Article(id=1215700942377374238, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1215700941538509036, articleNumber=null, orderNo=null, doi=10.19666/j.rlfd.202401012, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1705852800000, receivedDateStr=2024-01-22, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1767775291294, onlineDateStr=2026-01-07, pubDate=1721836800000, pubDateStr=2024-07-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1767775291294, onlineIssueDateStr=2026-01-07, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1767775291294, creator=13701087609, updateTime=1767775291294, updator=13701087609, issue=Issue{id=1215700941538509036, tenantId=1146029695717560320, journalId=1210938733613449225, year='2024', volume='53', issue='7', pageStart='1', pageEnd='158', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1767775291094, creator=13701087609, updateTime=1767775458121, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1215701642159243949, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1215700941538509036, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1215701642159243950, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1215700941538509036, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=119, endPage=128, ext={EN=ArticleExt(id=1215700942612255263, articleId=1215700942377374238, tenantId=1146029695717560320, journalId=1210938733613449225, language=EN, title=Interpretable prediction model for NOx mass concentration at SCR reactor inlet in coal-fired power plants under flexible operating conditions, columnId=1211002405299294959, journalTitle=Thermal Power Generation, columnName=Thermal energy science research, runingTitle=null, highlight=null, articleAbstract=

There is a delay in NOx measurement for flexible operations in coal-fired power plants, which leads to a delayed response in ammonia injection control system of selective catalytic reduction (SCR) reactor, resulting in potential over or under-injection of ammonia and significant fluctuations in NOx mass concentration at outlet of the SCR reactor. To enable proactive adjustment of ammonia injection and considering the interconnected factors influencing the NOx emissions from coal combustion, a prediction model for NOx mass concentration at the SCR reactor inlet is proposed based on convolutional neural networks (CNNs) and long short-term memory neural (LSTM) networks. By using operational parameters from a 330 MW coal-fired power plant, a Pearson coefficient method is employed to calculate the correlation between feature variables. Significant features are extracted to define the model input matrix and output matrix. The random search algorithm is used for hyper-parameters optimization to enhance predictive performance. The SHAP algorithm is then applied to interpret the model structure and explain the black-box model. Finally, the control effects of model with NOx concentration prediction is verified through Simulink simulation. The results indicate that, the CNN-LSTM prediction model demonstrates higher predictive accuracy for the variable NOx mass concentration at the SCR reactor inlet during the frequent load fluctuations. It can provide feedback to the ammonia injection control system of 25 seconds in advance. The optimized ammonia injection control strategy not only reduces the standard deviation between the NOx mass concentration at the SCR reactor outlet and the set value by 28%, but also improves the response speed of NH3/NOx regulation, reducing the maximum ammonia slip by 22%. The research findings can provide guidance for intelligent SCR denitration system and combustion optimizing operating during flexible operation of coal-fired 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=Ying LI, Jiankun ZHUO, Yifan WU, Yonggang FAN, Qiang YAO, Shuiqing LI), CN=ArticleExt(id=1215700947272127089, articleId=1215700942377374238, tenantId=1146029695717560320, journalId=1210938733613449225, language=CN, title=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, columnId=1211002405437706993, journalTitle=热力发电, columnName=热能科学研究, runingTitle=null, highlight=null, articleAbstract=

燃煤电厂灵活调峰过程NOx测量往往存在滞后现象,导致选择性催化还原(selective satalytic reduction,SCR)脱硝喷氨控制系统响应不及时,易造成喷氨量过高或过低,从而造成SCR反应器出口NOx质量浓度波动剧烈和氨逃逸率增大。为实现喷氨阀门的提前快速调节并考虑影响燃煤锅炉NOx排放量的因素存在耦合性,提出了一种基于卷积神经网络(convolutional neural network,CNN)和长短时记忆(long short-term memory,LSTM)神经网络混合模型的SCR反应器入口NOx预测模型。利用一台330 MW燃煤电站锅炉的运行参数,通过Pearson系数法计算特征变量之间的相关性,筛选出相关性较大的特征,并定义模型的输入矩阵和输出矩阵,采用随机搜索算法进行优化,以提高预测性能。进一步利用SHAP算法对黑箱模型进行解释,并通过Simulink仿真验证了带有NOx预测的控制效果。结果表明:CNN-LSTM预测模型在调峰负荷变化时,能够以较高的精度预测SCR反应器入口NOx质量浓度的变化,并能提前25 s为喷氨控制系统提供反馈;优化后的喷氨控制策略降低了出口NOx质量浓度与设定值间的标准差(降低28%),并提升了NH3/NOx的响应速度,减小最大氨逃逸量22%。该研究结果可为灵活调峰机组的智慧SCR脱硝技术及燃烧优化提出有效的指导。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
卓建坤(1975),男,博士,副研究员,主要研究方向为清洁燃烧及智慧电厂等,
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=IAD0DIIlOHl0wrrkvf4SIg==, magXml=OQpxHgO2PnO/tZxDWyzw4A==, pdfUrl=null, pdf=exx8h7KCl+tNR396/YtM3Q==, pdfFileSize=2447545, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=Mcr3DrEHadqVUmX6oYs5YA==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=xV6SvxLixhE3IjSSVIL0mQ==, mapNumber=null, authorCompany=null, fund=null, authors=

李影(1999),女,硕士研究生,主要研究方向为智慧电厂污染物控制等,

, authorsList=李影, 卓建坤, 吴逸凡, 樊永刚, 姚强, 李水清)}, authors=[Author(id=1215700947720917637, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=3214650576@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1215700947834163850, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, authorId=1215700947720917637, language=EN, stringName=Ying LI, firstName=Ying, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Electrical Engineering, Xinjiang University, Urumqi 830046, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215700947918049936, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, authorId=1215700947720917637, language=CN, stringName=李影, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.新疆大学电气工程学院,新疆 乌鲁木齐 830046, bio={"content":"

李影(1999),女,硕士研究生,主要研究方向为智慧电厂污染物控制等,

"}, bioImg=null, bioContent=

李影(1999),女,硕士研究生,主要研究方向为智慧电厂污染物控制等,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215700947523785335, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, xref=1., ext=[AuthorCompanyExt(id=1215700947527979639, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947523785335, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Electrical Engineering, Xinjiang University, Urumqi 830046, China), AuthorCompanyExt(id=1215700947536368248, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947523785335, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.新疆大学电气工程学院,新疆 乌鲁木齐 830046)])]), Author(id=1215700947993547413, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhuojk@tsinghua.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1215700948064850587, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, authorId=1215700947993547413, language=EN, stringName=Jiankun ZHUO, firstName=Jiankun, middleName=null, lastName=ZHUO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Key Laboratory for Thermal Science and Power Engineering of Ministry of Education, Tsinghua University, Beijing 100084, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215700948144542369, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, authorId=1215700947993547413, language=CN, stringName=卓建坤, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.清华大学热科学与动力工程教育部重点实验室,北京 100084, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215700947628642945, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, xref=2., ext=[AuthorCompanyExt(id=1215700947637031552, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947628642945, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Key Laboratory for Thermal Science and Power Engineering of Ministry of Education, Tsinghua University, Beijing 100084, China), AuthorCompanyExt(id=1215700947641225857, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947628642945, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.清华大学热科学与动力工程教育部重点实验室,北京 100084)])]), Author(id=1215700948241011365, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, 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=1215700948345868972, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, authorId=1215700948241011365, language=EN, stringName=Yifan WU, firstName=Yifan, middleName=null, lastName=WU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Key Laboratory for Thermal Science and Power Engineering of Ministry of Education, Tsinghua University, Beijing 100084, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215700948425560754, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, authorId=1215700948241011365, language=CN, stringName=吴逸凡, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.清华大学热科学与动力工程教育部重点实验室,北京 100084, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215700947628642945, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, xref=2., ext=[AuthorCompanyExt(id=1215700947637031552, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947628642945, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Key Laboratory for Thermal Science and Power Engineering of Ministry of Education, Tsinghua University, Beijing 100084, China), AuthorCompanyExt(id=1215700947641225857, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947628642945, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.清华大学热科学与动力工程教育部重点实验室,北京 100084)])]), Author(id=1215700948517835451, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, 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=1215700948631081661, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, authorId=1215700948517835451, language=EN, stringName=Yonggang FAN, firstName=Yonggang, middleName=null, lastName=FAN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Electrical Engineering, Xinjiang University, Urumqi 830046, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215700948769493699, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, authorId=1215700948517835451, language=CN, stringName=樊永刚, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.新疆大学电气工程学院,新疆 乌鲁木齐 830046, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215700947523785335, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, xref=1., ext=[AuthorCompanyExt(id=1215700947527979639, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947523785335, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Electrical Engineering, Xinjiang University, Urumqi 830046, China), AuthorCompanyExt(id=1215700947536368248, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947523785335, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.新疆大学电气工程学院,新疆 乌鲁木齐 830046)])]), Author(id=1215700948844991178, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, 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=1215700948970820306, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, authorId=1215700948844991178, language=EN, stringName=Qiang YAO, firstName=Qiang, middleName=null, lastName=YAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.School of Electrical Engineering, Xinjiang University, Urumqi 830046, China
2.Key Laboratory for Thermal Science and Power Engineering of Ministry of Education, Tsinghua University, Beijing 100084, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215700949205701337, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, authorId=1215700948844991178, language=CN, stringName=姚强, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.新疆大学电气工程学院,新疆 乌鲁木齐 830046
2.清华大学热科学与动力工程教育部重点实验室,北京 100084, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215700947523785335, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, xref=1., ext=[AuthorCompanyExt(id=1215700947527979639, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947523785335, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Electrical Engineering, Xinjiang University, Urumqi 830046, China), AuthorCompanyExt(id=1215700947536368248, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947523785335, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.新疆大学电气工程学院,新疆 乌鲁木齐 830046)]), AuthorCompany(id=1215700947628642945, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, xref=2., ext=[AuthorCompanyExt(id=1215700947637031552, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947628642945, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Key Laboratory for Thermal Science and Power Engineering of Ministry of Education, Tsinghua University, Beijing 100084, China), AuthorCompanyExt(id=1215700947641225857, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947628642945, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.清华大学热科学与动力工程教育部重点实验室,北京 100084)])]), Author(id=1215700950539490015, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, 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=1215700950644347620, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, authorId=1215700950539490015, language=EN, stringName=Shuiqing LI, firstName=Shuiqing, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Key Laboratory for Thermal Science and Power Engineering of Ministry of Education, Tsinghua University, Beijing 100084, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1215700950728233704, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, authorId=1215700950539490015, language=CN, stringName=李水清, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.清华大学热科学与动力工程教育部重点实验室,北京 100084, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1215700947628642945, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, xref=2., ext=[AuthorCompanyExt(id=1215700947637031552, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947628642945, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Key Laboratory for Thermal Science and Power Engineering of Ministry of Education, Tsinghua University, Beijing 100084, China), AuthorCompanyExt(id=1215700947641225857, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947628642945, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.清华大学热科学与动力工程教育部重点实验室,北京 100084)])])], keywords=[Keyword(id=1215700950841479917, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, orderNo=1, keyword=NOx prediction), Keyword(id=1215700950929560306, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, orderNo=2, keyword=coal-fired power unit), Keyword(id=1215700951009252088, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, orderNo=3, keyword=CNN-LSTM model), Keyword(id=1215700951080555260, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, orderNo=4, keyword=SHAP), Keyword(id=1215700951168635648, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, orderNo=5, keyword=flexible operation), Keyword(id=1215700951260910345, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, orderNo=1, keyword=NOx预测), Keyword(id=1215700951365767952, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, orderNo=2, keyword=燃煤机组), Keyword(id=1215700951470625557, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, orderNo=3, keyword=CNN-LSTM模型), Keyword(id=1215700951571288864, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, orderNo=4, keyword=SHAP), Keyword(id=1215700951667757868, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, orderNo=5, keyword=灵活调峰)], refs=[Reference(id=1215700958412198085, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=3, pageStart=9, pageEnd=26, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=null, journalName=中国统计, refType=null, unstructuredReference=中华人民共和国2021年国民经济和社会发展统计公报[J]. 中国统计, 2022(3): 9-26., articleTitle=中华人民共和国2021年国民经济和社会发展统计公报, refAbstract=null), Reference(id=1215700959691460812, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=3, pageStart=9, pageEnd=26, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=null, journalName=China Statistics, refType=null, unstructuredReference=Statistical Communique of the People’s Republic of China on the 2021 National Economic and Social Development[J]. China Statistics, 2022(3): 9-26., articleTitle=Statistical Communique of the People’s Republic of China on the 2021 National Economic and Social Development, refAbstract=null), Reference(id=1215700959796318417, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2014, volume=34, issue=29, pageStart=5029, pageEnd=5040, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=薛禹胜, 雷兴, 薛峰, journalName=中国电机工程学报, refType=null, unstructuredReference=薛禹胜, 雷兴, 薛峰, 等. 关于风电不确定性对电力系统影响的评述[J]. 中国电机工程学报, 2014, 34(29): 5029-5040., articleTitle=关于风电不确定性对电力系统影响的评述, refAbstract=null), Reference(id=1215700959884398806, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2014, volume=34, issue=29, pageStart=5029, pageEnd=5040, url=null, language=null, rfNumber=[2], rfOrder=3, authorNames=XUE Yusheng, LEI Xing, XUE Feng, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=XUE Yusheng, LEI Xing, XUE Feng, et al. A review on impacts of wind power uncertainties on power systems[J]. Proceedings of the CSEE, 2014, 34(29): 5029-5040., articleTitle=A review on impacts of wind power uncertainties on power systems, refAbstract=null), Reference(id=1215700959972479192, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2019, volume=39, issue=10, pageStart=2970, pageEnd=2980, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=闫来清, 董泽, journalName=中国电机工程学报, refType=null, unstructuredReference=闫来清, 董泽. 基于k-近邻互信息和WKOPLS的SCR脱硝系统动态预测模型[J]. 中国电机工程学报, 2019, 39(10): 2970-2980., articleTitle=基于k-近邻互信息和WKOPLS的SCR脱硝系统动态预测模型, refAbstract=null), Reference(id=1215700960085725406, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2019, volume=39, issue=10, pageStart=2970, pageEnd=2980, url=null, language=null, rfNumber=[3], rfOrder=5, authorNames=YAN Laiqing, DONG Ze, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=YAN Laiqing, DONG Ze. Dynamic prediction model of SCR denitrification system based on k-nearest neighbor mutual information and WKOPLS[J]. Proceedings of the CSEE, 2019, 39(10): 2970-2980., articleTitle=Dynamic prediction model of SCR denitrification system based on k-nearest neighbor mutual information and WKOPLS, refAbstract=null), Reference(id=1215700960207360230, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=5, pageStart=17, pageEnd=22, url=null, language=null, rfNumber=[4], rfOrder=6, authorNames=翁卫国, 刘博文, 郭一杉, journalName=锅炉制造, refType=null, unstructuredReference=翁卫国, 刘博文, 郭一杉, 等. 基于入口NOx浓度软测量的脱硝系统先进控制研究[J]. 锅炉制造, 2019(5): 17-22., articleTitle=基于入口NOx浓度软测量的脱硝系统先进控制研究, refAbstract=null), Reference(id=1215700960324800744, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=5, pageStart=17, pageEnd=22, url=null, language=null, rfNumber=[4], rfOrder=7, authorNames=WENG Weiguo, LIU Bowen, GUO Yishan, journalName=Boiler Manufacturing, refType=null, unstructuredReference=WENG Weiguo, LIU Bowen, GUO Yishan, et al. Model predictive control utilizing gas soft-sensors on SCR denitration system in thermoelectric unit[J]. Boiler Manufacturing, 2019(5): 17-22., articleTitle=Model predictive control utilizing gas soft-sensors on SCR denitration system in thermoelectric unit, refAbstract=null), Reference(id=1215700960396103918, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=8, authorNames=张晓雯, journalName=null, refType=null, unstructuredReference=张晓雯. 燃煤机组SCR脱硝系统建模与优化控制研究[D]. 南京: 东南大学, 2021: 1., articleTitle=燃煤机组SCR脱硝系统建模与优化控制研究, refAbstract=null), Reference(id=1215700960488378607, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=9, authorNames=ZHANG Xiaowen, journalName=null, refType=null, unstructuredReference=ZHANG Xiaowen. Modeling and optimal control of SCR denitrification system for coal-fired units[D]. Nanjing: Southeast University, 2021: 1., articleTitle=Modeling and optimal control of SCR denitrification system for coal-fired units, refAbstract=null), Reference(id=1215700960597430516, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2020, volume=274, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=10, authorNames=YANG T, MA K, LV Y, journalName=Fuel, refType=null, unstructuredReference=YANG T, MA K, LV Y, et al. Real-time dynamic prediction model of NOx emission of coal-fired boilers under variable load conditions[J]. Fuel, 2020, 274: 117811., articleTitle=Real-time dynamic prediction model of NOx emission of coal-fired boilers under variable load conditions, refAbstract=null), Reference(id=1215700960681316600, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2019, volume=176, issue=null, pageStart=429, pageEnd=436, url=null, language=null, rfNumber=[7], rfOrder=11, 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=1215700960748425469, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2015, volume=9, issue=10, pageStart=5011, pageEnd=5016, url=null, language=null, rfNumber=[8], rfOrder=12, authorNames=王桂林, 张宇, 王森, journalName=环境工程学报, refType=null, unstructuredReference=王桂林, 张宇, 王森, 等. 基于支持向量机的选择性催化还原脱硝系统运行优化[J]. 环境工程学报, 2015, 9(10): 5011-5016., articleTitle=基于支持向量机的选择性催化还原脱硝系统运行优化, refAbstract=null), Reference(id=1215700960815534337, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2015, volume=9, issue=10, pageStart=5011, pageEnd=5016, url=null, language=null, rfNumber=[8], rfOrder=13, authorNames=WANG Guilin, ZHANG Yu, WANG Sen, journalName=Chinese Journal of Environmental Engineering, refType=null, unstructuredReference=WANG Guilin, ZHANG Yu, WANG Sen, et al. Operation optimization of selective catalytic reduction system based on support vector machine[J]. Chinese Journal of Environmental Engineering, 2015, 9(10): 5011-5016., articleTitle=Operation optimization of selective catalytic reduction system based on support vector machine, refAbstract=null), Reference(id=1215700960895226117, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2017, volume=37, issue=11, pageStart=931, pageEnd=937, url=null, language=null, rfNumber=[9], rfOrder=14, authorNames=廖永进, 范军辉, 杨维结, journalName=动力工程学报, refType=null, unstructuredReference=廖永进, 范军辉, 杨维结, 等. 基于RBF神经网络的SCR脱硝系统喷氨优化[J]. 动力工程学报, 2017, 37(11): 931-937., articleTitle=基于RBF神经网络的SCR脱硝系统喷氨优化, refAbstract=null), Reference(id=1215700960979112205, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2017, volume=37, issue=11, pageStart=931, pageEnd=937, url=null, language=null, rfNumber=[9], rfOrder=15, authorNames=LIAO Yongjin, FAN Junhui, YANG Weijie, journalName=Journal of Power Engineering, refType=null, unstructuredReference=LIAO Yongjin, FAN Junhui, YANG Weijie, et al. Ammonia spraying optimization of an SCR denitrification system based on RBF neural network[J]. Journal of Power Engineering, 2017, 37(11): 931-937., articleTitle=Ammonia spraying optimization of an SCR denitrification system based on RBF neural network, refAbstract=null), Reference(id=1215700961088164112, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2020, volume=40, issue=20, pageStart=6633, pageEnd=6644, url=null, language=null, rfNumber=[10], rfOrder=16, authorNames=唐振浩, 柴向颖, 曹生现, journalName=中国电机工程学报, refType=null, unstructuredReference=唐振浩, 柴向颖, 曹生现, 等. 考虑时延特征的燃煤锅炉NOx排放深度学习建模[J]. 中国电机工程学报, 2020, 40(20): 6633-6644., articleTitle=考虑时延特征的燃煤锅炉NOx排放深度学习建模, refAbstract=null), Reference(id=1215700961218187543, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2020, volume=40, issue=20, pageStart=6633, pageEnd=6644, url=null, language=null, rfNumber=[10], rfOrder=17, authorNames=TANG Zhenhao, CHAI Xiangying, CAO Shengxian, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=TANG Zhenhao, CHAI Xiangying, CAO Shengxian, et al. Deep learning modeling for the NOx emissions of coal-fired boiler considering time-delay characteristics [J]. Proceedings of the CSEE, 2020, 40(20): 6633-6644., articleTitle=Deep learning modeling for the NOx emissions of coal-fired boiler considering time-delay characteristics, refAbstract=null), Reference(id=1215700961327239451, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=18, authorNames=王英男, journalName=null, refType=null, unstructuredReference=王英男. 燃煤锅炉的NOx排放预测与控制研究[D]. 北京: 华北电力大学, 2021: 1., articleTitle=燃煤锅炉的NOx排放预测与控制研究, refAbstract=null), Reference(id=1215700961411125537, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=19, authorNames=WANG Yingnan, journalName=null, refType=null, unstructuredReference=WANG Yingnan. Research on NOx emission prediction and control of coal-fired boiler[D]. Beijing: North China Electric Power University, 2021: 1., articleTitle=Research on NOx emission prediction and control of coal-fired boiler, refAbstract=null), Reference(id=1215700961515983140, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2022, volume=847, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=20, authorNames=QIAO J, journalName=Science of the Total Environment, refType=null, unstructuredReference=QIAO J. A novel online modeling for NOx generation prediction in coal-fired boiler[J]. Science of the Total Environment, 2022, 847: 157542., articleTitle=A novel online modeling for NOx generation prediction in coal-fired boiler, refAbstract=null), Reference(id=1215700961625035051, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2021, volume=289, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=21, authorNames=YUAN Z, MENG L, GU X, journalName=Fuel, refType=null, unstructuredReference=YUAN Z, MENG L, GU X, et al. Prediction of NOx emissions for coal-fired power plants with stacked-Generalization Ensemble Method[J]. Fuel, 2021, 289: 119748., articleTitle=Prediction of NOx emissions for coal-fired power plants with stacked-Generalization Ensemble Method, refAbstract=null), Reference(id=1215700961700532530, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2009, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=姚强, 李水清, 王宇, journalName=燃烧学导论, refType=null, unstructuredReference=姚强, 李水清, 王宇. 燃烧学导论[M]. 北京: 清华大学出版社, 2009: 1., articleTitle=null, refAbstract=null), Reference(id=1215700961822167358, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2009, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=23, authorNames=YAO Qiang, LI Shuiqing, WANG Yu, journalName=An introduction to combustion concepts and applications, refType=null, unstructuredReference=YAO Qiang, LI Shuiqing, WANG Yu, et al. An introduction to combustion concepts and applications[M]. Beijing: Tsinghua University Press, 2009: 1., articleTitle=null, refAbstract=null), Reference(id=1215700961931219272, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=3, pageStart=1052, pageEnd=1060, url=null, language=null, rfNumber=[15], rfOrder=24, authorNames=刘菡, 王英男, 李新利, journalName=中国电机工程学报, refType=null, unstructuredReference=刘菡, 王英男, 李新利, 等. 基于互信息-图卷积神经网络的燃煤电站NOx排放预测[J]. 中国电机工程学报, 2022, 42(3): 1052-1060., articleTitle=基于互信息-图卷积神经网络的燃煤电站NOx排放预测, refAbstract=null), Reference(id=1215700962015105358, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=3, pageStart=1052, pageEnd=1060, url=null, language=null, rfNumber=[15], rfOrder=25, authorNames=LIU Han, WANG Yingnan, LI Xinli, journalName=Proceeding of the CSEE, refType=null, unstructuredReference=LIU Han, WANG Yingnan, LI Xinli, et al. Prediction of NOx emission in coal-fired power plants based on mutual information-graph convolutional neural network[J]. Proceeding of the CSEE, 2022, 42(3): 1052-1060., articleTitle=Prediction of NOx emission in coal-fired power plants based on mutual information-graph convolutional neural network, refAbstract=null), Reference(id=1215700962111574354, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2011, volume=31, issue=26, pageStart=16, pageEnd=22, url=null, language=null, rfNumber=[16], rfOrder=26, authorNames=吕玉坤, 彭鑫, 赵锴, journalName=中国电机工程学报, refType=null, unstructuredReference=吕玉坤, 彭鑫, 赵锴. 电站锅炉热效率和NOx排放混合建模与优化[J]. 中国电机工程学报, 2011, 31(26): 16-22., articleTitle=电站锅炉热效率和NOx排放混合建模与优化, refAbstract=null), Reference(id=1215700962203849050, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2011, volume=31, issue=26, pageStart=16, pageEnd=22, url=null, language=null, rfNumber=[16], rfOrder=27, authorNames=LYU Yukun, PENG Xin, ZHAO Kai, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=LYU Yukun, PENG Xin, ZHAO Kai. Hybrid modeling optimization of thermal efficiency and NOx emission of utility boiler[J]. Proceedings of the CSEE, 2011, 31(26): 16-22., articleTitle=Hybrid modeling optimization of thermal efficiency and NOx emission of utility boiler, refAbstract=null), Reference(id=1215700962283540832, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2020, volume=8, issue=null, pageStart=85912, pageEnd=85922, url=null, language=null, rfNumber=[17], rfOrder=28, authorNames=LI N, HU Y, journalName=IEEE Access, refType=null, unstructuredReference=LI N, HU Y. The deep convolutional neural network for NOx emission prediction of a coal-fired boiler[J]. IEEE Access, 2020, 8: 85912-85922., articleTitle=The deep convolutional neural network for NOx emission prediction of a coal-fired boiler, refAbstract=null), Reference(id=1215700962367426920, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2023, volume=12, issue=18, pageStart=3929, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=29, authorNames=GUO Y, MAO Z, journalName=Electronics, refType=null, unstructuredReference=GUO Y, MAO Z. Long-term prediction model for NOx emission based on LSTM-transformer[J]. Electronics, 2023, 12(18): 3929., articleTitle=Long-term prediction model for NOx emission based on LSTM-transformer, refAbstract=null), Reference(id=1215700962480673133, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=7, pageStart=162, pageEnd=169, url=null, language=null, rfNumber=[19], rfOrder=30, authorNames=刘岳, 于静, 金秀章, journalName=热力发电, refType=null, unstructuredReference=刘岳, 于静, 金秀章. 基于特征优化和改进长短期记忆神经网络的NOx质量浓度预测[J]. 热力发电, 2021, 50(7): 162-169., articleTitle=基于特征优化和改进长短期记忆神经网络的NOx质量浓度预测, refAbstract=null), Reference(id=1215700962568753524, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=7, pageStart=162, pageEnd=169, url=null, language=null, rfNumber=[19], rfOrder=31, authorNames=LIU Yue, YU Jing, JIN Xiuzhang, journalName=Thermal Power Generation, refType=null, unstructuredReference=LIU Yue, YU Jing, JIN Xiuzhang. NOx mass concentration prediction based on feature optimization and improved LSTM network[J]. Thermal Power Generation, 2021, 50(7): 162-169., articleTitle=NOx mass concentration prediction based on feature optimization and improved LSTM network, refAbstract=null), Reference(id=1215700962665222523, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=1988, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=32, authorNames=null, journalName=null, refType=null, unstructuredReference=电站锅炉性能试验规程: GB/T 10184—1988[S]. 北京: 中国标准出版社, 1988: 1., articleTitle=null, refAbstract=null), Reference(id=1215700962761691518, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=1988, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[20], rfOrder=33, authorNames=null, journalName=null, refType=null, unstructuredReference=Procedures for performance testing of power station boilers: GB/T 10184—1988[S]. Beijing: Standards Press of China, 1988: 1., articleTitle=null, refAbstract=null), Reference(id=1215700962845577605, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=34, authorNames=朱明超, journalName=可解释的机器学习, refType=null, unstructuredReference=朱明超. 可解释的机器学习[M]. 北京: 电子工业出版社, 2021: 1., articleTitle=null, refAbstract=null), Reference(id=1215700962929463691, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=35, authorNames=ZHU Mingchao, journalName=Interpretable machine learning, refType=null, unstructuredReference=ZHU Mingchao. Interpretable machine learning[M]. Beijing: Electronic Industry Press, 2021: 1., articleTitle=null, refAbstract=null), Reference(id=1215700964162589070, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2019, volume=288, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[22], rfOrder=36, authorNames=ZHU X, LI Y, WANG X, journalName=Bioresource Technology, refType=null, unstructuredReference=ZHU X, LI Y, WANG X. Machine learning prediction of biochar yield and carbon contents in biochar based on biomass characteristics and pyrolysis conditions[J]. Bioresource Technology, 2019, 288: 121527., articleTitle=Machine learning prediction of biochar yield and carbon contents in biochar based on biomass characteristics and pyrolysis conditions, refAbstract=null), Reference(id=1215700964301001111, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2022, volume=364, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=37, authorNames=ASCHER S, WANG X, WATSON I, journalName=Bioresource Technology, refType=null, unstructuredReference=ASCHER S, WANG X, WATSON I, et al. Interpretable machine learning to model biomass and waste gasification[J]. Bioresource Technology, 2022, 364: 128062., articleTitle=Interpretable machine learning to model biomass and waste gasification, refAbstract=null), Reference(id=1215700964418441627, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=38, authorNames=杨昌兰, journalName=null, refType=null, unstructuredReference=杨昌兰. 基于深度学习及SHAP解释的城市空间扩展识别与驱动分析[D]. 武汉: 武汉大学, 2022: 1., articleTitle=基于深度学习及SHAP解释的城市空间扩展识别与驱动分析, refAbstract=null), Reference(id=1215700964514910624, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[24], rfOrder=39, authorNames=YANG Changlan, journalName=null, refType=null, unstructuredReference=YANG Changlan. Identification and driving analysis of urban spatial expansion through intergrating deep learning models and SHapley additive explanations[D]. Wuhan: Wuhan University, 2022: 1., articleTitle=Identification and driving analysis of urban spatial expansion through intergrating deep learning models and SHapley additive explanations, refAbstract=null), Reference(id=1215700964615573926, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2008, volume=null, issue=1, pageStart=142, pageEnd=146, url=null, language=null, rfNumber=[25], rfOrder=40, authorNames=董建勋, 李永华, 冯兆兴, journalName=动力工程, refType=null, unstructuredReference=董建勋, 李永华, 冯兆兴, 等. 选择性催化还原烟气脱硝反应器的变工况运行分析[J]. 动力工程, 2008(1): 142-146., articleTitle=选择性催化还原烟气脱硝反应器的变工况运行分析, refAbstract=null), Reference(id=1215700964686877100, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, doi=null, pmid=null, pmcid=null, year=2008, volume=null, issue=1, pageStart=142, pageEnd=146, url=null, language=null, rfNumber=[25], rfOrder=41, authorNames=DONG Jianxun, LI Yonghua, FENG Zhaoxing, journalName=Power Engineering, refType=null, unstructuredReference=DONG Jianxun, LI Yonghua, FENG Zhaoxing, et al. Operation analysis of flue gas denitrification reactors with selective catalytic reduction under variable working conditions[J]. Power Engineering, 2008(1): 142-146., articleTitle=Operation analysis of flue gas denitrification reactors with selective catalytic reduction under variable working conditions, refAbstract=null)], funds=[Fund(id=1215700958185705658, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, awardId=2023A01005-1, language=EN, fundingSource=Provincial Major Scientific and Technological Special Project(2023A01005-1), fundOrder=null, country=null), Fund(id=1215700958294757567, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, awardId=2023A01005-1, language=CN, fundingSource=自治区重大科技专项项目(2023A01005-1), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1215700947523785335, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, xref=1., ext=[AuthorCompanyExt(id=1215700947527979639, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947523785335, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Electrical Engineering, Xinjiang University, Urumqi 830046, China), AuthorCompanyExt(id=1215700947536368248, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947523785335, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.新疆大学电气工程学院,新疆 乌鲁木齐 830046)]), AuthorCompany(id=1215700947628642945, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, xref=2., ext=[AuthorCompanyExt(id=1215700947637031552, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947628642945, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Key Laboratory for Thermal Science and Power Engineering of Ministry of Education, Tsinghua University, Beijing 100084, China), AuthorCompanyExt(id=1215700947641225857, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, companyId=1215700947628642945, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.清华大学热科学与动力工程教育部重点实验室,北京 100084)])], figs=[ArticleFig(id=1215700951860695868, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.1, caption=Predictive algorithm process for NO mass concentration at the SCR reactor inlet , figureFileSmall=a5KgrB2+wPv0h4K7j3CUoA==, figureFileBig=Mcr3DrEHadqVUmX6oYs5YA==, tableContent=null), ArticleFig(id=1215700951961359176, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图1, caption=预测SCR反应器入口NO质量浓度算法流程, figureFileSmall=a5KgrB2+wPv0h4K7j3CUoA==, figureFileBig=Mcr3DrEHadqVUmX6oYs5YA==, tableContent=null), ArticleFig(id=1215700952246571866, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.2, caption=The heatmap of steady load correlation variables, figureFileSmall=J1ANH1vWxD85NZcdEWdrKw==, figureFileBig=OlYm1UBye2o0KdKGgkAB+Q==, tableContent=null), ArticleFig(id=1215700952426926948, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图2, caption=稳定负荷相关变量热力图, figureFileSmall=J1ANH1vWxD85NZcdEWdrKw==, figureFileBig=OlYm1UBye2o0KdKGgkAB+Q==, tableContent=null), ArticleFig(id=1215700952544367471, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.3, caption=The heatmap of variable load correlation variables, figureFileSmall=4mtUVrgGg3/bTrn10C7TkQ==, figureFileBig=pJ233RNhkfXdb7101JdITg==, tableContent=null), ArticleFig(id=1215700952661807990, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图3, caption=变负荷相关变量热力图, figureFileSmall=4mtUVrgGg3/bTrn10C7TkQ==, figureFileBig=pJ233RNhkfXdb7101JdITg==, tableContent=null), ArticleFig(id=1215700952770859907, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.4, caption=Feature variable groups , figureFileSmall=k9tONOjEcX+PQgMqQ3+hcQ==, figureFileBig=tLhhiBWuXH/qtlx+s84pNw==, tableContent=null), ArticleFig(id=1215700952896689040, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图4, caption=特征变量分组, figureFileSmall=k9tONOjEcX+PQgMqQ3+hcQ==, figureFileBig=tLhhiBWuXH/qtlx+s84pNw==, tableContent=null), ArticleFig(id=1215700953043489695, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.5, caption=Comparison between the predicted values and the actual values, figureFileSmall=0iYCiqpN8Ed4HAVcc6SgEA==, figureFileBig=7rruW236OZ38sSGBYl2QOg==, tableContent=null), ArticleFig(id=1215700953202873257, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图5, caption=预测值与测量值对比, figureFileSmall=0iYCiqpN8Ed4HAVcc6SgEA==, figureFileBig=7rruW236OZ38sSGBYl2QOg==, tableContent=null), ArticleFig(id=1215700953295147952, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.6, caption=Relationship between load variations and prediction errors, figureFileSmall=18FOYLiojvZEXWWf5J8ddQ==, figureFileBig=2RI92u9E42GZQnsEiM797g==, tableContent=null), ArticleFig(id=1215700953391616951, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图6, caption=负荷变化与预测误差的关系, figureFileSmall=18FOYLiojvZEXWWf5J8ddQ==, figureFileBig=2RI92u9E42GZQnsEiM797g==, tableContent=null), ArticleFig(id=1215700953488085951, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.7, caption=Comparison between the predicted values and actual values for peaks under operating condition 2, figureFileSmall=0dZqCaYirBj5LplWc8qr1g==, figureFileBig=/veGflq82M/PRtQxT7GDjQ==, tableContent=null), ArticleFig(id=1215700953622303691, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图7, caption=工况2波峰预测值和测量值对比, figureFileSmall=0dZqCaYirBj5LplWc8qr1g==, figureFileBig=/veGflq82M/PRtQxT7GDjQ==, tableContent=null), ArticleFig(id=1215700953710384086, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.8, caption=The variation of operating condition 5 after modification, figureFileSmall=h2b0vINaRqtUVLI4Eghqog==, figureFileBig=56+QgG7ynphBoeDBslC1Nw==, tableContent=null), ArticleFig(id=1215700954578605025, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图8, caption=修正后工况5变化, figureFileSmall=h2b0vINaRqtUVLI4Eghqog==, figureFileBig=56+QgG7ynphBoeDBslC1Nw==, tableContent=null), ArticleFig(id=1215700954670879722, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.9, caption=The load variation data after correction, figureFileSmall=y/sTV6UUdyCrlYsWAZb9Ng==, figureFileBig=z6WTNZItp731UxjlZNSJVQ==, tableContent=null), ArticleFig(id=1215700954746377199, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图9, caption=变负荷数据修正后, figureFileSmall=y/sTV6UUdyCrlYsWAZb9Ng==, figureFileBig=z6WTNZItp731UxjlZNSJVQ==, tableContent=null), ArticleFig(id=1215700954842846200, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.10, caption=The variable load data, figureFileSmall=pxvlohUsJ619JmKZZhSCkQ==, figureFileBig=YYy5cUdAmCyPdw108uM11g==, tableContent=null), ArticleFig(id=1215700954956092414, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图10, caption=变负荷数据, figureFileSmall=pxvlohUsJ619JmKZZhSCkQ==, figureFileBig=YYy5cUdAmCyPdw108uM11g==, tableContent=null), ArticleFig(id=1215700955077726208, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.11, caption=The steady load feature importance plot, figureFileSmall=t9BCaTsEDd1hDAnYji2c+w==, figureFileBig=wehTxDplkkP7jAr5ZSFEZw==, tableContent=null), ArticleFig(id=1215700955211943944, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图11, caption=稳定负荷特征VI图, figureFileSmall=t9BCaTsEDd1hDAnYji2c+w==, figureFileBig=wehTxDplkkP7jAr5ZSFEZw==, tableContent=null), ArticleFig(id=1215700955295830029, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.12, caption=The steady load of summary plot, figureFileSmall=zRorzOlikNQ1LRZ7pLrUWQ==, figureFileBig=PmSu7ehYq+jzh7JCQGGvGQ==, tableContent=null), ArticleFig(id=1215700955379716115, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图12, caption=稳定负荷概要, figureFileSmall=zRorzOlikNQ1LRZ7pLrUWQ==, figureFileBig=PmSu7ehYq+jzh7JCQGGvGQ==, tableContent=null), ArticleFig(id=1215700955476185115, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.13, caption=The variable load-state of summary plot, figureFileSmall=P9JBtzzUxif2nhfpmQeTsQ==, figureFileBig=3ZqfptMMd+ah7Rqfv0JaJQ==, tableContent=null), ArticleFig(id=1215700955585237022, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图13, caption=变负荷概要, figureFileSmall=P9JBtzzUxif2nhfpmQeTsQ==, figureFileBig=3ZqfptMMd+ah7Rqfv0JaJQ==, tableContent=null), ArticleFig(id=1215700955723649065, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.14, caption=The combined effect of the baffle opening of the secondary air damper and total airflow, figureFileSmall=Xvhs8gNXrDgO3IqN3T5vfw==, figureFileBig=8V/V7rh9PFrHdvRWwZLztQ==, tableContent=null), ArticleFig(id=1215700955832700977, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图14, caption=二次风挡板开度和总风量共同影响, figureFileSmall=Xvhs8gNXrDgO3IqN3T5vfw==, figureFileBig=8V/V7rh9PFrHdvRWwZLztQ==, tableContent=null), ArticleFig(id=1215700955924975671, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.15, caption=The combined effect of temperature at the SCR reactor inlet A and total airflow, figureFileSmall=wuzU2jLCE1rSrWXb8FfEYQ==, figureFileBig=XS1f2zVp6P0IIeehZBP4lg==, tableContent=null), ArticleFig(id=1215700956071776317, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图15, caption=SCR反应器入口A温度和总风量共同影响, figureFileSmall=wuzU2jLCE1rSrWXb8FfEYQ==, figureFileBig=XS1f2zVp6P0IIeehZBP4lg==, tableContent=null), ArticleFig(id=1215700956185022532, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.16, caption=Framework of the intelligent predictive feedforward control strategy for SCR denitrification, figureFileSmall=pyoRdLqtq/CyXm9ugdNyoQ==, figureFileBig=iayOsqf62deWGhA3VwpSow==, tableContent=null), ArticleFig(id=1215700956285685834, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图16, caption=SCR脱硝智能预测前馈控制策略框图, figureFileSmall=pyoRdLqtq/CyXm9ugdNyoQ==, figureFileBig=iayOsqf62deWGhA3VwpSow==, tableContent=null), ArticleFig(id=1215700956411514962, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.17, caption=The results of NH3/NO with and without feedforward control during load variation, figureFileSmall=JGC03wy4zWchA+cXYzIm3w==, figureFileBig=NSC6StCi//A524N/wIMToQ==, tableContent=null), ArticleFig(id=1215700956533149786, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图17, caption=变负荷时有无前馈控制NH3/NO结果, figureFileSmall=JGC03wy4zWchA+cXYzIm3w==, figureFileBig=NSC6StCi//A524N/wIMToQ==, tableContent=null), ArticleFig(id=1215700956591870048, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.18, caption=The simulated NOx mass concentrations at the outlet, figureFileSmall=nL+fzF4ZrULyjM10lvJT+Q==, figureFileBig=+wT0cPfEhTg0bLg5egF76A==, tableContent=null), ArticleFig(id=1215700956692533349, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图18, caption=出口NOx质量浓度仿真结果对比, figureFileSmall=nL+fzF4ZrULyjM10lvJT+Q==, figureFileBig=+wT0cPfEhTg0bLg5egF76A==, tableContent=null), ArticleFig(id=1215700956784808040, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Fig.19, caption=The simulated ammonia slip at the outlet, figureFileSmall=JYxZjoLFgHNb/4HsWmu6JQ==, figureFileBig=yAZ1R8g1JMHkMv7aLcaLjg==, tableContent=null), ArticleFig(id=1215700956860305517, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=图19, caption=出口氨逃逸仿真结果对比, figureFileSmall=JYxZjoLFgHNb/4HsWmu6JQ==, figureFileBig=yAZ1R8g1JMHkMv7aLcaLjg==, tableContent=null), ArticleFig(id=1215700956939997300, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Tab.1, caption=

The characteristic variables of the studied unit under operating conditions

, figureFileSmall=null, figureFileBig=null, tableContent=
变量标签
总风量/(t·h–1)Air Flow
总给煤量/(t·h–1)Coal
选择后发电机有功功率/MWLoad
A磨入口风量/(t·h–1)A_air
B磨入口风量/(t·h–1)B_air
C磨入口风量/(t·h–1)C_air
D磨入口风量/(t·h–1)D_air
烟气侧省煤器入口温度/℃Economizer_T
省煤器入口烟气温度(左侧)/℃Economizer_T_left
汽轮机入口蒸汽压力/MPaSteam pressure
主蒸汽流量/(t·h–1)Steam mass flow
5号低加抽汽压力/MPaNO.5 pressure
A空预器入口氧量/%Air preheater_O2
A一次风风机电流/AA_Primary airflow
B一次风风机电流/AB_Primary airflow
二次风挡板开度/%Baffle opening
SCR反应器B入口烟气温度/℃SCR_B_T
SCR反应器B入口O2体积分数/%SCR_B_O2
SCR反应器B烟气流量/(t·h–1)SCR_B_Flue_gas_Flow
SCR反应器B氨气流量/(t·h–1)B_NH3
SCR反应器A入口烟气温度/℃SCR_A_T
SCR反应器A入口O2体积分数/%SCR_A_O2
SCR反应器A烟气流量/(t·h–1)SCR_A_Flue_gas_Flow
SCR反应器A氨气流量/(t·h–1)A_NH3
SCR反应器A入口烟气压力/MPaSCR_A_pressure
SCR反应器A入口NO质量浓度/(mg·m–3)SCR_A_NO
), ArticleFig(id=1215700957040660601, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=表1, caption=

运行条件下研究机组的特征变量

, figureFileSmall=null, figureFileBig=null, tableContent=
变量标签
总风量/(t·h–1)Air Flow
总给煤量/(t·h–1)Coal
选择后发电机有功功率/MWLoad
A磨入口风量/(t·h–1)A_air
B磨入口风量/(t·h–1)B_air
C磨入口风量/(t·h–1)C_air
D磨入口风量/(t·h–1)D_air
烟气侧省煤器入口温度/℃Economizer_T
省煤器入口烟气温度(左侧)/℃Economizer_T_left
汽轮机入口蒸汽压力/MPaSteam pressure
主蒸汽流量/(t·h–1)Steam mass flow
5号低加抽汽压力/MPaNO.5 pressure
A空预器入口氧量/%Air preheater_O2
A一次风风机电流/AA_Primary airflow
B一次风风机电流/AB_Primary airflow
二次风挡板开度/%Baffle opening
SCR反应器B入口烟气温度/℃SCR_B_T
SCR反应器B入口O2体积分数/%SCR_B_O2
SCR反应器B烟气流量/(t·h–1)SCR_B_Flue_gas_Flow
SCR反应器B氨气流量/(t·h–1)B_NH3
SCR反应器A入口烟气温度/℃SCR_A_T
SCR反应器A入口O2体积分数/%SCR_A_O2
SCR反应器A烟气流量/(t·h–1)SCR_A_Flue_gas_Flow
SCR反应器A氨气流量/(t·h–1)A_NH3
SCR反应器A入口烟气压力/MPaSCR_A_pressure
SCR反应器A入口NO质量浓度/(mg·m–3)SCR_A_NO
), ArticleFig(id=1215700957170684033, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Tab.2, caption=

Comparison of predictive results for three sets of feature variables

, figureFileSmall=null, figureFileBig=null, tableContent=
项目Group1
(相关系数>0.7)
Group2
(相关系数>0.4)
Group3
(经验选取)
δRMSE/(mg·m–3)22.6518.5930.11
R20.840.870.79
PFC0.340.500.30
), ArticleFig(id=1215700957267153030, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=表2, caption=

3组特征变量预测结果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
项目Group1
(相关系数>0.7)
Group2
(相关系数>0.4)
Group3
(经验选取)
δRMSE/(mg·m–3)22.6518.5930.11
R20.840.870.79
PFC0.340.500.30
), ArticleFig(id=1215700957367816330, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Tab.3, caption=

Optimization results of hyper parameters of the CNN-LSTM model

, figureFileSmall=null, figureFileBig=null, tableContent=
项目设置
卷积层Conv卷积核数量(filters),尺寸(Kernel Size=2),卷积步长(Strides=1)
最大池化层MaxPooling池化窗口的尺寸(Pool size=2),池化层步长(Strides=1)
LSTMLSTM神经元数量(units),激活函数(Activation=relu)
全连接层Dense神经元数量(units=4)
优化器Adam
学习率learning_rate=0.001
epoch100
dropout0.3
batch_size512
), ArticleFig(id=1215700957485256851, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=表3, caption=

CNN-LSTM模型超参数优化结果

, figureFileSmall=null, figureFileBig=null, tableContent=
项目设置
卷积层Conv卷积核数量(filters),尺寸(Kernel Size=2),卷积步长(Strides=1)
最大池化层MaxPooling池化窗口的尺寸(Pool size=2),池化层步长(Strides=1)
LSTMLSTM神经元数量(units),激活函数(Activation=relu)
全连接层Dense神经元数量(units=4)
优化器Adam
学习率learning_rate=0.001
epoch100
dropout0.3
batch_size512
), ArticleFig(id=1215700957581725847, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Tab.4, caption=

The prediction results under different operating conditions

, figureFileSmall=null, figureFileBig=null, tableContent=
项目工况1工况2工况3工况4
δRMSE/(mg·m–3)15.88020.5445.41030.250
R20.900.870.950.75
PFC0.560.90.830.41
), ArticleFig(id=1215700957661417627, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=表4, caption=

工况对比预测结果

, figureFileSmall=null, figureFileBig=null, tableContent=
项目工况1工况2工况3工况4
δRMSE/(mg·m–3)15.88020.5445.41030.250
R20.900.870.950.75
PFC0.560.90.830.41
), ArticleFig(id=1215700957736915104, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Tab.5, caption=

The comparison of predicted results for variable operating load

, figureFileSmall=null, figureFileBig=null, tableContent=
项目工况6工况4工况5
δRMSE/(mg·m–3)18.1230.2510.52
R20.820.750.95
PFC0.510.410.65
), ArticleFig(id=1215700957904687271, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=表5, caption=

变负荷对比预测结果

, figureFileSmall=null, figureFileBig=null, tableContent=
项目工况6工况4工况5
δRMSE/(mg·m–3)18.1230.2510.52
R20.820.750.95
PFC0.510.410.65
), ArticleFig(id=1215700957996961964, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=EN, label=Tab.6, caption=

Optimization indexes with and without feedforward

, figureFileSmall=null, figureFileBig=null, tableContent=
无前馈控制有前馈控制
SCR反应器出口NOx质量浓度平均值/(mg·m–3)40.004 140.002 3
SCR反应器出口NOx质量浓度标准差/(mg·m–3)0.145 70.104 0
SCR反应器出口NOx质量浓度波动/(mg·m–3)0.30.2
平均氨逃逸量/(μL·L–1)2.131.65
), ArticleFig(id=1215700958080848047, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1215700942377374238, language=CN, label=表6, caption=

有无前馈控制优化指标

, figureFileSmall=null, figureFileBig=null, tableContent=
无前馈控制有前馈控制
SCR反应器出口NOx质量浓度平均值/(mg·m–3)40.004 140.002 3
SCR反应器出口NOx质量浓度标准差/(mg·m–3)0.145 70.104 0
SCR反应器出口NOx质量浓度波动/(mg·m–3)0.30.2
平均氨逃逸量/(μL·L–1)2.131.65
)], 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.202401012, detailUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/10.19666/j.rlfd.202401012, pdfUrlCn=https://castjournals.cast.org.cn/joweb/rlfd/CN/PDF/10.19666/j.rlfd.202401012, pdfUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/PDF/10.19666/j.rlfd.202401012, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
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
收藏切换
PDF下载
李影 1 , 卓建坤 2 , 吴逸凡 2 , 樊永刚 1 , 姚强 1, 2 , 李水清 2
热力发电 | 热能科学研究 2024,53(7): 119-128
收起
收藏切换
热力发电 | 热能科学研究 2024, 53(7): 119-128
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
全屏
李影1 , 卓建坤2 , 吴逸凡2, 樊永刚1, 姚强1, 2, 李水清2
作者信息
  • 1.新疆大学电气工程学院,新疆 乌鲁木齐 830046
  • 2.清华大学热科学与动力工程教育部重点实验室,北京 100084
  • 李影(1999),女,硕士研究生,主要研究方向为智慧电厂污染物控制等,

通讯作者:

卓建坤(1975),男,博士,副研究员,主要研究方向为清洁燃烧及智慧电厂等,
Interpretable prediction model for NOx mass concentration at SCR reactor inlet in coal-fired power plants under flexible operating conditions
Ying LI1 , Jiankun ZHUO2 , Yifan WU2, Yonggang FAN1, Qiang YAO1, 2, Shuiqing LI2
Affiliations
  • 1.School of Electrical Engineering, Xinjiang University, Urumqi 830046, China
  • 2.Key Laboratory for Thermal Science and Power Engineering of Ministry of Education, Tsinghua University, Beijing 100084, China
出版时间: 2024-07-25 doi: 10.19666/j.rlfd.202401012
文章导航
收藏切换

燃煤电厂灵活调峰过程NOx测量往往存在滞后现象,导致选择性催化还原(selective satalytic reduction,SCR)脱硝喷氨控制系统响应不及时,易造成喷氨量过高或过低,从而造成SCR反应器出口NOx质量浓度波动剧烈和氨逃逸率增大。为实现喷氨阀门的提前快速调节并考虑影响燃煤锅炉NOx排放量的因素存在耦合性,提出了一种基于卷积神经网络(convolutional neural network,CNN)和长短时记忆(long short-term memory,LSTM)神经网络混合模型的SCR反应器入口NOx预测模型。利用一台330 MW燃煤电站锅炉的运行参数,通过Pearson系数法计算特征变量之间的相关性,筛选出相关性较大的特征,并定义模型的输入矩阵和输出矩阵,采用随机搜索算法进行优化,以提高预测性能。进一步利用SHAP算法对黑箱模型进行解释,并通过Simulink仿真验证了带有NOx预测的控制效果。结果表明:CNN-LSTM预测模型在调峰负荷变化时,能够以较高的精度预测SCR反应器入口NOx质量浓度的变化,并能提前25 s为喷氨控制系统提供反馈;优化后的喷氨控制策略降低了出口NOx质量浓度与设定值间的标准差(降低28%),并提升了NH3/NOx的响应速度,减小最大氨逃逸量22%。该研究结果可为灵活调峰机组的智慧SCR脱硝技术及燃烧优化提出有效的指导。

NOx预测  /  燃煤机组  /  CNN-LSTM模型  /  SHAP  /  灵活调峰

There is a delay in NOx measurement for flexible operations in coal-fired power plants, which leads to a delayed response in ammonia injection control system of selective catalytic reduction (SCR) reactor, resulting in potential over or under-injection of ammonia and significant fluctuations in NOx mass concentration at outlet of the SCR reactor. To enable proactive adjustment of ammonia injection and considering the interconnected factors influencing the NOx emissions from coal combustion, a prediction model for NOx mass concentration at the SCR reactor inlet is proposed based on convolutional neural networks (CNNs) and long short-term memory neural (LSTM) networks. By using operational parameters from a 330 MW coal-fired power plant, a Pearson coefficient method is employed to calculate the correlation between feature variables. Significant features are extracted to define the model input matrix and output matrix. The random search algorithm is used for hyper-parameters optimization to enhance predictive performance. The SHAP algorithm is then applied to interpret the model structure and explain the black-box model. Finally, the control effects of model with NOx concentration prediction is verified through Simulink simulation. The results indicate that, the CNN-LSTM prediction model demonstrates higher predictive accuracy for the variable NOx mass concentration at the SCR reactor inlet during the frequent load fluctuations. It can provide feedback to the ammonia injection control system of 25 seconds in advance. The optimized ammonia injection control strategy not only reduces the standard deviation between the NOx mass concentration at the SCR reactor outlet and the set value by 28%, but also improves the response speed of NH3/NOx regulation, reducing the maximum ammonia slip by 22%. The research findings can provide guidance for intelligent SCR denitration system and combustion optimizing operating during flexible operation of coal-fired power plants.

NOx prediction  /  coal-fired power unit  /  CNN-LSTM model  /  SHAP  /  flexible operation
李影, 卓建坤, 吴逸凡, 樊永刚, 姚强, 李水清. 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. 热力发电, 2024 , 53 (7) : 119 -128 . DOI: 10.19666/j.rlfd.202401012
Ying LI, Jiankun ZHUO, Yifan WU, Yonggang FAN, Qiang YAO, Shuiqing LI. Interpretable prediction model for NOx mass concentration at SCR reactor inlet in coal-fired power plants under flexible operating conditions[J]. Thermal Power Generation, 2024 , 53 (7) : 119 -128 . DOI: 10.19666/j.rlfd.202401012
我国的能源结构以煤炭为主,这决定了以燃煤发电为主导的发电结构[1]。在“双碳”目标下,虽然以风、光为主的可再生能源的大规模发展有助于降低CO2排放,但这些能源具有随机性大、波动性强和间歇性等特点[2],因此燃煤发电机组需要适应由此带来的灵活调峰需求。燃煤电厂普遍采用选择性催化还原(selective satalytic reduction,SCR)进行烟气脱硝处理,但在机组负荷快速变化时,SCR反应器入口NOx质量浓度将出现较大扰动,难以满足日益严苛的排放控制[3]。传统的连续排放检测系统(continuous emissions monitoring system,CEMS)在测量SCR反应器入口NOx质量浓度时存在滞后性,滞后时间与烟气取样系统的伴热导管长度有关,通常在60 s左右[4]。此外,现有电厂的喷氨控制策略,如固定摩尔比控制和固定出口NOx质量浓度控制等[5],无法及时响应NOx质量浓度的快速变化,易导致NOx排放超标或氨逃逸增加[6],对机组的运行安全及经济性造成不利影响。
燃煤锅炉系统的运行复杂,运行数据具有高维度和大数据量等特点,且影响NOx生成的变量(如风量、给煤量、燃烧温度等)具有非线性、强耦合性、时滞性大[7],难以通过数值仿真实时计算,也无法精确在线测量重要过程变量。国内外学者利用机器学习方法及逆行软测量,针对CEMS测量NOx滞后和氨逃逸问题进行大量的研究。王桂林等[8]基于支持向量机建立了300 MW机组有功功率、排烟氧量等变量与SCR反应器入口NOx质量浓度和脱硝效率之间的预测模型,并利用遗传算法对喷氨量进行优化,得到成本最低的喷氨策略,优化后总成本下降约0.65%。廖永进等[9]采用径向基函数神经网络法,建立了锅炉负荷、烟气体积流量等5个变量与脱硝效率之间的关系,并随机选取负荷在50%~100%的125组数据进行训练,对脱硝效率及出口NOx质量浓度进行预测。唐振浩等[10]利用极限学习机误差模型,选用稳定负荷4 700组、升负荷4 500组、降负荷3 900组数据进行预测,预测模型在不同工况下的预测误差均小于2%。王英男[11]利用注意力机制和长短时记忆(long short-term memory,LSTM)神经网络组合模型有效降低预测误差至0.424%,但在机组负荷变化过大时,会出现模型失配问题。Qiao[12]利用改进型LSTM神经网络,选取7 212组数据,综合考虑变量的变化率,最终实现了提前30 s预测NOx质量浓度,预测相对误差为4%。Zhao等人[13]利用堆叠综合集成方法,实现了较高的回归系统和较小的均方根误差,具有较强的鲁棒性和泛化能力。上述研究证明了数据驱动方法在NOx质量浓度预测中的可行性,但所选取数据量较小,难以在复杂全工况下保持较高的精确度,模型预测精度还需提升。
针对燃煤电厂深度调峰,脱硝入口NOx质量浓度测量滞后和氨逃逸等问题,本文基于某330 MW燃煤电站分散控制系统(distributed control system,DCS)中的锅炉长期运行的时序数据,提出了基于CNN-LSTM的SCR反应器入口NOx质量浓度预测模型。首先进行数据预处理,并定义预测模型的输入矩阵X和输出矩阵Y,然后使用随机搜索算法对模型进行迭代优化,获得兼顾预测精度与工况适应性的最优模型超参数;接着,利用SHAP(Shapley additive explanation)算法对黑箱模型进行解释,分析稳定负荷运行和变负荷工况下NOx质量浓度的主要影响参数,并研究各参数对SCR反应器入口NOx浓度的协同作用机制;最后,通过Simulink设计SCR反应器出口NOx控制回路,研究本文提出CNN-LSTM预测模型对回路控制的影响。
本研究以某电厂330 MW四角切圆机组为对象,数据来源于DCS,时间间隔为5 s,数据量为812 000组。每组数据均包含所有变量的有效值,排除丢失数据情况。数据包括负荷上升、下降、稳定3种运行状态。
根据燃料型NOx、热力型NOx、快速型NOx 3种生成机理[14],本文选取了总风量、总煤量、A磨煤机(A磨)入口风量等26个变量,具体见表1。煤质是影响NOx(由于NO在NOx中占比较高,本文中NO数据即为NOx数据)排放的重要参数,由于DCS中没有实时测量煤质数据(如热值、工业分析或元素分析等),煤质的改变会直接影响煤量、风量等运行变量以及NOx生成。因此,可以通过相关参数的时序数据反映煤质的影响。
用Pearson相关系数(pearson correlation coefficient,PCC)[15]衡量任意2个变量之间的线性相关性(式(1)),式中x¯y¯表示变量xy的平均值。
r=i=1n(xix¯)i=1n(yiy¯)i=1n(xix¯)2i=1n(yiy¯)2
在建模之前,对所有输入值进行归一化处理,以消除量纲的影响[16],归一化公式为:
x^=xmin(x)max(x)min(x)
式中:x^为输入变量的归一化值;x为输入变量的原始值。
预测SCR反应器入口NO质量浓度的数据集如下,其中式(3)为训练集和式(4)为测试集:
X=[x(1,tis)...x(n,tis)...x(1,ti1)...x(n,ti1)x(1,ti)...x(n,ti)],   YNO(ti+m)
X=[x(1,tjs)...x(n,tjs)...x(1,tj1)...x(n,tj1)x(1,tj)...x(n,tj)],   YNO(tj)
式中:X为预测模型的输入特征矩阵;Y为预测模型的输出矩阵;tm理论上提前预测时间,ts为回溯时间,即预测模型中采用前ts时间内变量X的关系对ti+m时刻YNO的值进行预测。
使用Python语言和框架TensorFlow的Keras库构建了基于CNN-LSTM的燃煤电厂SCR反应器入口NO质量浓度预测模型。CNN通过卷积提取数据中的空间特征[17],获取NO质量浓度的周期性变化或突变,LSTM神经网络可以通过存储的历史信息捕捉NO质量浓度的变化趋势,捕捉时间相关性[18],模型结构如图1所示。
预测模型的性能通过回归系数(R squared,R2)、均方根误差(root mean squared error,δRMSE[19]以及自定义跟随系数PFC来评估,如式(5)—式(7)所示:
δRMSE=1Ni=1N(yrealypre)2
R2=i=1N(yrealyreal)i=1N(ypreypre)i=1N(yrealyreal)2i=1N(ypreypre)2
PFC=sum{sign(yreal[i+1]yreal[i]))==sign(ypre[i+1]ypre[i])}len(yreal)1
式中:δRMSE用于判断误差大小;R2计算相关性,PFC评估生成趋势是否一致;yreal为时刻tj+m的测量值;ypre为时刻tj+m的预测值。
稳定负荷指的是关键变量在一定时间范围内保持相对稳定,且波动幅度较小的状态。本文研究对象多数时刻处在低负荷或变负荷工况,根据《电站锅炉性能试验规程》(GB10184—1988)各运行参数处于稳定时的波动范围[20],以200 MW为标准负荷,将标准负荷的±6%范围定义为稳定负荷,其余定义为变负荷工况。
利用SHAP算法对CNN-LSTM黑箱模型预测结果进行可解释性分析。SHAP算法核心是计算每个特征变量的Shapley Value[21],表征方式有特征重要性(variable importance,VI)图、概要图(Summary plot)以及部分依赖(partial dependence plot,PDP)图[22]。通过VI图对影响NOx质量浓度特征变量的相对重要性进行排序。通过Summary plot图显示出变量对目标变量值是正向或负向的影响,横坐标为SHAP值,红色表示高特征值,蓝色表示低特征值,一个点离基线SHAP值越远,则对输出的影响就越强[23]。通过PDP图理解重要输入变量与输出变量之间依赖关系的本质,即通过可视化某一或2个特征对SCR入口NO质量浓度的总体影响趋势。
计算Pearson相关系数并绘制热力图,图2图3展示了稳定负荷和变负荷数据的相关热力图。热力图中每个单元格代表2个变量之间的线性相关性,相关性越大颜色越深。输入变量之间相关系数越高(尤其当|r|>0.7),则两者之间存在较强的多重共线性。结果表明,稳定负荷和变负荷的SCR入口NO质量浓度的主要相关变量存在差异。稳定负荷下各变量与NO的相关性都较低,约为0.2;而变负荷工况下各变量与NO的相关性较高,约为0.8。此外,还验证了在变负荷时,挡板开度与电流、烟气量与机组负荷存在较强的正相关性。
使用Pearson相关系数筛选不同的输入特征变量对模型进行训练:1)Group1相关系数大于0.7的变量;2)Group2相关系数大于0.4的变量;3)Group3根据经验选取变量。上述各方法选取的变量如图4所示,结果见表2。由表2得出,使用Group2模型实验组δRMSE比使用Group1和Group3模型的δRMSE低,R2PFC跟随性较高,则选用Group2特征变量进行后续的研究工作。因模型超参数还未进行优化,各组相关系数偏低。
确定工况回溯时间为60 s,延迟时间为90 s,以Group2作为模型输入,通过随机搜索优化模型的超参数,结果见表3。使用优化后的CNN-LSTM模型验证其预测性能,并对稳定负荷和变负荷的工况进行分析。
将测试集定义为4个工况进行分析评估。1)工况1,整个测试集的第0至17 500组样本序列;2)工况2,负荷变化较小(35%的数据负荷变化为标准负荷的±3%,65%的数据为标准负荷的–20%~+9%)第0至1 300组样本序列,用于验证小变化率下NOx的预测精度;3)工况3,稳定负荷(标准负荷的±3%)第1 300至12 500组样本序列,用于测试长期稳定负荷下的准确性;4)工况4,负荷变化较大(73%的数据负荷变化为标准负荷的+21%~+78%)第12 500至17 500组样本序列,用于验证瞬态较大负荷变化下的精确度,具体结果如图5图6所示。
表4为工况对比预测结果。从表4预测结果可知,在稳定负荷(工况3)下模型的dRMSE较低为5.410 mg/m3,且预测精度R2较高为0.95,说明模型表现出良好的预测能力。预测误差在变负荷时(工况2和工况4)的精度比稳定负荷工况(工况3)下低,工况2波峰预测值和测量值对比如图7所示。工况2波峰负荷变化较小时NO的预测值能够提前变化,在工况4负荷变化增大时,预测偏差增大。
在工况4中,负荷变化较大,相关系数R2下降至0.75,表明需对变负荷数据进行进一步训练,以提高预测的准确性。通过设定修正比例,对测量值和预测值进行修正,设修正参数φ[0,1],cin,NO修正后的NO质量浓度,ct,in,measure为时刻t的NO质量浓度的测量值,ct+tm,in,pre为时刻t+tm的NO质量浓度的预测值,修正过程为式(8)。修正后的工况5如图8所示,相关系数R2提高至0.95,高于未修正前工况1的R2。设2组数据之间的延迟时间tm为5~40 s,每间隔5 s依次计算二者的相关系数,当tm=25 s时相关系数最高为0.97,此时2条曲线最重合,则平均提前时间为25 s。变负荷数据修正后如图9所示,图9中修正后的值能够比同一时刻测量值最大提前时间为125 s。
ϕ=0.7cin,NO=ϕct,in,measure+(1ϕ)ct+tm,in,pre
选取现阶段全部样本的变工况(工况6)数据(图10)进行分析,预测结果见表5。由表5可见,工况6的相关系数R2为0.82,比负荷变化较大的工况4精度高。
利用SHAP算法对CNN-LSTM预测模型进行后解释分析[24]。通过分析平稳和负荷变化较大2种负荷情景下NO生成的驱动因素,从历史数据中选取工况3进行分析(图11图12)。图11所示的稳定负荷VI图中,影响SCR反应器入口NO质量浓度较大的变量是SCR反应器上游的烟气温度(如入口温度和省煤器入口温度)以及B磨入口风量。图12所示的稳态概要图中,SCR反应器入口温度、B磨入口风量、二次风挡板开度、A一次风机电流以及蒸汽压力与NO质量浓度呈正相关,而省煤器入口烟气温度、机组负荷、总风量、B一次风机电流、蒸汽流量以及SCR反应器入口压力呈负相关。SCR入口O2体积分数也是影响NO质量浓度的重要参数,其特征值较高时,SHAP值能达到最高或最低,表明O2体积分数对NOx的生成起到双向作用,与炉内分级燃烧状况密切相关。
选取工况6负荷变化较大数据进行分析(图13)。从图13变负荷概要图可看出,影响NO质量浓度的变量主要有机组负荷、D磨入口风量、主蒸汽流量以及省煤器入口温度等。但各变量与目标变量NO质量浓度均存在正向或负向的相关关系,但并无单向关系。
对于稳定负荷工况各个变量之间的关系,代表性结果如图14所示。由图14可知:当二次风挡板开度小于33%时,总风量较小且对NO质量浓度是正向作用;随着挡板开度增大总风量随之增大,对NO生成存在双向的影响,主要分布在负相关方向,表明了在高负荷工况下,炉内空气分级燃烧作用明显,增大二次风挡板开度,有利于降低NO质量浓度。
变负荷时NO质量浓度被SCR反应器入口A温度和总风量共同影响下,NO质量浓度的结果如图15所示。
图15可知:在变负荷时当SCR反应器入口A温度小于330 ℃时,总风量较小且对NO质量浓度主要是负向作用,说明在较低负荷时,增大负荷可降低NO的生成;当SCR反应器入口A温度升高时增大总风量,对NO的生成逐渐为正向影响。高负荷运行时,增大负荷且增加总风量,将会影响炉内的分级燃烧,增加NO的生成。
在建立SCR反应器入口NOx质量浓度预测模型的基础下,设计并改进了SCR反应器脱硝智能预测前馈控制系统。主PID控制器对喷氨量进行调节,副PID控制器驱动喷氨阀门开度,控制逻辑框图如图16所示。将前期预测时刻t+tm的SCR反应器入口NOx质量浓度修正值作为前馈信号,固定出口NOx质量浓度为40 mg/m3,补偿氨氮比。
实现SCR脱硝智能预测前馈控制系统的控制逻辑如下:1)利用SCR反应器入口NO质量浓度修正值与SCR反应器出口NO的设定值计算理论脱硝量;2)利用SCR反应器出口NO质量浓度测量值与SCR反应器出口NO质量浓度的设定值计算补偿脱硝量;3)根据理论脱硝量和补偿脱硝量计算氨气设定值;4)利用喷氨格栅喷出的氨气测量值与氨气设定值计算氨气补偿量;5)利用氨氮比乘以0.951 6计算得到最大脱硝率;6)根据脱硝率的补数计算SCR反应器出口NO质量浓度。
当外部负荷发生变化时,SCR喷氨控制系统能够提前tm动作,使喷氨量与烟气中的NOx量相匹配,从而减少系统调节时间。选用500 s运行数据,包括负荷变化情况,采用以上控制逻辑,仿真有无前馈控制的NH3/NO结果如图17所示。由图17可知,当机组负荷变化时,有智能预测前馈控制方法的NH3/NO先响应。负荷降低可能造成燃烧不完全,NO质量浓度增大,NH3量增多,则NH3/NO比值增大。
仿真有无前馈控制的SCR脱硝出口NOx波动情况对比输出结果如图18表6所示。由图18表6可知,有预测前馈控制可有效降低SCR系统出口NOx质量浓度,波动范围在0.2 mg/m3左右,标准差降低28%。标准差计算公式为:
Sx=(xix¯)2n1
式中:Sx为标准差;x¯为样本序列平均值;n为样本序列个数。
实际SCR脱硝反应中NH3与NOx进行脱硝反应比值近似为1:1。根据脱硝率计算SCR反应器出口氨逃逸并进行折算,具体如式(10)—式(13)所示[25]
4NH3+4NO+O2=4N2+6H2O
η=cin,NOxcout,NOxcin,NOx
cNH3=ci,NH3ηci,NOx=ci,NOx(rη)
pNH3=cNH317×106
式中:cNH3cNH3氨逃逸质量浓度;r为氨氮比;η为脱硝效率;ci,NOx为SCR反应器入口NOx质量浓度;cout,NOx为出口NOx的质量浓度;cin,NH3为SCR反应器入口实际NH3质量浓度;pNH3为基于标况下(298 K和101 kPa)的氨气密度,将氨气质量浓度折算后的值。
计算氨逃逸结果如图19所示。由图19可知,有前馈控制比无前馈控制降低了氨逃逸,无前馈控制时氨逃逸量最大为2.13 μL/L,有前馈控制时氨逃逸量为1.65 μL/L,则有前馈控制降低最大氨逃逸22%。
本文针对NOx质量浓度测量滞后问题,提出了一种CNN-LSTM数据驱动模型,用于预测机组全工况运行时的NOx生成质量浓度,并应用于某电厂330 MW四角切圆锅炉的NOx排放预测,主要结论包括如下。
1)通过热力图相关性分析,发现稳定工况和变负荷时,影响SCR反应器入口NO质量浓度生成的主要变量存在显著差异。
2)将SCR反应器入口NO质量浓度预测值与测量值设置一定的比例7:3修正SCR反应器入口NO质量浓度,通过Simulink仿真评估,修正后的SCR反应器入口NO质量浓度能够提前25 s调节喷氨量。优化后的喷氨控制策略降低出口NOx质量浓度与设定值间的标准差(降低28%),并提升了NH3/NOx调节的响应速度,减少最大氨逃逸量22%,实现了变负荷下的NOx的排放控制。
3)利用SHAP算法对CNN-LSTM模型进行分析,确定了各变量对SCR反应器入口NO质量浓度的正向或负向影响,在变负荷时影响SCR反应器入口NO质量浓度最大的变量是机组负荷和D磨入口风量,反映了不同负荷下炉内分级燃烧的深度存在差异。
  • 自治区重大科技专项项目(2023A01005-1)
参考文献 引证文献
排序方式:
[1]
中华人民共和国2021年国民经济和社会发展统计公报[J]. 中国统计, 2022(3): 9-26.
Statistical Communique of the People’s Republic of China on the 2021 National Economic and Social Development[J]. China Statistics, 2022(3): 9-26.
[2]
薛禹胜, 雷兴, 薛峰, 等. 关于风电不确定性对电力系统影响的评述[J]. 中国电机工程学报, 2014, 34(29): 5029-5040.
XUE Yusheng, LEI Xing, XUE Feng, et al. A review on impacts of wind power uncertainties on power systems[J]. Proceedings of the CSEE, 2014, 34(29): 5029-5040.
[3]
闫来清, 董泽. 基于k-近邻互信息和WKOPLS的SCR脱硝系统动态预测模型[J]. 中国电机工程学报, 2019, 39(10): 2970-2980.
YAN Laiqing, DONG Ze. Dynamic prediction model of SCR denitrification system based on k-nearest neighbor mutual information and WKOPLS[J]. Proceedings of the CSEE, 2019, 39(10): 2970-2980.
[4]
翁卫国, 刘博文, 郭一杉, 等. 基于入口NOx浓度软测量的脱硝系统先进控制研究[J]. 锅炉制造, 2019(5): 17-22.
WENG Weiguo, LIU Bowen, GUO Yishan, et al. Model predictive control utilizing gas soft-sensors on SCR denitration system in thermoelectric unit[J]. Boiler Manufacturing, 2019(5): 17-22.
[5]
张晓雯. 燃煤机组SCR脱硝系统建模与优化控制研究[D]. 南京: 东南大学, 2021: 1.
ZHANG Xiaowen. Modeling and optimal control of SCR denitrification system for coal-fired units[D]. Nanjing: Southeast University, 2021: 1.
[6]
YANG T, MA K, LV Y, et al. Real-time dynamic prediction model of NOx emission of coal-fired boilers under variable load conditions[J]. Fuel, 2020, 274: 117811.
[7]
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.
[8]
王桂林, 张宇, 王森, 等. 基于支持向量机的选择性催化还原脱硝系统运行优化[J]. 环境工程学报, 2015, 9(10): 5011-5016.
WANG Guilin, ZHANG Yu, WANG Sen, et al. Operation optimization of selective catalytic reduction system based on support vector machine[J]. Chinese Journal of Environmental Engineering, 2015, 9(10): 5011-5016.
[9]
廖永进, 范军辉, 杨维结, 等. 基于RBF神经网络的SCR脱硝系统喷氨优化[J]. 动力工程学报, 2017, 37(11): 931-937.
LIAO Yongjin, FAN Junhui, YANG Weijie, et al. Ammonia spraying optimization of an SCR denitrification system based on RBF neural network[J]. Journal of Power Engineering, 2017, 37(11): 931-937.
[10]
唐振浩, 柴向颖, 曹生现, 等. 考虑时延特征的燃煤锅炉NOx排放深度学习建模[J]. 中国电机工程学报, 2020, 40(20): 6633-6644.
TANG Zhenhao, CHAI Xiangying, CAO Shengxian, et al. Deep learning modeling for the NOx emissions of coal-fired boiler considering time-delay characteristics [J]. Proceedings of the CSEE, 2020, 40(20): 6633-6644.
[11]
王英男. 燃煤锅炉的NOx排放预测与控制研究[D]. 北京: 华北电力大学, 2021: 1.
WANG Yingnan. Research on NOx emission prediction and control of coal-fired boiler[D]. Beijing: North China Electric Power University, 2021: 1.
[12]
QIAO J. A novel online modeling for NOx generation prediction in coal-fired boiler[J]. Science of the Total Environment, 2022, 847: 157542.
[13]
YUAN Z, MENG L, GU X, et al. Prediction of NOx emissions for coal-fired power plants with stacked-Generalization Ensemble Method[J]. Fuel, 2021, 289: 119748.
[14]
姚强, 李水清, 王宇. 燃烧学导论[M]. 北京: 清华大学出版社, 2009: 1.
YAO Qiang, LI Shuiqing, WANG Yu, et al. An introduction to combustion concepts and applications[M]. Beijing: Tsinghua University Press, 2009: 1.
[15]
刘菡, 王英男, 李新利, 等. 基于互信息-图卷积神经网络的燃煤电站NOx排放预测[J]. 中国电机工程学报, 2022, 42(3): 1052-1060.
LIU Han, WANG Yingnan, LI Xinli, et al. Prediction of NOx emission in coal-fired power plants based on mutual information-graph convolutional neural network[J]. Proceeding of the CSEE, 2022, 42(3): 1052-1060.
[16]
吕玉坤, 彭鑫, 赵锴. 电站锅炉热效率和NOx排放混合建模与优化[J]. 中国电机工程学报, 2011, 31(26): 16-22.
LYU Yukun, PENG Xin, ZHAO Kai. Hybrid modeling optimization of thermal efficiency and NOx emission of utility boiler[J]. Proceedings of the CSEE, 2011, 31(26): 16-22.
[17]
LI N, HU Y. The deep convolutional neural network for NOx emission prediction of a coal-fired boiler[J]. IEEE Access, 2020, 8: 85912-85922.
[18]
GUO Y, MAO Z. Long-term prediction model for NOx emission based on LSTM-transformer[J]. Electronics, 2023, 12(18): 3929.
[19]
刘岳, 于静, 金秀章. 基于特征优化和改进长短期记忆神经网络的NOx质量浓度预测[J]. 热力发电, 2021, 50(7): 162-169.
LIU Yue, YU Jing, JIN Xiuzhang. NOx mass concentration prediction based on feature optimization and improved LSTM network[J]. Thermal Power Generation, 2021, 50(7): 162-169.
[20]
电站锅炉性能试验规程: GB/T 10184—1988[S]. 北京: 中国标准出版社, 1988: 1.
Procedures for performance testing of power station boilers: GB/T 10184—1988[S]. Beijing: Standards Press of China, 1988: 1.
[21]
朱明超. 可解释的机器学习[M]. 北京: 电子工业出版社, 2021: 1.
ZHU Mingchao. Interpretable machine learning[M]. Beijing: Electronic Industry Press, 2021: 1.
[22]
ZHU X, LI Y, WANG X. Machine learning prediction of biochar yield and carbon contents in biochar based on biomass characteristics and pyrolysis conditions[J]. Bioresource Technology, 2019, 288: 121527.
[23]
ASCHER S, WANG X, WATSON I, et al. Interpretable machine learning to model biomass and waste gasification[J]. Bioresource Technology, 2022, 364: 128062.
[24]
杨昌兰. 基于深度学习及SHAP解释的城市空间扩展识别与驱动分析[D]. 武汉: 武汉大学, 2022: 1.
YANG Changlan. Identification and driving analysis of urban spatial expansion through intergrating deep learning models and SHapley additive explanations[D]. Wuhan: Wuhan University, 2022: 1.
[25]
董建勋, 李永华, 冯兆兴, 等. 选择性催化还原烟气脱硝反应器的变工况运行分析[J]. 动力工程, 2008(1): 142-146.
DONG Jianxun, LI Yonghua, FENG Zhaoxing, et al. Operation analysis of flue gas denitrification reactors with selective catalytic reduction under variable working conditions[J]. Power Engineering, 2008(1): 142-146.
2024年第53卷第7期
PDF下载
173
80
引用本文
BibTeX
文章信息
doi: 10.19666/j.rlfd.202401012
  • 接收时间:2024-01-22
  • 首发时间:2026-01-07
  • 出版时间:2024-07-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-01-22
基金
Provincial Major Scientific and Technological Special Project(2023A01005-1)
自治区重大科技专项项目(2023A01005-1)
作者信息
    1.新疆大学电气工程学院,新疆 乌鲁木齐 830046
    2.清华大学热科学与动力工程教育部重点实验室,北京 100084

通讯作者:

卓建坤(1975),男,博士,副研究员,主要研究方向为清洁燃烧及智慧电厂等,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202401012
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