Article(id=1236596125436801094, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1236596124832821317, articleNumber=null, orderNo=null, doi=10.19666/j.rlfd.202408222, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1724774400000, receivedDateStr=2024-08-28, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1772757091148, onlineDateStr=2026-03-06, pubDate=1748102400000, pubDateStr=2025-05-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1772757091148, onlineIssueDateStr=2026-03-06, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1772757091148, creator=13701087609, updateTime=1772757091148, updator=13701087609, issue=Issue{id=1236596124832821317, tenantId=1146029695717560320, journalId=1210938733613449225, year='2025', volume='54', issue='5', pageStart='1', pageEnd='162', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=0, articleOrder=1, issueType=-1, specialIssue=null, createTime=1772757091004, creator=13701087609, updateTime=1772757664851, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1236598531780309922, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1236596124832821317, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1236598531780309923, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1236596124832821317, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=132, endPage=139, ext={EN=ArticleExt(id=1236596125763956810, articleId=1236596125436801094, tenantId=1146029695717560320, journalId=1210938733613449225, language=EN, title=Prediction of key indicators of utility boiler based on multi-task uncertainty loss, columnId=1236596125684265033, journalTitle=Thermal Power Generation, columnName=Power generation technology, runingTitle=null, highlight=null, articleAbstract=

With the increasing demand for flexible operation of power plant boilers, frequent variable-load operation leads to a wide range of fluctuations in pollutant concentrations and flue gas parameters. Modeling of key indicators such as single pollutant or flue gas parameter can no longer meet the actual demand, so it is necessary to consider the coupling of multiple key indicators for synergistic predictive modeling. Based on the historical operation data of coal-fired power plants, feature extraction is performed through kernel function mapping, and a long short-term memory neural network with a hard parameter sharing structure is constructed for multi task prediction modeling. The prediction model is optimized using uncertainty loss methods. The experimental results show that, the proposed prediction model exhibits high prediction accuracy under variable load conditions, and the prediction errors for the key metrics involved in this study are reduced by 25.5%, 41.8% and 4.7%, respectively. The proposed method is capable of predicting several key indicators of utility boilers under variable load conditions, which can assist power plants to achieve pollution control and optimize the thermal efficiency of combustion, and provide technical support for intelligent operation of power plants.

, 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=Yufei WANG, Nan LI, Gang XIE, Xiaohong ZHANG, Xiaoyin NIE, Yong ZHOU), CN=ArticleExt(id=1236596128528003211, articleId=1236596125436801094, tenantId=1146029695717560320, journalId=1210938733613449225, language=CN, title=基于多任务不确定性损失的电站锅炉关键指标预测, columnId=1211002409581679375, journalTitle=热力发电, columnName=发电技术论坛, runingTitle=null, highlight=null, articleAbstract=

随着电站锅炉灵活运行需求的增加,频繁的变负荷运行导致污染物含量和烟气参数大范围波动,对单一污染物或烟气参数等关键指标进行建模已无法满足电厂实际需求,因此需要考虑多种关键指标的耦合性进行协同预测建模。基于燃煤电厂的历史运行数据,通过核函数映射进行特征提取,构建硬参数共享结构的长短时记忆神经网络进行多任务预测建模,利用不确定性损失的方法优化预测模型。实验结果表明,所提出的预测模型在变负荷工况下表现出较高的预测精度,对于所涉及的关键指标空气预热器出口烟气含氧量、烟气温度、炉膛出口NOx质量浓度的预测,均方根误差分别降低了25.5%、41.8%和4.7%。所提方法能够在变负荷工况下对电站锅炉多个关键指标进行预测,能够辅助电厂实现污染控制和燃烧效率优化,可为电厂智能化运行提供技术支持。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
谢刚(1972),男,博士,教授,主要研究方向为人工智能技术及其应用,
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=jYlx4RdI9Jgs30u5qmEkCQ==, magXml=diwM4sd6REMZ8Pq1x41QiQ==, pdfUrl=null, pdf=gzLr8zWJQYQ94qj06sFIng==, pdfFileSize=1768305, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=SsE0oigDB9V4/cmotkNdlg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=IpHBmkY2WHJn/wJ1ZbrwiA==, mapNumber=null, authorCompany=null, fund=null, authors=

王宇飞(1996),女,博士研究生,主要研究方向为燃煤发电过程建模、控制与优化,

, authorsList=王宇飞, 李楠, 谢刚, 张晓红, 聂晓音, 周勇)}, authors=[Author(id=1236610615498822447, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=b202215110034@stu.tyust.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1236610615607874359, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, authorId=1236610615498822447, language=EN, stringName=Yufei WANG, firstName=Yufei, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Shanxi Key Laboratory of Advanced Control and Industrial Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1236610615704343356, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, authorId=1236610615498822447, language=CN, stringName=王宇飞, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.太原科技大学先进控制与工业智能山西省重点实验室,山西 太原 030024, bio={"content":"

王宇飞(1996),女,博士研究生,主要研究方向为燃煤发电过程建模、控制与优化,

"}, bioImg=null, bioContent=

王宇飞(1996),女,博士研究生,主要研究方向为燃煤发电过程建模、控制与优化,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1236610615209415454, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, xref=1., ext=[AuthorCompanyExt(id=1236610615217804064, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615209415454, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Shanxi Key Laboratory of Advanced Control and Industrial Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, China), AuthorCompanyExt(id=1236610615226192673, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615209415454, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.太原科技大学先进控制与工业智能山西省重点实验室,山西 太原 030024)])]), Author(id=1236610615805006661, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, 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=1236610615884698443, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, authorId=1236610615805006661, language=EN, stringName=Nan LI, firstName=Nan, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Shanxi Key Laboratory of Advanced Control and Industrial Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1236610615981167439, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, authorId=1236610615805006661, language=CN, stringName=李楠, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.太原科技大学先进控制与工业智能山西省重点实验室,山西 太原 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1236610615209415454, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, xref=1., ext=[AuthorCompanyExt(id=1236610615217804064, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615209415454, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Shanxi Key Laboratory of Advanced Control and Industrial Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, China), AuthorCompanyExt(id=1236610615226192673, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615209415454, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.太原科技大学先进控制与工业智能山西省重点实验室,山西 太原 030024)])]), Author(id=1236610616060859222, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, orderNo=2, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=xiegang@tyust.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1236610616144745306, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, authorId=1236610616060859222, language=EN, stringName=Gang XIE, firstName=Gang, middleName=null, lastName=XIE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Shanxi Key Laboratory of Advanced Control and Industrial Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1236610616237019998, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, authorId=1236610616060859222, language=CN, stringName=谢刚, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.太原科技大学先进控制与工业智能山西省重点实验室,山西 太原 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1236610615209415454, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, xref=1., ext=[AuthorCompanyExt(id=1236610615217804064, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615209415454, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Shanxi Key Laboratory of Advanced Control and Industrial Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, China), AuthorCompanyExt(id=1236610615226192673, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615209415454, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.太原科技大学先进控制与工业智能山西省重点实验室,山西 太原 030024)])]), Author(id=1236610616350266214, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, 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=1236610616471901035, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, authorId=1236610616350266214, language=EN, stringName=Xiaohong ZHANG, firstName=Xiaohong, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Shanxi Key Laboratory of Advanced Control and Industrial Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1236610616551592816, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, authorId=1236610616350266214, language=CN, stringName=张晓红, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.太原科技大学先进控制与工业智能山西省重点实验室,山西 太原 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1236610615209415454, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, xref=1., ext=[AuthorCompanyExt(id=1236610615217804064, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615209415454, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Shanxi Key Laboratory of Advanced Control and Industrial Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, China), AuthorCompanyExt(id=1236610615226192673, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615209415454, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.太原科技大学先进控制与工业智能山西省重点实验室,山西 太原 030024)])]), Author(id=1236610616631284599, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, 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=1236610616752919421, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, authorId=1236610616631284599, language=EN, stringName=Xiaoyin NIE, firstName=Xiaoyin, middleName=null, lastName=NIE, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Shanxi Key Laboratory of Advanced Control and Industrial Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1236610616874554245, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, authorId=1236610616631284599, language=CN, stringName=聂晓音, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.太原科技大学先进控制与工业智能山西省重点实验室,山西 太原 030024, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1236610615209415454, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, xref=1., ext=[AuthorCompanyExt(id=1236610615217804064, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615209415454, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Shanxi Key Laboratory of Advanced Control and Industrial Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, China), AuthorCompanyExt(id=1236610615226192673, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615209415454, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.太原科技大学先进控制与工业智能山西省重点实验室,山西 太原 030024)])]), Author(id=1236610616966828942, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, 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=1236610617092658068, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, authorId=1236610616966828942, language=EN, stringName=Yong ZHOU, firstName=Yong, middleName=null, lastName=ZHOU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Shanxi Huaguang Power Generation Co., Ltd., Lüliang 033399, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1236610617193321369, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, authorId=1236610616966828942, language=CN, stringName=周勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.山西华光发电有限责任公司,山西 吕梁 033399, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1236610615356216104, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, xref=2., ext=[AuthorCompanyExt(id=1236610615372993321, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615356216104, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Shanxi Huaguang Power Generation Co., Ltd., Lüliang 033399, China), AuthorCompanyExt(id=1236610615381381930, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615356216104, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.山西华光发电有限责任公司,山西 吕梁 033399)])])], keywords=[Keyword(id=1236610617474339749, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=EN, orderNo=1, keyword=coal-fired boiler), Keyword(id=1236610617604363180, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=EN, orderNo=2, keyword=prediction model), Keyword(id=1236610617738580916, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=EN, orderNo=3, keyword=LSTM neural network), Keyword(id=1236610617872798651, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=EN, orderNo=4, keyword=multi-task learning), Keyword(id=1236610618011210691, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=EN, orderNo=5, keyword=uncertainty loss), Keyword(id=1236610618153817035, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=CN, orderNo=1, keyword=燃煤锅炉), Keyword(id=1236610618275451858, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=CN, orderNo=2, keyword=预测模型), Keyword(id=1236610618363532249, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=CN, orderNo=3, keyword=LSTM神经网络), Keyword(id=1236610618472584160, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=CN, orderNo=4, keyword=多任务学习), Keyword(id=1236610618703270884, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=CN, orderNo=5, keyword=不确定性损失)], refs=[Reference(id=1236610621718974603, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=3, pageStart=166, pageEnd=174, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=高耀岿, 王林, 高海东, journalName=热力发电, refType=null, unstructuredReference=高耀岿, 王林, 高海东, 等. 火电厂智能控制系统体系架构及关键技术[J]. 热力发电, 2022, 51(3): 166-174., articleTitle=火电厂智能控制系统体系架构及关键技术, refAbstract=null), Reference(id=1236610621840609424, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=3, pageStart=166, pageEnd=174, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=GAO Yaokui, WANG Lin, GAO Haidong, journalName=Thermal Power Generation, refType=null, unstructuredReference=GAO Yaokui, WANG Lin, GAO Haidong, et al. Architecture and key technology of intelligent control system in thermal power plant[J]. Thermal Power Generation, 2022, 51(3): 166-174., articleTitle=Architecture and key technology of intelligent control system in thermal power plant, refAbstract=null), Reference(id=1236610621949661332, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=11, pageStart=993, pageEnd=1004, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=刘吉臻, 李云鸷, 宋子秋, journalName=动力工程学报, refType=null, unstructuredReference=刘吉臻, 李云鸷, 宋子秋, 等. 灵活智能燃煤发电技术及评价体系[J]. 动力工程学报, 2022, 42(11): 993-1004., articleTitle=灵活智能燃煤发电技术及评价体系, refAbstract=null), Reference(id=1236610622037741720, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=11, pageStart=993, pageEnd=1004, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=LIU Jizhen, LI Yunzhi, SONG Ziqiu, journalName=Journal of Chinese Society of Power Engineering, refType=null, unstructuredReference=LIU Jizhen, LI Yunzhi, SONG Ziqiu, et al. Flexible and intelligent coalfired power generation technology and its evaluation system[J]. Journal of Chinese Society of Power Engineering, 2022, 42(11): 993-1004., articleTitle=Flexible and intelligent coalfired power generation technology and its evaluation system, refAbstract=null), Reference(id=1236610622121627807, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2023, volume=417, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=NEMITALLAH M A, NABHAN M A, ALOWAIFEER M, journalName=Journal of Cleaner Production, refType=null, unstructuredReference=NEMITALLAH M A, NABHAN M A, ALOWAIFEER M, et al. Artificial intelligence for control and optimization of boilers’ performance and emissions: a review[J]. Journal of Cleaner Production, 2023, 417: 138109., articleTitle=Artificial intelligence for control and optimization of boilers’ performance and emissions: a review, refAbstract=null), Reference(id=1236610622247456930, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=6, pageStart=2080, pageEnd=2100, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=赵永亮, 许朋江, 居文平, journalName=中国电机工程学报, refType=null, unstructuredReference=赵永亮, 许朋江, 居文平, 等. 燃煤发电机组瞬态过程灵活高效协同运行的理论与技术研究综述[J]. 中国电机工程学报, 2023, 43(6): 2080-2100., articleTitle=燃煤发电机组瞬态过程灵活高效协同运行的理论与技术研究综述, refAbstract=null), Reference(id=1236610622373286058, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=6, pageStart=2080, pageEnd=2100, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=ZHAO Yongliang, XU Pengjiang, JU Wenping, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=ZHAO Yongliang, XU Pengjiang, JU Wenping, et al. Overview of theoretical and technical research on flexible and efficient synergistic operation of coal-fired power units during transient processes[J]. Proceedings of the CSEE, 2023, 43(6): 2080-2100., articleTitle=Overview of theoretical and technical research on flexible and efficient synergistic operation of coal-fired power units during transient processes, refAbstract=null), Reference(id=1236610622473949355, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2022, volume=15, issue=14, pageStart=5289, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=7, authorNames=ZHU C P, HUANG P, LI Y G, journalName=Energies, refType=null, unstructuredReference=ZHU C P, HUANG P, LI Y G. Closed-loop combustion optimization based on dynamic and adaptive models with application to a coal-fired boiler[J]. Energies, 2022, 15(14): 5289., articleTitle=Closed-loop combustion optimization based on dynamic and adaptive models with application to a coal-fired boiler, refAbstract=null), Reference(id=1236610622633332916, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2019, volume=170, issue=null, pageStart=804, pageEnd=817, url=null, language=null, rfNumber=[6], rfOrder=8, authorNames=SHI Y, ZHONG WEN Q, CHEN X, journalName=Energy, refType=null, unstructuredReference=SHI Y, ZHONG WEN Q, CHEN X, et al. Combustion optimization of ultra supercritical boiler based on artificial intelligence[J]. Energy, 2019, 170: 804-817., articleTitle=Combustion optimization of ultra supercritical boiler based on artificial intelligence, refAbstract=null), Reference(id=1236610622746579130, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2022, volume=256, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=TANG Z H, WANG S K, CHAI X Y, journalName=Energy, refType=null, unstructuredReference=TANG Z H, WANG S K, CHAI X Y, et al. Auto-encoder-extreme learning machine model for boiler NOx emission concentration prediction[J]. Energy, 2022, 256: 124552., articleTitle=Auto-encoder-extreme learning machine model for boiler NOx emission concentration prediction, refAbstract=null), Reference(id=1236610622864019646, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=1, pageStart=19, pageEnd=26, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=李胜男, 谭鹏, 饶德备, journalName=工程热物理学报, refType=null, unstructuredReference=李胜男, 谭鹏, 饶德备, 等. 融合数据与机理的燃煤发电机组协调系统建模[J]. 工程热物理学报, 2022, 43(1): 19-26., articleTitle=融合数据与机理的燃煤发电机组协调系统建模, refAbstract=null), Reference(id=1236610622956294340, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=1, pageStart=19, pageEnd=26, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=LI Shengnan, TAN Peng, RAO Debei, journalName=Journal of Engineering Thermophysics, refType=null, unstructuredReference=LI Shengnan, TAN Peng, RAO Debei, et al. Modeling of coal-fired generating unit coordination system with data and mechanism[J]. Journal of Engineering Thermophysics, 2022, 43(1): 19-26., articleTitle=Modeling of coal-fired generating unit coordination system with data and mechanism, refAbstract=null), Reference(id=1236610623031791814, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2022, volume=52, issue=5, pageStart=943, pageEnd=952, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=徐文韬, 黄亚继, 曹歌瀚, journalName=东南大学学报(自然科学版), refType=null, unstructuredReference=徐文韬, 黄亚继, 曹歌瀚, 等. 基于BP-改进NSGA-Ⅱ锅炉燃烧多目标优化[J]. 东南大学学报(自然科学版), 2022, 52(5): 943-952., articleTitle=基于BP-改进NSGA-Ⅱ锅炉燃烧多目标优化, refAbstract=null), Reference(id=1236610623115677898, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2022, volume=52, issue=5, pageStart=943, pageEnd=952, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=XU Wentao, HUANG Yaji, CAO Gehan, journalName=Journal of Southeast University (Natural Science Edition), refType=null, unstructuredReference=XU Wentao, HUANG Yaji, CAO Gehan, et al. Multi-objective combustion optimization for boiler based on BP-improved NSGA-II[J]. Journal of Southeast University (Natural Science Edition), 2022, 52(5): 943-952., articleTitle=Multi-objective combustion optimization for boiler based on BP-improved NSGA-II, refAbstract=null), Reference(id=1236610623220535504, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=9, pageStart=3488, pageEnd=3498, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=李悦, 唐振浩, 曹生现, journalName=中国电机工程学报, refType=null, unstructuredReference=李悦, 唐振浩, 曹生现, 等. 基于动态时延分析和典型样本筛选的NOx排放浓度预测[J]. 中国电机工程学报, 2023, 43(9): 3488-3498., articleTitle=基于动态时延分析和典型样本筛选的NOx排放浓度预测, refAbstract=null), Reference(id=1236610623367336149, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2023, volume=43, issue=9, pageStart=3488, pageEnd=3498, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=LI Yue, TANG Zhenhao, CAO Shengxian, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=LI Yue, TANG Zhenhao, CAO Shengxian, et al. Prediction of NOx emission concentration based on dynamic time delay analysis and typical sample selection[J]. Proceedings of the CSEE, 2023, 43(9): 3488-3498., articleTitle=Prediction of NOx emission concentration based on dynamic time delay analysis and typical sample selection, refAbstract=null), Reference(id=1236610623505748185, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2019, volume=182, issue=null, pageStart=37, pageEnd=47, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=TANG Z H, ZHANG Z J, journalName=Energy, refType=null, unstructuredReference=TANG Z H, ZHANG Z J. The multi-objective optimization of combustion system operations based on deep data-driven models[J]. Energy, 2019, 182: 37-47., articleTitle=The multi-objective optimization of combustion system operations based on deep data-driven models, refAbstract=null), Reference(id=1236610623614800092, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2019, volume=160, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=HAN Y M, FAN C Y, XU M, journalName=Applied Thermal Engineering, refType=null, unstructuredReference=HAN Y M, FAN C Y, XU M, et al. Production capacity analysis and energy saving of complex chemical processes using LSTM based on attention mechanism[J]. Applied Thermal Engineering, 2019, 160: 114072., articleTitle=Production capacity analysis and energy saving of complex chemical processes using LSTM based on attention mechanism, refAbstract=null), Reference(id=1236610623786766564, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2020, volume=197, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=18, authorNames=WANG J Q, DU Y, WANG J, journalName=Energy, refType=null, unstructuredReference=WANG J Q, DU Y, WANG J. LSTM based long-term energy consumption prediction with periodicity[J]. Energy, 2020, 197: 117197., articleTitle=LSTM based long-term energy consumption prediction with periodicity, refAbstract=null), Reference(id=1236610623862264039, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2024, volume=238, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=19, authorNames=WANG K, TANG X Y, ZHAO S M, journalName=Expert Systems with Applications, refType=null, unstructuredReference=WANG K, TANG X Y, ZHAO S M. Robust multi-step wind speed forecasting based on a graph-based data reconstruction deep learning method[J]. Expert Systems with Applications, 2024, 238: 121886., articleTitle=Robust multi-step wind speed forecasting based on a graph-based data reconstruction deep learning method, refAbstract=null), Reference(id=1236610623941955819, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2019, volume=176, issue=null, pageStart=429, pageEnd=436, url=null, language=null, rfNumber=[15], rfOrder=20, authorNames=TAN P, HE B, ZHANG C, journalName=Energy, refType=null, unstructuredReference=TAN P, HE B, ZHANG C, et al. Dynamic modeling of NOx emission in a 660 MW coal-fired boiler with long short-term memory[J]. Energy, 2019, 176: 429-436., articleTitle=Dynamic modeling of NOx emission in a 660 MW coal-fired boiler with long short-term memory, refAbstract=null), Reference(id=1236610624042619120, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2020, volume=190, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=21, authorNames=XIE P R, GAO M M, ZHANG H F, journalName=Energy, refType=null, unstructuredReference=XIE P R, GAO M M, ZHANG H F, et al. Dynamic modeling for NOx emission sequence prediction of SCR system outlet based on sequence to sequence long short-term memory network[J]. Energy, 2020, 190: 116482., articleTitle=Dynamic modeling for NOx emission sequence prediction of SCR system outlet based on sequence to sequence long short-term memory network, refAbstract=null), Reference(id=1236610624160059636, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2021, volume=148, issue=null, pageStart=867, pageEnd=878, url=null, language=null, rfNumber=[17], rfOrder=22, authorNames=KANG J J, NIU Y G, HU B, journalName=Process Safety and Environmental Protection, refType=null, unstructuredReference=KANG J J, NIU Y G, HU B, et al. Dynamic modeling of SCR denitration systems in coal-fired power plants based on a bi-directional long short-term memory method[J]. Process Safety and Environmental Protection, 2021, 148: 867-878., articleTitle=Dynamic modeling of SCR denitration systems in coal-fired power plants based on a bi-directional long short-term memory method, refAbstract=null), Reference(id=1236610624277500149, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=5, pageStart=120, pageEnd=126, url=null, language=null, rfNumber=[18], rfOrder=23, authorNames=金志远, 李胜男, 谭鹏, journalName=热力发电, refType=null, unstructuredReference=金志远, 李胜男, 谭鹏, 等. 基于长短时记忆神经网络的锅炉多参数协同预测模型[J]. 热力发电, 2021, 50(5): 120-126., articleTitle=基于长短时记忆神经网络的锅炉多参数协同预测模型, refAbstract=null), Reference(id=1236610624378163449, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=5, pageStart=120, pageEnd=126, url=null, language=null, rfNumber=[18], rfOrder=24, authorNames=JIN Zhiyuan, LI Shengnan, TAN Peng, journalName=Thermal Power Generation, refType=null, unstructuredReference=JIN Zhiyuan, LI Shengnan, TAN Peng, et al. Multi-parameter collaborative prediction model of boilers based on long-short-term memory neural network[J]. Thermal Power Generation, 2021, 50(5): 120-126., articleTitle=Multi-parameter collaborative prediction model of boilers based on long-short-term memory neural network, refAbstract=null), Reference(id=1236610624483021055, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2022, volume=310, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=25, authorNames=WANG X W, LIU W J, WANG Y N, journalName=Fuel, refType=null, unstructuredReference=WANG X W, LIU W J, WANG Y N, et al. A hybrid NOx emission prediction model based on CEEMDAN and AM-LSTM[J]. Fuel, 2022, 310: 122486., articleTitle=A hybrid NOx emission prediction model based on CEEMDAN and AM-LSTM, refAbstract=null), Reference(id=1236610624579490049, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2023, volume=13, issue=8, pageStart=4905, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=26, authorNames=ZHAO Y B, CAI Y L, JIANG H N, journalName=Applied Sciences, refType=null, unstructuredReference=ZHAO Y B, CAI Y L, JIANG H N. Recurrent neural network-based hybrid modeling method for digital twin of boiler system in coal-fired power plant[J]. Applied Sciences, 2023, 13(8): 4905., articleTitle=Recurrent neural network-based hybrid modeling method for digital twin of boiler system in coal-fired power plant, refAbstract=null), Reference(id=1236610624696930567, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2022, volume=44, issue=7, pageStart=3614, pageEnd=3633, url=null, language=null, rfNumber=[21], rfOrder=27, authorNames=VANDENHENDE S, GEORGOULIS S, GANSBEKE W V, journalName=IEEE Transactions on Pattern Analysis and Machine Intelligence, refType=null, unstructuredReference=VANDENHENDE S, GEORGOULIS S, GANSBEKE W V, et al. Multi-task learning for dense prediction tasks: a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(7): 3614-3633., articleTitle=Multi-task learning for dense prediction tasks: a survey, refAbstract=null), Reference(id=1236610624810176780, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2022, volume=28, issue=2, pageStart=141, pageEnd=159, url=null, language=null, rfNumber=[22], rfOrder=28, authorNames=NARAGHI Z G, NICKABADI A, SAFABAKHSH R, journalName=Journal of Universal Computer Science, refType=null, unstructuredReference=NARAGHI Z G, NICKABADI A, SAFABAKHSH R. LogSE: an uncertainty-based multi-task loss function for learning two regression tasks[J]. Journal of Universal Computer Science, 2022, 28(2): 141-159., articleTitle=LogSE: an uncertainty-based multi-task loss function for learning two regression tasks, refAbstract=null), Reference(id=1236610624894062862, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2021, volume=5, issue=7, pageStart=101, pageEnd=110, url=null, language=null, rfNumber=[23], rfOrder=29, authorNames=杨晗迅, 周德群, 马静, journalName=数据分析与知识发现, refType=null, unstructuredReference=杨晗迅, 周德群, 马静, 等. 基于不确定性损失函数和任务层级注意力机制的多任务谣言检测研究[J]. 数据分析与知识发现, 2021, 5(7): 101-110., articleTitle=基于不确定性损失函数和任务层级注意力机制的多任务谣言检测研究, refAbstract=null), Reference(id=1236610625032474900, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2021, volume=5, issue=7, pageStart=101, pageEnd=110, url=null, language=null, rfNumber=[23], rfOrder=30, authorNames=YANG Hanxun, ZHOU Dequn, MA Jing, journalName=Data Analysis and Knowledge Discovery, refType=null, unstructuredReference=YANG Hanxun, ZHOU Dequn, MA Jing, et al. Detecting rumors with uncertain loss and task-level attention mechanism[J]. Data Analysis and Knowledge Discovery, 2021, 5(7): 101-110., articleTitle=Detecting rumors with uncertain loss and task-level attention mechanism, refAbstract=null), Reference(id=1236610625133138196, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=7482, pageEnd=7491, url=null, language=null, rfNumber=[24], rfOrder=31, authorNames=KENDALL A, GAL Y, CIPOLLA R, journalName=null, refType=null, unstructuredReference=KENDALL A, GAL Y, CIPOLLA R. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 7482-7491., articleTitle=Multi-task learning using uncertainty to weigh losses for scene geometry and semantics, refAbstract=null), Reference(id=1236610625246384406, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, doi=null, pmid=null, pmcid=null, year=2020, volume=206, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=32, authorNames=YUAN K X, LIU J, YANG S C, journalName=Knowledge Based Systems, refType=null, unstructuredReference=YUAN K X, LIU J, YANG S C, et al. Time series forecasting based on kernel mapping and high-order fuzzy cognitive maps[J]. Knowledge Based Systems, 2020, 206: 106359., articleTitle=Time series forecasting based on kernel mapping and high-order fuzzy cognitive maps, refAbstract=null)], funds=[Fund(id=1236610621127577709, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, awardId=202201090301013, language=EN, fundingSource=Major Science and Technology Project of Shanxi Province(202201090301013), fundOrder=null, country=null), Fund(id=1236610621245018227, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, awardId=202201090301013, language=CN, fundingSource=山西省科技重大专项计划(202201090301013), fundOrder=null, country=null), Fund(id=1236610621358264438, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, awardId=2023KY637, language=EN, fundingSource=Innovation Project Foundation for Postgraduates in Shanxi Province(2023KY637), fundOrder=null, country=null), Fund(id=1236610621454733436, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, awardId=2023KY637, language=CN, fundingSource=山西省研究生科研创新项目(2023KY637), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1236610615209415454, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, xref=1., ext=[AuthorCompanyExt(id=1236610615217804064, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615209415454, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Shanxi Key Laboratory of Advanced Control and Industrial Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, China), AuthorCompanyExt(id=1236610615226192673, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615209415454, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.太原科技大学先进控制与工业智能山西省重点实验室,山西 太原 030024)]), AuthorCompany(id=1236610615356216104, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, xref=2., ext=[AuthorCompanyExt(id=1236610615372993321, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615356216104, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Shanxi Huaguang Power Generation Co., Ltd., Lüliang 033399, China), AuthorCompanyExt(id=1236610615381381930, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, companyId=1236610615356216104, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.山西华光发电有限责任公司,山西 吕梁 033399)])], figs=[ArticleFig(id=1236610618946540535, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=EN, label=Fig.1, caption=The results of variable correlation analysis, figureFileSmall=HxR5/EFpkvM2i6KcyZXP3g==, figureFileBig=z4w90y16p1WZn4nE3FTLYw==, tableContent=null), ArticleFig(id=1236610619059786751, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=CN, label=图1, caption=变量相关性分析的结果, figureFileSmall=HxR5/EFpkvM2i6KcyZXP3g==, figureFileBig=z4w90y16p1WZn4nE3FTLYw==, tableContent=null), ArticleFig(id=1236610619210780677, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=EN, label=Fig.2, caption=Architecture of a long short-term memory cell, figureFileSmall=RTEcNDRFPNIqUFV4SPgnFA==, figureFileBig=DoJ5meW8eG2x50Hco1uOkA==, tableContent=null), ArticleFig(id=1236610619303055370, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=CN, label=图2, caption=LSTM神经网络单元结构, figureFileSmall=RTEcNDRFPNIqUFV4SPgnFA==, figureFileBig=DoJ5meW8eG2x50Hco1uOkA==, tableContent=null), ArticleFig(id=1236610619420495886, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=EN, label=Fig.3, caption=The architecture of multi-task learning model for hard parameter sharing, figureFileSmall=EDPlZWwHpFWw7BgoY4UFHQ==, figureFileBig=ssV0TylCMKEf7JD+GQZSUg==, tableContent=null), ArticleFig(id=1236610619525353494, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=CN, label=图3, caption=硬参数共享的多任务学习模型结构, figureFileSmall=EDPlZWwHpFWw7BgoY4UFHQ==, figureFileBig=ssV0TylCMKEf7JD+GQZSUg==, tableContent=null), ArticleFig(id=1236610619630211098, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=EN, label=Fig.4, caption=Flowchart of Kernel-LSTM-UL prediction model, figureFileSmall=gZOLCky02mQ1tVDAdnU/UA==, figureFileBig=pk6U0lwaBOMm2QzVrpoeAw==, tableContent=null), ArticleFig(id=1236610619747651615, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=CN, label=图4, caption=Kernel-LSTM-UL预测模型流程, figureFileSmall=gZOLCky02mQ1tVDAdnU/UA==, figureFileBig=pk6U0lwaBOMm2QzVrpoeAw==, tableContent=null), ArticleFig(id=1236610619877675042, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=EN, label=Fig.5, caption=Range of unit load variations in the test set, figureFileSmall=Rtl2bB4qggXIof1HC8Az0g==, figureFileBig=EMQsWPjBGfiTRzUPnCOAvw==, tableContent=null), ArticleFig(id=1236610619999309867, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=CN, label=图5, caption=测试集机组负荷变化范围, figureFileSmall=Rtl2bB4qggXIof1HC8Az0g==, figureFileBig=EMQsWPjBGfiTRzUPnCOAvw==, tableContent=null), ArticleFig(id=1236610620141916212, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=EN, label=Fig.6, caption=Prediction curves for different models, figureFileSmall=WLHthKfQZGRK5XmMQT2t5Q==, figureFileBig=SBvliAjrsNHqNYndBqlNTw==, tableContent=null), ArticleFig(id=1236610620242579517, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=CN, label=图6, caption=不同模型对不同变量的预测曲线, figureFileSmall=WLHthKfQZGRK5XmMQT2t5Q==, figureFileBig=SBvliAjrsNHqNYndBqlNTw==, tableContent=null), ArticleFig(id=1236610620339048516, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=EN, label=Fig.7, caption=Distributions of prediction errors for different models, figureFileSmall=SB8atvpJeMIiJ84Qp8B1MA==, figureFileBig=PoNz1kOuSKKMoo3oPCXGiA==, tableContent=null), ArticleFig(id=1236610620431323210, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=CN, label=图7, caption=不同模型的预测误差分布, figureFileSmall=SB8atvpJeMIiJ84Qp8B1MA==, figureFileBig=PoNz1kOuSKKMoo3oPCXGiA==, tableContent=null), ArticleFig(id=1236610620548763728, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=EN, label=Tab.1, caption=

Value ranges for relative parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
变量名变化范围字母
空预器出口烟气含氧量/%1.66~7.71O
空预器出口烟气温度/℃109.88~145.82T
炉膛出口NOx质量浓度/(mg·m–3)1.09~531.22N
机组负荷/MW239.15~581.71L
总煤量/(t·h–1)237.54~632.88F
总风量/(t·h–1)692.16~1 413.60A
给水量/(t·h–1)787.65~2 044.00W
), ArticleFig(id=1236610620691370071, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=CN, label=表1, caption=

相关变量的数值范围

, figureFileSmall=null, figureFileBig=null, tableContent=
变量名变化范围字母
空预器出口烟气含氧量/%1.66~7.71O
空预器出口烟气温度/℃109.88~145.82T
炉膛出口NOx质量浓度/(mg·m–3)1.09~531.22N
机组负荷/MW239.15~581.71L
总煤量/(t·h–1)237.54~632.88F
总风量/(t·h–1)692.16~1 413.60A
给水量/(t·h–1)787.65~2 044.00W
), ArticleFig(id=1236610620817199196, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=EN, label=Tab.2, caption=

The prediction errors of four forecasting models

, figureFileSmall=null, figureFileBig=null, tableContent=
评价指标预测模型预测变量字母表示
OTN
δRMSELSTM0.1450.55539.688
Kernel-LSTM0.1290.43238.128
LSTM-UL0.1410.42138.752
Kernel-LSTM-UL0.1080.32337.836
δMAELSTM0.1020.42521.116
Kernel-LSTM0.0910.33018.787
LSTM-UL0.1020.31619.322
Kernel-LSTM-UL0.0730.24317.814
δMAPELSTM2.3060.33817.666
Kernel-LSTM2.0720.26213.785
LSTM-UL2.2470.25016.722
Kernel-LSTM-UL1.6560.19313.407
), ArticleFig(id=1236610620917862499, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1236596125436801094, language=CN, label=表2, caption=

4种模型预测误差对比

, figureFileSmall=null, figureFileBig=null, tableContent=
评价指标预测模型预测变量字母表示
OTN
δRMSELSTM0.1450.55539.688
Kernel-LSTM0.1290.43238.128
LSTM-UL0.1410.42138.752
Kernel-LSTM-UL0.1080.32337.836
δMAELSTM0.1020.42521.116
Kernel-LSTM0.0910.33018.787
LSTM-UL0.1020.31619.322
Kernel-LSTM-UL0.0730.24317.814
δMAPELSTM2.3060.33817.666
Kernel-LSTM2.0720.26213.785
LSTM-UL2.2470.25016.722
Kernel-LSTM-UL1.6560.19313.407
)], 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.202408222, detailUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/10.19666/j.rlfd.202408222, pdfUrlCn=https://castjournals.cast.org.cn/joweb/rlfd/CN/PDF/10.19666/j.rlfd.202408222, pdfUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/PDF/10.19666/j.rlfd.202408222, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于多任务不确定性损失的电站锅炉关键指标预测
收藏切换
PDF下载
王宇飞 1 , 李楠 1 , 谢刚 1 , 张晓红 1 , 聂晓音 1 , 周勇 2
热力发电 | 发电技术论坛 2025,54(5): 132-139
收起
收藏切换
热力发电 | 发电技术论坛 2025, 54(5): 132-139
基于多任务不确定性损失的电站锅炉关键指标预测
全屏
王宇飞1 , 李楠1, 谢刚1 , 张晓红1, 聂晓音1, 周勇2
作者信息
  • 1.太原科技大学先进控制与工业智能山西省重点实验室,山西 太原 030024
  • 2.山西华光发电有限责任公司,山西 吕梁 033399
  • 王宇飞(1996),女,博士研究生,主要研究方向为燃煤发电过程建模、控制与优化,

通讯作者:

谢刚(1972),男,博士,教授,主要研究方向为人工智能技术及其应用,
Prediction of key indicators of utility boiler based on multi-task uncertainty loss
Yufei WANG1 , Nan LI1, Gang XIE1 , Xiaohong ZHANG1, Xiaoyin NIE1, Yong ZHOU2
Affiliations
  • 1.Shanxi Key Laboratory of Advanced Control and Industrial Intelligence, Taiyuan University of Science and Technology, Taiyuan 030024, China
  • 2.Shanxi Huaguang Power Generation Co., Ltd., Lüliang 033399, China
出版时间: 2025-05-25 doi: 10.19666/j.rlfd.202408222
文章导航
收藏切换

随着电站锅炉灵活运行需求的增加,频繁的变负荷运行导致污染物含量和烟气参数大范围波动,对单一污染物或烟气参数等关键指标进行建模已无法满足电厂实际需求,因此需要考虑多种关键指标的耦合性进行协同预测建模。基于燃煤电厂的历史运行数据,通过核函数映射进行特征提取,构建硬参数共享结构的长短时记忆神经网络进行多任务预测建模,利用不确定性损失的方法优化预测模型。实验结果表明,所提出的预测模型在变负荷工况下表现出较高的预测精度,对于所涉及的关键指标空气预热器出口烟气含氧量、烟气温度、炉膛出口NOx质量浓度的预测,均方根误差分别降低了25.5%、41.8%和4.7%。所提方法能够在变负荷工况下对电站锅炉多个关键指标进行预测,能够辅助电厂实现污染控制和燃烧效率优化,可为电厂智能化运行提供技术支持。

燃煤锅炉  /  预测模型  /  LSTM神经网络  /  多任务学习  /  不确定性损失

With the increasing demand for flexible operation of power plant boilers, frequent variable-load operation leads to a wide range of fluctuations in pollutant concentrations and flue gas parameters. Modeling of key indicators such as single pollutant or flue gas parameter can no longer meet the actual demand, so it is necessary to consider the coupling of multiple key indicators for synergistic predictive modeling. Based on the historical operation data of coal-fired power plants, feature extraction is performed through kernel function mapping, and a long short-term memory neural network with a hard parameter sharing structure is constructed for multi task prediction modeling. The prediction model is optimized using uncertainty loss methods. The experimental results show that, the proposed prediction model exhibits high prediction accuracy under variable load conditions, and the prediction errors for the key metrics involved in this study are reduced by 25.5%, 41.8% and 4.7%, respectively. The proposed method is capable of predicting several key indicators of utility boilers under variable load conditions, which can assist power plants to achieve pollution control and optimize the thermal efficiency of combustion, and provide technical support for intelligent operation of power plants.

coal-fired boiler  /  prediction model  /  LSTM neural network  /  multi-task learning  /  uncertainty loss
王宇飞, 李楠, 谢刚, 张晓红, 聂晓音, 周勇. 基于多任务不确定性损失的电站锅炉关键指标预测. 热力发电, 2025 , 54 (5) : 132 -139 . DOI: 10.19666/j.rlfd.202408222
Yufei WANG, Nan LI, Gang XIE, Xiaohong ZHANG, Xiaoyin NIE, Yong ZHOU. Prediction of key indicators of utility boiler based on multi-task uncertainty loss[J]. Thermal Power Generation, 2025 , 54 (5) : 132 -139 . DOI: 10.19666/j.rlfd.202408222
在“双碳”目标压力下,深度调峰、超低排放、灵活运行已成为火电行业的必然发展趋势和长期研究热点,同时各大电厂急需引进新技术向智慧电厂转型[1-2]。然而,频繁的变负荷运行导致污染物含量和烟气参数等大范围波动,火力发电过程中产生的污染物如氮氧化物(NOx)以及影响燃烧效率的排烟温度和烟气含氧量等关键指标,对环境保护和电厂运行经济性有着重要影响。因此,如何有效地预测这些关键指标,优化生产过程,减少污染物排放,成为了当前研究的热点问题之一[3]
随着人工智能技术的发展,数据驱动方法在燃烧建模领域占据了主导地位。在电力行业,分散控制系统(distributed control system,DCS)可以用于电厂的自动化控制和监控,其中存储了大量的生产运行数据;并且随着可再生能源的接入,运行数据中包含了丰富的工况信息。数据驱动建模只需要海量存储的历史数据,通过智能优化算法即可获得机组的动态模型[4-5]。为了弥补早期机理模型的不足,不少学者将人工神经网络(artificial neural network,ANN)应用于模型中[6-10]。深度学习在时间序列相关的特征提取和模型拟合方面比浅层模型具有明显的优势,依靠多层神经元之间的连接模式,深度学习善于从原始输入数据中挖掘更多的抽象特征表示,具有良好的泛化能力[11]。循环神经网络(recurrent neural network,RNN)因其特殊的神经网络结构,不仅考虑了前一时刻的输入,还赋予了神经网络对前一时刻内容的“记忆”功能。为了克服RNN训练过程中的梯度消失和梯度爆炸问题,Hochreiter和Schmidhuber提出了长短时记忆(long short-term memory,LSTM)神经网络,并成功应用于许多序列相关问题[12-14]。基于LSTM模型对燃煤电厂动态建模的研究逐渐增多[15-20]
然而,以上建模大部分都是对单一目标进行建模。在“双碳”目标压力下,各大电厂急需引进新技术向智慧化转型升级,单一目标建模在模型部署时会占据更大的计算内存导致效率降低;并且锅炉系统的各个关键指标之间并不独立,而是存在相互制约和耦合的关系。利用神经网络算法对锅炉系统多指标协同预测建模,可以在学习多个变量潜在关系的情况下,优化预测模型的性能。多任务学习(multi-task learning,MTL)方法因其能够同时学习多个相关任务的特性,通过共享不同任务的潜在表示,可以提高模型的泛化能力和预测精度[21-24]。在本研究中,关注的污染物和烟气参数分别是炉膛出口NOx质量浓度、排烟温度和烟气含氧量这3项指标。它们虽然具有不同的物理意义,但在发电过程中的变化趋势和影响因素却有着密切的联系。通过多任务学习方法,可以同时学习这3项指标的预测任务,从而充分利用它们之间的关联信息,提高预测模型的整体性能。
本研究采用LSTM神经网络对炉膛出口NOx质量浓度、烟气温度和烟气含氧量等关键指标进行多任务预测建模,通过硬参数共享(即底层LSTM神经网络共享权重与偏置,顶层构建不同任务全连接层)的多任务学习结构,能够充分利用参数之间的关联信息,并通过不确定性加权损失函数优化多目标预测过程,提升整体预测性能。
本研究对象是火力发电厂的燃煤锅炉。在电力生产中,炉膛出口NOx质量浓度、排烟温度和烟气含氧量是关键的性能指标。烟气中的氧气含量反映燃烧过程的空气过剩系数,过高或过低的氧气含量都可能导致燃烧效率的下降和污染物的增加;排烟温度是衡量锅炉燃烧效率的重要指标之一;NOx是燃烧过程中产生的主要污染物。这些指标不仅反映锅炉的燃烧效率和污染物排放水平,而且通过预测这些关键指标可以辅助电厂实现污染控制、优化燃烧。因此本研究选取空气预热器(空预器)出口烟气含氧量、空预器出口烟气温度和炉膛出口NOx质量浓度作为预测的目标变量。
实验数据取自某燃煤电厂DCS,数据范围为2022-12-02 00:00—2022-12-06 04:59,以1 min为采样间隔共采集6 000组时序数据,兼顾专家经验和模型复杂度,选取机组负荷、给煤量、给水量和给风量等4个辅助变量与3个目标变量作为输入特征,这些输入特征将用于后续的模型训练。变量的数值范围见表1
变量相关性直接影响预测模型的准确度。为了验证所选变量之间具有较高的相关性,对各目标变量和辅助变量之间的相关性采用皮尔逊相关系数法(Pearson correlation coefficient)进行计算。该系数用于衡量2个变量之间的线性相关性,其值介于-1~1,绝对值越大表示相关性越强。变量相关性分析的结果如图1所示。
图1可知,各变量之间的相关性不同,但所选变量之间相关性系数的绝对值均在0.5以上。证明所选的输入特征变量之间具有较高的相关性,可以用于后续的模型训练。
从电厂DCS中采集的时间序列集合为X,其中包含多个时间序列向量。具体地,原始数据集合包含以下时间序列向量:
X=[xO,xT,xN,xL,xF,xA,xW]
每个时间序列向量xv(v=O,T,N,L,F,A,W)表示为:
xv=[xv,1,xv,2,,xv,D]T
式中:D为采集的时间序列样本的长度。
建模前对数据进行预处理。首先,对异常的数据进行剔除和修正。其次,根据7:3的比例将数据集划分为训练集和测试集。因为电厂运行中不同变量的尺度偏差较大,为了有助于加快模型的收敛速度和稳定模型训练过程,将数据集进行标准化处理,将数据标准化到[0,1]区间内。
燃煤锅炉是大滞后、缓变的系统,部分变量变化相对缓慢,面向灵活调峰的需求,其中也存在部分波动较大的变量。本文构造了一组非线性函数组成的映射函数,将原始时间序列嵌入高维特征空间中,称为核函数映射(kernel mapping)。
g(x)=x2,g(x)=x3,...,g(x)=xs+1
g(x)=x12,g(x)=x13,...,g(x)=x1s+1
g(x)=xs+1s,g(x)=xs+2s,...,g(x)=xs+ss
g(x)=xss+1,g(x)=xss+2,...,g(x)=xss+s
高维特征空间中还包含一个线性函数:
g(x)=x
式中:s用来刻画映射函数陡峭程度的参数,且s> 1。为了在充分提取特征的同时兼顾模型的计算效率,这里取s=4。
经过核函数映射提取特征,一维时间序列转化为维度m=15的高维特征空间,表示为:
[g1(xv),g2(xv),,gm(xv)]=[g1(xv,1)g2(xv,1)...gm(xv,1)g1(xv,2)g2(xv,2)...gm(xv,2).........g1(xv,D)g2(xv,D)...gm(xv,D)]
式中:gi(·)为第i个核函数映射的输出结果。
核函数映射将时序数据转换至高维特征空间,使得在新空间中的数据分布更接近线性,降低非平稳时间序列的回归难度;此外,核函数映射具有挖掘时间序列隐含模式的能力,特别对于复杂的非平稳时间序列[25]。通过核函数映射提取特征,可以提高预测模型的准确性。
采用LSTM神经网络作为主要网络,LSTM神经网络通过引入记忆单元和门控机制解决了长时间依赖问题,使其在处理长时间依赖的序列数据时表现更加优越。LSTM神经网络的基本单元是LSTM单元,针对本研究任务,通过滑动窗口法构造LSTM层的输入[Xt-k+1, …, Xt-1, Xt]Tk为滑动步长。
Xt=[g1(xO,t)g2(xO,t)...gm(xO,t)g1(xT,t)g2(xT,t)...gm(xT,t)g1(xN,t)g2(xN,t)...gm(xN,t)g1(xL,t)g2(xL,t)...gm(xL,t)g1(xF,t)g2(xF,t)...gm(xF,t)g1(xA,t)g2(xA,t)...gm(xA,t)g1(xW,t)g2(xW,t)...gm(xW,t)]
式中:Xt为在t时刻各个变量经过核函数映射后得到的高维特征矩阵。LSTM层共有k个长短时记忆单元,各个单元的输入依次为Xnn∈[tk+1, t]。
图2为单个LSTM神经网络单元结构,其核心结构包括遗忘门、输入门和输出门。门控机制作用于记忆单元,从而控制信息的流动和状态更新。LSTM神经网络单元计算公式为:
ft=σ(Wf[ht1,Xt]+bf)
it=σ(Wi[ht1,Xt]+bi)
mt=tanh(Wc[ht1,Xt]+bc)
Ct=ftCt1+itmt
ot=σ(Wo[ht1,Xt]+bo)
ht=ottanh(Ct)
式中:ftitCtot分别为遗忘门、输入门、记忆单元和输出门的输出;WfWiWcWo分别为对应门的权重矩阵;bfbibcbo分别为对应门的偏置;mt为记忆单元状态函数;ht–1Xt分别为前一状态和当前输入;ht为LSTM层的输出;⊗表示Hadamard乘积;σ(·)和tanh(·)分别表示对应的激活函数,记为:
σ(β)=11+eβ
tanh(β)=eβeβeβ+eβ
在本研究中,构建了一个基于多任务学习的神经网络预测模型,该模型使用了硬参数共享(hard parameter sharing)的结构捕获潜在关联信息。引入同方差不确定性,将简单加权求和的损失函数转化为不确定性损失函数,对多任务学习中各个任务的权重进行优化。多任务学习模型的实现步骤如下。
1)定义模型结构 定义了一个多输出的LSTM模型,其中每个输出节点对应一个预测任务。模型的主要结构包括1个单层的共享LSTM层、1个Dropout层和3个Dense层:共享LSTM层学习输入特征之间的关系,隐含层节点数为256;每个Dense层对应1个输出任务;Dropout层用于防止模型过拟合,丢弃率为0.3。模型结构如图3所示。
硬参数共享结构的预测模型表示为:
[y*1,t+1,y*2,t+1,y*3,t+1]=FLSTM[Xtk,Xtk+1,...,Xt]
式中:y*1,t+1y*2,t+1y*3,t+1分别为该模型在t+1时刻3个任务的预测值,任务1是预测空预器出口烟气含氧量,任务2是预测空预器出口烟气温度、任务3是预测炉膛出口NOx质量浓度;FLSTM是构建的神经网络预测模型。
2)定义不确定性损失函数(uncertainty loss,UL) 在多任务学习领域,同方差不确定性表明了任务的相对置信度,在本研究中其反映了预测任务的不确定性。因此,本文将同方差不确定性作为误差项对多任务学习中各个任务的权重进行优化。每个任务的损失函数不仅包含了均方误差的误差项,同时还结合了不确定性参数。具体计算公式为:
Li=1Mj=1Mexp(lnσi2)(y*i,jyi,j)2+lnσi2,i{1,2,3}
式中:Li为各个任务的损失函数;lnσi2为任务i的不确定性;exp(-lnσi2)为加权因子,用于根据不确定性调整误差的权重;y*i,j为任务ij个样本的预测值;yi,j为任务ij个样本的真实值;M为训练的样本数量。
最终的损失函数是各个任务损失函数Li的加权和,形成总的损失函数L
L=i=13Li
3)模型训练 在模型训练中,通过学习自动寻找最优的参数lnσi2,这个过程不仅降低每个任务的预测误差,同时降低各个任务的不确定性,最终得到最小的总损失函数L的值。
采用基于LSTM神经网络的多任务学习模型预测燃煤电厂锅炉NOx质量浓度、烟气含氧量和烟气温度,本文Kernel-LSTM-UL预测模型流程如图4所示。
为了验证所构建模型的有效性,分别设计了有、无核函数映射提取特征和有、无不确定性损失函数的对比实验。选用一段具有代表性的连续时序数据作为测试集进行实验;机组运行在260~580 MW的负荷范围内,且包含多段稳定工况和负荷突变工况,具体如图5所示。
本文进行实验的操作系统为Windows10,CPU为Intel(R)Core i9-13900K。使用的软件包和版本包括Python 3.19、TensorFlow 2.4.1、Keras 2.4.3、NumPy 1.20.1以及Matplotlib 3.4.3。为了保证实验结果的可靠性,在相同的实验环境下对所有实验任务重复10次。
选用3种评价指标对模型性能进行评价。考虑到对误差的高敏感性以及与预测变量相同的单位,选用均方根误差作为一项指标;为了便于理解和解释,直接表示预测值与真实值的平均误差,选用平均绝对误差作为一项指标;同时选用平均绝对百分误差作为评价指标,这样预测误差以百分比的形式表达出来更易观察和理解。
各评价指标计算表达式如下。
均方根误差(root mean squared error)δRMSE
ΔRMSE=1nj=1n(yi,jyi,j)2
平均绝对误差(mean absolute error)δMAE
ΔMAE=1nj=1n|yi,jyi,j|
平均绝对百分误差(mean absolute percentage error)δMAPE
ΔMAPE=1nj=1n|yi,jyi,jyi,j|
式中:n为测试集的样本个数。
为了验证所提出Kernel-LSTM-UL模型的准确性,在数据预处理方法一致的情况下,与LSTM模型、Kernel-LSTM模型、LSTM-UL这3种模型进行对比,图6为不同模型使用同一测试集的对比结果。从图6可以看出,所构建的Kernel-LSTM-UL模型相较于其他模型有着更好的拟合效果,预测曲线可以实时跟踪真实曲线,具有更高的建模精度。并且在变负荷工况及负荷突变的情况下,Kernel-LSTM-UL模型能够更精准、更快速地跟随变化。
图7为4种预测方法的误差分布。由图7可以看出,所有模型的误差均呈现接近于正态分布的形态,且大多数误差集中在0附近。其中,Kernel-LSTM-UL模型的误差分布最窄,峰值最高,表明该模型在此变量上的预测精度最高。可以得出本文所提Kernel-LSTM-UL模型在此研究中的表现最佳。
表2为4种不同预测模型在相同测试集上的误差评价指标对比。通过分析得到,Kernel-LSTM-UL模型的3项误差评价指标都优于其他3种模型。在测试集上,所提出算法的均方根误差相较于传统LSTM算法分别降低了25.5%、41.8%和4.7%;所提出算法的平均绝对误差相较于传统LSTM算法分别降低了28.4%、42.8%和15.6%;所提出算法的平均绝对百分误差相较于传统LSTM算法分别降低了28.2%、42.9%和24.1%。可见Kernel-LSTM-UL模型有着更高的建模精度,可以更好地预测烟气含氧量、烟气温度、炉膛出口NOx质量浓度等多个锅炉关键指标。
火力发电厂锅炉的关键指标(如炉膛出口NOx质量浓度、排烟温度和烟气含氧量)之间存在复杂的关联性,传统的单任务预测方法无法充分利用这些关联信息。本研究提出一种基于核函数映射特征提取和多任务不确定性损失的预测模型,针对燃煤锅炉关键指标的协同建模展开研究,实验验证得到以下主要结论。
1)核函数映射将原始特征序列映射到高维特征空间中,有效提取了关键指标的潜在特征,能够有效提高预测模型精度。
2)基于不确定性损失构造多任务学习模型,优化了各个任务的权重分配,规避了主观设定权重的局限性,有效提高关键指标预测的整体性能。
3)构建Kernel-LSTM-UL预测模型,采用亚临界600 MW机组锅炉实际运行过程数据进行实验验证,对3个关键指标的预测均方根误差分别降低了25.5%、41.8%和4.7%。
本研究所提模型可在变负荷工况下进行动态预测,预测结果可以反映锅炉的燃烧效率和污染物排放水平,为电厂污染控制、燃烧优化及智慧化运行提供技术支撑。
  • 山西省科技重大专项计划(202201090301013)
  • 山西省研究生科研创新项目(2023KY637)
参考文献 引证文献
排序方式:
[1]
高耀岿, 王林, 高海东, 等. 火电厂智能控制系统体系架构及关键技术[J]. 热力发电, 2022, 51(3): 166-174.
GAO Yaokui, WANG Lin, GAO Haidong, et al. Architecture and key technology of intelligent control system in thermal power plant[J]. Thermal Power Generation, 2022, 51(3): 166-174.
[2]
刘吉臻, 李云鸷, 宋子秋, 等. 灵活智能燃煤发电技术及评价体系[J]. 动力工程学报, 2022, 42(11): 993-1004.
LIU Jizhen, LI Yunzhi, SONG Ziqiu, et al. Flexible and intelligent coalfired power generation technology and its evaluation system[J]. Journal of Chinese Society of Power Engineering, 2022, 42(11): 993-1004.
[3]
NEMITALLAH M A, NABHAN M A, ALOWAIFEER M, et al. Artificial intelligence for control and optimization of boilers’ performance and emissions: a review[J]. Journal of Cleaner Production, 2023, 417: 138109.
[4]
赵永亮, 许朋江, 居文平, 等. 燃煤发电机组瞬态过程灵活高效协同运行的理论与技术研究综述[J]. 中国电机工程学报, 2023, 43(6): 2080-2100.
ZHAO Yongliang, XU Pengjiang, JU Wenping, et al. Overview of theoretical and technical research on flexible and efficient synergistic operation of coal-fired power units during transient processes[J]. Proceedings of the CSEE, 2023, 43(6): 2080-2100.
[5]
ZHU C P, HUANG P, LI Y G. Closed-loop combustion optimization based on dynamic and adaptive models with application to a coal-fired boiler[J]. Energies, 2022, 15(14): 5289.
[6]
SHI Y, ZHONG WEN Q, CHEN X, et al. Combustion optimization of ultra supercritical boiler based on artificial intelligence[J]. Energy, 2019, 170: 804-817.
[7]
TANG Z H, WANG S K, CHAI X Y, et al. Auto-encoder-extreme learning machine model for boiler NOx emission concentration prediction[J]. Energy, 2022, 256: 124552.
[8]
李胜男, 谭鹏, 饶德备, 等. 融合数据与机理的燃煤发电机组协调系统建模[J]. 工程热物理学报, 2022, 43(1): 19-26.
LI Shengnan, TAN Peng, RAO Debei, et al. Modeling of coal-fired generating unit coordination system with data and mechanism[J]. Journal of Engineering Thermophysics, 2022, 43(1): 19-26.
[9]
徐文韬, 黄亚继, 曹歌瀚, 等. 基于BP-改进NSGA-Ⅱ锅炉燃烧多目标优化[J]. 东南大学学报(自然科学版), 2022, 52(5): 943-952.
XU Wentao, HUANG Yaji, CAO Gehan, et al. Multi-objective combustion optimization for boiler based on BP-improved NSGA-II[J]. Journal of Southeast University (Natural Science Edition), 2022, 52(5): 943-952.
[10]
李悦, 唐振浩, 曹生现, 等. 基于动态时延分析和典型样本筛选的NOx排放浓度预测[J]. 中国电机工程学报, 2023, 43(9): 3488-3498.
LI Yue, TANG Zhenhao, CAO Shengxian, et al. Prediction of NOx emission concentration based on dynamic time delay analysis and typical sample selection[J]. Proceedings of the CSEE, 2023, 43(9): 3488-3498.
[11]
TANG Z H, ZHANG Z J. The multi-objective optimization of combustion system operations based on deep data-driven models[J]. Energy, 2019, 182: 37-47.
[12]
HAN Y M, FAN C Y, XU M, et al. Production capacity analysis and energy saving of complex chemical processes using LSTM based on attention mechanism[J]. Applied Thermal Engineering, 2019, 160: 114072.
[13]
WANG J Q, DU Y, WANG J. LSTM based long-term energy consumption prediction with periodicity[J]. Energy, 2020, 197: 117197.
[14]
WANG K, TANG X Y, ZHAO S M. Robust multi-step wind speed forecasting based on a graph-based data reconstruction deep learning method[J]. Expert Systems with Applications, 2024, 238: 121886.
[15]
TAN P, HE B, ZHANG C, et al. Dynamic modeling of NOx emission in a 660 MW coal-fired boiler with long short-term memory[J]. Energy, 2019, 176: 429-436.
[16]
XIE P R, GAO M M, ZHANG H F, et al. Dynamic modeling for NOx emission sequence prediction of SCR system outlet based on sequence to sequence long short-term memory network[J]. Energy, 2020, 190: 116482.
[17]
KANG J J, NIU Y G, HU B, et al. Dynamic modeling of SCR denitration systems in coal-fired power plants based on a bi-directional long short-term memory method[J]. Process Safety and Environmental Protection, 2021, 148: 867-878.
[18]
金志远, 李胜男, 谭鹏, 等. 基于长短时记忆神经网络的锅炉多参数协同预测模型[J]. 热力发电, 2021, 50(5): 120-126.
JIN Zhiyuan, LI Shengnan, TAN Peng, et al. Multi-parameter collaborative prediction model of boilers based on long-short-term memory neural network[J]. Thermal Power Generation, 2021, 50(5): 120-126.
[19]
WANG X W, LIU W J, WANG Y N, et al. A hybrid NOx emission prediction model based on CEEMDAN and AM-LSTM[J]. Fuel, 2022, 310: 122486.
[20]
ZHAO Y B, CAI Y L, JIANG H N. Recurrent neural network-based hybrid modeling method for digital twin of boiler system in coal-fired power plant[J]. Applied Sciences, 2023, 13(8): 4905.
[21]
VANDENHENDE S, GEORGOULIS S, GANSBEKE W V, et al. Multi-task learning for dense prediction tasks: a survey[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2022, 44(7): 3614-3633.
[22]
NARAGHI Z G, NICKABADI A, SAFABAKHSH R. LogSE: an uncertainty-based multi-task loss function for learning two regression tasks[J]. Journal of Universal Computer Science, 2022, 28(2): 141-159.
[23]
杨晗迅, 周德群, 马静, 等. 基于不确定性损失函数和任务层级注意力机制的多任务谣言检测研究[J]. 数据分析与知识发现, 2021, 5(7): 101-110.
YANG Hanxun, ZHOU Dequn, MA Jing, et al. Detecting rumors with uncertain loss and task-level attention mechanism[J]. Data Analysis and Knowledge Discovery, 2021, 5(7): 101-110.
[24]
KENDALL A, GAL Y, CIPOLLA R. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018: 7482-7491.
[25]
YUAN K X, LIU J, YANG S C, et al. Time series forecasting based on kernel mapping and high-order fuzzy cognitive maps[J]. Knowledge Based Systems, 2020, 206: 106359.
2025年第54卷第5期
PDF下载
100
43
引用本文
BibTeX
文章信息
doi: 10.19666/j.rlfd.202408222
  • 接收时间:2024-08-28
  • 首发时间:2026-03-06
  • 出版时间:2025-05-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-08-28
基金
Major Science and Technology Project of Shanxi Province(202201090301013)
山西省科技重大专项计划(202201090301013)
Innovation Project Foundation for Postgraduates in Shanxi Province(2023KY637)
山西省研究生科研创新项目(2023KY637)
作者信息
    1.太原科技大学先进控制与工业智能山西省重点实验室,山西 太原 030024
    2.山西华光发电有限责任公司,山西 吕梁 033399

通讯作者:

谢刚(1972),男,博士,教授,主要研究方向为人工智能技术及其应用,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202408222
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