Article(id=1295068056414351501, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1295068001842262748, articleNumber=null, orderNo=null, doi=10.19666/j.rlfd.202507085, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1753891200000, receivedDateStr=2025-07-31, revisedDate=1760889600000, revisedDateStr=2025-10-20, acceptedDate=1762185600000, acceptedDateStr=2025-11-04, onlineDate=1786697885850, onlineDateStr=2026-08-14, pubDate=1777046400000, pubDateStr=2026-04-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1786697885850, onlineIssueDateStr=2026-08-14, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1786697885850, creator=13701087609, updateTime=1786697885850, updator=13701087609, issue=Issue{id=1295068001842262748, tenantId=1146029695717560320, journalId=1210938733613449225, year='2026', volume='55', issue='4', pageStart='1', pageEnd='190', issueExtLink='null', onlineDate='null', pubDate='1777046400000', pubDateStr='2026-04-25', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1786697872839, creator='13701087609', updateTime=1786698854295, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1295072118417416228, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1295068001842262748, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1295072118417416229, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1295068001842262748, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=156, endPage=165, ext={EN=ArticleExt(id=1295068056674398351, articleId=1295068056414351501, tenantId=1146029695717560320, journalId=1210938733613449225, language=EN, title=Multi-model dynamic prediction and collaborative deployment of NOx mass concentration at inlet of SCR denitration system in coal-fired power units, columnId=1295068056598900878, journalTitle=Thermal Power Generation, columnName=Power generation techonology forum, runingTitle=null, highlight=null, articleAbstract=

To meet the high requirements of selective catalytic reduction (SCR) systems in coal-fired power plants for accurate and low-latency prediction of nitrogen oxides (NOx) mass concentrations, this study designs and proposes a soft sensing and deployment framework that balances high accuracy and real-time performance. Using more than 110 000 sets of high-dimensional operational data from a 660 MW coal-fired unit, a systematic comparison of deep learning (DL) and XGBoost models was conducted on a unified platform. Time series cross-validation combined with grid search was employed to optimize hyperparameters, and model performance was comprehensively evaluated in terms of predictive accuracy, computational efficiency, and interpretability via local interpretable model-agnostic explanations. On this basis, an “edge-embedded” collaborative deployment strategy was proposed, in which the DL model is deployed on edge servers to deliver high-accuracy predictions, while the XGBoost model is embedded into the distributed control system (DCS) to ensure real-time responsiveness. The results show that the DL model outperforms XGBoost in dynamic response and predictive accuracy, achieving root mean square errors approximately 10% lower than that of the XGBoost, and maintaining stability under highly fluctuating conditions. Variable importance analysis highlights flue gas oxygen content, burner wall temperature, and total air volume as the dominant factors affecting NOx formation. The proposed collaborative architecture can theoretically achieve millisecond-level inference and provide offline fault tolerance, offering a practical pathway for intelligent ammonia injection control and combustion optimization.

, authors=Deyong LU1, Zhiyou WEI2, Yubo LIU1, Haiqiang LI1, Delong DING2, Bo SHEN2, Lai LI2, authorsList=Deyong LU, Zhiyou WEI, Yubo LIU, Haiqiang LI, Delong DING, Bo SHEN, Lai LI, authorCompany=null, correspAuthors=Zhiyou WEI, 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, fund=null), CN=ArticleExt(id=1295068059664937114, articleId=1295068056414351501, tenantId=1146029695717560320, journalId=1210938733613449225, language=CN, title=燃煤机组SCR脱硝入口NOx质量浓度的多模型动态预测及协同部署, columnId=1211002409581679375, journalTitle=热力发电, columnName=发电技术论坛, runingTitle=null, highlight=null, articleAbstract=

为满足燃煤机组选择性催化还原(selective catalytic reduction, SCR)脱硝系统对氮氧化物(NOx)质量浓度预测的高需求,设计并提出一种兼具高精度和低延迟的软测量及部署方案。基于某660 MW燃煤机组11万余组高维运行数据,在统一平台下系统对比了深度学习(deep learning,DL)与XGBoost(extreme gradient boosting)2种模型,采用时序交叉验证结合网格搜索优化模型超参数,并从预测精度、计算效率及可解释性三方面进行综合评估。在此基础上,提出“边缘–嵌入式”协同部署策略,将DL模型部署于边缘服务器以获取高精度预测结果,XGBoost模型嵌入分散控制系统(distributed control system,DCS)保障实时性。结果表明:DL模型在动态响应与预测精度上表现更优,其测试集均方根误差较XGBoost模型降低约10%,并在工况剧烈波动时DL模型能保持稳定性;变量重要性分析显示,烟气含氧量、燃烧器壁温和总风量是影响NOx生成的主要因素。所提协同部署架构理论上可实现毫秒级推理,并具备离线容错能力。

, authors=卢得勇1, 韦智友2, 刘宇博1, 李海强1, 丁得龙2, 沈波2, 李来2, authorsList=卢得勇, 韦智友, 刘宇博, 李海强, 丁得龙, 沈波, 李来, authorCompany=null, correspAuthors=韦智友, authorNote=

卢得勇(1989),男,硕士,工程师,主要研究方向为热能与动力工程,

, correspAuthorsNote=
韦智友(1992),男,博士,高级工程师,主要研究方向为能源环保工程,
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=6jK5RbyJbcbmU4kBqO5uTw==, magXml=LXQyTMqDXghlvlUIeG44Gw==, pdfUrl=null, pdf=eGDxuyp19oCGULlyp5UgTA==, pdfFileSize=1951073, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=2M1LXHlTentpIsE35Hs0Hw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=fjAuImZiGoEzs7jTMWgvoA==, mapNumber=null, fund=null)}, authors=[Author(id=1295068060071784610, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=ludeyong@oamail.zhenergy.com.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1295068060143087780, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060071784610, language=EN, stringName=Deyong LU, firstName=Deyong, middleName=null, lastName=LU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Zhejiang Zheneng Lanxi Power Generation Co., Ltd., Jinhua 321102, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068060252139685, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060071784610, language=CN, stringName=卢得勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.浙江浙能兰溪发电有限责任公司,浙江 金华 321102, bio={"content":"

卢得勇(1989),男,硕士,工程师,主要研究方向为热能与动力工程,

"}, bioImg=null, bioContent=

卢得勇(1989),男,硕士,工程师,主要研究方向为热能与动力工程,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068059904012443, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=1., ext=[AuthorCompanyExt(id=1295068059912401052, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059904012443, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Zhejiang Zheneng Lanxi Power Generation Co., Ltd., Jinhua 321102, China), AuthorCompanyExt(id=1295068059924983965, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059904012443, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.浙江浙能兰溪发电有限责任公司,浙江 金华 321102)])]), Author(id=1295068060340220071, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhiyou_weii@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1295068060449271977, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060340220071, language=EN, stringName=Zhiyou WEI, firstName=Zhiyou, middleName=null, lastName=WEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068060512186538, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060340220071, language=CN, stringName=韦智友, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068059992092830, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=2., ext=[AuthorCompanyExt(id=1295068060000481439, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China), AuthorCompanyExt(id=1295068060004675744, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121)])]), Author(id=1295068060579295404, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, 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=1295068060650598574, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060579295404, language=EN, stringName=Yubo LIU, firstName=Yubo, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Zhejiang Zheneng Lanxi Power Generation Co., Ltd., Jinhua 321102, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068060730290351, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060579295404, language=CN, stringName=刘宇博, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.浙江浙能兰溪发电有限责任公司,浙江 金华 321102, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068059904012443, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=1., ext=[AuthorCompanyExt(id=1295068059912401052, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059904012443, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Zhejiang Zheneng Lanxi Power Generation Co., Ltd., Jinhua 321102, China), AuthorCompanyExt(id=1295068059924983965, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059904012443, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.浙江浙能兰溪发电有限责任公司,浙江 金华 321102)])]), Author(id=1295068060822565041, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, 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=1295068060893868211, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060822565041, language=EN, stringName=Haiqiang LI, firstName=Haiqiang, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Zhejiang Zheneng Lanxi Power Generation Co., Ltd., Jinhua 321102, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068060981948596, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060822565041, language=CN, stringName=李海强, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.浙江浙能兰溪发电有限责任公司,浙江 金华 321102, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068059904012443, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=1., ext=[AuthorCompanyExt(id=1295068059912401052, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059904012443, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Zhejiang Zheneng Lanxi Power Generation Co., Ltd., Jinhua 321102, China), AuthorCompanyExt(id=1295068059924983965, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059904012443, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.浙江浙能兰溪发电有限责任公司,浙江 金华 321102)])]), Author(id=1295068061049057462, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, 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=1295068061124554936, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068061049057462, language=EN, stringName=Delong DING, firstName=Delong, middleName=null, lastName=DING, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068061200052409, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068061049057462, language=CN, stringName=丁得龙, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068059992092830, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=2., ext=[AuthorCompanyExt(id=1295068060000481439, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China), AuthorCompanyExt(id=1295068060004675744, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121)])]), Author(id=1295068061296521403, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, 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=1295068061392990397, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068061296521403, language=EN, stringName=Bo SHEN, firstName=Bo, middleName=null, lastName=SHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068061481070782, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068061296521403, language=CN, stringName=沈波, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068059992092830, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=2., ext=[AuthorCompanyExt(id=1295068060000481439, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China), AuthorCompanyExt(id=1295068060004675744, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121)])]), Author(id=1295068061564956864, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, orderNo=6, 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=1295068061636260034, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068061564956864, language=EN, stringName=Lai LI, firstName=Lai, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068061728534723, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068061564956864, language=CN, stringName=李来, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068059992092830, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=2., ext=[AuthorCompanyExt(id=1295068060000481439, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China), AuthorCompanyExt(id=1295068060004675744, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121)])])], keywords=[Keyword(id=1295068061862752452, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=EN, orderNo=1, keyword=NOx mass concentration prediction), Keyword(id=1295068061934055621, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=EN, orderNo=2, keyword=deep learning), Keyword(id=1295068063599194310, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=EN, orderNo=3, keyword=variable importance), Keyword(id=1295068063683080391, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=EN, orderNo=4, keyword=edge computing), Keyword(id=1295068063750189256, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=EN, orderNo=5, keyword=model deployment), Keyword(id=1295068063829881033, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=CN, orderNo=1, keyword=NOx质量浓度预测), Keyword(id=1295068063909572810, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=CN, orderNo=2, keyword=深度学习), Keyword(id=1295068063993458891, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=CN, orderNo=3, keyword=变量重要性), Keyword(id=1295068064056373452, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=CN, orderNo=4, keyword=边缘计算), Keyword(id=1295068064115093709, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=CN, orderNo=5, keyword=模型部署)], refs=[Reference(id=1295068065348219100, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2016, volume=13, issue=null, pageStart=133, pageEnd=141, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=BONINGARI T, SMIRNIOTIS P G, journalName=Current Opinion in Chemical Engineering, refType=null, unstructuredReference=BONINGARI T, SMIRNIOTIS P G. Impact of nitrogen oxides on the environment and human health: Mn-based materials for the NOx abatement[J]. Current Opinion in Chemical Engineering, 2016, 13: 133-141., articleTitle=Impact of nitrogen oxides on the environment and human health: Mn-based materials for the NOx abatement, refAbstract=null), Reference(id=1295068065423716573, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2016, volume=2, issue=null, pageStart=115, pageEnd=133, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=MURRAY L T, journalName=Current Pollution Reports, refType=null, unstructuredReference=MURRAY L T. Lightning NOx and impacts on air quality[J]. Current Pollution Reports, 2016, 2: 115-133., articleTitle=Lightning NOx and impacts on air quality, refAbstract=null), Reference(id=1295068065503408350, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=1989, volume=31, issue=4, pageStart=25, pageEnd=27, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=WILSON R, journalName=Environment: Science and Policy for Sustainable Development, refType=null, unstructuredReference=WILSON R. Air pollution, the automobile, and public health[J]. Environment: Science and Policy for Sustainable Development, 1989, 31(4): 25-27., articleTitle=Air pollution, the automobile, and public health, refAbstract=null), Reference(id=1295068065570517215, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2025, volume=16, issue=1, pageStart=1730, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=YANG S, LI M, GUO C, journalName=Nature Communications, refType=null, unstructuredReference=YANG S, LI M, GUO C, et al. Associations of long-term exposure to nitrogen oxides with all-cause and cause-specific mortality[J]. Nature Communications, 2025, 16(1): 1730., articleTitle=Associations of long-term exposure to nitrogen oxides with all-cause and cause-specific mortality, refAbstract=null), Reference(id=1295068065629237472, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2018, volume=9, issue=null, pageStart=611, pageEnd=629, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=YAMASHITA R, NISHIO M, DO R K G, journalName=Insights Into Imaging, refType=null, unstructuredReference=YAMASHITA R, NISHIO M, DO R K G, et al. Convolutional neural networks: an overview and application in radiology[J]. Insights Into Imaging, 2018, 9: 611-629., articleTitle=Convolutional neural networks: an overview and application in radiology, refAbstract=null), Reference(id=1295068065725706465, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2020, volume=8, issue=null, pageStart=14, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=MANISALIDIS I, STAVROPOULOU E, STAVROPOULOS A, journalName=Frontiers in Public Health, refType=null, unstructuredReference=MANISALIDIS I, STAVROPOULOU E, STAVROPOULOS A, et al. Environmental and health impacts of air pollution: a review[J]. Frontiers in Public Health, 2020, 8: 14., articleTitle=Environmental and health impacts of air pollution: a review, refAbstract=null), Reference(id=1295068065838952674, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2007, volume=333, issue=4, pageStart=249, pageEnd=256, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=CHEN T M, KUSCHNER W G, GOKHALE J, journalName=The American Journal of the Medical Sciences, refType=null, unstructuredReference=CHEN T M, KUSCHNER W G, GOKHALE J, et al. Outdoor air pollution: nitrogen dioxide, sulfur dioxide, and carbon monoxide health effects[J]. The American Journal of the Medical Sciences, 2007, 333(4): 249-256., articleTitle=Outdoor air pollution: nitrogen dioxide, sulfur dioxide, and carbon monoxide health effects, refAbstract=null), Reference(id=1295068065918644451, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2024, volume=24, issue=14, pageStart=4442, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=HE K, DING H, journalName=Sensors, refType=null, unstructuredReference=HE K, DING H. Prediction of NOx emissions in thermal power plants using a dynamic soft sensor based on random forest and just-in-time learning methods[J]. Sensors, 2024, 24(14): 4442., articleTitle=Prediction of NOx emissions in thermal power plants using a dynamic soft sensor based on random forest and just-in-time learning methods, refAbstract=null), Reference(id=1295068065985753316, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2013, volume=55, issue=null, pageStart=319, pageEnd=329, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=LV Y, LIU J, YANG T, journalName=Energy, refType=null, unstructuredReference=LV Y, LIU J, YANG T, et al. A novel least squares support vector machine ensemble model for NOx emission prediction of a coal-fired boiler[J]. Energy, 2013, 55: 319-329., articleTitle=A novel least squares support vector machine ensemble model for NOx emission prediction of a coal-fired boiler, refAbstract=null), Reference(id=1295068066065445093, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2022, volume=13, issue=5, pageStart=686, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=SONG M, XUE J, GAO S, journalName=Atmosphere, refType=null, unstructuredReference=SONG M, XUE J, GAO S, et al. Prediction of NOx concentration at SCR inlet based on BMIFS-LSTM[J]. Atmosphere, 2022, 13(5): 686., articleTitle=Prediction of NOx concentration at SCR inlet based on BMIFS-LSTM, refAbstract=null), Reference(id=1295068066136748262, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2024, volume=305, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=WU Z, ZHANG Y, DONG Z, journalName=Energy, refType=null, unstructuredReference=WU Z, ZHANG Y, DONG Z. NOx concentration prediction based on multi-channel fused spectral temporal graph neural network in coal-fired power plants[J]. Energy, 2024, 305: 132222., articleTitle=NOx concentration prediction based on multi-channel fused spectral temporal graph neural network in coal-fired power plants, refAbstract=null), Reference(id=1295068066203857127, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2022, volume=256, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=11, authorNames=TANG Z, WANG S, CHAI X, journalName=Energy, refType=null, unstructuredReference=TANG Z, WANG S, CHAI X, et al. Auto-encoder-extreme learning machine model for boiler NOx emission concentration prediction[J]. Energy, 2022, 256: 124552., articleTitle=Auto-encoder-extreme learning machine model for boiler NOx emission concentration prediction, refAbstract=null), Reference(id=1295068066279354600, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2020, volume=190, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=12, authorNames=XIE P, GAO M, ZHANG H, journalName=Energy, refType=null, unstructuredReference=XIE P, GAO M, ZHANG H, et al. Dynamic modeling for NOx emission sequence prediction of SCR system outlet based on sequence to sequence long short-term memory network[J]. Energy, 2020, 190: 116482., articleTitle=Dynamic modeling for NOx emission sequence prediction of SCR system outlet based on sequence to sequence long short-term memory network, refAbstract=null), Reference(id=1295068066342269161, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2023, volume=16, issue=1, pageStart=76, pageEnd=null, url=null, language=null, rfNumber=[14], rfOrder=13, authorNames=LI N, LV Y, HU Y, journalName=Energies, refType=null, unstructuredReference=LI N, LV Y, HU Y. Prediction of NOx emissions from a coal-fired boiler based on convolutional neural networks with a channel attention mechanism[J]. Energies, 2023, 16(1): 76., articleTitle=Prediction of NOx emissions from a coal-fired boiler based on convolutional neural networks with a channel attention mechanism, refAbstract=null), Reference(id=1295068067592171754, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=14, authorNames=GOODFELLOW I, BENGIO Y, COURVILLE A, journalName=Deep learning, refType=null, unstructuredReference=GOODFELLOW I, BENGIO Y, COURVILLE A, et al. Deep learning[M]. Cambridge: MIT Press, 2016: 1., articleTitle=null, refAbstract=null), Reference(id=1295068068112265451, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2023, volume=264, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=15, authorNames=WEN X, LI K, WANG J, journalName=Energy, refType=null, unstructuredReference=WEN X, LI K, WANG J. NOx emission predicting for coal-fired boilers based on ensemble learning methods and optimized base learners[J]. Energy, 2023, 264: 126171., articleTitle=NOx emission predicting for coal-fired boilers based on ensemble learning methods and optimized base learners, refAbstract=null), Reference(id=1295068068175180012, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2021, volume=289, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[17], rfOrder=16, 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=1295068068250677485, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2021, volume=47, issue=12, pageStart=79, pageEnd=86, url=null, language=null, rfNumber=[18], rfOrder=17, authorNames=王印松, 陈瑞杰, journalName=中国测试, refType=null, unstructuredReference=王印松,陈瑞杰. 基于Elastic Net特征变量选择的SCR入口NOx软测量模型[J]. 中国测试202147(12):79-86., articleTitle=基于Elastic Net特征变量选择的SCR入口NOx软测量模型, refAbstract=null), Reference(id=1295068068313592046, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2021, volume=47, issue=12, pageStart=79, pageEnd=86, url=null, language=null, rfNumber=[18], rfOrder=18, authorNames=WANG Yinsong, CHEN Ruijie, journalName=China Measurement & Test, refType=null, unstructuredReference=WANG Yinsong, CHEN Ruijie. Soft sensor model of SCR inlet NOx based on Elastic Net feature variable selection[J]. China Measurement & Test, 2021, 47(12): 79-86., articleTitle=Soft sensor model of SCR inlet NOx based on Elastic Net feature variable selection, refAbstract=null), Reference(id=1295068068384895215, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2023, volume=30, issue=9, pageStart=1616, pageEnd=1623, url=null, language=null, rfNumber=[19], rfOrder=19, authorNames=于静, 金秀章, 刘岳, journalName=控制工程, refType=null, unstructuredReference=于静,金秀章,刘岳. 基于结构改进RBF神经网络的NOx预测模型比较[J]. 控制工程202330(9):1616-1623., articleTitle=基于结构改进RBF神经网络的NOx预测模型比较, refAbstract=null), Reference(id=1295068068452004080, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2023, volume=30, issue=9, pageStart=1616, pageEnd=1623, url=null, language=null, rfNumber=[19], rfOrder=20, authorNames=YU Jing, JIN Xiuzhang, LIU Yue, journalName=Control Engineering, refType=null, unstructuredReference=YU Jing, JIN Xiuzhang, LIU Yue. Comparison of NOx prediction models based on structurally improved RBF neural network[J]. Control Engineering, 2023, 30(9): 1616-1623., articleTitle=Comparison of NOx prediction models based on structurally improved RBF neural network, refAbstract=null), Reference(id=1295068068519112945, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=7, pageStart=551, pageEnd=557, url=null, language=null, rfNumber=[20], rfOrder=21, authorNames=金秀章, 于静, 刘岳, journalName=动力工程学报, refType=null, unstructuredReference=金秀章,于静,刘岳. 基于人工鱼群-径向基神经网络的NOx预测模型[J]. 动力工程学报202141(7):551-557., articleTitle=基于人工鱼群-径向基神经网络的NOx预测模型, refAbstract=null), Reference(id=1295068068586221810, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2021, volume=41, issue=7, pageStart=551, pageEnd=557, url=null, language=null, rfNumber=[20], rfOrder=22, authorNames=JIN Xiuzhang, YU Jing, LIU Yue, journalName=Journal of Power Engineering, refType=null, unstructuredReference=JIN Xiuzhang, YU Jing, LIU Yue. NOx prediction model based on artificial fish swarm-RBF neural network[J]. Journal of Power Engineering, 2021, 41(7): 551-557., articleTitle=NOx prediction model based on artificial fish swarm-RBF neural network, refAbstract=null), Reference(id=1295068068640747763, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2001, volume=null, issue=null, pageStart=1189, pageEnd=1232, url=null, language=null, rfNumber=[21], rfOrder=23, authorNames=FRIEDMAN J H, journalName=Annals of Statistics, refType=null, unstructuredReference=FRIEDMAN J H. Greedy function approximation: a gradient boosting machine[J]. Annals of Statistics, 2001: 1189-1232., articleTitle=Greedy function approximation: a gradient boosting machine, refAbstract=null), Reference(id=1295068068720439540, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2020, volume=null, issue=null, pageStart=1287, pageEnd=1296, url=null, language=null, rfNumber=[22], rfOrder=24, authorNames=GARREAU D, LUXBURG U, journalName=null, refType=null, unstructuredReference=GARREAU D, LUXBURG U. Explaining the explainer: a first theoretical analysis of LIME[C]. International Conference on Artificial Intelligence and Statistics. PMLR, 2020: 1287-1296., articleTitle=Explaining the explainer: a first theoretical analysis of LIME, refAbstract=null), Reference(id=1295068068808519925, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=1135, pageEnd=1144, url=null, language=null, rfNumber=[23], rfOrder=25, authorNames=RIBEIRO M T, SINGH S, GUESTRIN C, journalName=null, refType=null, unstructuredReference=RIBEIRO M T, SINGH S, GUESTRIN C. “Why should I trust you?” Explaining the predictions of any classifier[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016: 1135-1144., articleTitle=“Why should I trust you?” Explaining the predictions of any classifier, refAbstract=null), Reference(id=1295068068896600310, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2020, volume=2, issue=1, pageStart=56, pageEnd=67, url=null, language=null, rfNumber=[24], rfOrder=26, authorNames=LUNDBERG S M, ERION G, CHEN H, journalName=Nature Machine Intelligence, refType=null, unstructuredReference=LUNDBERG S M, ERION G, CHEN H, et al. From local explanations to global understanding with explainable AI for trees[J]. Nature Machine Intelligence, 2020, 2(1): 56-67., articleTitle=From local explanations to global understanding with explainable AI for trees, refAbstract=null), Reference(id=1295068068955320567, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2023, volume=170, issue=null, pageStart=647, pageEnd=659, url=null, language=null, rfNumber=[25], rfOrder=27, authorNames=CARTER A, IMTIAZ S, NATERER G F, journalName=Process Safety and Environmental Protection, refType=null, unstructuredReference=CARTER A, IMTIAZ S, NATERER G F. Review of interpretable machine learning for process industries[J]. Process Safety and Environmental Protection, 2023, 170: 647-659., articleTitle=Review of interpretable machine learning for process industries, refAbstract=null), Reference(id=1295068069035012344, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2020, volume=10, issue=24, pageStart=9151, pageEnd=null, url=null, language=null, rfNumber=[26], rfOrder=28, authorNames=LIANG Y C, MAIMURY Y, CHEN A H L, journalName=Applied Sciences, refType=null, unstructuredReference=LIANG Y C, MAIMURY Y, CHEN A H L, et al. Machine learning-based prediction of air quality[J]. Applied Sciences, 2020, 10(24): 9151., articleTitle=Machine learning-based prediction of air quality, refAbstract=null), Reference(id=1295068069110509817, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2023, volume=56, issue=9, pageStart=10031, pageEnd=10066, url=null, language=null, rfNumber=[27], rfOrder=29, authorNames=MÉNDEZ M, MERAYO M G, NÚÑEZ M, journalName=Artificial Intelligence Review, refType=null, unstructuredReference=MÉNDEZ M, MERAYO M G, NÚÑEZ M. Machine learning algorithms to forecast air quality: a survey[J]. Artificial Intelligence Review, 2023, 56(9): 10031-10066., articleTitle=Machine learning algorithms to forecast air quality: a survey, refAbstract=null), Reference(id=1295068069177618682, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[28], rfOrder=30, authorNames=null, journalName=null, refType=null, unstructuredReference=固定污染源烟气(SO2、NO、颗粒物)排放连续监测技术规范:HJ 75—2017[S]. 北京:中国环境科学出版社,2018:1., articleTitle=null, refAbstract=null), Reference(id=1295068069236338939, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[28], rfOrder=31, authorNames=null, journalName=null, refType=null, unstructuredReference=Technical specification for continuous emissions monitoring of flue gas from stationary pollution sources (SO2, NOx, particulate matter): HJ 75—2017[S]. Beijing: China Environmental Science Press, 2018: 1., articleTitle=null, refAbstract=null), Reference(id=1295068069324419324, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2019, volume=176, issue=null, pageStart=429, pageEnd=436, url=null, language=null, rfNumber=[29], rfOrder=32, 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=1295068069391528189, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2023, volume=389, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[30], rfOrder=33, authorNames=WANG Z, PENG X, CAO S, journalName=Journal of Cleaner Production, refType=null, unstructuredReference=WANG Z, PENG X, CAO S, et al. NOx emission prediction using a lightweight convolutional neural network for cleaner production in a down-fired boiler[J]. Journal of Cleaner Production, 2023, 389: 136060., articleTitle=NOx emission prediction using a lightweight convolutional neural network for cleaner production in a down-fired boiler, refAbstract=null), Reference(id=1295068069458637054, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2018, volume=11, issue=11, pageStart=3028, pageEnd=null, url=null, language=null, rfNumber=[31], rfOrder=34, authorNames=PAPAGIANNAKIS R G, RAKOPOULOS D C, RAKOPOULOS C D, journalName=Energies, refType=null, unstructuredReference=PAPAGIANNAKIS R G, RAKOPOULOS D C, RAKOPOULOS C D. Evaluation of the air oxygen enrichment effects on combustion and emissions of natural gas/diesel dual-fuel engines at various loads and pilot fuel quantities[J]. Energies, 2018, 11(11): 3028., articleTitle=Evaluation of the air oxygen enrichment effects on combustion and emissions of natural gas/diesel dual-fuel engines at various loads and pilot fuel quantities, refAbstract=null), Reference(id=1295068069525745919, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2020, volume=6, issue=null, pageStart=13, pageEnd=null, url=null, language=null, rfNumber=[32], rfOrder=35, authorNames=IAVARONE S, PARENTE A, journalName=Frontiers in Mechanical Engineering, refType=null, unstructuredReference=IAVARONE S, PARENTE A. NOx formation in MILD combustion: potential and limitations of existing approaches in CFD[J]. Frontiers in Mechanical Engineering, 2020, 6: 13., articleTitle=NOx formation in MILD combustion: potential and limitations of existing approaches in CFD, refAbstract=null), Reference(id=1295068069597049088, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2023, volume=13, issue=4, pageStart=252, pageEnd=null, url=null, language=null, rfNumber=[33], rfOrder=36, authorNames=陈东东, 伍林玲, 苑梦兰, journalName=化学工程与技术, refType=null, unstructuredReference=陈东东,伍林玲,苑梦兰,. 水泥窑低氮分级燃烧下脱硝工程技术的研究综述[J]. 化学工程与技术202313(4):252., articleTitle=水泥窑低氮分级燃烧下脱硝工程技术的研究综述, refAbstract=null), Reference(id=1295068069685129473, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2023, volume=13, issue=4, pageStart=252, pageEnd=null, url=null, language=null, rfNumber=[33], rfOrder=37, authorNames=CHEN Dongdong, WU Linling, YUAN Menglan, journalName=Journal of Chemical Engineering and Technology, refType=null, unstructuredReference=CHEN Dongdong, WU Linling, YUAN Menglan, et al. Review of denitrification engineering technology under low-nitrogen staged combustion in cement kilns[J]. Journal of Chemical Engineering and Technology, 2023, 13(4): 252., articleTitle=Review of denitrification engineering technology under low-nitrogen staged combustion in cement kilns, refAbstract=null), Reference(id=1295068069794181378, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=142, pageEnd=150, url=null, language=null, rfNumber=[34], rfOrder=38, authorNames=ALQAHTANI D K, CHEEMA M A, TOOSI A N, journalName=null, refType=null, unstructuredReference=ALQAHTANI D K, CHEEMA M A, TOOSI A N. Benchmarking deep learning models for object detection on edge computing devices[C]//Proceedings of the International Conference on Service-Oriented Computing. Singapore: Springer Nature Singapore, 2024: 142-150., articleTitle=Benchmarking deep learning models for object detection on edge computing devices, refAbstract=null), Reference(id=1295068069873873155, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, doi=null, pmid=null, pmcid=null, year=2025, volume=15, issue=16, pageStart=2926, pageEnd=null, url=null, language=null, rfNumber=[35], rfOrder=39, authorNames=LU L, CAO Z, CHEN X, journalName=Buildings, refType=null, unstructuredReference=LU L, CAO Z, CHEN X, et al. Hybrid precision gradient accumulation for CNN-LSTM in sports venue buildings analytics: energy-efficient spatiotemporal modeling[J]. Buildings, 2025, 15(16): 2926., articleTitle=Hybrid precision gradient accumulation for CNN-LSTM in sports venue buildings analytics: energy-efficient spatiotemporal modeling, refAbstract=null)], funds=[Fund(id=1295068065193029850, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, awardId=ZNKJ-2025-034, language=EN, fundingSource=Science and Technology Project of Zhejiang Energy Group Co., Ltd.(ZNKJ-2025-034), fundOrder=null, country=null), Fund(id=1295068065268527323, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, awardId=ZNKJ-2025-034, language=CN, fundingSource=浙江省能源集团有限公司科学技术项目(ZNKJ-2025-034), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1295068059904012443, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=1., ext=[AuthorCompanyExt(id=1295068059912401052, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059904012443, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Zhejiang Zheneng Lanxi Power Generation Co., Ltd., Jinhua 321102, China), AuthorCompanyExt(id=1295068059924983965, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059904012443, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.浙江浙能兰溪发电有限责任公司,浙江 金华 321102)]), AuthorCompany(id=1295068059992092830, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=2., ext=[AuthorCompanyExt(id=1295068060000481439, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China), AuthorCompanyExt(id=1295068060004675744, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121)])], figs=[ArticleFig(id=1295068064240922830, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=EN, label=Fig.1, caption=The predicted NOx mass concentrations of DL and XGBoost models on test sets and the actual values, figureFileSmall=JwXEDhJyNerLDybIQB+BkQ==, figureFileBig=2M1LXHlTentpIsE35Hs0Hw==, tableContent=null), ArticleFig(id=1295068064312225999, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=CN, label=图1, caption=DL与XGBoost模型在测试集上的NOx质量浓度预测值与实际值对比, figureFileSmall=JwXEDhJyNerLDybIQB+BkQ==, figureFileBig=2M1LXHlTentpIsE35Hs0Hw==, tableContent=null), ArticleFig(id=1295068064471609552, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=EN, label=Fig.2, caption=Comparison of residuals between DL and XGBoost models on the test set, figureFileSmall=wnrOYe6yMO9S5c6FGvoJQg==, figureFileBig=MFNaJLqg9PkWAKeykMN3rw==, tableContent=null), ArticleFig(id=1295068064530329809, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=CN, label=图2, caption=DL与XGBoost模型在测试集上的残差对比, figureFileSmall=wnrOYe6yMO9S5c6FGvoJQg==, figureFileBig=MFNaJLqg9PkWAKeykMN3rw==, tableContent=null), ArticleFig(id=1295068064593244370, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=EN, label=Fig.3, caption=Comparison of DL and XGBoost models in terms of predictive performance and computational efficiency on the test set, figureFileSmall=k4Y+6dohqUciF95lKkMe2g==, figureFileBig=vq6ChgYs6r6hccL1x1oe2w==, tableContent=null), ArticleFig(id=1295068064668741843, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=CN, label=图3, caption=DL与XGBoost模型在测试集预测性能及计算效率对比, figureFileSmall=k4Y+6dohqUciF95lKkMe2g==, figureFileBig=vq6ChgYs6r6hccL1x1oe2w==, tableContent=null), ArticleFig(id=1295068064735850708, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=EN, label=Fig.4, caption=Variable importance analysis from DL model and XGBoost model, figureFileSmall=SZlSGR4crMtAk5ouKs5IMA==, figureFileBig=8LqFmcSLQtBum5rr7UaoyQ==, tableContent=null), ArticleFig(id=1295068064811348181, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=CN, label=图4, caption=DL模型和XGBoost模型预测变量重要性分析, figureFileSmall=SZlSGR4crMtAk5ouKs5IMA==, figureFileBig=8LqFmcSLQtBum5rr7UaoyQ==, tableContent=null), ArticleFig(id=1295068064891039958, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=EN, label=Fig.5, caption=Framework of NOx soft-sensing control system based on edge-embedded collaborative architecture, figureFileSmall=RQkXx0pS7FhMBHKj7y4HyQ==, figureFileBig=+80lYEjnKhLFCv26dWMhYQ==, tableContent=null), ArticleFig(id=1295068064970731735, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=CN, label=图5, caption=基于边缘-嵌入式协同架构的NOx软测量控制系统框架, figureFileSmall=RQkXx0pS7FhMBHKj7y4HyQ==, figureFileBig=+80lYEjnKhLFCv26dWMhYQ==, tableContent=null), ArticleFig(id=1295068065050423512, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=EN, label=Tab.1, caption=

Performance comparison of multiple NOx emission prediction models on the test set

, figureFileSmall=null, figureFileBig=null, tableContent=
模型类型样本数特征维度δRMSE/(mg·m³)R²
LSTM单步预测[29]10 00050A侧:13.799A侧:0.954
B侧:10.600B侧:0.955
Stacking/Blending[16]15 0002714.115/14.0170.972/0.973
CNN+ECA[14]86 40055A侧:3.030A侧:0.992
B侧:3.240B侧:0.990
C3-CNN[30]14 4194913.5270.933
JIT-RF[8]5 184383.6960.930
XGBoost模型118 81475A侧:9.4A侧:0.977
B侧:9.0B侧:0.968
DL模型118 81475A侧:8.4A侧:0.981
B侧:8.1B侧:0.974
), ArticleFig(id=1295068065109143769, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, language=CN, label=表1, caption=

在测试集上多种NOx排放预测模型性能对比

, figureFileSmall=null, figureFileBig=null, tableContent=
模型类型样本数特征维度δRMSE/(mg·m³)R²
LSTM单步预测[29]10 00050A侧:13.799A侧:0.954
B侧:10.600B侧:0.955
Stacking/Blending[16]15 0002714.115/14.0170.972/0.973
CNN+ECA[14]86 40055A侧:3.030A侧:0.992
B侧:3.240B侧:0.990
C3-CNN[30]14 4194913.5270.933
JIT-RF[8]5 184383.6960.930
XGBoost模型118 81475A侧:9.4A侧:0.977
B侧:9.0B侧:0.968
DL模型118 81475A侧:8.4A侧:0.981
B侧:8.1B侧:0.974
)], 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=IcKGK23kpfWlBK6GqYtS5g==, journalPrice=null, startedYear=null, abbrevIsoEn=Thermal Power Generation, journalRemark=null, publicationField=null, createdTime=1766639718774, updatedTime=1784018130043, createdBy=18614031015, updatedBy=13041195026, firstLetterCn=R, firstLetterEn=R, subjectCode=Engineering, subjectName=Engineering, subjectCodeEn=Engineering, subjectNameEn=null, picCn=IcKGK23kpfWlBK6GqYtS5g==, picEn=UzifuamzuAk3uXMVSOtdyA==, jcr=null, cjcr=null, exts=[JournalExt(id=1283828346035356554, 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=1784018130072, updatedTime=1784018130072, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://rlfdauthor.cast.org.cn/webm, submissionEditorUrl=https://rlfdeditor.cast.org.cn/webm, submissionReviewUrl=https://rlfdauthor.cast.org.cn/webm, submissionCeEditorUrl=https://rlfdeditor.cast.org.cn/webm, submissionAeEditorUrl=https://rlfdeditor.cast.org.cn/webm, option={"copyright":""}), JournalExt(id=1283828346094076811, 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=1784018130086, updatedTime=1784018130086, createdBy=13041195026, updatedBy=13041195026, submissionGuidelinesUrl=, submissionAuthorUrl=https://rlfdauthor.cast.org.cn/webm, submissionEditorUrl=https://rlfdeditor.cast.org.cn/webm, submissionReviewUrl=https://rlfdauthor.cast.org.cn/webm, submissionCeEditorUrl=https://rlfdeditor.cast.org.cn/webm, submissionAeEditorUrl=https://rlfdeditor.cast.org.cn/webm, 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=1307280923934876518, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=articleTextType, value=kx, createTime=1789609660371, updateTime=1789609660371, creator=18614031015, updator=18614031015), WebsiteProps(id=1307280923905516387, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=banner, value=null, createTime=1789609660364, updateTime=1789609660364, creator=18614031015, updator=18614031015), WebsiteProps(id=1307280923960042345, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=grayFlag, value=0, createTime=1789609660377, updateTime=1789609660377, creator=18614031015, updator=18614031015), WebsiteProps(id=1307280923880350562, 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=1789609660358, updateTime=1789609660358, creator=18614031015, updator=18614031015), WebsiteProps(id=1307280923976819563, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=minRunFlag, value=0, createTime=1789609660381, updateTime=1789609660381, creator=18614031015, updator=18614031015), WebsiteProps(id=1307280923926487909, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/rlfd/CN/file/pic, createTime=1789609660369, updateTime=1789609660369, creator=18614031015, updator=18614031015), WebsiteProps(id=1307280923968430954, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=silenceFlag, value=0, createTime=1789609660379, updateTime=1789609660379, creator=18614031015, updator=18614031015), WebsiteProps(id=1307280923913904996, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1789609660366, updateTime=1789609660366, creator=18614031015, updator=18614031015), WebsiteProps(id=1307280923943265127, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=themeColor, value=null, createTime=1789609660373, updateTime=1789609660373, creator=18614031015, updator=18614031015), WebsiteProps(id=1307280923951653736, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=themeStyle, value=.style-1 .main-menu ul>li { margin-right: 18px; }, createTime=1789609660375, updateTime=1789609660375, 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=1218204520857915865, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=articleTextType, value=kx, createTime=1768372190918, updateTime=1768372190918, creator=18614031015, updator=18614031015), WebsiteProps(id=1218204520841138646, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=banner, value=null, createTime=1768372190914, updateTime=1768372190914, creator=18614031015, updator=18614031015), WebsiteProps(id=1218204520874693084, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=grayFlag, value=0, createTime=1768372190922, updateTime=1768372190922, creator=18614031015, updator=18614031015), WebsiteProps(id=1218204520828555733, 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=1768372190911, updateTime=1768372190911, creator=18614031015, updator=18614031015), WebsiteProps(id=1218204520887275998, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=minRunFlag, value=0, createTime=1768372190925, updateTime=1768372190925, creator=18614031015, updator=18614031015), WebsiteProps(id=1218204520853721560, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/rlfd/EN/file/pic, createTime=1768372190917, updateTime=1768372190917, creator=18614031015, updator=18614031015), WebsiteProps(id=1218204520883081693, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=silenceFlag, value=0, createTime=1768372190924, updateTime=1768372190924, creator=18614031015, updator=18614031015), WebsiteProps(id=1218204520845332951, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1768372190915, updateTime=1768372190915, creator=18614031015, updator=18614031015), WebsiteProps(id=1218204520866304474, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=themeColor, value=null, createTime=1768372190920, updateTime=1768372190920, creator=18614031015, updator=18614031015), WebsiteProps(id=1218204520870498779, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=themeStyle, value=.style-1 .main-menu ul>li { margin-right: 15px; }, createTime=1768372190921, updateTime=1768372190921, creator=18614031015, updator=18614031015)])], journalTitle=热力发电, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=Thermal Power Generation, journalPhotoCn=IcKGK23kpfWlBK6GqYtS5g==, journalPhotoEn=UzifuamzuAk3uXMVSOtdyA==, journalFirstLetter=R, 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, interPubPlatform=, interPubPlatformUrl=null), detailUrlCn=https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202507085, detailUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/10.19666/j.rlfd.202507085, pdfUrlCn=https://castjournals.cast.org.cn/joweb/rlfd/CN/PDF/10.19666/j.rlfd.202507085, pdfUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/PDF/10.19666/j.rlfd.202507085, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1777046400000, fullTextJson=null, articleText=null, reference=null)
收藏切换
燃煤机组SCR脱硝入口NOx质量浓度的多模型动态预测及协同部署
收藏切换
PDF下载
卢得勇 1 , 韦智友 2 , 刘宇博 1 , 李海强 1 , 丁得龙 2 , 沈波 2 , 李来 2
热力发电 | 发电技术论坛 2026,55(4): 156-165
收起
收藏切换
热力发电 |发电技术论坛 2026 , 55 (4) : 156 -165
燃煤机组SCR脱硝入口NOx质量浓度的多模型动态预测及协同部署
全屏
[Author(id=1295068060071784610, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=ludeyong@oamail.zhenergy.com.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1295068060143087780, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060071784610, language=EN, stringName=Deyong LU, firstName=Deyong, middleName=null, lastName=LU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Zhejiang Zheneng Lanxi Power Generation Co., Ltd., Jinhua 321102, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068060252139685, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060071784610, language=CN, stringName=卢得勇, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.浙江浙能兰溪发电有限责任公司,浙江 金华 321102, bio={"content":"

卢得勇(1989),男,硕士,工程师,主要研究方向为热能与动力工程,

"}, bioImg=null, bioContent=

卢得勇(1989),男,硕士,工程师,主要研究方向为热能与动力工程,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068059904012443, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=1., ext=[AuthorCompanyExt(id=1295068059912401052, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059904012443, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Zhejiang Zheneng Lanxi Power Generation Co., Ltd., Jinhua 321102, China), AuthorCompanyExt(id=1295068059924983965, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059904012443, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.浙江浙能兰溪发电有限责任公司,浙江 金华 321102)])]), Author(id=1295068060340220071, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhiyou_weii@163.com, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1295068060449271977, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060340220071, language=EN, stringName=Zhiyou WEI, firstName=Zhiyou, middleName=null, lastName=WEI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068060512186538, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060340220071, language=CN, stringName=韦智友, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068059992092830, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=2., ext=[AuthorCompanyExt(id=1295068060000481439, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China), AuthorCompanyExt(id=1295068060004675744, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121)])]), Author(id=1295068060579295404, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, 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=1295068060650598574, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060579295404, language=EN, stringName=Yubo LIU, firstName=Yubo, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Zhejiang Zheneng Lanxi Power Generation Co., Ltd., Jinhua 321102, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068060730290351, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060579295404, language=CN, stringName=刘宇博, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.浙江浙能兰溪发电有限责任公司,浙江 金华 321102, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068059904012443, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=1., ext=[AuthorCompanyExt(id=1295068059912401052, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059904012443, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Zhejiang Zheneng Lanxi Power Generation Co., Ltd., Jinhua 321102, China), AuthorCompanyExt(id=1295068059924983965, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059904012443, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.浙江浙能兰溪发电有限责任公司,浙江 金华 321102)])]), Author(id=1295068060822565041, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, 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=1295068060893868211, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060822565041, language=EN, stringName=Haiqiang LI, firstName=Haiqiang, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.Zhejiang Zheneng Lanxi Power Generation Co., Ltd., Jinhua 321102, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068060981948596, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068060822565041, language=CN, stringName=李海强, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.浙江浙能兰溪发电有限责任公司,浙江 金华 321102, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068059904012443, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=1., ext=[AuthorCompanyExt(id=1295068059912401052, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059904012443, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.Zhejiang Zheneng Lanxi Power Generation Co., Ltd., Jinhua 321102, China), AuthorCompanyExt(id=1295068059924983965, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059904012443, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.浙江浙能兰溪发电有限责任公司,浙江 金华 321102)])]), Author(id=1295068061049057462, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, 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=1295068061124554936, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068061049057462, language=EN, stringName=Delong DING, firstName=Delong, middleName=null, lastName=DING, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068061200052409, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068061049057462, language=CN, stringName=丁得龙, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068059992092830, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=2., ext=[AuthorCompanyExt(id=1295068060000481439, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China), AuthorCompanyExt(id=1295068060004675744, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121)])]), Author(id=1295068061296521403, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, 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=1295068061392990397, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068061296521403, language=EN, stringName=Bo SHEN, firstName=Bo, middleName=null, lastName=SHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068061481070782, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068061296521403, language=CN, stringName=沈波, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068059992092830, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=2., ext=[AuthorCompanyExt(id=1295068060000481439, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China), AuthorCompanyExt(id=1295068060004675744, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121)])]), Author(id=1295068061564956864, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, orderNo=6, 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=1295068061636260034, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068061564956864, language=EN, stringName=Lai LI, firstName=Lai, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068061728534723, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, authorId=1295068061564956864, language=CN, stringName=李来, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068059992092830, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, xref=2., ext=[AuthorCompanyExt(id=1295068060000481439, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China), AuthorCompanyExt(id=1295068060004675744, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068056414351501, companyId=1295068059992092830, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121)])])]
卢得勇1 , 韦智友2 , 刘宇博1, 李海强1, 丁得龙2, 沈波2, 李来2
作者信息
  • 1.浙江浙能兰溪发电有限责任公司,浙江 金华 321102
  • 2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121
通讯作者:
韦智友(1992),男,博士,高级工程师,主要研究方向为能源环保工程,
作者简介:

卢得勇(1989),男,硕士,工程师,主要研究方向为热能与动力工程,

Multi-model dynamic prediction and collaborative deployment of NOx mass concentration at inlet of SCR denitration system in coal-fired power units
Deyong LU1 , Zhiyou WEI2 , Yubo LIU1, Haiqiang LI1, Delong DING2, Bo SHEN2, Lai LI2
Affiliations
  • 1.Zhejiang Zheneng Lanxi Power Generation Co., Ltd., Jinhua 321102, China
  • 2.Zhejiang Zheneng Technology & Environment Group Co., Ltd., Hangzhou 311121, China
出版时间: 2026-04-25 doi: 10.19666/j.rlfd.202507085
文章导航
收藏切换

为满足燃煤机组选择性催化还原(selective catalytic reduction, SCR)脱硝系统对氮氧化物(NOx)质量浓度预测的高需求,设计并提出一种兼具高精度和低延迟的软测量及部署方案。基于某660 MW燃煤机组11万余组高维运行数据,在统一平台下系统对比了深度学习(deep learning,DL)与XGBoost(extreme gradient boosting)2种模型,采用时序交叉验证结合网格搜索优化模型超参数,并从预测精度、计算效率及可解释性三方面进行综合评估。在此基础上,提出“边缘–嵌入式”协同部署策略,将DL模型部署于边缘服务器以获取高精度预测结果,XGBoost模型嵌入分散控制系统(distributed control system,DCS)保障实时性。结果表明:DL模型在动态响应与预测精度上表现更优,其测试集均方根误差较XGBoost模型降低约10%,并在工况剧烈波动时DL模型能保持稳定性;变量重要性分析显示,烟气含氧量、燃烧器壁温和总风量是影响NOx生成的主要因素。所提协同部署架构理论上可实现毫秒级推理,并具备离线容错能力。

NOx质量浓度预测  /  深度学习  /  变量重要性  /  边缘计算  /  模型部署

To meet the high requirements of selective catalytic reduction (SCR) systems in coal-fired power plants for accurate and low-latency prediction of nitrogen oxides (NOx) mass concentrations, this study designs and proposes a soft sensing and deployment framework that balances high accuracy and real-time performance. Using more than 110 000 sets of high-dimensional operational data from a 660 MW coal-fired unit, a systematic comparison of deep learning (DL) and XGBoost models was conducted on a unified platform. Time series cross-validation combined with grid search was employed to optimize hyperparameters, and model performance was comprehensively evaluated in terms of predictive accuracy, computational efficiency, and interpretability via local interpretable model-agnostic explanations. On this basis, an “edge-embedded” collaborative deployment strategy was proposed, in which the DL model is deployed on edge servers to deliver high-accuracy predictions, while the XGBoost model is embedded into the distributed control system (DCS) to ensure real-time responsiveness. The results show that the DL model outperforms XGBoost in dynamic response and predictive accuracy, achieving root mean square errors approximately 10% lower than that of the XGBoost, and maintaining stability under highly fluctuating conditions. Variable importance analysis highlights flue gas oxygen content, burner wall temperature, and total air volume as the dominant factors affecting NOx formation. The proposed collaborative architecture can theoretically achieve millisecond-level inference and provide offline fault tolerance, offering a practical pathway for intelligent ammonia injection control and combustion optimization.

NOx mass concentration prediction  /  deep learning  /  variable importance  /  edge computing  /  model deployment
卢得勇, 韦智友, 刘宇博, 李海强, 丁得龙, 沈波, 李来. 燃煤机组SCR脱硝入口NOx质量浓度的多模型动态预测及协同部署. 热力发电, 2026 , 55 (4) : 156 -165 . DOI: 10.19666/j.rlfd.202507085
Deyong LU, Zhiyou WEI, Yubo LIU, Haiqiang LI, Delong DING, Bo SHEN, Lai LI. Multi-model dynamic prediction and collaborative deployment of NOx mass concentration at inlet of SCR denitration system in coal-fired power units[J]. Thermal Power Generation, 2026 , 55 (4) : 156 -165 . DOI: 10.19666/j.rlfd.202507085
燃煤电厂排放大量氮氧化物(NOx),其作为主要大气污染物之一,严重危害人体健康和生态环境,如何实现其高效控制具有重要意义[1-7]。选择性催化还原(selective catalytic reduction, SCR)脱硝技术是当前电厂脱硝的主流手段,其喷氨控制的关键是精准、实时地获取SCR脱硝入口NOx含量。然而,传统的连续排放监测系统(continuous emission monitoring system,CEMS)存在响应滞后和易受工况干扰等问题[8],难以满足SCR脱硝系统快速前馈控制需求,易导致NOx排放超标或氨逃逸。
近年来,数据驱动模型凭借对高维、非线性工业运行数据的强大建模能力,在NOx含量软测量领域展现出显著优势,已成为国内外研究热点[9-20]。国内外学者围绕不同算法框架开展了广泛探索:在特征选择方面,二元互信息特征选择(binary mutual information feature selection,BMIFS)[10]、主成分分析(principal component analysis,PCA)[17]、Elastic Net[18]等方法被用于筛选关键变量;在模型架构方面,长短时记忆(long short-term memory,LSTM)神经网络[1015]、图神经网络(GNN)[11]、卷积神经网络(CNN)[14]、融合注意力机制的序列模型(Seq2Seq)[13]以及各类集成学习策略(Stacking/Blending)[16-17]等被相继应用于捕捉NOx生成的复杂时空动态特性;在模型优化方面,即时学习(JITL)[8]、智能优化算法(PSO,AFSA)[19-20]等策略被引入以提升模型的实时性与工况适应性。上述方法在多项研究中取得了显著进展。例如,Song等人将BMIFS特征筛选与LSTM模型相结合,大幅降低了SCR脱硝入口NOx质量浓度预测误差[10];Wu等人构建了融合光谱时序信息的图神经网络,有效捕捉NOx生成的复杂时空特性[11];Li等人采用CNN并引入通道注意力机制,将NOx预测的决定系数(R2)提升至0.99以上[14]。国内研究方面,王印松等利用Elastic Net方法筛选关键特征变量,明显提升了NOx软测量模型的精度[18];于静等提出结构改进的RBF神经网络用于NOx质量浓度预测[19];金秀章等在RBF神经网络基础上融合人工鱼群算法优化模型参数,提高了模型的实时响应能力[20]等。
尽管现有研究在SCR脱硝入口NOx质量浓度预测方面取得了一定进展,但仍存在若干亟待突破的问题,制约其向工程化应用的深入推进:1)模型对比缺乏系统性,多数研究聚焦单一算法,缺乏在统一大规模数据集上对深度学习(deep learning,DL)与XGBoost(extreme gradient boosting)等主流模型的精度、效率、可解释性及部署可行性进行多维度边界对比,导致工程技术人员在模型选择时缺乏依据;2)动态工况适应性不足,现有模型对机组启停、负荷骤变等强瞬变过程的预测鲁棒性验证不充分;3)部署层面存在高精度与高效率的矛盾,DL模型难以直接嵌入资源受限的分散控制系统(distributed control system,DCS),而轻量模型(如XGBoost)在极端工况下的精度与稳定性存疑,尚缺协同架构以扬长避短;4)模型可解释性薄弱,特别是DL模型的“黑箱”特性使其难以揭示关键操作变量(如含氧量、壁温)的影响机制,限制了其对燃烧优化的指导价值。
针对上述问题,本文基于11万余组高维全工况数据,在统一平台下系统比较了DL与XGBoost模型预测NOx的综合性能,量化其在精度、效率和可解释性方面的差异;构建了具体的协同架构,将高精度DL模型部署于边缘服务器,将轻量XGBoost模型嵌入DCS,二者通过标准协议协同工作,实现了精度与实时性的有效平衡,为工程落地提供了新路径;利用覆盖复杂工况的数据集确保了模型的强泛化能力,并通过可解释性分析了NOx生成的主导因素,这对燃烧调控具有直接指导意义。
本研究数据来源于某660 MW燃煤机组的实际运行数据库,以20 s采样间隔连续采集约30天的锅炉运行参数,累计获得11万余组记录,覆盖机组负荷波动、设备启停等典型工况。为全面捕捉影响SCR脱硝入口NOx质量浓度的因素,模型输入变量选取锅炉燃烧、空气配风、炉膛温度和烟气成分等多个关键维度的参数。建模前,对原始数据进行了系统的清洗与预处理:采用线性插值填补缺失值;根据各参数的物理合理范围识别并剔除异常值,降低噪声干扰并提升数据质量;随后采用最大值-最小值归一化将所有特征缩放至[0,1]区间。为进一步提高模型训练效率和泛化能力,本研究基于锅炉燃烧机理分析与统计相关性评估,对初始特征进行筛选,剔除冗余变量,最终保留75个关键特征,并将其归纳为5类:1)机组主控参数,包括机组负荷、主蒸汽压力与温度、总风量;2)燃料供给参数,包括总煤量、6台给煤机瞬时煤量、6台磨煤机进口一次风量和一次风温;3)配风系统参数,包括左右侧燃烧器区域二次风风量、上下层燃尽风流量;4)炉膛状态参数,包括炉膛压力、燃烧器壁温、磨煤机出口风温;5)烟气系统参数,包括A/B侧入口烟气温度、A/B侧入口含氧量、A/B侧空预器出口温度、过热器温度、再热器温度。
本研究采用按时间顺序的数据划分策略。模型输入采用滑动时间窗口方法,以每个采样时刻为基准,选取其前5 min(共15个连续采样点)的历史数据,计算该窗口内各运行特征的均值、标准差及变化率,共同构成该时刻的模型输入特征向量。将所有按此方法生成的样本,按时间顺序进行划分,其中前70%的样本构成训练集,用于模型训练;后30%的样本作为验证集。
DL模型基于人工神经网络(ANN)架构学习NOx质量浓度与各影响因素之间复杂的非线性关系[14-15]。该ANN为由输入层、多个隐含层和输出层组成的前馈多层感知机(feedforward multilayer perceptron,MLP):输入层接收经过预处理的75维工况特征,隐含层通过加权求和与非线性激活函数逐层提取变量间的耦合特征,输出层生成NOx质量浓度的预测值。本文所构建的MLP包含3个隐含层,其神经元节点数依次为80、200和80。神经网络的前向传播过程如下:
h(1)=tanh(XW(1)+b(1))
h(2)=tanh(h(1)W(2)+b(2))
h(3)=tanh(h(2)W(3)+b(3))
y^=h(3)W(4)+b(4)
式中:X为输入特征矩阵;y^为模型输出的NOx质量浓度预测值;W(1)W(2)W(3)W(4)b(1)b(2)b(3)b(4)分别对应各层的权重矩阵和偏置向量。式中使用双曲正切函数(tanh)作为激活函数,该函数将线性变换结果映射到(–1,1)区间,有助于缓解梯度消失问题并提供非线性表达能力。
模型的训练通过最小化损失函Jθ)来实现,该损失函数旨在减小模型预测值与真实值之间的误差,并加入正则化以提升泛化能力。
J(θ)=1Ni=1N(yiy^i)+λ1l=1LW(1)1+λ22l=1LW(1)2θ
式中:N为训练样本数;L为隐含层与输出层的层数;λ1λ2分别为控制L1L2正则化强度的超参数;‖W(1)1和‖W(2)2分别为权重矩阵的L1范数(矩阵元素绝对值之和)和L2范数的平方(矩阵元素平方和)。
训练采用带动量(momentum)的梯度下降法对上述损失函数进行优化。每次参数更新遵循以下迭代公式:
νt=βνt1+(1β)J(θ)
θt=θt1ανt
式中:vt为当前迭代步的动量累积向量;▽Jθ)为损失函数对参数梯度;α为学习率;β为动量因子。
此外,通过时序交叉验证结合网格搜索对训练轮数(Epochs)、初始学习率(learning rate,LR)、L2正则化系数等主要超参数进行调优,最终选定的最优参数组合显著提升模型的验证集性能,确保SCR脱硝入口NOx质量浓度预测的高精度与稳健性。
XGBoost是一种高效的梯度提升决策树集成算法[21],通过迭代训练多棵决策树逐步拟合残差,不断提高模型的预测精度。其优化的目标函数Lt由训练损失和正则化项两部分构成:
L(t)=i=1Nl(yi,y^i(t1)+ft(xi))+Ω(ft)
式中:N为样本数;y^i(t1)为模型经过t–1轮迭代后对i个样本的预测值;l()为衡量预测值与真实值yi之间差异的可微损失函数(均方误差),并使用t轮新增的树模型ftx)降低当前残差;Ωft)为第t棵树的复杂度惩罚项,用于控制模型复杂度以防止过拟合,其定义如下:
Ω(f)=γT+λ2j=1Tωj2
式中:T为树的叶节点数量;Ωj为第j个叶节点的权重值;γλ为正则化系数。完成所有训练后,模型的最终预测结果为所有树输出的加权累加和:
y^(x)=m=1Kηfm(x)
式中:K为树的总数(迭代轮数);η为学习率(亦称步长),用于收缩每棵树的贡献,进一步提升模型的泛化能力。
相较传统梯度提升算法,XGBoost在训练效率和泛化性能方面进行了诸多优化:利用并行和增量式的树构建策略大幅加快了大规模数据的训练速度;引入上述正则化项,内置的缺失值处理以及列采样、行采样机制有效提升了模型对噪声和异质数据的适应能力。在本研究中,对XGBoost模型的关键超参数(包括迭代树的棵数(rounds)、学习率、最大深度(Max Depth)、正则化系数等)进行了调节优化。通过时序交叉验证结合网格搜索选取了验证集上表现最佳的参数配置,并利用Early Stopping确定了最优迭代轮数。
为提升模型的可解释性并识别影响SCR脱硝入口NOx预测结果的关键因素,本研究采用了模型无关的局部解释方法(local interpretable model-agnostic explanations,LIME)对输入变量的重要性进行评估。LIME是可解释人工智能领域的一种重要技术方法,能够解释深度神经网络、梯度提升树等黑箱模型的预测结果[22-23]。该方法已广泛应用于医学、文本、工业控制及环境等领域,用于量化各输入特征对模型预测的贡献,并提升模型透明度[24-27]。LIME通过在目标样本附近生成扰动数据并利用原模型的预测结果训练一个局部线性代理模型来近似原模型在该区域的行为。线性模型的系数反映了各输入变量对目标预测结果的正负贡献,实现对单次预测结果的解释。LIME具有模型无关和局部忠实的优势,并且通过汇总所有样本的局部解释结果,还可以得到各输入变量在整体预测中的重要性排序,为模型评估和特征优化提供依据。
通过严格的时序交叉验证结合网格搜索方法分别确定DL模型的最优设置:Epochs=100、LR=0.008、L2=0.000 01;XGBoost模型:rounds=1 500、LR=0.01、Max Depth=6、Lambda=1。在此基础上,本节将重点分析模型精度与效率的量化权衡机制、基于变量重要性的锅炉局部燃烧特征识别、面向工业应用的边缘智能部署范式以及从关键特征到控制调节路径的工程转化潜力,为NOx排放量的智能预测与过程优化控制提供系统化支撑。
图1展示了DL模型与XGBoost模型在SCR脱硝入口A侧和B侧的NOx质量浓度预测与实测值的对比结果。由图1可见,DL模型预测曲线与实测值高度吻合,精准捕捉了NOx质量浓度动态变化,即使在工况剧烈波动时也无明显滞后,峰值预测精度优于XGBoost模型。XGBoost模型虽然在平稳工况下表现稳定,但在极端变化时出现轻微滞后,预测峰值略低于实测值。
高精度的实时动态预测在工业应用中具有重要意义。燃煤机组SCR脱硝控制系统对NOx质量浓度测量精度要求极高,通常需将误差控制在12 mg/m3以内,并实现数秒级的响应延迟,以确保喷氨量调节的准确性,避免因测量滞后导致NOx排放超标或氨逃逸现象[28]。本研究中,DL模型在测试集上的预测均方根误差稳定在个位数,决定系数接近1,完全满足工程控制的精度与响应要求。相比之下,传统SCR脱硝控制系统依赖的CEMS测量普遍存在几十秒甚至更长的延迟,易引发控制滞后,影响排放达标。采用DL模型,可提前数秒至数十秒准确预测NOx质量浓度变化,向控制系统提供前馈调节信号,从而实现更加精准及时的脱硝控制,有效降低NOx排放的波动性和风险。
图2给出了2种模型在A、B两侧测点的预测残差分布。由图2可见,2种模型的预测残差均集中于零值附近,且无明显随时间积累的系统性偏差。DL残差波动范围更小,呈现高度集中的正态分布,表明其捕捉了主要影响因素,剩余误差以随机噪声为主;XGBoost模型残差分布略宽,但同样未表现出系统偏差。这表明,2种模型均有效提取了NOx质量浓度动态特征,适应了工业燃烧过程的复杂非线性特性。DL模型凭借更强的非线性拟合能力和瞬态响应能力,在捕捉短时剧烈波动方面更具优势,与文献[14]中DL模型表现出的更佳瞬态预测性能一致。
为评估模型性能并权衡精度与计算效率,本研究在相同数据集上对比了DL模型与XGBoost模型,结果如图3所示。在A侧测试集上,DL模型展现出更高的预测精度(均方根误差δRMSE=8.4 mg/m3,决定系数R2=0.981),优于XGBoost模型(δRMSE=9.4 mg/m3R2=0.977)。在B侧测试集上,DL模型同样保持优势(δRMSE=8.1 mg/m3R2=0.974),而XGBoost模型的δRMSE=9.0 mg/m3R2=0.968。综合来看,DL模型将预测误差平均降低了约10%,拟合优度(R2)亦略有提升,表明其在捕获NOx排放复杂非线性关系方面具备更强的能力。值得注意的是,2种模型在训练集与测试集上的误差均非常接近,未观察到明显的过拟合现象,验证了模型在工业级数据量上具备良好的泛化性能。然而,DL模型所获得的精度优势是以更高的计算资源消耗为代价的。这主要源于DL模型在训练中需要反复优化数百万参数,对计算资源要求较高。相比之下,XGBoost模型凭借高效的梯度提升树算法,可快速完成迭代优化,大幅降低计算资源。2种模型在单次推理计算延迟均处于毫秒级,都能满足SCR脱硝实时控制系统的工业要求。
表1为在测试集上多种NOx排放预测模型性能对比。由表1可见,与近期代表性工作[8141629-30]相比,本研究在数据规模、特征维度和工况适应性等方面均具有明显优势:1)数据规模(约11.9万条)显著大于对比研究,覆盖更全面工况,大幅提升模型泛化能力;2)特征维度(75维)高于同类模型维度,涵盖几乎所有主要影响因素,结合正则化方法确保高维训练的稳定性与信息完整性,从而提高预测精度;3)工况适应性方面,超过一个月的数据采集包含启停、负荷骤变等完整工况,远超通常采用的短期稳态数据(小于10天)。模型在全工况下仍保持高精度(R²≈ 0.970~0.980,δRMSE≈ 8.0~9.0 mg/m³),鲁棒性优异,为实际部署提供了可靠支撑。
图4为DL模型和XGBoost模型预测变量重要性分析。由图4可知,SCR脱硝入口烟气含氧量在2种模型中始终具有最大的权重,表明烟气含氧量是NOx生成的首要控制因素。多处燃烧器壁温(如锅炉E1、B2、B4等壁温)在DL模型中具有较高权重(0.21~0.39),表明火焰温度对NOx的生成也具有显著影响。这与NOx在锅炉中的生成机理是一致的[31-32],即随着燃烧区域供氧量的增加,炉膛燃烧强度和火焰温度升高,热力型NOx和燃料型NOx的生成量均随之增加。气流量及其分配对NOx的生成也有一定程度的影响,其中总风量作为整体过量空气的度量,在A侧和B侧中的权重均排名靠前(DL模型在A侧和B侧的权重均为0.33,在XGBoost模型中B侧达到0.65)。
从燃烧机理来看,较大的总风量意味着过量空气系数升高,虽可能降低局部温度,但通常会提高氧量,整体会使NOx质量浓度增加。在现有的电厂分布式控制系统中,氧量主要通过总风量设定值和二次风配风方式进行调节,而燃烧器壁温则间接反映了燃烧中心的温度场分布,可通过调整燃烧器摆角、二次风门开度以及磨煤机组合方式来进行优化。此外,机组负荷的增加会引发燃烧系统多方面的协同变化,具体表现为一次风比例下降、二次风比例上升,导致主燃烧区域的氧气供应增强;同时,为满足负荷提升的需求,燃料投加量也相应增加。这些变化共同强化燃烧反应,提升炉膛温度,从而显著加剧了热力型和燃料型NOx的生成。陈东东等指出,锅炉负荷降低时,NOx排放呈现出明显的下降趋势;而负荷升高则伴随着炉温上升、一次风比例下降和给煤量增加,最终导致NOx排放质量浓度显著升高[33]。B侧预测结果中,XGBoost模型将机组负荷识别为影响NOx质量浓度的重要变量(权重达0.21),从模型角度进一步验证了负荷对炉膛燃烧状态与NOx排放水平的控制效应。在实际运行中,负荷指令通常由电网调度下达,被视为一个不可控的边界条件。当负荷变化时,模型的实用性应体现在能提前预测NOx的波动趋势,并给出风量、氧量等可控参数的补偿性调整建议。
在SCR脱硝入口A侧数据的全局变量重要性分析中,DL模型与XGBoost模型对前十特征变量的排序表现出一定的一致性,同时也存在显著差异。两者在主要特征方面较为接近,例如均识别出含氧量、壁温和风量等为关键变量,而差异主要集中在次要特征的选择上,这种差异根本上源于2种模型对数据特征结构的学习机制不同。具体而言,DL模型更倾向于挖掘变量间的连续性和非线性关系。例如,它在多个锅炉燃烧器壁温(反映局部火焰温度)、SCR脱硝入口温度以及总风量等变量上赋予较高权重,说明其善于捕捉这类在物理变化过程中呈现连续影响的特征。而XGBoost模型作为基于梯度提升的树模型,更偏好具有明确阈值或可分段的变量,例如一、二次风量和磨煤机出口风温等,这些变量在决策树分裂时能显著降低节点的不确定性(即减少不纯度),因此更容易被赋予较高重要性。这种偏好使其更擅长识别带有“阈值效应”的输入特征。这提示在DCS中可优先基于这些变量建立规则库或逻辑判断模块,提升控制的实时性与可靠性。在B侧数据中,类似的特征选择分化也同样存在。DL模型关注的重点仍是各区域壁温和进口温度等热力学指标,如“锅炉F4/A5/D5/C6燃烧器壁温”与“B侧入口温度”;而XGBoost模型则再次突出“总风量”(权重高达0.65)、“磨煤机出口风温”及“给煤机煤量”等风量与燃料供应相关变量。在实际部署中,可将DL模型的变量重要性输出作为XGBoost模型的特征权重先验知识,进一步优化嵌入式模型的解释性与控制效果。
基于上述分析可知,DL模型与XGBoost模型在预测性能与工程部署适应性方面各有优劣,适用于不同的工业应用场景。然而,现有高精度预测方案仍普遍存在工程应用瓶颈。例如,CNN+ECA模型[14]和Stacking集成模型[16]虽具备较高预测精度,但因模型结构复杂,计算需求较大,通常需要高性能GPU设备支持或并行运行多个子模型,显著提高了现场部署成本;而JIT-RF模型[8]尽管能够实现较好的实时响应,但其推理过程涉及历史数据检索和局部模型的即时训练,导致存储开销大,实时性受限。
针对上述挑战,本研究提出了一种兼顾预测精度、计算效率和现场部署灵活性的“边缘-嵌入式”协同架构(图5)。在该架构中,现场传感器实时采集并以固定频率向边缘服务器(DL推理)与DCS(XGBoost模块)同时传输75个过程变量数据。边缘服务器上部署的DL模型以Docker容器形式运行。部署前,模型通过大量数据训练和超参数优化,已具备高精度预测能力。在部署阶段,通过模型量化、计算图优化(如使用TensorRT)并利用边缘服务器内置GPU加速推理,最终实现了毫秒级延迟的预测响应。并通过RESTful接口将预测结果实时提供给DCS;而在DCS端,轻量化XGBoost模型实现亚毫秒级本地推理,与来自边缘服务器的DL模型预测结果融合后生成最终控制信号,并迅速反馈给SCR脱硝系统氨喷射阀,实现精准喷氨控制。
近期有研究表明,毫秒级延迟可通过面向工业场景的系统性优化方案实现,具体措施可包括模型轻量化与优化、GPU计算加速、推理加速与容器化部署以及高效通信机制等。例如,Alqahtani等人[34]在树莓派5结合Google Coral Edge TPU的硬件上,通过优化实现了目标检测模型约10 ms的推理延迟;Lu等人[35]报道了在NVIDIA Jetson AGX Orin边缘设备上部署优化的CNN-LSTM模型,实现了<5 ms的推理延迟。另外,本文使用的深度学习模型经过充分训练,能够在复杂工况下实现高预测准确度;同时XGBoost模型擅长处理高维结构化数据,也具有良好的泛化性能。2种模型的结合可以在保持精度的同时,利用XGBoost模型快速响应突发变化,提高系统鲁棒性。这种部署方式当边缘服务器暂时不可用,DCS端的XGBoost模型仍可独立输出预测结果,保证控制系统不间断运行。而且该协同架构基于现有DCS和边缘计算节点,只需在边缘添加低成本的GPU硬件,并在DCS中加载几十兆字节的轻量模型,无需对现场系统进行大规模改造,降低了硬件投资和维护成本,更易于集成到现有控制平台中。
本研究针对燃煤机组SCR脱硝系统入口NOx质量浓度精准预测与高效工程化部署需求,基于超过11万条工业数据样本,对DL和XGBoost模型进行了深入对比分析与优化研究,取得以下结论。
1)2种模型均能达到高预测精度(δRMSE约8.0~9.0 mg/m3R2约0.970~0.980),满足SCR脱硝控制的严格要求。其中,DL模型预测误差平均比XGBoost模型降低约10%,且在捕捉负荷剧烈变化下的NOx瞬态波动方面表现更优,实时性突出。
2)基于超11万样本、75个特征的全工况数据集训练得到的模型具有优异的泛化性能与鲁棒性,未出现明显过拟合现象,特别是在机组启停和负荷骤变等复杂工况下依然保持预测的稳定性和准确性。
3)变量重要性分析明确烟气含氧量、燃烧器壁温等关键因素对NOx生成的主导作用,与机理分析高度吻合。两模型虽在主要特征识别上趋同,但在次要变量排序存在差异,这体现了模型在特征提取机制上的差异性,为燃烧过程调控与优化提供了新见解。
4)结合DL模型的高精度优势和XGBoost模型的快速推理特点,提出“边缘-嵌入式”协同部署策略,实现精度与推理快速响应的有效融合。该策略有望降低现场部署的硬件成本和技术复杂度,为智慧化电厂控制系统的优化提供新的思路。
  • 浙江省能源集团有限公司科学技术项目(ZNKJ-2025-034)
参考文献 引证文献
排序方式:
[1]
BONINGARI T, SMIRNIOTIS P G. Impact of nitrogen oxides on the environment and human health: Mn-based materials for the NOx abatement[J]. Current Opinion in Chemical Engineering, 2016, 13: 133-141.
[2]
MURRAY L T. Lightning NOx and impacts on air quality[J]. Current Pollution Reports, 2016, 2: 115-133.
[3]
WILSON R. Air pollution, the automobile, and public health[J]. Environment: Science and Policy for Sustainable Development, 1989, 31(4): 25-27.
[4]
YANG S, LI M, GUO C, et al. Associations of long-term exposure to nitrogen oxides with all-cause and cause-specific mortality[J]. Nature Communications, 2025, 16(1): 1730.
[5]
YAMASHITA R, NISHIO M, DO R K G, et al. Convolutional neural networks: an overview and application in radiology[J]. Insights Into Imaging, 2018, 9: 611-629.
[6]
MANISALIDIS I, STAVROPOULOU E, STAVROPOULOS A, et al. Environmental and health impacts of air pollution: a review[J]. Frontiers in Public Health, 2020, 8: 14.
[7]
CHEN T M, KUSCHNER W G, GOKHALE J, et al. Outdoor air pollution: nitrogen dioxide, sulfur dioxide, and carbon monoxide health effects[J]. The American Journal of the Medical Sciences, 2007, 333(4): 249-256.
[8]
HE K, DING H. Prediction of NOx emissions in thermal power plants using a dynamic soft sensor based on random forest and just-in-time learning methods[J]. Sensors, 2024, 24(14): 4442.
[9]
LV Y, LIU J, YANG T, et al. A novel least squares support vector machine ensemble model for NOx emission prediction of a coal-fired boiler[J]. Energy, 2013, 55: 319-329.
[10]
SONG M, XUE J, GAO S, et al. Prediction of NOx concentration at SCR inlet based on BMIFS-LSTM[J]. Atmosphere, 2022, 13(5): 686.
[11]
WU Z, ZHANG Y, DONG Z. NOx concentration prediction based on multi-channel fused spectral temporal graph neural network in coal-fired power plants[J]. Energy, 2024, 305: 132222.
[12]
TANG Z, WANG S, CHAI X, et al. Auto-encoder-extreme learning machine model for boiler NOx emission concentration prediction[J]. Energy, 2022, 256: 124552.
[13]
XIE P, GAO M, ZHANG H, et al. Dynamic modeling for NOx emission sequence prediction of SCR system outlet based on sequence to sequence long short-term memory network[J]. Energy, 2020, 190: 116482.
[14]
LI N, LV Y, HU Y. Prediction of NOx emissions from a coal-fired boiler based on convolutional neural networks with a channel attention mechanism[J]. Energies, 2023, 16(1): 76.
[15]
GOODFELLOW I, BENGIO Y, COURVILLE A, et al. Deep learning[M]. Cambridge: MIT Press, 2016: 1.
[16]
WEN X, LI K, WANG J. NOx emission predicting for coal-fired boilers based on ensemble learning methods and optimized base learners[J]. Energy, 2023, 264: 126171.
[17]
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.
[18]
王印松,陈瑞杰. 基于Elastic Net特征变量选择的SCR入口NOx软测量模型[J]. 中国测试202147(12):79-86.
WANG Yinsong, CHEN Ruijie. Soft sensor model of SCR inlet NOx based on Elastic Net feature variable selection[J]. China Measurement & Test, 2021, 47(12): 79-86.
[19]
于静,金秀章,刘岳. 基于结构改进RBF神经网络的NOx预测模型比较[J]. 控制工程202330(9):1616-1623.
YU Jing, JIN Xiuzhang, LIU Yue. Comparison of NOx prediction models based on structurally improved RBF neural network[J]. Control Engineering, 2023, 30(9): 1616-1623.
[20]
金秀章,于静,刘岳. 基于人工鱼群-径向基神经网络的NOx预测模型[J]. 动力工程学报202141(7):551-557.
JIN Xiuzhang, YU Jing, LIU Yue. NOx prediction model based on artificial fish swarm-RBF neural network[J]. Journal of Power Engineering, 2021, 41(7): 551-557.
[21]
FRIEDMAN J H. Greedy function approximation: a gradient boosting machine[J]. Annals of Statistics, 2001: 1189-1232.
[22]
GARREAU D, LUXBURG U. Explaining the explainer: a first theoretical analysis of LIME[C]. International Conference on Artificial Intelligence and Statistics. PMLR, 2020: 1287-1296.
[23]
RIBEIRO M T, SINGH S, GUESTRIN C. “Why should I trust you?” Explaining the predictions of any classifier[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 2016: 1135-1144.
[24]
LUNDBERG S M, ERION G, CHEN H, et al. From local explanations to global understanding with explainable AI for trees[J]. Nature Machine Intelligence, 2020, 2(1): 56-67.
[25]
CARTER A, IMTIAZ S, NATERER G F. Review of interpretable machine learning for process industries[J]. Process Safety and Environmental Protection, 2023, 170: 647-659.
[26]
LIANG Y C, MAIMURY Y, CHEN A H L, et al. Machine learning-based prediction of air quality[J]. Applied Sciences, 2020, 10(24): 9151.
[27]
MÉNDEZ M, MERAYO M G, NÚÑEZ M. Machine learning algorithms to forecast air quality: a survey[J]. Artificial Intelligence Review, 2023, 56(9): 10031-10066.
[28]
固定污染源烟气(SO2、NO、颗粒物)排放连续监测技术规范:HJ 75—2017[S]. 北京:中国环境科学出版社,2018:1.
Technical specification for continuous emissions monitoring of flue gas from stationary pollution sources (SO2, NOx, particulate matter): HJ 75—2017[S]. Beijing: China Environmental Science Press, 2018: 1.
[29]
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.
[30]
WANG Z, PENG X, CAO S, et al. NOx emission prediction using a lightweight convolutional neural network for cleaner production in a down-fired boiler[J]. Journal of Cleaner Production, 2023, 389: 136060.
[31]
PAPAGIANNAKIS R G, RAKOPOULOS D C, RAKOPOULOS C D. Evaluation of the air oxygen enrichment effects on combustion and emissions of natural gas/diesel dual-fuel engines at various loads and pilot fuel quantities[J]. Energies, 2018, 11(11): 3028.
[32]
IAVARONE S, PARENTE A. NOx formation in MILD combustion: potential and limitations of existing approaches in CFD[J]. Frontiers in Mechanical Engineering, 2020, 6: 13.
[33]
陈东东,伍林玲,苑梦兰,. 水泥窑低氮分级燃烧下脱硝工程技术的研究综述[J]. 化学工程与技术202313(4):252.
CHEN Dongdong, WU Linling, YUAN Menglan, et al. Review of denitrification engineering technology under low-nitrogen staged combustion in cement kilns[J]. Journal of Chemical Engineering and Technology, 2023, 13(4): 252.
[34]
ALQAHTANI D K, CHEEMA M A, TOOSI A N. Benchmarking deep learning models for object detection on edge computing devices[C]//Proceedings of the International Conference on Service-Oriented Computing. Singapore: Springer Nature Singapore, 2024: 142-150.
[35]
LU L, CAO Z, CHEN X, et al. Hybrid precision gradient accumulation for CNN-LSTM in sports venue buildings analytics: energy-efficient spatiotemporal modeling[J]. Buildings, 2025, 15(16): 2926.
2026年第55卷第4期
PDF下载
174
83
引用本文
BibTeX
文章信息
doi: 10.19666/j.rlfd.202507085
  • 接收时间:2025-07-31
  • 首发时间:2026-08-14
  • 出版时间:2026-04-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-07-31
  • 修回日期:2025-10-20
  • 录用日期:2025-11-04
基金
Science and Technology Project of Zhejiang Energy Group Co., Ltd.(ZNKJ-2025-034)
浙江省能源集团有限公司科学技术项目(ZNKJ-2025-034)
作者信息
    1.浙江浙能兰溪发电有限责任公司,浙江 金华 321102
    2.浙江浙能科技环保集团股份有限公司,浙江 杭州 311121

通讯作者:

韦智友(1992),男,博士,高级工程师,主要研究方向为能源环保工程,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202507085
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