法诊断精度显著提高。然而,由于传统机器学习故障诊断方法模型结构简单,计算复杂度高,特征提取能力有限,这使得BP神经网络等传统方法难以应对复杂供热网络故障诊断。
深度学习作为现如今蓬勃发展的人工智能方法,通过学习和提取数据中的内在特征,可以快速建立观测数据和标签之间的相关性,已成功应用于数据分类、时间序列预测、机器翻译和计算机视觉等众多领域。近年来,基于深度学习的复杂工业系统故障检测研究也逐渐成为新的发展方向。Fan等[13]采用深度信念网络建立了区域供热网络泄漏故障诊断模型,实现管网泄漏位置的定位。张向宇等[14]提出了一个耦合同步挤压小波变换和Transformer的轴承早期故障诊断模型。孟宏宇等[15]建立了一种基于注意力机制的卷积神经网络(convolutional neural networks, CNN)和双向长短期记忆神经网络的飞行器直流微电网故障诊断模型。朱晋等[16]提出了一个结合CNN和门控循环神经网络(gate recurrent unit, GRU)的风力发电机电力传输变换器故障诊断模型。
通过上述研究综述可以看出,针对区域供热管网的泄漏故障诊断,现有研究仍然相对较少。同时,现存研究方法多采用较为简单的传统机器学习网络模型,其数据特征提取能力有限,使得模型对于复杂供热网络的诊断性能较弱。此外,由于区域供热网络通常涉及多个监测参数,如不同管道的压力、流量等,不同监测参数之间也存在复杂的相互作用关系,例如压力和流量之间的非线性关系,也使得流量、压力监测数据通常是大量的高维非线性数据,而深度学习方法具有较强的特征提取能力,是一种很有前途的故障诊断方法。因此,针对上述问题,现提出一种基于深度学习的区域供热网络泄漏故障诊断模型。通过结合CNN和Transformer网络,构建CNN-Transformer模型,提取数据序列的局部与全局特征信息,实现不同时间尺度和空间特征的联合学习。提出基于故障特征的多级特征提取与融合机制,从而提高供热网络泄漏故障诊断精度。
区域供热网络的实际水力动态工况十分复杂,为了简化供热网络的水力模型,综合现有研究文献,做出了如下的假设[17]
(1)供回水管网中的热流体被认为是连续不可压缩流体。
(2)整个供热网络被认为是准稳态。当发生泄漏时,压力和流量在瞬间做出改变,其响应时间忽略不计。
通常,区域供热网络发生泄漏故障可能会发生在供水(回水)管段或者节点位置。当管网发生泄漏故障后,供回水网络的流量和压力都会发生变化,这使得热网水力动态结构转变为非对称的空间管网建模问题[18]。因此,基于图论理论将复杂的空间管网动态拓扑结构表示为矩阵形式的网络结构。对于空间供热网络,根据节点连续性方程、伯努利方程和基本回路能量方程,供热网络水力数学模型[19]可以表示为
AG=Q
BfΔH=0
$\Delta H=S|G| G-D H$
式中:A为热网基本关联矩阵;G为热网中各管段质量流量组成的列向量;Q为热网中各节点处泄漏量组成的列向量;Bf为热网的基本回路矩阵;ΔH为热网中各管段首末两端压降组成的列向量;S为热网中各管段阻抗系数对角矩阵; G为热网中各管段组成质量流量绝对值对角矩阵;DH为热网中各管段水泵扬程组成的列向量,当该管段不含水泵时,DH=0。
建立完供热网络的水力数学模型后,热网中各管段阻抗系数和水泵扬程也均为确定参数,进一步采用基本回路分析法进行计算求解管段节点拓扑结构方程组,从而求得泄漏故障发生时各管段压力及流量值。求解的流程图如图1所示。由于篇幅的限制,水力模型求解不是核心工作,详细求解过程参见文献[9,13]。
为了有效地诊断供热网络的泄漏故障,保障供热网络的稳定高效运行,提出了一种CNN-Transformer结构的深度学习故障诊断网络模型。其中CNN擅长处理多维序列数据,能够有效提取局部特征。而Transformer则通过其自注意力机制,能够处理数据的全局依赖关系,捕获长距离的数据关联。在供热网络泄漏诊断中,CNN-Transformer模型能够同时处理来自供热网络的多种数据类型,如压力和流量等指标。CNN部分对这些数据进行局部特征提取,例如识别特定区域的异常压力变化。而Transformer部分对整个网络的数据进行分析,最后结合两个部分提取的特征来识别可能的泄漏模式。提出的CNN-Transformer模型不仅能够诊断现有的泄漏,还能进行实时监控,提前发现潜在的故障。这可以大大减少突发故障的可能性,保障供热系统的连续运行。
CNN是由卷积层、激活层、池化层和全连接层组成的深层前馈神经网络,被广泛应用于图像识别、数据分类、自然语言处理等领域。卷积层通过对输入数据应用不同的滤波器,能够捕捉到各种空间关联,进一步提取输入数据中的局部特征[20]。激活层用于引入非线性,使网络能够学习更复杂的模式。池化层用于减少数据的空间大小,从而降低计算复杂度。全连接层在CNN的末端,用于将前面卷积层和池化层学到的特征整合,进行最终的分类或回归。CNN通过逐层提取输入数据的特征来工作。在一个CNN中,第l层的净输入z(l)为第l-1层活性值a(l-1)和卷积核的卷积[21-22],即
$\boldsymbol{z}^{(l)}=\boldsymbol{w}^{(l)} \otimes \boldsymbol{a}^{(l-1)}+\boldsymbol{b}^{(l)}$
式(4)中:w(l)为可学习的权重向量;⊗为张量积乘法;b(l)为可学习的偏置向量。此外,CNN的卷积层中的每一神经元仅和前一层的某个局部窗口神经元相连接,构成了一个局部神经网络,并且同一层的神经元权重参数都是共享的。
Transformer是2017年由Google的研究者提出的深度学习模型架构。Transformer的基本结构包括编码器和解码器部分。编码器由多个相同的层堆叠而成,每层包含自注意力机制和前馈神经网络。解码器也由多个层构成,但在自注意力和前馈网络之外,还增加了一个编码器-解码器注意力层,用于关注编码器的输出。Transformer的核心概念是“自注意力机制”(Self-Attention),这一机制允许模型在处理一个序列时,可以考虑序列中的所有元素,并计算它们之间的关联度。同时,注意力机制作为向量的加权组合,自动学习输入数据对输出数据的贡献大小。这使得模型能够专注于特定的特征子集,同时过滤掉不相关的信息,从而表现出优秀的全局特征提取能力。在Transformer中,这种机制通过“查询(Query)”、“键(Key)”和“值(Value)”3个向量来实现[23]。自注意力机制[24-25]计算如下。
$\text { self-attention }(\boldsymbol{Q}, \boldsymbol{K}, \boldsymbol{V})=\boldsymbol{V}_{\text {softmax }}\left(\frac{\boldsymbol{K}^{\mathrm{T}} \boldsymbol{Q}}{\sqrt{D_{k}}}\right)$
$\left\{\begin{array}{l} \boldsymbol{Q}=\boldsymbol{W}_{q} \boldsymbol{H} \\ \boldsymbol{K}=\boldsymbol{W}_{k} \boldsymbol{H} \\ \boldsymbol{V}=\boldsymbol{W}_{v} \boldsymbol{H} \end{array}\right.$
式中:WqWkWv为3个投影系数矩阵;Dk为输入矩阵QK中列向量的维度。
多头注意力机制是单个自注意力机制的改进版本,将每个注意力操作分配给多个头部,从不同维度提取特征信息,即在多个线性空间内,QKV将经历不同的线性投影,以捕捉不同的交互信息[26]。最终多个输出直接连接并再次投影以获得最终值。多头注意力机制[27]可以表示为
$\operatorname{MultiHead}(\boldsymbol{H})=\boldsymbol{W}_{\mathrm{o}}\left[\operatorname{head}_{1}, \operatorname{head}_{2}, \cdots, \operatorname{head}_{m}\right]$
$\text { head }_{m}=\text { self-attention }\left(\boldsymbol{Q}_{m}, \boldsymbol{K}_{m}, \boldsymbol{V}_{m}\right)$
$\left\{\begin{array}{l} \boldsymbol{Q}_{m}=\boldsymbol{W}_{q}^{m} \boldsymbol{H} \\ \boldsymbol{K}_{m}=\boldsymbol{W}_{k}^{m} \boldsymbol{H} \\ \boldsymbol{V}_{m}=\boldsymbol{W}_{v}^{m} \boldsymbol{H} \end{array}\right.$
式中:Wo为输出投影矩阵; W q m W k m W v m为3个m头注意力的投影矩阵。
区域供热网络通常由多个热源站点和支路管线组成,当某节点发生泄漏故障时,不同管线的压力、流量等变量具有相似的内部水力变化机理。因此,不同位置泄漏故障的管线压力、流量之间具有相似的相关性,提取这些变量之间的潜在特征对于复杂供热管网泄漏故障诊断具有重要意义。现有的迁移学习模型通常使用CNN来提取数据特征。CNN通过卷积核可以提取相邻变量之间的信息,在局部特征提取方面表现出色。然而,CNN仅可以刻画相邻变量之间的特征(即相邻的管线流量压力关系),无法捕获长序列所有变量之间的关系,对于供热管网而言,即全局管线流量压力关系。而Transformer在处理长距离依赖关系方面表现优异,但在处理数据部分特征时缺乏CNN的局部感知能力。因此,结合两者的优势,提出了一种更合理的CNN-Transformer框架,来实现供热管网泄漏故障诊断。建立的模型可以同时捕捉数据局部特征和全局依赖关系。
图2为提出的CNN-Transformer的模型结构。构建的CNN-Transformer模型由并行的3个网络构成,其中2个CNN用于提取局部特征,1个Transformer用于捕获全局特征。初始化后的样本序列X=[x1,x2,…,xm]T分别输入到并行的3个网络中。输入Transformer网络中的数据被看作是长序列,并送入具有多头自注意力层的编码器模块中以取每种泄漏故障的全局结构特征。Transformer的注意力机制可获以提取样本序列中不同变量的全局关系,并且Transformer的输出包含原始样本中各变量的相关信息,这有助于更好地理解供热网络中各节点压力流量之间的相关性。此外,2个并列的CNN网络架构分别采用卷积核提取样本序列的局部特征。并列的CNN层通过扩展通道来增加特征图的复杂性,可以帮助网络学习到多样化的特征。最终,通过全连接层Dense实现2个CNN网络提取的局部特征和Transformer网络提取的全局特征的结合,并将其作为模型捕获的泄漏故障诊断信息,再通过归一化指数函数层输出故障类型分类结果。
提出的基于CNN-Transformer的供热管网泄漏故障诊断模型流程图如图3所示。故障诊断算法的具体步骤如下。
步骤1 数据收集和初始化。收集区域供热网络的运行数据(正常数据集和故障数据集),包括供热网络热源与管段的流量,供回水压力监测值和泄漏故障记录。进一步对数据集进行数据清洗和初始化,滤除噪声和异常值,并将其归一化,以便于模型处理。
步骤2 局部特征提取。使用CNN自动提取供热网络数据的特征。CNN能够从时间序列数据中识别出局部的时空特征,如突变点、周期性模式等,这些特征对于识别泄漏事件类型具有重要作用。
步骤3 全局特征提取。将初始化后的样本序列输入到Transformer模型中。Transformer通过自注意力机制能够捕捉时间序列数据中的长距离依赖关系,这有助于捕获供热网络中各节点压力流量的相关性。
步骤4 训练模型。使用历史的泄漏事件数据来训练CNN-Transformer模型。在训练过程中,模型学习如何从数据特征中区分正常运行状态和泄漏故障状态。训练完成后,进一步在独立的测试集上评估模型的性能,使用准确率指标来衡量模型在泄漏故障诊断任务上的效果。
步骤5 模型安装与部署。将训练好的模型部署到实际的供热网络监控系统中。模型将实时分析各网络节点传感器数据,对可能的泄漏事件进行识别和报警。一旦模型检测到潜在的泄漏事件,系统将触发一个故障诊断流程。自动关闭受影响区域的阀门,通知维修人员,并启动相关的检查维修工作。
步骤6 模型持续学习及更新。为了保持模型的准确性,需要定期使用新收集的数据来重新训练模型。这可以帮助模型适应供热网络运行的变化,以及新的泄漏模式。
为了验证前面建立的基于CNN-Transformer的供热管网泄漏故障诊断模型的性能,以环状供热管网系统作为案例进行仿真实验研究[28]图4图5为所选取的环状供热管网系统的供回水管网,整个系统共有1个热源,15个热力站,40条供/回水管段。管网的设计总环流量为2 196.4 m3/h,循环水泵的扬程为55 m,选取节点n1'为定压节点,其他节点为压力监测点。
参考实际供热管网系统,并非所有的管道节点配备传感器,环状供热管网系统案例共计有47个压力和流量监测点。其中,节点压力传感器和管段远程流量计安装在供回水管网的热源和换热站(除了回水管网的压力定压节点n1')。供热管网的泄漏位置包括节点泄漏和管段泄漏,其中管段泄漏发生在距离管道起点每隔10 m处以及管段起点和终点。设定泄漏量为额定循环流量的1%~4%。通过模拟各管段的不同泄漏位置发生不同泄漏程度的故障,总共可以得到15 115组供热管网泄漏故障模拟数据,其中50%的样本数据作为训练集,20%的样本数据作为验证集,30%的样本数据作为测试集。
基于CNN-Transformer的供热管网泄漏故障诊断模型使用交叉熵损失函数来判断模型实际的输出与期望的输出的接近程度。当模型无法预测正确的故障类别时,模型会被严重惩罚。采用计算和收敛速度更快的自适应矩估计(adaptive moment, Adam)优化器训练模型,模型超参数详细的设置如表1所示。
将提出的CNN-Transformer方法与其他泄漏故障诊断模型进行了比较,以证明新建立模型的有效性。实验比较了5种故障诊断方法:CNN-Transformer、长短期记忆循环神经网络(long short term memory, LSTM)、GRU、CNN和Transformer。供热管网系统的泄漏故障诊断是一个基于有监督学习的多分类问题,因此,采用77×77的混淆矩阵来表示不同模型的故障诊断结果,同时采用准确率作为模型的诊断精度评价指标,其计算公式为
A= T P T P + F P×100%
式(10)中:TP为故障预测正确样本数量;FP 为故障预测错误样本数量。
表2为不同故障诊断方法准确率的对比结果。如表2所示,与其他故障诊断方法相比,CNN-Transformer方法在测试集上准确率最高。相较于LSTM、GRU、CNN和Transformer,提出的CNN-Transformer方法的准确率分别提高了13.21%、7.49%、6.1%和4.62%。尽管CNN和Transformer两种诊断方法都获得了相对较好的准确率,但CNN-Transformer仍然有所提高,达到90.30%。CNN-Transformer模型通过结合了Transformer提取的全局变量关系和CNN捕获的局部数据特征,增强了样本数据特征的高可判别性。
图6~图10对比了不同模型在测试集下的泄漏故障诊断结果的混淆矩阵,混淆矩阵横轴表示预测的故障类别,纵轴表示实际的故障类别。以热度图的形式可视化混淆矩阵,将原混淆矩阵中每列中的故障类别结果计数值作归一化处理来表示该故障识别结果的热力值,值域为[0,1]。从图6中可以看出,混淆矩阵的主对角线热力值均近似为1,而非主对角线上的热力值均近似为0,这说明所建立的CNN-Transformer模型可以通过输入的部分节点管段流量监测值,准确地识别出不同位置的泄漏故障。尽管在测试集的个别故障工况下,模型给出了不正确的发生泄漏故障管道位置,但是输出的不正确预测结果与真实泄漏位置总是相邻的,这也极大地帮助了系统维护人员快速定位到泄漏位置。上述结果也验证了所建立的供热管网泄漏故障诊断模型的高准确率检测性能和可靠性。同时,将实时收集的47个压力和流量监测点数据导入训练好的CNN-Transformer模型中,可以对供回水管网77个管段实时在线监测,并诊断其是否发生泄漏故障。因此,仅通过布置47个传感器,实现77个供回水管段进行监测,相较于在每个管段和节点布置传感器,提出的方法可以在安装较少管线流量压力传感器的情况下,实现供热管网泄漏故障位置的准确诊断和检测,从而节省安装投资成本,保障管网安全稳定运行。
针对复杂供热网络的泄漏管道难以精准定位的问题,提出了一种基于CNN-Transformer的泄漏故障诊断模型。提出的CNN-Transformer可以提取供热管网实时监测压力流量的数据序列特征,进行在线定位供热网络泄漏管线的位置,得出的结论如下。
(1)提出的模型结合了CNN和Transformer网络,CNN部分进行数据局部特征提取,而Transformer部分通过其自注意力机制,捕获全局数据依赖关系,最后结合两个部分提取的特征来识别可能的泄漏模式。
(2)与其他故障诊断方法相比,CNN-Transformer方法在测试集上准确率最高。相较于LSTM、GRU、CNN和Transformer,提出的CNN-Transformer方法的准确率分别提高了13.21%、7.49%、6.1%和4.62%。
(3)在未来的工作中,将进一步研究基于数据驱动的两级复杂环状供热管网泄漏故障诊断模型,其中如何精准识别故障发生复杂环状供热网络管段泄漏点位置将是工作的重点。
  • 国家自然科学基金(51976164)
  • 陕西省自然科学基础研究计划(2024JC-YBMS-257)
参考文献 引证文献
排序方式:
[1]
Vallee M, Wissocq T, Gaoua Y, et al. Generation and evaluation of a synthetic dataset to improve fault detection in district heating and cooling systems[J]. Energy, 2023, 283: 128387.
[2]
Liu J, Li X, Zhang Q, et al. An efficient sensor and thermal coupling fault diagnosis methodology for building energy systems[J]. Energy & Buildings, 2023, 296: 113367.
[3]
Neumayer M, Stecher D, Grimm S, et al. Fault and anomaly detection in district heating substations: a survey on methodology and data sets[J]. Energy, 2023, 276: 127569.
[4]
Zhang T, Tan Y, Zhang X, et al. A novel hybrid technique for leak detection and location in straight pipelines[J]. Journal of Loss Prevention in the Process Industries, 2015, 35: 157-168.
[5]
秦绪忠, 江亿. 区域热网管网阻力系数的在线辨识与故障诊断[J]. 清华大学学报(自然科学版), 2000, 40(2): 81-85.
Qin Xuzhong, Jiang Yi. Identification of flow resistance coefficient and fault diagnosis in district heating networks[J]. Journal of Tsinghua University (Science and Technology), 2000, 40(2): 81-85.
[6]
Lu W, Liang W, Zhang L, et al. A novel noise reduction method applied in negative pressure wave for pipeline leakage localization[J]. Process Safety and Environmental Protection, 2016, 104: 142-149.
[7]
韩为明. 热力管网泄漏的红外热像检测技术研究[D]. 天津: 河北工业大学, 2017.
Han Weiming. Research on the infrared thermographic technology of leakage in heating network[D]. Tianjin: Hebei University of Technology, 2017.
[8]
任冠企. 基于PSO-EM改进GMM的换热站故障诊断研究[D]. 大连: 大连海事大学, 2020.
Ren Guanqi. Research on fault diagnosis of heat exchange station based on improved GMM of PSO-EM[D]. Dalian: Dalian Maritime University, 2020.
[9]
Xue P, Jiang Y, Zhou Z, et al. Machine learning-based leakage fault detection for district heating networks[J]. Energy & Buildings, 2020, 223: 110161.
[10]
崔建敏. 基于支持向量机的供暖系统智能诊断方法研究[D]. 哈尔滨: 哈尔滨工业大学, 2021.
Cui Jianmin. Research on the intelligent diagnosis method of heating system based on support vector machine[D]. Harbin: Harbin Institute of Technology, 2021.
[11]
郝江勇, 段鹏飞, 杜永峰, 等. 一种GA-ACO-BP模型的热网泄漏故障诊断研究[J]. 太原理工大学学报, 2024, 55(2): 338-347.
Hao Jiangyong, Duan Pengfei, Du Yongfeng, et al. A study on fault diagnosis of heat network leakage based on GA-ACO-BP model[J]. Journal of Taiyuan University of Technology, 2024, 55(2): 338-347.
[12]
杜永峰, 段鹏飞, 赵秉旭, 等. 基于CABC-BP模型的供热管网泄漏诊断研究[J]. 广西大学学报(自然科学版), 2023, 48(4): 835-846.
Du Yongfeng, Duan Pengfei, Zhao Bingxu, et al. Leakage diagnosis model of heating pipe network based on CABC optimization of BP neural network[J]. Journal of Guangxi University (Natural Science Edition), 2023, 48(4): 835-846.
[13]
Fan Q, Guo Y, Wu S, et al. Two-level diagnosis of heating pipe network leakage based on deep belief network[J]. IEEE Access, 2019, 7: 182983-182992.
[14]
张向宇, 王衍学. 基于同步挤压小波变换和Transformer的轴承故障诊断模型[J]. 机电工程, 2024, 41(6): 1011-1019.
Zhang Xiangyu, Wang Yanxue. Fault diagnosis model of rolling bearing based on synchro squeezing wavelet transform (SST) and Transformer[J]. Journal of Mechanical & Electrical Engineering, 2024, 41(6): 1011-1019.
[15]
孟宏宇, 张建良, 蔡兆龙, 等. 基于CNN-BiLSTM-Attention的直流微电网故障诊断研究[J/OL]. 中国电机工程学报, 1-12[2025-02-20]. http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html. http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html
Meng Hongyu, Zhang Jianliang, Cai Zhaolong, et al. Research on DC microgrid fault diagnosis based on CNN-BiLSTM-Attention[J/OL]. Proceedings of the CSEE, 1-12[2025-02-20]. http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html. http://kns.cnki.net/kcms/detail/11.2107.TM.20231213.1111.002.html
[16]
朱晋, 程启明, 程尹曼. 基于CNN-GRU深度学习的模块化多电平矩阵变换器故障诊断[J]. 南方电网技术, 2024, 18(11): 13-22.
Zhu Jin, Cheng Qiming, Cheng Yinman. Fault diagnosis of modular multilevel matrix converter based on CNN-GRU deep learning[J]. Southern Power System Technology, 2024, 18(11): 13-22.
[17]
王晓霞, 赵立华, 邹平华, 等. 基于图论的空间热网拓扑结构[J]. 计算物理, 2014, 31(2): 207-215.
Wang Xiaoxia, Zhao Lihua, Zou Pinghua, et al. Topology structure of spatial heat-supply network based on graph theory[J]. Chinese Journal of Computational Physics, 2014, 31(2): 207-215.
[18]
雷翠红. 供热管网泄漏故障诊断的研究[D]. 哈尔滨: 哈尔滨工业大学, 2010.
Lei Cuihong. Study on leakage fault diagnosis for heating supply network[D]. Harbin: Harbin Institute of Technology, 2010.
[19]
王晓霞, 邹平华. 多热源环状空间热网拓扑结构研究[J]. 暖通空调, 2009, 39(2): 1-4.
Wang Xiaoxia, Zou Pinghua. Topological structure of multi-heat source ring-shaped heat-supply network[J]. Heating Ventilating & Air Conditioning, 2009, 39(2): 1-4.
[20]
丁津津, 邵庆祝, 齐振兴, 等. 基于迁移学习的卷积神经网络电网故障诊断[J]. 科学技术与工程, 2022, 22(14): 5653-5658.
Ding Jinjin, Shao Qingzhu, Qi Zhenxing, et al. CNN distribution network fault diagnosis method based on Transfer learning[J]. Science Technology and Engineering, 2022, 22(14): 5653-5658.
[21]
孙祺淳, 李媛媛. DE算法优化CNN的滚动轴承故障诊断研究[J]. 噪声与振动控制, 2022, 42(4): 165-171.
Sun Qichun, Li Yuanyuan. Research on fault diagnosis of rolling bearings based on DE algorithm optimization of CNN[J]. Noise and Vibration Control, 2022, 42(4): 165-171.
[22]
郝旺身, 陈耀, 孙浩, 等. 基于全矢-CNN的轴承故障诊断研究[J]. 郑州大学学报(工学版), 2020, 41(5): 92-96.
Hao Wangshen, Chen Yao, Sun Hao, et al. Bearing fault diagnosis based on full vector-CNN[J]. Journal of Zhengzhou University (Engineering Science), 2020, 41(5): 92-96.
[23]
汤翔中, 高丙朋. 融合注意力空洞卷积和Transformer的矿石图像分割[J]. 科学技术与工程, 2023, 23(16): 6974-6982.
Tang Xiangzhong, Gao Binpeng. Ore image segmentation based on attention hole convolution and Transformer[J]. Science Technology and Engineering, 2023, 23(16): 6974-6982.
[24]
Fan C, Lei Y, Sun Y, et al. Novel transformer-based self-supervised learning methods for improved HVAC fault diagnosis performance with limited labeled data[J]. Energy, 2023, 278: 127972.
[25]
李赵春, 周永照, 冯卫奔, 等. 基于Transformer模型的手势脑电信号分类识别[J]. 科学技术与工程, 2023, 23 (5): 2044-2050.
Li Zhaochun, Zhou Yongzhao, Feng Weiben, et al. Gesture action electroencephalogram classification and recognition based on Transformer model[J]. Science Technology and Engineering, 2023, 23(5): 2044-2050.
[26]
杜康宁, 宁少慧. 基于ADASYN和Swin Transformer的滚动轴承故障诊断研究[J]. 机床与液压, 2023, 51(15): 209-215.
Du Kangning, Ning Shaohui. Study of rolling bearing fault diagnosis based on ADASYN and Swin Transformer[J]. Machine Tool & Hydraulics, 2023, 51(15): 209-215.
[27]
Zhao J, Feng X, Wang J, et al. Battery fault diagnosis and failure prognosis for electric vehicles using spatio-temporal transformer networks[J]. Applied Energy, 2023, 352: 121949.
[28]
Xue P, Jiang Y, Zhou Z, et al. Data for: machine learning-based leakage fault detection for district heating networks[DB/OL]. (2020-02-14) [2024-06-24]. https://data.mendeley.com/datasets/sh72jwth68/1. https://data.mendeley.com/datasets/sh72jwth68/1
2025年第25卷第13期
PDF下载
316
117
引用本文
BibTeX
文章信息
doi: 10.12404/j.issn.1671-1815.2404698
  • 接收时间:2024-06-24
  • 首发时间:2025-07-09
  • 出版时间:2025-05-08
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-06-24
  • 修回日期:2025-02-06
基金
国家自然科学基金(51976164)
陕西省自然科学基础研究计划(2024JC-YBMS-257)
作者信息
    1 国能宁夏供热有限公司, 银川 750004
    2 国能数智科技开发(北京)有限公司, 北京 100040
    3 西安交通大学热流科学与工程教育部重点实验室, 西安 710049

通讯作者:

* 孟现阳(1978—),男,汉族,河南清丰人,博士,教授。研究方向:能源系统优化。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kxjsygc/CN/10.12404/j.issn.1671-1815.2404698
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