Article(id=1217836024844174283, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1217836019408360416, articleNumber=null, orderNo=null, doi=10.19666/j.rlfd.202502032, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1740326400000, receivedDateStr=2025-02-24, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1768284334621, onlineDateStr=2026-01-13, pubDate=1764000000000, pubDateStr=2025-11-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1768284334621, onlineIssueDateStr=2026-01-13, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1768284334621, creator=13701087609, updateTime=1768284334621, updator=13701087609, issue=Issue{id=1217836019408360416, tenantId=1146029695717560320, journalId=1210938733613449225, year='2025', volume='54', issue='11', pageStart='1', pageEnd='168', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1768284333326, creator=13701087609, updateTime=1768284453982, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1217836525543408117, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1217836019408360416, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1217836525543408118, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1217836019408360416, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=136, endPage=141, ext={EN=ArticleExt(id=1217836025108415456, articleId=1217836024844174283, tenantId=1146029695717560320, journalId=1210938733613449225, language=EN, title=Modeling of SCR denitrification reactor for thermal power units based on improved grey wolf optimization LSTM network, columnId=1211002405299294959, journalTitle=Thermal Power Generation, columnName=Thermal energy science research, runingTitle=null, highlight=null, articleAbstract=

A hybrid prediction model combining enhanced grey wolf optimization algorithm (EGWO) and long short-term memory (LSTM) neural network is proposed to address the problem of low accuracy in predicting the mass concentration of NOx at the outlet of selective catalytic reduction (SCR) denitrification reactors using conventional mechanism modeling methods. Firstly, based on principal component analysis (PCA), the raw data is processed and filtered to achieve dimensionality reduction of input variables. Then, the EGWO is used to optimize the hyperparameters of LSTM. Finally, the input variables are used as inputs for the EGWO-LSTM model to predict the mass concentration of NOx at the outlet. Taking a 1 000 MW ultra supercritical thermal power unit in China as an example, simulation results show that the proposed model performs the best in error control, with root mean square error reduces by 50.36% compared to the conventional LSTM model, and by 76.14% compared to the BP model, and the mean absolute percentage error of the model is only 1.01%. The EGWO has fewer iterations and higher convergence accuracy compared to the GWO when converging to the optimal solution.

, 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=Lei WU, Hua GU, Yiming YAO, Jun ZHANG, Jun SU, Yi CHEN), CN=ArticleExt(id=1217836027616608327, articleId=1217836024844174283, tenantId=1146029695717560320, journalId=1210938733613449225, language=CN, title=基于增强灰狼优化LSTM神经网络的火电机组SCR脱硝反应器建模, columnId=1211002405437706993, journalTitle=热力发电, columnName=热能科学研究, runingTitle=null, highlight=null, articleAbstract=

针对传统机理建模方法预测选择性催化还原技术(SCR)脱硝反应器出口NOx质量浓度精度不高的问题,提出了一种结合增强型灰狼优化算法(EGWO)与长短时记忆(LSTM)神经网络的混合预测模型。首先,基于主成分分析(PCA)对原始数据进行处理与筛选,实现输入变量的降维。然后,利用EGWO优化LSTM神经网络的超参数。最终,将输入变量作为EGWO-LSTM模型的输入,预测出口NOx质量浓度。以国内某超超临界1 000 MW火电机组为例,仿真结果表明,该模型在误差控制方面表现最优,均方根误差较传统LSTM模型下降50.36%,较BP模型下降76.14%,模型平均绝对百分比误差仅为1.01%。EGWO相对于GWO收敛至最优解时的迭代次数更少,且具有更高的收敛精度。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
张军(1966),男,博士,副教授,主要研究方向为机器学习、复杂系统智能控制与优化,
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=MPIOWWKrL7AOAZsFS5mvOQ==, magXml=vfhE40QOQHAN+L8Ilf2hXQ==, pdfUrl=null, pdf=VB34MSrbA37XK91m+TfeGw==, pdfFileSize=1492082, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=PuZuWrMFc4ux30QTd4S9Xw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=xXtmXo6V6j83jMFdQ4+VxQ==, mapNumber=null, authorCompany=null, fund=null, authors=

吴磊(1996),男,硕士,助理工程师,主要研究方向为非线性系统建模、控制与优化,电网运维,

, authorsList=吴磊, 顾华, 姚一鸣, 张军, 苏军, 陈依)}, authors=[Author(id=1217836028170256506, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=1784646353@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1217836028287697027, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, authorId=1217836028170256506, language=EN, stringName=Lei WU, firstName=Lei, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.State Grid Shanghai Qingpu Electric Power Supply Company, Shanghai 201700, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836028463857803, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, authorId=1217836028170256506, language=CN, stringName=吴磊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.国网上海青浦供电公司,上海 201700, bio={"content":"

吴磊(1996),男,硕士,助理工程师,主要研究方向为非线性系统建模、控制与优化,电网运维,

"}, bioImg=null, bioContent=

吴磊(1996),男,硕士,助理工程师,主要研究方向为非线性系统建模、控制与优化,电网运维,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836027847295067, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, xref=1., ext=[AuthorCompanyExt(id=1217836027851489372, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027847295067, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Grid Shanghai Qingpu Electric Power Supply Company, Shanghai 201700, China), AuthorCompanyExt(id=1217836027859877981, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027847295067, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.国网上海青浦供电公司,上海 201700)])]), Author(id=1217836028623241364, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, 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=1217836028740681884, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, authorId=1217836028623241364, language=EN, stringName=Hua GU, firstName=Hua, middleName=null, lastName=GU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.State Grid Shanghai Qingpu Electric Power Supply Company, Shanghai 201700, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836028858122401, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, authorId=1217836028623241364, language=CN, stringName=顾华, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.国网上海青浦供电公司,上海 201700, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836027847295067, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, xref=1., ext=[AuthorCompanyExt(id=1217836027851489372, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027847295067, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Grid Shanghai Qingpu Electric Power Supply Company, Shanghai 201700, China), AuthorCompanyExt(id=1217836027859877981, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027847295067, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.国网上海青浦供电公司,上海 201700)])]), Author(id=1217836028975562926, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, 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=1217836029088809145, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, authorId=1217836028975562926, language=EN, stringName=Yiming YAO, firstName=Yiming, middleName=null, lastName=YAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.State Grid Shanghai Qingpu Electric Power Supply Company, Shanghai 201700, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836029185278149, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, authorId=1217836028975562926, language=CN, stringName=姚一鸣, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.国网上海青浦供电公司,上海 201700, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836027847295067, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, xref=1., ext=[AuthorCompanyExt(id=1217836027851489372, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027847295067, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Grid Shanghai Qingpu Electric Power Supply Company, Shanghai 201700, China), AuthorCompanyExt(id=1217836027859877981, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027847295067, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.国网上海青浦供电公司,上海 201700)])]), Author(id=1217836029323690194, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=86610598@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1217836029436936413, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, authorId=1217836029323690194, language=EN, stringName=Jun ZHANG, firstName=Jun, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2.School of Automation Engineering, Shanghai University of Electric Power, Shanghai 200090, China
3.Shanghai Key Laboratory of Power Station Automation Technology, Shanghai 200090, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836029520822498, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, authorId=1217836029323690194, language=CN, stringName=张军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, 3, address=2.上海电力大学自动化工程学院,上海 200090
3.上海市电站自动化技术重点实验室,上海 200090, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836027947958371, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, xref=2., ext=[AuthorCompanyExt(id=1217836027956346980, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027947958371, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Automation Engineering, Shanghai University of Electric Power, Shanghai 200090, China), AuthorCompanyExt(id=1217836027968929893, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027947958371, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.上海电力大学自动化工程学院,上海 200090)]), AuthorCompany(id=1217836028065398892, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, xref=3., ext=[AuthorCompanyExt(id=1217836028073787501, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836028065398892, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Shanghai Key Laboratory of Power Station Automation Technology, Shanghai 200090, China), AuthorCompanyExt(id=1217836028082176110, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836028065398892, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.上海市电站自动化技术重点实验室,上海 200090)])]), Author(id=1217836029613097197, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, 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=1217836029717954805, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, authorId=1217836029613097197, language=EN, stringName=Jun SU, firstName=Jun, middleName=null, lastName=SU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.State Grid Shanghai Qingpu Electric Power Supply Company, Shanghai 201700, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836029801840894, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, authorId=1217836029613097197, language=CN, stringName=苏军, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.国网上海青浦供电公司,上海 201700, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836027847295067, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, xref=1., ext=[AuthorCompanyExt(id=1217836027851489372, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027847295067, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Grid Shanghai Qingpu Electric Power Supply Company, Shanghai 201700, China), AuthorCompanyExt(id=1217836027859877981, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027847295067, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.国网上海青浦供电公司,上海 201700)])]), Author(id=1217836029881532677, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, 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=1217836030007361805, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, authorId=1217836029881532677, language=EN, stringName=Yi CHEN, firstName=Yi, middleName=null, lastName=CHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.State Grid Shanghai Qingpu Electric Power Supply Company, Shanghai 201700, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1217836030120608023, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, authorId=1217836029881532677, language=CN, stringName=陈依, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.国网上海青浦供电公司,上海 201700, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1217836027847295067, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, xref=1., ext=[AuthorCompanyExt(id=1217836027851489372, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027847295067, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Grid Shanghai Qingpu Electric Power Supply Company, Shanghai 201700, China), AuthorCompanyExt(id=1217836027859877981, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027847295067, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.国网上海青浦供电公司,上海 201700)])])], keywords=[Keyword(id=1217836030321934624, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=EN, orderNo=1, keyword=SCR denitration reactor), Keyword(id=1217836030493901098, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=EN, orderNo=2, keyword=prediction model), Keyword(id=1217836030607147312, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=EN, orderNo=3, keyword=NOx), Keyword(id=1217836031886410040, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=EN, orderNo=4, keyword=LSTM), Keyword(id=1217836031978684735, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=EN, orderNo=5, keyword=principal component analysis), Keyword(id=1217836032079348036, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=EN, orderNo=6, keyword=enhanced grey wolf optimization algorithm), Keyword(id=1217836032180011340, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=CN, orderNo=1, keyword=SCR脱硝反应器), Keyword(id=1217836032301646163, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=CN, orderNo=2, keyword=预测模型), Keyword(id=1217836032393920855, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=CN, orderNo=3, keyword=NOx), Keyword(id=1217836032486195550, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=CN, orderNo=4, keyword=LSTM), Keyword(id=1217836032574275940, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=CN, orderNo=5, keyword=主成分分析), Keyword(id=1217836032700105070, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=CN, orderNo=6, keyword=增强灰狼优化算法)], refs=[Reference(id=1217836034700788180, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2021, volume=54, issue=11, pageStart=199, pageEnd=205, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=柴有国, 何晓燕, 苏永健, journalName=中国电力, refType=null, unstructuredReference=柴有国, 何晓燕, 苏永健, 等. 考虑安全环保及补偿的火电机组调峰经济性研究[J]. 中国电力, 2021, 54(11): 199-205., articleTitle=考虑安全环保及补偿的火电机组调峰经济性研究, refAbstract=null), Reference(id=1217836034784674267, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2021, volume=54, issue=11, pageStart=199, pageEnd=205, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=CHAI Youguo, HE Xiaoyan, SU Yongjian, journalName=Electric Power, refType=null, unstructuredReference=CHAI Youguo, HE Xiaoyan, SU Yongjian, et al. Economic study on peak shaving of thermal power units considering safety, environmental protection, and compensation[J]. Electric Power, 2021, 54(11): 199-205., articleTitle=Economic study on peak shaving of thermal power units considering safety, environmental protection, and compensation, refAbstract=null), Reference(id=1217836034889531872, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2020, volume=40, issue=6, pageStart=486, pageEnd=491, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=许壮, 康英伟, journalName=动力工程学报, refType=null, unstructuredReference=许壮, 康英伟. 基于随机森林的火电机组SCR脱硝反应器建模[J]. 动力工程学报, 2020, 40(6): 486-491., articleTitle=基于随机森林的火电机组SCR脱硝反应器建模, refAbstract=null), Reference(id=1217836034990195173, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2020, volume=40, issue=6, pageStart=486, pageEnd=491, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=XU Zhuang, KANG Yingwei, journalName=Journal of Power Engineering, refType=null, unstructuredReference=XU Zhuang, KANG Yingwei. Modeling of SCR denitrification reactor for thermal power units based on random forest[J]. Journal of Power Engineering, 2020, 40(6): 486-491., articleTitle=Modeling of SCR denitrification reactor for thermal power units based on random forest, refAbstract=null), Reference(id=1217836035136995818, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2023, volume=52, issue=1, pageStart=7, pageEnd=17, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=张珑慧, 林德海, 王颖, journalName=热力发电, refType=null, unstructuredReference=张珑慧, 林德海, 王颖, 等. 机器学习在火电厂NOx减排中的应用综述[J]. 热力发电, 2023, 52(1): 7-17., articleTitle=机器学习在火电厂NOx减排中的应用综述, refAbstract=null), Reference(id=1217836036407869935, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2023, volume=52, issue=1, pageStart=7, pageEnd=17, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=ZHANG Longhui, LIN Dehai, WANG Ying, journalName=Thermal Power Generation, refType=null, unstructuredReference=ZHANG Longhui, LIN Dehai, WANG Ying, et al. Overview of the application of machine learning in NOx reduction in thermal power plants[J]. Thermal Power Generation, 2023, 52(1): 7-17., articleTitle=Overview of the application of machine learning in NOx reduction in thermal power plants, refAbstract=null), Reference(id=1217836036504338931, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=6, pageStart=114, pageEnd=120, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=张晓雯, 向文国, 陈时熠, journalName=热力发电, refType=null, unstructuredReference=张晓雯, 向文国, 陈时熠, 等. 基于小波去噪和PCA-ANFIS的SCR脱硝系统建模[J]. 热力发电, 2021, 50(6): 114-120., articleTitle=基于小波去噪和PCA-ANFIS的SCR脱硝系统建模, refAbstract=null), Reference(id=1217836036588225016, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=6, pageStart=114, pageEnd=120, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=ZHANG Xiaowen, XIANG Wenguo, CHEN Shiyi, journalName=Thermal Power Generation, refType=null, unstructuredReference=ZHANG Xiaowen, XIANG Wenguo, CHEN Shiyi, et al. Modeling of SCR denitrification system based on wavelet denoising and PCA-AFIS[J]. Thermal Power Generation, 2021, 50(6): 114-120., articleTitle=Modeling of SCR denitrification system based on wavelet denoising and PCA-AFIS, refAbstract=null), Reference(id=1217836036667916798, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2023, volume=17, issue=11, pageStart=3721, pageEnd=3729, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=徐圆圆, 龚德鸿, 邓传记, journalName=环境工程学报, refType=null, unstructuredReference=徐圆圆, 龚德鸿, 邓传记, 等. SCR反应器入口参数与反应温度对脱硝性能的交互作用[J]. 环境工程学报, 2023, 17(11): 3721-3729., articleTitle=SCR反应器入口参数与反应温度对脱硝性能的交互作用, refAbstract=null), Reference(id=1217836036760191491, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2023, volume=17, issue=11, pageStart=3721, pageEnd=3729, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=XU Yuanyuan, GONG Dehong, DENG Chuanji, journalName=Journal of Environmental Engineering, refType=null, unstructuredReference=XU Yuanyuan, GONG Dehong, DENG Chuanji, et al. The interaction between SCR reactor inlet parameters and reaction temperature on denitrification performance[J]. Journal of Environmental Engineering, 2023, 17(11): 3721-3729., articleTitle=The interaction between SCR reactor inlet parameters and reaction temperature on denitrification performance, refAbstract=null), Reference(id=1217836036839883273, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2023, volume=62, issue=36, pageStart=14286, pageEnd=14299, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=AN B, TANG M, QIU J, journalName=Industrial & Engineering Chemistry Research, refType=null, unstructuredReference=AN B, TANG M, QIU J, et al. Dynamic NOx prediction model for SCR denitrification outlet of coal-fired power plants based on hybrid data-driven and model ensemble[J]. Industrial & Engineering Chemistry Research, 2023, 62(36): 14286-14299., articleTitle=Dynamic NOx prediction model for SCR denitrification outlet of coal-fired power plants based on hybrid data-driven and model ensemble, refAbstract=null), Reference(id=1217836036940546573, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2021, volume=148, issue=1, pageStart=867, pageEnd=878, url=null, language=null, rfNumber=[7], rfOrder=11, authorNames=JUNJIE K, YUGUANG N, BO H, journalName=Process Safety and Environmental Protection, refType=null, unstructuredReference=JUNJIE K, YUGUANG N, BO H, 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(1): 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=1217836037049598482, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2024, volume=53, issue=7, pageStart=119, pageEnd=128, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=李影, 卓建坤, 吴逸凡, journalName=热力发电, refType=null, unstructuredReference=李影, 卓建坤, 吴逸凡, 等. 可解释的变负荷下燃煤机组SCR反应器入口NOx质量浓度预测模型[J]. 热力发电, 2024, 53(7): 119-128., articleTitle=可解释的变负荷下燃煤机组SCR反应器入口NOx质量浓度预测模型, refAbstract=null), Reference(id=1217836037150261782, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2024, volume=53, issue=7, pageStart=119, pageEnd=128, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=LI Ying, ZHUO Jiankun, WU Yifan, journalName=Thermal Power Generation, refType=null, unstructuredReference=LI Ying, ZHUO Jiankun, WU Yifan, et al. Explainable predictive model for NOx mass concentration at the inlet of SCR reactor in coal-fired power units under variable load[J]. Thermal Power Generation, 2024, 53(7): 119-128., articleTitle=Explainable predictive model for NOx mass concentration at the inlet of SCR reactor in coal-fired power units under variable load, refAbstract=null), Reference(id=1217836037234147865, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=3, pageStart=80, pageEnd=87, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=陆必伟, 李捷辉, journalName=车用发动机, refType=null, unstructuredReference=陆必伟, 李捷辉. 基于GWO-LSTM的柴油机NOx排放预测[J]. 车用发动机, 2024(3): 80-87., articleTitle=基于GWO-LSTM的柴油机NOx排放预测, refAbstract=null), Reference(id=1217836037318033952, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=3, pageStart=80, pageEnd=87, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=LU Biwei, LI Jiehui, journalName=Automotive Engines, refType=null, unstructuredReference=LU Biwei, LI Jiehui. Prediction of NOx emissions from diesel engines based on GWO-LSTM[J]. Automotive Engines, 2024(3): 80-87., articleTitle=Prediction of NOx emissions from diesel engines based on GWO-LSTM, refAbstract=null), Reference(id=1217836037435474468, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2018, volume=32, issue=1, pageStart=188, pageEnd=193, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=董浩, 李明星, 张淑清, journalName=电子测量与仪器学报, refType=null, unstructuredReference=董浩, 李明星, 张淑清, 等. 基于核主成分分析和极限学习机的短期电力负荷预测[J]. 电子测量与仪器学报, 2018, 32(1): 188-193., articleTitle=基于核主成分分析和极限学习机的短期电力负荷预测, refAbstract=null), Reference(id=1217836037527749161, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2018, volume=32, issue=1, pageStart=188, pageEnd=193, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=DONG Hao, LI Mingxing, ZHANG Shuqing, journalName=Journal of Electronic Measurement and Instrumentation, refType=null, unstructuredReference=DONG Hao, LI Mingxing, ZHANG Shuqing, et al. Short term power load forecasting based on kernel principal component analysis and extreme learning machine[J]. Journal of Electronic Measurement and Instrumentation, 2018, 32(1): 188-193., articleTitle=Short term power load forecasting based on kernel principal component analysis and extreme learning machine, refAbstract=null), Reference(id=1217836037632606769, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=增刊1, pageStart=210, pageEnd=220, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=胡阳, 杨泽, 房方, journalName=中国电机工程学报, refType=null, unstructuredReference=胡阳, 杨泽, 房方, 等. 火电机组供电碳减排高维运行特征提取及其最优基准值确定[J]. 中国电机工程学报, 2021, 41(增刊1): 210-220., articleTitle=火电机组供电碳减排高维运行特征提取及其最优基准值确定, refAbstract=null), Reference(id=1217836037737464373, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=Suppl.1, pageStart=210, pageEnd=220, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=HU Yang, YANG Ze, FANG Fang, journalName=Proceedings of CSEE, refType=null, unstructuredReference=HU Yang, YANG Ze, FANG Fang, et al. High dimensional operation feature extraction and optimal benchmark value determination for carbon emission reduction in power supply of thermal power units[J]. Proceedings of CSEE, 2021, 41(Suppl.1): 210-220., articleTitle=High dimensional operation feature extraction and optimal benchmark value determination for carbon emission reduction in power supply of thermal power units, refAbstract=null), Reference(id=1217836037859099194, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=1997, volume=9, issue=8, pageStart=1735, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=HOCHREITER S J, UUM L, SCHMIDHUBER R, journalName=Neural Computation, refType=null, unstructuredReference=HOCHREITER S J, UUM L, SCHMIDHUBER R. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735., articleTitle=Long short-term memory, refAbstract=null), Reference(id=1217836037947179582, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=12, pageStart=66, pageEnd=73, url=null, language=null, rfNumber=[13], rfOrder=21, authorNames=吴磊, 康英伟, journalName=热力发电, refType=null, unstructuredReference=吴磊, 康英伟. 基于改进粒子群优化长短时记忆神经网络的脱硫系统SO2预测模型[J]. 热力发电, 2021, 50(12): 66-73., articleTitle=基于改进粒子群优化长短时记忆神经网络的脱硫系统SO2预测模型, refAbstract=null), Reference(id=1217836038035259969, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=12, pageStart=66, pageEnd=73, url=null, language=null, rfNumber=[13], rfOrder=22, authorNames=WU Lei, KANG Yingwei, journalName=Thermal Power Generation, refType=null, unstructuredReference=WU Lei, KANG Yingwei. SO2 prediction model for desulfurization system based on improved particle swarm optimization long short-term memory neural network[J]. Thermal Power Generation, 2021, 50(12): 66-73., articleTitle=SO2 prediction model for desulfurization system based on improved particle swarm optimization long short-term memory neural network, refAbstract=null), Reference(id=1217836038156894794, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2014, volume=69, issue=null, pageStart=46, pageEnd=61, url=null, language=null, rfNumber=[14], rfOrder=23, authorNames=MIRJALILI S, MIRJALILI S M, LEWIS A, journalName=Advance in Engineering Software, refType=null, unstructuredReference=MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer[J]. Advance in Engineering Software, 2014, 69: 46-61., articleTitle=Grey wolf optimizer, refAbstract=null), Reference(id=1217836038261752399, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2017, volume=41, issue=9, pageStart=2987, pageEnd=2995, url=null, language=null, rfNumber=[15], rfOrder=24, authorNames=左剑, 张程稳, 肖逸, journalName=电网技术, refType=null, unstructuredReference=左剑, 张程稳, 肖逸, 等. 基于灰狼优化算法的多机电力系统稳定器参数最优设计[J]. 电网技术, 2017, 41(9): 2987-2995., articleTitle=基于灰狼优化算法的多机电力系统稳定器参数最优设计, refAbstract=null), Reference(id=1217836038374998610, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2017, volume=41, issue=9, pageStart=2987, pageEnd=2995, url=null, language=null, rfNumber=[15], rfOrder=25, authorNames=ZUO Jian, ZHANG Chengwen, XIAO Yi, journalName=Grid Technology, refType=null, unstructuredReference=ZUO Jian, ZHANG Chengwen, XIAO Yi, et al. Optimal design of stabilizer parameters for multi machine power systems based on grey wolf optimization algorithm[J]. Grid Technology, 2017, 41(9): 2987-2995., articleTitle=Optimal design of stabilizer parameters for multi machine power systems based on grey wolf optimization algorithm, refAbstract=null), Reference(id=1217836038471467604, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2024, volume=31, issue=12, pageStart=2140, pageEnd=2148, url=null, language=null, rfNumber=[16], rfOrder=26, authorNames=仝卫国, 郭超宇, 赵如意, journalName=控制工程, refType=null, unstructuredReference=仝卫国, 郭超宇, 赵如意. 基于变量选择和MGWO-LSTM的浆液pH值预测[J]. 控制工程, 2024, 31(12): 2140-2148., articleTitle=基于变量选择和MGWO-LSTM的浆液pH值预测, refAbstract=null), Reference(id=1217836038580519516, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, doi=null, pmid=null, pmcid=null, year=2024, volume=31, issue=12, pageStart=2140, pageEnd=2148, url=null, language=null, rfNumber=[16], rfOrder=27, authorNames=TONG Weiguo, GUO Chaoyu, ZHAO Ruyi, journalName=Control Engineering, refType=null, unstructuredReference=TONG Weiguo, GUO Chaoyu, ZHAO Ruyi. Prediction of pH value of slurry based on variable selection and MGWO-LSTM[J]. Control Engineering, 2024, 31(12): 2140-2148., articleTitle=Prediction of pH value of slurry based on variable selection and MGWO-LSTM, refAbstract=null)], funds=[Fund(id=1217836034260386239, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, awardId=61273190, language=EN, fundingSource=National Natural Science Foundation of China(61273190), fundOrder=null, country=null), Fund(id=1217836034348466629, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, awardId=61273190, language=CN, fundingSource=国家自然科学基金项目(61273190), fundOrder=null, country=null), Fund(id=1217836034453324233, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, awardId=13DZ2273800, language=EN, fundingSource=Funding Project of Shanghai Key Laboratory of Power Station Automation Technology(13DZ2273800), fundOrder=null, country=null), Fund(id=1217836034579153361, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, awardId=13DZ2273800, language=CN, fundingSource=上海市电站自动化技术重点实验室资助项目(13DZ2273800), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1217836027847295067, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, xref=1., ext=[AuthorCompanyExt(id=1217836027851489372, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027847295067, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Grid Shanghai Qingpu Electric Power Supply Company, Shanghai 201700, China), AuthorCompanyExt(id=1217836027859877981, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027847295067, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.国网上海青浦供电公司,上海 201700)]), AuthorCompany(id=1217836027947958371, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, xref=2., ext=[AuthorCompanyExt(id=1217836027956346980, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027947958371, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Automation Engineering, Shanghai University of Electric Power, Shanghai 200090, China), AuthorCompanyExt(id=1217836027968929893, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836027947958371, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.上海电力大学自动化工程学院,上海 200090)]), AuthorCompany(id=1217836028065398892, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, xref=3., ext=[AuthorCompanyExt(id=1217836028073787501, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836028065398892, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Shanghai Key Laboratory of Power Station Automation Technology, Shanghai 200090, China), AuthorCompanyExt(id=1217836028082176110, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, companyId=1217836028065398892, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.上海市电站自动化技术重点实验室,上海 200090)])], figs=[ArticleFig(id=1217836032851100023, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=EN, label=Fig.1, caption=Structure diagram of the LSTM neural network, figureFileSmall=ExfecHuqh87RXy8cf2Ktvg==, figureFileBig=PuZuWrMFc4ux30QTd4S9Xw==, tableContent=null), ArticleFig(id=1217836032939180413, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=CN, label=图1, caption=LSTM神经网络结构示意, figureFileSmall=ExfecHuqh87RXy8cf2Ktvg==, figureFileBig=PuZuWrMFc4ux30QTd4S9Xw==, tableContent=null), ArticleFig(id=1217836033127924103, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=EN, label=Fig.2, caption=Hierarchical diagram of grey wolf social hierarchy system, figureFileSmall=8zqWv8oTvpH22UCIKDMoUA==, figureFileBig=2eYWgXLI3dyaGdtSLRhX8w==, tableContent=null), ArticleFig(id=1217836033245364623, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=CN, label=图2, caption=灰狼等级制度分级, figureFileSmall=8zqWv8oTvpH22UCIKDMoUA==, figureFileBig=2eYWgXLI3dyaGdtSLRhX8w==, tableContent=null), ArticleFig(id=1217836033362805139, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=EN, label=Fig.3, caption=Framework diagram of the EGWO-LSTM prediction model, figureFileSmall=wqCFxmjZ2PaHgKIgQG3dCw==, figureFileBig=1jTSqa5lB1p3n+DJL6Sn7A==, tableContent=null), ArticleFig(id=1217836033476051354, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=CN, label=图3, caption=EGWO-LSTM预测模型框架结构, figureFileSmall=wqCFxmjZ2PaHgKIgQG3dCw==, figureFileBig=1jTSqa5lB1p3n+DJL6Sn7A==, tableContent=null), ArticleFig(id=1217836033580908959, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=EN, label=Fig.4, caption=Changes in the fitness of each model, figureFileSmall=bmHcuPT94Him2scBhRbgNQ==, figureFileBig=cBI0MN2MD8htDCujDl63vA==, tableContent=null), ArticleFig(id=1217836033673183651, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=CN, label=图4, caption=各模型适应度变化, figureFileSmall=bmHcuPT94Him2scBhRbgNQ==, figureFileBig=cBI0MN2MD8htDCujDl63vA==, tableContent=null), ArticleFig(id=1217836033790624166, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=EN, label=Tab.1, caption=

The eigenvalues and cumulative contribution rates corresponding to each principal component

, figureFileSmall=null, figureFileBig=null, tableContent=
各主成分特征值贡献率/%累计贡献率/%
SCR入口NOx质量浓度8.127 10.406 30.406 3
锅炉负荷4.115 80.205 70.612 0
SCR入口温度1.974 70.097 50.709 5
SCR入口烟气氧量1.396 40.069 60.779 1
SCR入口烟气量1.001 90.050 20.829 3
NH3入口流量0.797 10.039 80.869 1
), ArticleFig(id=1217836033916453294, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=CN, label=表1, caption=

各主成分对应的特征值和累计贡献率

, figureFileSmall=null, figureFileBig=null, tableContent=
各主成分特征值贡献率/%累计贡献率/%
SCR入口NOx质量浓度8.127 10.406 30.406 3
锅炉负荷4.115 80.205 70.612 0
SCR入口温度1.974 70.097 50.709 5
SCR入口烟气氧量1.396 40.069 60.779 1
SCR入口烟气量1.001 90.050 20.829 3
NH3入口流量0.797 10.039 80.869 1
), ArticleFig(id=1217836034021310898, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=EN, label=Tab.2, caption=

Performance comparison of different models

, figureFileSmall=null, figureFileBig=null, tableContent=
模型δRMSE/(mg·m–3)δMAPE/%训练模型耗时/s
PCA-LSTM21.372.03429.85
PCA-GWO-LSTM21.121.65267.73
PCA-EGWO-LSTM20.681.01189.06
PCA-LSSVM2.383.52596.70
PCA-BP2.854.21837.65
), ArticleFig(id=1217836034142945719, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1217836024844174283, language=CN, label=表2, caption=

不同模型的预测性能对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型δRMSE/(mg·m–3)δMAPE/%训练模型耗时/s
PCA-LSTM21.372.03429.85
PCA-GWO-LSTM21.121.65267.73
PCA-EGWO-LSTM20.681.01189.06
PCA-LSSVM2.383.52596.70
PCA-BP2.854.21837.65
)], 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.202502032, detailUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/10.19666/j.rlfd.202502032, pdfUrlCn=https://castjournals.cast.org.cn/joweb/rlfd/CN/PDF/10.19666/j.rlfd.202502032, pdfUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/PDF/10.19666/j.rlfd.202502032, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于增强灰狼优化LSTM神经网络的火电机组SCR脱硝反应器建模
收藏切换
PDF下载
吴磊 1 , 顾华 1 , 姚一鸣 1 , 张军 2, 3 , 苏军 1 , 陈依 1
热力发电 | 热能科学研究 2025,54(11): 136-141
收起
收藏切换
热力发电 | 热能科学研究 2025, 54(11): 136-141
基于增强灰狼优化LSTM神经网络的火电机组SCR脱硝反应器建模
全屏
吴磊1 , 顾华1, 姚一鸣1, 张军2, 3 , 苏军1, 陈依1
作者信息
  • 1.国网上海青浦供电公司,上海 201700
  • 2.上海电力大学自动化工程学院,上海 200090
  • 3.上海市电站自动化技术重点实验室,上海 200090
  • 吴磊(1996),男,硕士,助理工程师,主要研究方向为非线性系统建模、控制与优化,电网运维,

通讯作者:

张军(1966),男,博士,副教授,主要研究方向为机器学习、复杂系统智能控制与优化,
Modeling of SCR denitrification reactor for thermal power units based on improved grey wolf optimization LSTM network
Lei WU1 , Hua GU1, Yiming YAO1, Jun ZHANG2, 3 , Jun SU1, Yi CHEN1
Affiliations
  • 1.State Grid Shanghai Qingpu Electric Power Supply Company, Shanghai 201700, China
  • 2.School of Automation Engineering, Shanghai University of Electric Power, Shanghai 200090, China
  • 3.Shanghai Key Laboratory of Power Station Automation Technology, Shanghai 200090, China
出版时间: 2025-11-25 doi: 10.19666/j.rlfd.202502032
文章导航
收藏切换

针对传统机理建模方法预测选择性催化还原技术(SCR)脱硝反应器出口NOx质量浓度精度不高的问题,提出了一种结合增强型灰狼优化算法(EGWO)与长短时记忆(LSTM)神经网络的混合预测模型。首先,基于主成分分析(PCA)对原始数据进行处理与筛选,实现输入变量的降维。然后,利用EGWO优化LSTM神经网络的超参数。最终,将输入变量作为EGWO-LSTM模型的输入,预测出口NOx质量浓度。以国内某超超临界1 000 MW火电机组为例,仿真结果表明,该模型在误差控制方面表现最优,均方根误差较传统LSTM模型下降50.36%,较BP模型下降76.14%,模型平均绝对百分比误差仅为1.01%。EGWO相对于GWO收敛至最优解时的迭代次数更少,且具有更高的收敛精度。

SCR脱硝反应器  /  预测模型  /  NOx  /  LSTM  /  主成分分析  /  增强灰狼优化算法

A hybrid prediction model combining enhanced grey wolf optimization algorithm (EGWO) and long short-term memory (LSTM) neural network is proposed to address the problem of low accuracy in predicting the mass concentration of NOx at the outlet of selective catalytic reduction (SCR) denitrification reactors using conventional mechanism modeling methods. Firstly, based on principal component analysis (PCA), the raw data is processed and filtered to achieve dimensionality reduction of input variables. Then, the EGWO is used to optimize the hyperparameters of LSTM. Finally, the input variables are used as inputs for the EGWO-LSTM model to predict the mass concentration of NOx at the outlet. Taking a 1 000 MW ultra supercritical thermal power unit in China as an example, simulation results show that the proposed model performs the best in error control, with root mean square error reduces by 50.36% compared to the conventional LSTM model, and by 76.14% compared to the BP model, and the mean absolute percentage error of the model is only 1.01%. The EGWO has fewer iterations and higher convergence accuracy compared to the GWO when converging to the optimal solution.

SCR denitration reactor  /  prediction model  /  NOx  /  LSTM  /  principal component analysis  /  enhanced grey wolf optimization algorithm
吴磊, 顾华, 姚一鸣, 张军, 苏军, 陈依. 基于增强灰狼优化LSTM神经网络的火电机组SCR脱硝反应器建模. 热力发电, 2025 , 54 (11) : 136 -141 . DOI: 10.19666/j.rlfd.202502032
Lei WU, Hua GU, Yiming YAO, Jun ZHANG, Jun SU, Yi CHEN. Modeling of SCR denitrification reactor for thermal power units based on improved grey wolf optimization LSTM network[J]. Thermal Power Generation, 2025 , 54 (11) : 136 -141 . DOI: 10.19666/j.rlfd.202502032
在全球倡导绿色发展与可持续能源战略的大背景下,火电作为能源供应的重要支柱,其环保性能备受关注[1]。SCR脱硝技术凭借其高效的脱硝能力,成为火电厂控制NOx排放的关键手段,是实现火电绿色转型的核心技术之一。火电厂的NOx排放水平与运行成本,和SCR脱硝反应器的性能息息相关。所以,构建精确的SCR脱硝反应器模型,对优化脱硝系统运行、减少NOx排放极为关键。然而SCR脱硝反应器的运行过程极为复杂,涉及复杂的化学反应、多变的工况条件以及众多相互关联的运行参数,这些因素导致传统的机理建模难以准确预测反应器出口的NOx质量浓度[2]
随着监控信息系统(SIS)在火电厂信息化建设领域的普遍应用,存储的运行数据为构建数据驱动模型创造了基础条件[3]。因此,运用机器学习等数据分析技术,可有效利用电厂运行历史数据库构建高精度的SCR脱硝反应器模型。
目前对SCR脱硝反应器进行建模的方法有很多,如文献[4]利用小波去噪、PCA和自适应神经模糊推理系统(adaptive neuro-fuzzy inference system,ANFIS)构建SCR脱硝系统模型。文献[5]建立SCR脱硝反应一维模型,通过数值仿真来优化燃煤电厂SCR脱硝性能。文献[6]利用混合数据驱动建模方式对SCR脱硝系统出口NOx排放浓度进行预测。文献[7]将互信息与双向长短时记忆(LSTM)神经网络相结合,实现NOx质量浓度排放预测。文献[8]构建卷积神经网络(CNN)和LSTM神经网络的混合模型对SCR脱硝反应器入口NOx进行预测,但未开展针对LSTM神经网络超参数的优化。文献[9]虽然利用GWO算法对LSTM神经网络神经元个数和学习率进行优化,但其采用的线性迭代更新收敛因子调整机制存在一定缺陷。
为此,本文提出通过非线性策略对收敛因子实施动态更新,运用变异策略提升GWO算法的性能,针对LSTM的超参数,即神经元个数、学习率和迭代次数,运用优化后的EGWO算法进行调优,有效提升了模型的预测能力。
PCA算法是一种基于最大方差投影理论的数据降维技术[3]。该算法通过对原始变量实施线性变换,将原始样本转化为彼此线性不相关的主成分,以此削减原始输入变量的复杂度。在本文的研究中,应用PCA算法的主要目的是对SCR脱硝反应器的输入变量进行降维操作,一方面提高原始数据的品质,另一方面缩短模型构建时长,最终确保模型不仅拥有较高的精度,还具备良好的泛化能力。该PCA算法能够有效应对不同场景下的任务需求。
设原始SCR脱硝反应器的运行数据集为X=[x1T;x2T;;xmT]m×p,其中m为样本数量,xip表示第i个样本的p维工况参数。协方差矩阵定义为:
C=1m1XTXp×p
通过特征值分解可得:
Cvj=λjvj(j=1,2,,p)
其中λ1λ2≥…≥λp为特征值,对应正交特征向量vjp,称为最佳投影向量[10]。构造投影矩阵A=[v1,v2,,vl]p×l,满足方差最大化准则:
maxAtr(ATCA)s.tATA=I
步骤1)对原始数据矩阵进行Z-score标准化
x˜ij=xijμjδi(i=1,2,,m;j=1,2,,p)
μj=1mi=1mxij
δj2=1m1i=1m(xijμj)2
步骤2)协方差矩阵计算
标准化后数据的协方差矩阵为:
C=1m1XTXp×p
步骤3)特征空间分解
求解特征方程:
Cvj=λjvj(j=1,2,,p)
按特征值降序排列得λ1λ2≥…≥λp
步骤4)主成分筛选
计算方差贡献率及累计贡献率:
ηj=λjk=1pλk,Γl=j=1lηj
选择最小l使得Гl≥85%,构建投影矩阵A=[v1, v2, …, vl]。
步骤5)数据降维映射
得到降维后数据集:
Y=XAm×l
其中,第iyi=[yi1, yi2, …, yil]为样本xil维主成分特征。
LSTM神经网络是针对传统循环神经网络(RNN)时序建模缺陷提出的改进型架构[11]。LSTM神经网络通过创新性地引入细胞状态(cell state)与三重门控结构,成功攻克了RNN长期困扰的梯度消失与梯度爆炸难题[12],其结构如图1所示。其中包括遗忘门、输入门、输出门和ht隐含层单元输出量,其计算公式可参考文献[13]。
2014年,Mirjalili等人[14]从自然界灰狼群体的捕猎行为中汲取灵感,提出了一种群智能优化算法—GWO算法。该算法具有较强的搜索能力和较快的收敛速度、所需参数少,易实现等特点,被广泛应用于函数优化、机器学习等领域。狼群个体间严格执行等级制度分级图(图2),其中α狼负责领导群体,βδ狼协助α狼做出决策,ω狼服从其他狼的指挥。
通过不断更新狼的位置,逐步逼近猎物,更新方式如式(11)、式(12)所示:
D=|CXP(t)X(t)|
X(t+1)=XP(t)AD
式中:t为迭代次数;CA为向量系数;X为当前位置;D为灰狼和猎物间的距离;XP为更新之前种群个体的位置。其中向量系数的更新公式为:
C=2r2
A=2αr1α
式中:r1r2均为闭区间[0,1]内的一个随机数;α为收敛因子,其表达式为:
α=22t/Tmax
式中:Tmax为最大迭代次数。
可以看出,随着迭代的不断进行,α按照线性规律,由2逐步递减至0。
捕猎过程的更新过程如式(16)—式(18)所示。式(16)是灰狼个体追踪猎物位置的数学描述,式(17)是ω狼向αβδ狼靠近的数学描述,式(18)是ω狼最终位置的数学描述。
{Dα=|C1XαX|Dβ=|C2XβX|Dδ=|C3XδX|
{X1=XαA1DαX2=XβA2DβX3=XδA3Dδ
X(t+1)=X1+X2+X33
式中:DαDβDδ分别为当前个体αβδ到猎物的距离;XαXβXδ分别为αβδ的位置;C1C2C3为随机向量;X为当前位置。
在传统GWO算法里,位置更新过度依赖于α狼,这使得算法在局部寻优时表现出色,却造成了全局寻优能力不足的问题。而SCR脱硝反应器建模预测出口NOx质量浓度过程中,算法的搜索过程呈现出较高的复杂性,线性收敛因子难以契合搜索时的实际状况,这极易导致算法被困于局部最优解,拉低算法的精度。因此本文对标准GWO算法进行如下改进:
1)非线性策略更新收敛因子
收敛因子更新策略不同会严重影响算法的性能[15],本文采用非线性策略更新收敛因子,计算公式如下:
α=2[1sin(π2tTmax)]
改进后的收敛因子在迭代前期快速递减,有利于灰狼种群在搜索区域内快速开展全面搜索,确定目标搜索区域;到了迭代后期,收敛因子递减速度放缓,灰狼种群在目标搜索区域仔细进行局部搜索,提高了算法收敛至全局最优解的概率。这样的改进能有效平衡整个算法的全局最优和局部最优。
2)变异策略
为了解决标准GWO算法容易陷入局部最优问题,对式(18)进行高斯变异:
X(t+1)=X(t+1)[1+α2N(01)]
灰狼算法在初期提高扰动,增强算法的全局搜索能力,在末期降低扰动,防止最优解波动,进而加快算法收敛速度。
图3为EGWO-LSTM预测模型的框架结构。
步骤1) 初始化GWO种群,包括种群规模、迭代次数,设置LSTM神经网络神经元个数、学习率、迭代次数等。
步骤2) 搭建LSTM预测模型,并对灰狼个体的适应度函数进行计算,保留适应度最好的αβδ狼的信息。
步骤3) 利用非线性策略更新收敛因子,变异策略更新个体位置
步骤4) 确认当前迭代次数是否达到预先设定的最大迭代次数。若尚未达到,则程序返回步骤2)继续执行;若达到,则根据灰狼最终位置,确定LSTM神经网络超参数,构建EGWO-LSTM模型,输出出口NOx预测值,并开展评价指标分析。
前文提到SCR脱硝反应器的运行过程极为复杂,传统机理建模方式导致出口NOx质量浓度预测精度低。SIS中保留SCR脱硝反应器的各项运行数据,其中锅炉负荷、温度、压力、SCR入口NOx质量浓度、入口烟气氧量、锅炉送风量、脱硝效率、耗煤量等都会对出口NOx质量浓度有直接的影响。采用PCA方法对16个工艺参数及出口NOx质量浓度进行特征提取。通过计算各主成分的累计贡献率(表1),前6个主成分的累计贡献率为86.91%,因此将这6个主成分选定为模型输入变量。同时,考虑到出口NOx质量浓度具有时间序列相关性,将上一采样时刻的NOx质量浓度纳入输入变量集,最终确定7个特征参数作为EGWO-LSTM预测模型的输入参数。
研究数据来源于国内某超超临界1 000 MW燃煤发电机组的SIS历史运行数据,数据采样间隔为1 s,选取1 400组用于预测实验,含800组训练集、300组测试集、300组验证集。经检测无异常数据,为确保LSTM模型的预测稳定性,对输入数据进行归一化预处理,设最大值为0.9,最小值为0.1。
本文采用均方根误差(δRMSE)和平均绝对百分比误差(δMAPE)作为模型效果的量化评估依据。通过结合2种具有互补特性的统计量(前者反映绝对偏差幅度,后者刻画相对误差水平),构建多维度的性能评价体系,其表达式为:
δRMSE=1ni=1n(yif(xi))2
δMAPE=1ni=1n|yif(xi)|yi×100%
式中:yi为实际值;f(xi)为预测输出值;n为预测样本总数。
考虑LSTM神经网络隐含层层数的不同会对预测精度影响较大[16]。因此,本文研究基于Python 2.0深度学习框架,构建了3种不同结构的预测模型:单层LSTM(PCA-LSTM1)、双层LSTM(PCA-LSTM2)和3层LSTM(PCA-LSTM3)。各模型采用相同数据集,3种不同隐含层层数的LSTM神经网络的均方根误差分别为1.92、1.59、2.14 mg/m3,平均绝对百分比误差分别为2.84%、2.35%、3.15%。2层隐含层比1层和3层隐含层预测精度分别提高了17.20%和25.50%。表明在一定范围内,模型预测精度随隐含层数量增加呈现正向改善趋势。然而随着隐含层层数的不断增加,误差开始增大,出现过拟合现象,模型泛化能力降低。因此,后续仿真实验中LSTM隐含层设为2层。LSTM神经网络的神经元数量、学习率和迭代次数会对预测精度造成较大影响,故建立5种模型进行对比,分别为收敛因子采用常规线性更新迭代的PCA-GWO-LSTM2、动态非线性更新收敛因子和高斯变异的PCA-EGWO-LSTM2,以及构建的PCA-LSSVM和PCA-BP网络,各模型采用相同数据集。LSSVM中采用径向基函数(radial basis function,RBF)作为核函数,BP(back propagation)神经网络隐含层采用tanh激活函数,Adam优化器。
灰狼算法种群数量为5,迭代次数为100次。设置LSTM神经网络各隐含层的神经元数量在[1, 100],学习率的调节区间设置为[0.001, 0.01],同时训练迭代次数的取值范围限定在[100, 800]。表2为上述各模型的预测性能对比。
在预测精度方面,PCA-BP模型的预测误差最大,PCA-LSSVM模型次之,PCA-LSTM2模型相对于BP和LSSVM预测精度分别提高了51.93%和42.44%,表明LSTM神经网络更加适合处理长时间序列数据。PCA-GWO-LSTM2相对于PCA-LSTM2预测精度提高了18.25%。PCA-EGWO-LSTM2模型误差最小,预测效果最好,其均方根误差为0.68 mg/m3,平均绝对百分比误差为1.01%,相对于采用常规线性更新收敛因子的PCA-GWO-LSTM2模型预测精度提高了39.29%;相对于PCA-LSTM2和PCA-BP,均方根误差分别减小了50.36%和76.14%,平均绝对百分比误差减小了50.25%和76.01%。
在训练模型耗时方面,PCA-EGWO-LSTM2模型耗时最短,仅为189.06 s,较PCA-BP和PCA-LSSVM模型耗时分别缩短了77.43%和68.32%。EGWO模型相较于GWO模型,计算效率提升了29.38%。综上,灰狼算法可以对LSTM神经网络进行优化,以获取最佳超参数组合。采用动态非线性更新收敛因子和高斯变异策略优化灰狼算法可以进一步提升LSTM神经网络的预测性能。
图4展示了常规GWO与EGWO算法优化LSTM神经网络时适应度变化。由图4可见,同等迭代次数下,采用非线性更新收敛因子和高斯变异策略的EGWO收敛到最小值更快。前40次迭代,GWO陷入局部最优的频次远超EGWO。随着迭代的进行,GWO第36步获全局最优值,而EGWO第9步就可以获得全局最优值。可见,EGWO全局寻优能力更强,收敛速度更快,陷入局部最优概率低,更易找到理想最优解。
1)SCR脱硝反应器运行复杂,机理建模难以精准预测出口NOx质量浓度,构建PCA-EGWO-LSTM预测模型,利用实际数据仿真验证模型的有效性。
2)利用PCA算法降低了模型的输入变量,优化模型的预测精度,提高了泛化能力。相对于GWO,EGWO为LSTM提供更优的参数组合。本文所建模型的均方根误差降低至0.68 mg/m3,平均绝对百分比误差仅为1.01%。
3)利用动态非线性迭代更新收敛因子和变异策略优化EGWO算法,使得EGWO算法获得最优解时的迭代次数更少,且全局寻优能力更强、收敛速度更快,收敛精度更高。
  • 国家自然科学基金项目(61273190)
  • 上海市电站自动化技术重点实验室资助项目(13DZ2273800)
参考文献 引证文献
排序方式:
[1]
柴有国, 何晓燕, 苏永健, 等. 考虑安全环保及补偿的火电机组调峰经济性研究[J]. 中国电力, 2021, 54(11): 199-205.
CHAI Youguo, HE Xiaoyan, SU Yongjian, et al. Economic study on peak shaving of thermal power units considering safety, environmental protection, and compensation[J]. Electric Power, 2021, 54(11): 199-205.
[2]
许壮, 康英伟. 基于随机森林的火电机组SCR脱硝反应器建模[J]. 动力工程学报, 2020, 40(6): 486-491.
XU Zhuang, KANG Yingwei. Modeling of SCR denitrification reactor for thermal power units based on random forest[J]. Journal of Power Engineering, 2020, 40(6): 486-491.
[3]
张珑慧, 林德海, 王颖, 等. 机器学习在火电厂NOx减排中的应用综述[J]. 热力发电, 2023, 52(1): 7-17.
ZHANG Longhui, LIN Dehai, WANG Ying, et al. Overview of the application of machine learning in NOx reduction in thermal power plants[J]. Thermal Power Generation, 2023, 52(1): 7-17.
[4]
张晓雯, 向文国, 陈时熠, 等. 基于小波去噪和PCA-ANFIS的SCR脱硝系统建模[J]. 热力发电, 2021, 50(6): 114-120.
ZHANG Xiaowen, XIANG Wenguo, CHEN Shiyi, et al. Modeling of SCR denitrification system based on wavelet denoising and PCA-AFIS[J]. Thermal Power Generation, 2021, 50(6): 114-120.
[5]
徐圆圆, 龚德鸿, 邓传记, 等. SCR反应器入口参数与反应温度对脱硝性能的交互作用[J]. 环境工程学报, 2023, 17(11): 3721-3729.
XU Yuanyuan, GONG Dehong, DENG Chuanji, et al. The interaction between SCR reactor inlet parameters and reaction temperature on denitrification performance[J]. Journal of Environmental Engineering, 2023, 17(11): 3721-3729.
[6]
AN B, TANG M, QIU J, et al. Dynamic NOx prediction model for SCR denitrification outlet of coal-fired power plants based on hybrid data-driven and model ensemble[J]. Industrial & Engineering Chemistry Research, 2023, 62(36): 14286-14299.
[7]
JUNJIE K, YUGUANG N, BO H, 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(1): 867-878.
[8]
李影, 卓建坤, 吴逸凡, 等. 可解释的变负荷下燃煤机组SCR反应器入口NOx质量浓度预测模型[J]. 热力发电, 2024, 53(7): 119-128.
LI Ying, ZHUO Jiankun, WU Yifan, et al. Explainable predictive model for NOx mass concentration at the inlet of SCR reactor in coal-fired power units under variable load[J]. Thermal Power Generation, 2024, 53(7): 119-128.
[9]
陆必伟, 李捷辉. 基于GWO-LSTM的柴油机NOx排放预测[J]. 车用发动机, 2024(3): 80-87.
LU Biwei, LI Jiehui. Prediction of NOx emissions from diesel engines based on GWO-LSTM[J]. Automotive Engines, 2024(3): 80-87.
[10]
董浩, 李明星, 张淑清, 等. 基于核主成分分析和极限学习机的短期电力负荷预测[J]. 电子测量与仪器学报, 2018, 32(1): 188-193.
DONG Hao, LI Mingxing, ZHANG Shuqing, et al. Short term power load forecasting based on kernel principal component analysis and extreme learning machine[J]. Journal of Electronic Measurement and Instrumentation, 2018, 32(1): 188-193.
[11]
胡阳, 杨泽, 房方, 等. 火电机组供电碳减排高维运行特征提取及其最优基准值确定[J]. 中国电机工程学报, 2021, 41(增刊1): 210-220.
HU Yang, YANG Ze, FANG Fang, et al. High dimensional operation feature extraction and optimal benchmark value determination for carbon emission reduction in power supply of thermal power units[J]. Proceedings of CSEE, 2021, 41(Suppl.1): 210-220.
[12]
HOCHREITER S J, UUM L, SCHMIDHUBER R. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735.
[13]
吴磊, 康英伟. 基于改进粒子群优化长短时记忆神经网络的脱硫系统SO2预测模型[J]. 热力发电, 2021, 50(12): 66-73.
WU Lei, KANG Yingwei. SO2 prediction model for desulfurization system based on improved particle swarm optimization long short-term memory neural network[J]. Thermal Power Generation, 2021, 50(12): 66-73.
[14]
MIRJALILI S, MIRJALILI S M, LEWIS A. Grey wolf optimizer[J]. Advance in Engineering Software, 2014, 69: 46-61.
[15]
左剑, 张程稳, 肖逸, 等. 基于灰狼优化算法的多机电力系统稳定器参数最优设计[J]. 电网技术, 2017, 41(9): 2987-2995.
ZUO Jian, ZHANG Chengwen, XIAO Yi, et al. Optimal design of stabilizer parameters for multi machine power systems based on grey wolf optimization algorithm[J]. Grid Technology, 2017, 41(9): 2987-2995.
[16]
仝卫国, 郭超宇, 赵如意. 基于变量选择和MGWO-LSTM的浆液pH值预测[J]. 控制工程, 2024, 31(12): 2140-2148.
TONG Weiguo, GUO Chaoyu, ZHAO Ruyi. Prediction of pH value of slurry based on variable selection and MGWO-LSTM[J]. Control Engineering, 2024, 31(12): 2140-2148.
2025年第54卷第11期
PDF下载
101
46
引用本文
BibTeX
文章信息
doi: 10.19666/j.rlfd.202502032
  • 接收时间:2025-02-24
  • 首发时间:2026-01-13
  • 出版时间:2025-11-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-02-24
基金
National Natural Science Foundation of China(61273190)
国家自然科学基金项目(61273190)
Funding Project of Shanghai Key Laboratory of Power Station Automation Technology(13DZ2273800)
上海市电站自动化技术重点实验室资助项目(13DZ2273800)
作者信息
    1.国网上海青浦供电公司,上海 201700
    2.上海电力大学自动化工程学院,上海 200090
    3.上海市电站自动化技术重点实验室,上海 200090

通讯作者:

张军(1966),男,博士,副教授,主要研究方向为机器学习、复杂系统智能控制与优化,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202502032
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