Article(id=1222503115153199203, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1222503107959968541, articleNumber=null, orderNo=null, doi=10.19666/j.rlfd.202306390, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=null, receivedDateStr=null, revisedDate=1686067200000, revisedDateStr=2023-06-07, acceptedDate=null, acceptedDateStr=null, onlineDate=1769397055661, onlineDateStr=2026-01-26, pubDate=1698163200000, pubDateStr=2023-10-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1769397055661, onlineIssueDateStr=2026-01-26, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1769397055661, creator=13701087609, updateTime=1769397055661, updator=13701087609, issue=Issue{id=1222503107959968541, tenantId=1146029695717560320, journalId=1210938733613449225, year='2023', volume='52', issue='10', pageStart='1', pageEnd='198', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1769397053947, creator=13701087609, updateTime=1773966614026, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1241669232136614309, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1222503107959968541, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1241669232136614310, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1222503107959968541, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=176, endPage=186, ext={EN=ArticleExt(id=1222503115463577712, articleId=1222503115153199203, tenantId=1146029695717560320, journalId=1210938733613449225, language=EN, title=Optimization method of waste heat valve control based on fusion drive, columnId=1211002409397129992, journalTitle=Thermal Power Generation, columnName=Power generation technology forum, runingTitle=null, highlight=null, articleAbstract=

The traditional waste heat valve control technology is mainly divided into two methods, mechanism modeling and data-driven. However, in practical applications, the former is difficult to accurately describe due to the complex mechanism. The latter requires high data quality and full working condition samples, which is difficult to meet in a short time. Aiming at the above problems, a fusion-driven optimization method for waste heat valve control is proposed. Firstly, the mechanism knowledge and data knowledge are fused to construct a knowledge graph model based on fuzzy sets, and the valve opening knowledge is materialized. Secondly, the LSTM valve opening optimization model based on time protection mechanism is established, and the time protection mechanism algorithm is proposed to determine the optimal adjustment frequency of the valve. Finally, the recommended valve opening is obtained by knowledge reasoning. Through experimental analysis and verification, this method integrates qualitative knowledge such as waste heat recovery mechanism and quantitative knowledge such as equipment operation data. While improving the safety of equipment, the probability of generating high-temperature saturated steam enthalpy is increased by 94%, and the average daily increase is 8 640 kJ, which realizes the intelligent decision of waste heat recovery valve opening.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Jing LIU, Chaoran LI, Jiannan ZHANG, Jia ZHAO), CN=ArticleExt(id=1222503115698458743, articleId=1222503115153199203, tenantId=1146029695717560320, journalId=1210938733613449225, language=CN, title=基于融合驱动的余热阀门控制优化方法, columnId=1211002409581679375, journalTitle=热力发电, columnName=发电技术论坛, runingTitle=null, highlight=null, articleAbstract=

传统余热阀门控制技术主要分为机理建模和数据驱动2种方法,但在实际的应用中前者因机理复杂,难以准确描述,后者要求数据质量高、工况样本全,难以短时间满足。针对上述问题,提出一种基于融合驱动的余热阀门控制优化方法,该方法首先融合机理知识与数据知识构建基于模糊集合的知识图谱模型,将阀门开度知识实体化;其次,建立基于时间保护机制的长短时记忆(long short-term memory,LSTM)神经网络阀门开度优化模型,并提出时间保护机制算法,确定阀门最优调节频率;最后,通过知识推理得到推荐阀门开度。经实验分析验证,该方法通过融合余热回收机理等定性知识和设备运行数据等定量知识,在提升设备安全性的同时,产生的高温饱和蒸汽焓值提升概率为94%,平均每天可提升8 640 kJ,实现了余热回收阀门开度的智慧决策。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
赵佳(1989),女,博士,副教授,主要研究方向为数据挖掘和微分算子谱理论,
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=fUxa4oplPoV6UOauPw9YYw==, magXml=3bASbCwiO1jHHTVaj13Kcw==, pdfUrl=null, pdf=PEjKWU9cZ0zy3P5R0/0esg==, pdfFileSize=1753952, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=NkfUkB9GupCe2nDxTUCglQ==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=XjreOkTC1cq14yAdzpNrPw==, mapNumber=null, authorCompany=null, fund=null, authors=

刘晶(1979),女,博士,研究员,主要研究方向为工业人工智能,

, authorsList=刘晶, 李超然, 张建楠, 赵佳)}, authors=[Author(id=1241694386346578356, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=liujing@scse.hebut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241694386464018874, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, authorId=1241694386346578356, language=EN, stringName=Jing LIU, firstName=Jing, middleName=null, lastName=LIU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.School of Artificial Intelligence, Hebei University of Technology, Tianjin 300400, China
2.Hebei Data Driven Industrial Intelligent Engineering Research Center, Tianjin 300400, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241694386568876481, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, authorId=1241694386346578356, language=CN, stringName=刘晶, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.河北工业大学人工智能与数据科学学院,天津 300400
2.河北省数据驱动工业智能工程研究中心,天津 300400, bio={"content":"

刘晶(1979),女,博士,研究员,主要研究方向为工业人工智能,

"}, bioImg=null, bioContent=

刘晶(1979),女,博士,研究员,主要研究方向为工业人工智能,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241694385885204877, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, xref=1., ext=[AuthorCompanyExt(id=1241694385889399182, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694385885204877, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Artificial Intelligence, Hebei University of Technology, Tianjin 300400, China), AuthorCompanyExt(id=1241694385897787791, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694385885204877, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.河北工业大学人工智能与数据科学学院,天津 300400)]), AuthorCompany(id=1241694385981673877, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, xref=2., ext=[AuthorCompanyExt(id=1241694385990062487, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694385981673877, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Hebei Data Driven Industrial Intelligent Engineering Research Center, Tianjin 300400, China), AuthorCompanyExt(id=1241694386002645402, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694385981673877, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.河北省数据驱动工业智能工程研究中心,天津 300400)])]), Author(id=1241694386673734090, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241694386795368915, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, authorId=1241694386673734090, language=EN, stringName=Chaoran LI, firstName=Chaoran, middleName=null, lastName=LI, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Artificial Intelligence, Hebei University of Technology, Tianjin 300400, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241694386891837918, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, authorId=1241694386673734090, language=CN, stringName=李超然, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.河北工业大学人工智能与数据科学学院,天津 300400, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241694385885204877, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, xref=1., ext=[AuthorCompanyExt(id=1241694385889399182, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694385885204877, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Artificial Intelligence, Hebei University of Technology, Tianjin 300400, China), AuthorCompanyExt(id=1241694385897787791, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694385885204877, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.河北工业大学人工智能与数据科学学院,天津 300400)])]), Author(id=1241694386988306914, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, 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=1241694387160273391, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, authorId=1241694386988306914, language=EN, stringName=Jiannan ZHANG, firstName=Jiannan, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.School of Artificial Intelligence, Hebei University of Technology, Tianjin 300400, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241694387349017082, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, authorId=1241694386988306914, language=CN, stringName=张建楠, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.河北工业大学人工智能与数据科学学院,天津 300400, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241694385885204877, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, xref=1., ext=[AuthorCompanyExt(id=1241694385889399182, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694385885204877, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Artificial Intelligence, Hebei University of Technology, Tianjin 300400, China), AuthorCompanyExt(id=1241694385897787791, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694385885204877, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.河北工业大学人工智能与数据科学学院,天津 300400)])]), Author(id=1241694387445486078, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=zhaojia@hebut.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1241694387571315209, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, authorId=1241694387445486078, language=EN, stringName=Jia ZHAO, firstName=Jia, middleName=null, lastName=ZHAO, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, 4, address=3.Tianjin Development Zone Jingnuo Data Technology Co., Ltd., Tianjin 300400, China
4.School of Science, Hebei University of Technology, Tianjin 300400, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1241694387680367118, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, authorId=1241694387445486078, language=CN, stringName=赵佳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=3, 4, address=3.天津开发区精诺瀚海数据科技有限公司,天津 300400
4.河北工业大学理学院,天津 300400, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1241694386103308705, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, xref=3., ext=[AuthorCompanyExt(id=1241694386111697312, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694386103308705, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Tianjin Development Zone Jingnuo Data Technology Co., Ltd., Tianjin 300400, China), AuthorCompanyExt(id=1241694386120085921, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694386103308705, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.天津开发区精诺瀚海数据科技有限公司,天津 300400)]), AuthorCompany(id=1241694386224943530, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, xref=4., ext=[AuthorCompanyExt(id=1241694386233332138, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694386224943530, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.School of Science, Hebei University of Technology, Tianjin 300400, China), AuthorCompanyExt(id=1241694386241720747, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694386224943530, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.河北工业大学理学院,天津 300400)])])], keywords=[Keyword(id=1241694387906859542, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, orderNo=1, keyword=fusion drive), Keyword(id=1241694388049465887, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, orderNo=2, keyword=waste heat recovery), Keyword(id=1241694388171100712, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, orderNo=3, keyword=valve control), Keyword(id=1241694388292735536, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, orderNo=4, keyword=knowledge graph), Keyword(id=1241694388418564663, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, orderNo=5, keyword=LSTM neural network), Keyword(id=1241694388519227964, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, orderNo=1, keyword=融合驱动), Keyword(id=1241694388619891265, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, orderNo=2, keyword=余热回收), Keyword(id=1241694388745720393, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, orderNo=3, keyword=阀门控制), Keyword(id=1241694390255669836, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, orderNo=4, keyword=知识图谱), Keyword(id=1241694390364721745, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, orderNo=5, keyword=LSTM神经网络)], refs=[Reference(id=1241694397184660295, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2020, volume=49, issue=2, pageStart=1, pageEnd=9, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=时国华, 刘彦琛, 李晓静, journalName=热力发电, refType=null, unstructuredReference=时国华,刘彦琛,李晓静,等.天然气烟气余热高效回收技术研究进展[J].热力发电202049(2):1-9., articleTitle=天然气烟气余热高效回收技术研究进展, refAbstract=null), Reference(id=1241694397285323596, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2020, volume=49, issue=2, pageStart=1, pageEnd=9, url=null, language=null, rfNumber=[1], rfOrder=1, authorNames=SHI Guohua, LIU Yanchen, LI Xiaojing, journalName=Thermal Power Generation, refType=null, unstructuredReference=SHI Guohua, LIU Yanchen, LI Xiaojing, et al. Research advances on waste heat recovery technology of natural gas-fired flue gas[J]. Thermal Power Generation, 2020, 49(2): 1-9., articleTitle=Research advances on waste heat recovery technology of natural gas-fired flue gas, refAbstract=null), Reference(id=1241694397419541330, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2018, volume=6, issue=null, pageStart=268, pageEnd=289, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=JOUHARA H, KHORDEHGAH N, ALMAHMOUD S, journalName=Thermal Science and Engineering Progress, refType=null, unstructuredReference=JOUHARA H, KHORDEHGAH N, ALMAHMOUD S, et al. Waste heat recovery technologies and applications[J]. Thermal Science and Engineering Progress, 2018, 6: 268-289., articleTitle=Waste heat recovery technologies and applications, refAbstract=null), Reference(id=1241694397520204628, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2021, volume=9, issue=null, pageStart=111062, pageEnd=111071, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=XIAO Y, ZHANG Y, ZHOU W, journalName=IEEE Access, refType=null, unstructuredReference=XIAO Y, ZHANG Y, ZHOU W, et al. Research on algorithm fusion for the control of a roots-type waste heat power generation system[J]. IEEE Access, 2021, 9: 111062-111071., articleTitle=Research on algorithm fusion for the control of a roots-type waste heat power generation system, refAbstract=null), Reference(id=1241694397633450839, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2018, volume=6, issue=null, pageStart=268, pageEnd=289, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=JOUHARA H, KHORDEHGAH N, ALMAHMOUD S, journalName=Thermal Science and Engineering Progress, refType=null, unstructuredReference=JOUHARA H, KHORDEHGAH N, ALMAHMOUD S, et al. Waste heat recovery technologies and applications[J]. Thermal Science and Engineering Progress, 2018, 6: 268-289., articleTitle=Waste heat recovery technologies and applications, refAbstract=null), Reference(id=1241694399130817369, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2018, volume=47, issue=4, pageStart=48, pageEnd=54, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=王金平, 安连锁, 张学镭, journalName=热力发电, refType=null, unstructuredReference=王金平,安连锁,张学镭.燃煤锅炉烟气余热深度回收及脱水性能分析[J].热力发电201847(4):48-54., articleTitle=燃煤锅炉烟气余热深度回收及脱水性能分析, refAbstract=null), Reference(id=1241694399206314843, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2018, volume=47, issue=4, pageStart=48, pageEnd=54, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=WANG Jinping, AN Liansuo, ZHANG Xuelei, journalName=Thermal Power Generation, refType=null, unstructuredReference=WANG Jinping, AN Liansuo, ZHANG Xuelei. Performance analysis on heat and water recovery from flue gas of coal-fired boiler[J]. Thermal Power Generation, 2018, 47(4): 48-54., articleTitle=Performance analysis on heat and water recovery from flue gas of coal-fired boiler, refAbstract=null), Reference(id=1241694399273423708, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2017, volume=202, issue=null, pageStart=153, pageEnd=168, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=YIN Q, DU W J, CHENG L, journalName=Applied Energy, refType=null, unstructuredReference=YIN Q, DU W J, CHENG L. Optimization design of heat recovery systems on rotary kilns using genetic algorithms[J]. Applied Energy, 2017, 202: 153-168., articleTitle=Optimization design of heat recovery systems on rotary kilns using genetic algorithms, refAbstract=null), Reference(id=1241694399336338270, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2017, volume=108, issue=null, pageStart=712, pageEnd=720, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=CHEN Q, HAO J H, ZHAO T, journalName=International Journal of Heat and Mass Transfer, refType=null, unstructuredReference=CHEN Q, HAO J H, ZHAO T. An alternative energy flow model for analysis and optimization of heat transfer systems[J]. International Journal of Heat and Mass Transfer, 2017, 108: 712-720., articleTitle=An alternative energy flow model for analysis and optimization of heat transfer systems, refAbstract=null), Reference(id=1241694399403447136, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2013, volume=2, issue=7, pageStart=631, pageEnd=637, url=null, language=null, rfNumber=[8], rfOrder=9, authorNames=AHMAD R, KHAN T A, AGARWAL V, journalName=International Journal of Scientific Engineering and Technology, refType=null, unstructuredReference=AHMAD R, KHAN T A, AGARWAL V. Mass and energy balance in grate cooler of cement plant[J]. International Journal of Scientific Engineering and Technology, 2013, 2(7): 631-637., articleTitle=Mass and energy balance in grate cooler of cement plant, refAbstract=null), Reference(id=1241694399466361699, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=6, pageStart=111, pageEnd=121, url=null, language=null, rfNumber=[9], rfOrder=10, authorNames=王义函, 李镓睿, 陈衡, journalName=热力发电, refType=null, unstructuredReference=王义函,李镓睿,陈衡,等.耦合燃煤机组的水泥窑余热利用系统热力学性能分析[J].热力发电202251(6):111-121., articleTitle=耦合燃煤机组的水泥窑余热利用系统热力学性能分析, refAbstract=null), Reference(id=1241694399537664870, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=6, pageStart=111, pageEnd=121, url=null, language=null, rfNumber=[9], rfOrder=11, authorNames=WANG Yihan, LI Jiarui, CHEN Heng, journalName=Thermal Power Generation, refType=null, unstructuredReference=WANG Yihan, LI Jiarui, CHEN Heng, et al. Thermomechanical performance analysis for waste heat recovery and utilization system of cement kiln coupled with coal-fired power plant[J]. Thermal Power Generation, 2022, 51(6): 111-121., articleTitle=Thermomechanical performance analysis for waste heat recovery and utilization system of cement kiln coupled with coal-fired power plant, refAbstract=null), Reference(id=1241694399613162343, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2020, volume=262, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=12, authorNames=XU B, RATHOD D, YEBI A, journalName=Applied Energy, refType=null, unstructuredReference=XU B, RATHOD D, YEBI A, et al. Real-time realization of dynamic programming using machine learning methods for IC engine waste heat recovery system power optimization[J]. Applied Energy, 2020, 262: 114514., articleTitle=Real-time realization of dynamic programming using machine learning methods for IC engine waste heat recovery system power optimization, refAbstract=null), Reference(id=1241694399718019947, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2018, volume=164, issue=null, pageStart=15, pageEnd=26, url=null, language=null, rfNumber=[11], rfOrder=13, authorNames=YANG F, CHO H, ZHANG H, journalName=Energy conversion and management, refType=null, unstructuredReference=YANG F, CHO H, ZHANG H, et al. Artificial neural network(ANN) based prediction and optimization of an organic Rankine cycle (ORC) for diesel engine waste heat recovery[J]. Energy conversion and management, 2018, 164: 15-26., articleTitle=Artificial neural network(ANN) based prediction and optimization of an organic Rankine cycle (ORC) for diesel engine waste heat recovery, refAbstract=null), Reference(id=1241694399827071854, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2020, volume=12, issue=2, pageStart=259, pageEnd=null, url=null, language=null, rfNumber=[12], rfOrder=14, authorNames=GARUD K S, SEO J H, CHO C P, journalName=Symmetry, refType=null, unstructuredReference=GARUD K S, SEO J H, CHO C P, et al. Artificial neural network and adaptive neuro-fuzzy interface system modelling to predict thermal performances of thermoelectric generator for waste heat recovery[J]. Symmetry, 2020, 12(2): 259., articleTitle=Artificial neural network and adaptive neuro-fuzzy interface system modelling to predict thermal performances of thermoelectric generator for waste heat recovery, refAbstract=null), Reference(id=1241694399923540849, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2017, volume=34, issue=5, pageStart=295, pageEnd=299, url=null, language=null, rfNumber=[13], rfOrder=15, authorNames=李松柏, 耿志敏, 江乐新, journalName=计算机仿真, refType=null, unstructuredReference=李松柏,耿志敏,江乐新,等.空压机余热回收解耦控制算法研究[J].计算机仿真201734(5):295-299., articleTitle=空压机余热回收解耦控制算法研究, refAbstract=null), Reference(id=1241694399999038323, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2017, volume=34, issue=5, pageStart=295, pageEnd=299, url=null, language=null, rfNumber=[13], rfOrder=16, authorNames=LI Songbai, GENG Zhimin, JIANG Lexin, journalName=Computer Simulation, refType=null, unstructuredReference=LI Songbai, GENG Zhimin, JIANG Lexin, et al. Research on heat recovery of air compressor control based on BP neural network[J]. Computer Simulation, 2017, 34(5): 295-299., articleTitle=Research on heat recovery of air compressor control based on BP neural network, refAbstract=null), Reference(id=1241694400082924405, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2016, volume=33, issue=1, pageStart=64, pageEnd=68, url=null, language=null, rfNumber=[14], rfOrder=17, authorNames=张军, 曹俊雅, 曾齐斌, journalName=计算机与应用化学, refType=null, unstructuredReference=张军,曹俊雅,曾齐斌,等.基于ASPEN PLUS和MATLAB遗传算法工具箱对天然气锅炉烟气冷凝换热器的设计与优化[J].计算机与应用化学201633(1):64-68., articleTitle=基于ASPEN PLUS和MATLAB遗传算法工具箱对天然气锅炉烟气冷凝换热器的设计与优化, refAbstract=null), Reference(id=1241694400166810487, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2016, volume=33, issue=1, pageStart=64, pageEnd=68, url=null, language=null, rfNumber=[14], rfOrder=18, authorNames=ZHANG Jun, CAO Junya, ZENG Qibin, journalName=Computers and Applied Chemistry, refType=null, unstructuredReference=ZHANG Jun, CAO Junya, ZENG Qibin, et al. Design and optimization for the flue gas heat exchanger of natural gas boiler based on ASPEN PLUS and MATLAB genetic algorithm tool[J]. Computers and Applied Chemistry, 2016, 33(1): 64-68., articleTitle=Design and optimization for the flue gas heat exchanger of natural gas boiler based on ASPEN PLUS and MATLAB genetic algorithm tool, refAbstract=null), Reference(id=1241694400246502265, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2013, volume=58, issue=null, pageStart=473, pageEnd=482, url=null, language=null, rfNumber=[15], rfOrder=19, authorNames=XI H, LI M J, XU C, journalName=Energy, refType=null, unstructuredReference=XI H, LI M J, XU C, et al. Parametric optimization of regenerative organic Rankine cycle(ORC) for low grade waste heat recovery using genetic algorithm[J]. Energy, 2013, 58: 473-482., articleTitle=Parametric optimization of regenerative organic Rankine cycle(ORC) for low grade waste heat recovery using genetic algorithm, refAbstract=null), Reference(id=1241694400347165563, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2018, volume=140, issue=7, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=20, authorNames=KHADSE A, BLANCHETTE L, KAPAT J, journalName=Journal of energy resources technology, refType=null, unstructuredReference=KHADSE A, BLANCHETTE L, KAPAT J, et al. Optimization of supercritical CO2 Brayton cycle for simple cycle gas turbines exhaust heat recovery using genetic algorithm[J]. Journal of energy resources technology, 2018, 140(7): 071601., articleTitle=Optimization of supercritical CO2 Brayton cycle for simple cycle gas turbines exhaust heat recovery using genetic algorithm, refAbstract=null), Reference(id=1241694400435245949, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=1, pageStart=109, pageEnd=110, url=null, language=null, rfNumber=[17], rfOrder=21, authorNames=刘强, 付文成, 尚小科, journalName=化工管理, refType=null, unstructuredReference=刘强,付文成,尚小科.基于BP神经网络策略的中低温余热发电系统性能优化[J].化工管理2019(1):109-110., articleTitle=基于BP神经网络策略的中低温余热发电系统性能优化, refAbstract=null), Reference(id=1241694400506549119, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=1, pageStart=109, pageEnd=110, url=null, language=null, rfNumber=[17], rfOrder=22, authorNames=LIU Qiang, FU Wencheng, SHANG Xiaoke, journalName=Chemical Management, refType=null, unstructuredReference=LIU Qiang, FU Wencheng, SHANG Xiaoke. The performance optimization of medium and low temperature waste heat power generation system based on BP neural network strategy[J]. Chemical Management, 2019(1): 109-110., articleTitle=The performance optimization of medium and low temperature waste heat power generation system based on BP neural network strategy, refAbstract=null), Reference(id=1241694400582046593, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=6, pageStart=9162, pageEnd=9178, url=null, language=null, rfNumber=[18], rfOrder=23, authorNames=ALI A, KAMAL K, RATLAMWALA T A H, journalName=International Journal of Energy Research, refType=null, unstructuredReference=ALI A, KAMAL K, RATLAMWALA T A H, et al. Power prediction of waste heat recovery system for a cement plant using back propagation neural network and its thermodynamic modeling[J]. International Journal of Energy Research, 2021, 45(6): 9162-9178., articleTitle=Power prediction of waste heat recovery system for a cement plant using back propagation neural network and its thermodynamic modeling, refAbstract=null), Reference(id=1241694400657544067, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2016, volume=null, issue=null, pageStart=1, pageEnd=8, url=null, language=null, rfNumber=[19], rfOrder=24, authorNames=ALCOFORADO G N G, DE OLIVEIRA V B, DE ALMEIDA G M, journalName=null, refType=null, unstructuredReference=ALCOFORADO G N G, DE OLIVEIRA V B, DE ALMEIDA G M, et al. A model of process steam network in a steel plant with identification of parameters by a genetic algorithm[C]//2016 12th IEEE International Conference on Industry Applications (INDUSCON). IEEE, 2016: 1-8., articleTitle=A model of process steam network in a steel plant with identification of parameters by a genetic algorithm, refAbstract=null), Reference(id=1241694400762401669, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=1, pageStart=76, pageEnd=86, url=null, language=null, rfNumber=[20], rfOrder=25, authorNames=刘晶, 秦国帅, 孟德凯, journalName=燕山大学学报, refType=null, unstructuredReference=刘晶,秦国帅,孟德凯,等.数据融合驱动的余热锅炉阀门调节方法[J].燕山大学学报202145(1):76-86., articleTitle=数据融合驱动的余热锅炉阀门调节方法, refAbstract=null), Reference(id=1241694400905008007, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2021, volume=45, issue=1, pageStart=76, pageEnd=86, url=null, language=null, rfNumber=[20], rfOrder=26, authorNames=LIU Jing, QIN Guoshuai, MENG Dekai, journalName=Journal of Yanshan University, refType=null, unstructuredReference=LIU Jing, QIN Guoshuai, MENG Dekai, et al. Data fusion driven waste heat bolier valve adjustment method[J]. Journal of Yanshan University, 2021, 45(1): 76-86., articleTitle=Data fusion driven waste heat bolier valve adjustment method, refAbstract=null), Reference(id=1241694401001477001, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=null, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[21], rfOrder=27, authorNames=SINGHAL A, journalName=null, refType=null, unstructuredReference=SINGHAL A. Introducing the knowledge graph: things, not strings[EB/OL]. (2012-05-16)[2022-11-01]. https://blog.google/products/search/introducing-knowledge-graph-things-not/., articleTitle=Introducing the knowledge graph: things, not strings, refAbstract=null), Reference(id=1241694401089557386, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=1965, volume=8, issue=3, pageStart=338, pageEnd=353, url=null, language=null, rfNumber=[22], rfOrder=28, authorNames=ZEDEH L A, journalName=Information and Control, refType=null, unstructuredReference=ZEDEH L A. Fuzzy sets[J]. Information and Control, 1965, 8(3): 338-353., articleTitle=Fuzzy sets, refAbstract=null), Reference(id=1241694401165054859, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2021, volume=107, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[23], rfOrder=29, authorNames=CHAN P P K, ZHENG J, LIU H, journalName=Applied Soft Computing, refType=null, unstructuredReference=CHAN P P K, ZHENG J, LIU H, et al. Robustness analysis of classical and fuzzy decision trees under adversarial evasion attack[J]. Applied Soft Computing, 2021, 107: 107311., articleTitle=Robustness analysis of classical and fuzzy decision trees under adversarial evasion attack, refAbstract=null), Reference(id=1241694401240552332, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2013, volume=null, issue=null, pageStart=1310, pageEnd=1318, url=null, language=null, rfNumber=[24], rfOrder=30, authorNames=PASCANU R, MIKOLOV T, BENGIO Y, journalName=null, refType=null, unstructuredReference=PASCANU R, MIKOLOV T, BENGIO Y. On the difficulty of training recurrent neural networks[C]. //International conference on machine learning. Pmlr, 2013: 1310-1318., articleTitle=On the difficulty of training recurrent neural networks, refAbstract=null), Reference(id=1241694401324438413, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2022, volume=28, issue=11, pageStart=3558, pageEnd=3575, url=null, language=null, rfNumber=[25], rfOrder=31, authorNames=王万良, 胡明志, 张仁贡, journalName=计算机集成制造系统, refType=null, unstructuredReference=王万良,胡明志,张仁贡,等.改进时间卷积网络和长短时记忆网络的泸水河流域月径流量预测模型[J].计算机集成制造系统202228(11):3558-3575., articleTitle=改进时间卷积网络和长短时记忆网络的泸水河流域月径流量预测模型, refAbstract=null), Reference(id=1241694401412518798, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2022, volume=28, issue=11, pageStart=3558, pageEnd=3575, url=null, language=null, rfNumber=[25], rfOrder=32, authorNames=WANG Wanliang, HU Mingzhi, ZHANG Rengong, journalName=Computer Integrated Manufacturing Systems, refType=null, unstructuredReference=WANG Wanliang, HU Mingzhi, ZHANG Rengong, et al. Monthly runoff prediction model of Lushui river basin based on improved TCN and LSTM[J]. Computer Integrated Manufacturing Systems, 2022, 28(11): 3558-3575., articleTitle=Monthly runoff prediction model of Lushui river basin based on improved TCN and LSTM, refAbstract=null), Reference(id=1241694401504793487, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2021, volume=33, issue=1, pageStart=257, pageEnd=270, url=null, language=null, rfNumber=[26], rfOrder=33, authorNames=YAN X, WEIHAN W, CHANG M, journalName=Neural Computing and Applications, refType=null, unstructuredReference=YAN X, WEIHAN W, CHANG M. Research on financial assets transaction prediction model based on LSTM neural network[J]. Neural Computing and Applications, 2021, 33(1): 257-270., articleTitle=Research on financial assets transaction prediction model based on LSTM neural network, refAbstract=null), Reference(id=1241694401584485264, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2021, volume=38, issue=2, pageStart=291, pageEnd=298, url=null, language=null, rfNumber=[27], rfOrder=34, authorNames=王英伟, 马树才, journalName=计算机应用与软件, refType=null, unstructuredReference=王英伟,马树才.基于ARIMA和LSTM混合模型的时间序列预测[J].计算机应用与软件202138(2):291-298., articleTitle=基于ARIMA和LSTM混合模型的时间序列预测, refAbstract=null), Reference(id=1241694401689342865, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, doi=null, pmid=null, pmcid=null, year=2021, volume=38, issue=2, pageStart=291, pageEnd=298, url=null, language=null, rfNumber=[27], rfOrder=35, authorNames=WANG Yingwei, MA Shucai, journalName=Computer Applications and Software, refType=null, unstructuredReference=WANG Yingwei, MA Shucai. Time series forecasting based on ARIMA_DLSTM hybrid model[J]. Computer Applications and Software, 2021, 38(2): 291-298., articleTitle=Time series forecasting based on ARIMA_DLSTM hybrid model, refAbstract=null)], funds=[Fund(id=1241694396698121012, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, awardId=G2021202013, language=EN, fundingSource=Beijing-Tianjin-Hebei Cooperation Special Foundation for Basic Research(G2021202013), fundOrder=null, country=null), Fund(id=1241694396790395703, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, awardId=G2021202013, language=CN, fundingSource=京津冀基础研究合作专项项目(G2021202013), fundOrder=null, country=null), Fund(id=1241694396865893180, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, awardId=F2022202021, language=EN, fundingSource=Natural Science Foundation of Hebei Province(F2022202021), fundOrder=null, country=null), Fund(id=1241694396974945088, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, awardId=F2022202021, language=CN, fundingSource=河北省自然科学基金资助项目(F2022202021), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1241694385885204877, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, xref=1., ext=[AuthorCompanyExt(id=1241694385889399182, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694385885204877, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.School of Artificial Intelligence, Hebei University of Technology, Tianjin 300400, China), AuthorCompanyExt(id=1241694385897787791, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694385885204877, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.河北工业大学人工智能与数据科学学院,天津 300400)]), AuthorCompany(id=1241694385981673877, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, xref=2., ext=[AuthorCompanyExt(id=1241694385990062487, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694385981673877, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Hebei Data Driven Industrial Intelligent Engineering Research Center, Tianjin 300400, China), AuthorCompanyExt(id=1241694386002645402, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694385981673877, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.河北省数据驱动工业智能工程研究中心,天津 300400)]), AuthorCompany(id=1241694386103308705, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, xref=3., ext=[AuthorCompanyExt(id=1241694386111697312, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694386103308705, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.Tianjin Development Zone Jingnuo Data Technology Co., Ltd., Tianjin 300400, China), AuthorCompanyExt(id=1241694386120085921, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694386103308705, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=3.天津开发区精诺瀚海数据科技有限公司,天津 300400)]), AuthorCompany(id=1241694386224943530, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, xref=4., ext=[AuthorCompanyExt(id=1241694386233332138, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694386224943530, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.School of Science, Hebei University of Technology, Tianjin 300400, China), AuthorCompanyExt(id=1241694386241720747, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, companyId=1241694386224943530, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=4.河北工业大学理学院,天津 300400)])], figs=[ArticleFig(id=1241694390599602782, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Fig.1, caption=Waste heat recovery schematic, figureFileSmall=oRaBg8ab+J7Nn90rCm8uOQ==, figureFileBig=H2GPvWIu7EtZRa/30ni9Fw==, tableContent=null), ArticleFig(id=1241694390738014818, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=图1, caption=余热回收原理, figureFileSmall=oRaBg8ab+J7Nn90rCm8uOQ==, figureFileBig=H2GPvWIu7EtZRa/30ni9Fw==, tableContent=null), ArticleFig(id=1241694390935147114, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Fig.2, caption=Optimization method of waste heat valve control based on fusion drive, figureFileSmall=9vTAw6AfFk9Jp55BGMg3WA==, figureFileBig=DmvoODwQfO4G/E4GOH7SAg==, tableContent=null), ArticleFig(id=1241694391044199023, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=图2, caption=基于融合驱动的余热阀门控制优化方法, figureFileSmall=9vTAw6AfFk9Jp55BGMg3WA==, figureFileBig=DmvoODwQfO4G/E4GOH7SAg==, tableContent=null), ArticleFig(id=1241694391165833842, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Fig.3, caption=Feature and feature diagram, figureFileSmall=mk9NPGdA2RT3bT+z7tQAHw==, figureFileBig=OqRDyTuROH/MW3yMxOgW4A==, tableContent=null), ArticleFig(id=1241694391270691447, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=图3, caption=特征与特征示意, figureFileSmall=mk9NPGdA2RT3bT+z7tQAHw==, figureFileBig=OqRDyTuROH/MW3yMxOgW4A==, tableContent=null), ArticleFig(id=1241694391404909179, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Fig.4, caption=Decision Tree Relation Extraction Fused with EST Standard, figureFileSmall=Jy2u9ZxwKQTwgPmeJUALMg==, figureFileBig=F7BWmIR/n92VL68HnyoaOA==, tableContent=null), ArticleFig(id=1241694391501378174, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=图4, caption=融合EST标准的决策树关系抽取, figureFileSmall=Jy2u9ZxwKQTwgPmeJUALMg==, figureFileBig=F7BWmIR/n92VL68HnyoaOA==, tableContent=null), ArticleFig(id=1241694391610430082, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Fig.5, caption=Model of OV-LSTM, figureFileSmall=J7UMaEBaTunvbQaKcsv32A==, figureFileBig=iCkBmq/JBhRnAA/qpV8h2w==, tableContent=null), ArticleFig(id=1241694391702704777, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=图5, caption=OV-LSTM模型, figureFileSmall=J7UMaEBaTunvbQaKcsv32A==, figureFileBig=iCkBmq/JBhRnAA/qpV8h2w==, tableContent=null), ArticleFig(id=1241694391811756688, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Fig.6, caption=Schematic diagram of time protection mechanism, figureFileSmall=B/5uDbdXCnkwmb+WbVzuog==, figureFileBig=YAIFUd80q6tUExlvpmfvcQ==, tableContent=null), ArticleFig(id=1241694391950168723, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=图6, caption=时间保护机制示意, figureFileSmall=B/5uDbdXCnkwmb+WbVzuog==, figureFileBig=YAIFUd80q6tUExlvpmfvcQ==, tableContent=null), ArticleFig(id=1241694392042443415, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Fig.7, caption=Partial data of a cement plant, figureFileSmall=dMfjEu8yCKhsniBwIWxsPA==, figureFileBig=mwyfqR6Tf11zOm8JS/W2lg==, tableContent=null), ArticleFig(id=1241694392164078237, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=图7, caption=某水泥厂部分数据, figureFileSmall=dMfjEu8yCKhsniBwIWxsPA==, figureFileBig=mwyfqR6Tf11zOm8JS/W2lg==, tableContent=null), ArticleFig(id=1241694392294101664, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Fig.8, caption=Pearson correlation coefficient, figureFileSmall=KPZ+H6OvtT75eSM1WAgvNg==, figureFileBig=6gdH8gHfJvfgz3WqC2wBmw==, tableContent=null), ArticleFig(id=1241694392398959272, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=图8, caption=皮尔逊相关系数, figureFileSmall=KPZ+H6OvtT75eSM1WAgvNg==, figureFileBig=6gdH8gHfJvfgz3WqC2wBmw==, tableContent=null), ArticleFig(id=1241694392499622575, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Fig.9, caption=Goodness of variance fit, figureFileSmall=Hb0mKTvTAEYWqb0QSmorKw==, figureFileBig=hAK4PTDtnYrHSz1/RqEv7Q==, tableContent=null), ArticleFig(id=1241694392579314356, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=图9, caption=方差拟合优度, figureFileSmall=Hb0mKTvTAEYWqb0QSmorKw==, figureFileBig=hAK4PTDtnYrHSz1/RqEv7Q==, tableContent=null), ArticleFig(id=1241694392692560571, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Fig.10, caption=Contour coefficient, figureFileSmall=1v8xqGYX9cT0nM5snZI3LQ==, figureFileBig=vESfjQ/UarpnbRwWNhh0pQ==, tableContent=null), ArticleFig(id=1241694392805806784, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=图10, caption=轮廓系数, figureFileSmall=1v8xqGYX9cT0nM5snZI3LQ==, figureFileBig=vESfjQ/UarpnbRwWNhh0pQ==, tableContent=null), ArticleFig(id=1241694392914858694, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Fig.11, caption=Knowledge graph model based on fuzzy set, figureFileSmall=zsbY3TFjBnxIazzfSOjOcg==, figureFileBig=cKWWF/P4llhslOBkh58ljg==, tableContent=null), ArticleFig(id=1241694393011327691, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=图11, caption=基于模糊集合的知识图谱, figureFileSmall=zsbY3TFjBnxIazzfSOjOcg==, figureFileBig=cKWWF/P4llhslOBkh58ljg==, tableContent=null), ArticleFig(id=1241694393128768209, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Fig.12, caption=Prediction comparison line chart of OV-LSTM and LSTM, figureFileSmall=aFoN4oO4/18BboNemEZxtA==, figureFileBig=+3hyqzeD2p+E1/WIpQatiQ==, tableContent=null), ArticleFig(id=1241694393246208728, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=图12, caption=OV-LSTM与LSTM预测对比折线图, figureFileSmall=aFoN4oO4/18BboNemEZxtA==, figureFileBig=+3hyqzeD2p+E1/WIpQatiQ==, tableContent=null), ArticleFig(id=1241694394718409438, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Fig.13, caption=Changes of enthalpy before and after application of OWF, figureFileSmall=cuQz90nASrfUelgRAIw9dg==, figureFileBig=iQnd53tXJdGd64eojRYu/Q==, tableContent=null), ArticleFig(id=1241694394835849957, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=图13, caption=应用OWF前后焓值变化, figureFileSmall=cuQz90nASrfUelgRAIw9dg==, figureFileBig=iQnd53tXJdGd64eojRYu/Q==, tableContent=null), ArticleFig(id=1241694394957484779, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Fig.14, caption=Comparison of bypass valve opening at low temperature, figureFileSmall=2/J8WbXAZ7Mg2QaNgTlEXg==, figureFileBig=+dbhCfsX8KDhb7YEEwWKkw==, tableContent=null), ArticleFig(id=1241694395121062641, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=图14, caption=温度过低时旁通阀开度对比, figureFileSmall=2/J8WbXAZ7Mg2QaNgTlEXg==, figureFileBig=+dbhCfsX8KDhb7YEEwWKkw==, tableContent=null), ArticleFig(id=1241694395221725943, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Fig.15, caption=Comparison of cold air valve opening at high temperature, figureFileSmall=yjeLDCPXj39H1671VKT03A==, figureFileBig=p0czMC3eQ1InhgauW5U3XA==, tableContent=null), ArticleFig(id=1241694395322389244, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=图15, caption=温度过高时冷风阀开度对比, figureFileSmall=yjeLDCPXj39H1671VKT03A==, figureFileBig=p0czMC3eQ1InhgauW5U3XA==, tableContent=null), ArticleFig(id=1241694395431441151, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Tab.1, caption=

LSTM-CNN model parameters

, figureFileSmall=null, figureFileBig=null, tableContent=
模型组件内核尺寸卷积核(神经元)数量激活函数
卷积层13×116relu
池化层2×1
卷积层24×1256relu
LSTM层4×164tanh
BN层1×1
Dense层3softmax
), ArticleFig(id=1241694395536298759, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=表1, caption=

LSTM-CNN模型参数

, figureFileSmall=null, figureFileBig=null, tableContent=
模型组件内核尺寸卷积核(神经元)数量激活函数
卷积层13×116relu
池化层2×1
卷积层24×1256relu
LSTM层4×164tanh
BN层1×1
Dense层3softmax
), ArticleFig(id=1241694395666322186, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Tab.2, caption=

Characteristic parameter

, figureFileSmall=null, figureFileBig=null, tableContent=
编号名称
1主蒸汽温度/℃
2AQC高压蒸汽流量/kPa
3AQC旁通阀开度/%
4AQC锅炉混风烟道调节阀(冷风阀)开度/%
5AQC炉联合过热器前烟气温度/℃
6AQC炉出口烟道烟气压力/kPa
7AQC炉联合过热器前烟气压力/kPa
8调节阀门到饱和蒸汽变化的延时/s
), ArticleFig(id=1241694395842482961, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=表2, caption=

特征参数

, figureFileSmall=null, figureFileBig=null, tableContent=
编号名称
1主蒸汽温度/℃
2AQC高压蒸汽流量/kPa
3AQC旁通阀开度/%
4AQC锅炉混风烟道调节阀(冷风阀)开度/%
5AQC炉联合过热器前烟气温度/℃
6AQC炉出口烟道烟气压力/kPa
7AQC炉联合过热器前烟气压力/kPa
8调节阀门到饱和蒸汽变化的延时/s
), ArticleFig(id=1241694395972506389, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Tab.3, caption=

Comparison of decision tree accuracy

, figureFileSmall=null, figureFileBig=null, tableContent=
编号方法训练集准确率测试集准确率
1传统ID3决策树87.287.1
2融合EST标准的决策树88.988.6
), ArticleFig(id=1241694396081558300, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=表3, caption=

决策树准确率对比

, figureFileSmall=null, figureFileBig=null, tableContent=
编号方法训练集准确率测试集准确率
1传统ID3决策树87.287.1
2融合EST标准的决策树88.988.6
), ArticleFig(id=1241694396236747553, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Tab.4, caption=

Comparison of OV-LSTM and LSTM

, figureFileSmall=null, figureFileBig=null, tableContent=
编号模型δMAEδRMSE
1OV-LSTM0.1210.126
2LSTM0.1230.146
), ArticleFig(id=1241694396333216549, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=表4, caption=

OV-LSTM与LSTM对比

, figureFileSmall=null, figureFileBig=null, tableContent=
编号模型δMAEδRMSE
1OV-LSTM0.1210.126
2LSTM0.1230.146
), ArticleFig(id=1241694396438074152, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=EN, label=Tab.5, caption=

Valve regulation times before and after adding time protection mechanism

, figureFileSmall=null, figureFileBig=null, tableContent=
模型旁通阀调节次数冷风阀调节次数
加时间保护机制后8025
未加时间保护机制12587
), ArticleFig(id=1241694396526154541, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1222503115153199203, language=CN, label=表5, caption=

加时间保护机制前后阀门调节次数

, figureFileSmall=null, figureFileBig=null, tableContent=
模型旁通阀调节次数冷风阀调节次数
加时间保护机制后8025
未加时间保护机制12587
)], attaches=null, journal=Journal(id=1210938006006558725, delFlag=0, nameCn=热力发电, nameEn=Thermal Power Generation, nameHistory1=null, nameHistory2=null, issn=1002-3364, eissn=null, cn=61-1111/TM, coden=null, periodic=0, language=CN, oaType=null, ccby=null, superviseOffice=null, ownerOffice=null, pubOffice=null, editorOffice=null, officeType=null, aims=null, clcCode=null, officeProv=null, officeCity=null, officeAddr=null, officeZip=null, officeEmail=null, officePhone=null, editDirector=null, officeDirector=null, officeDirectorPhone=null, officeStaffNum=null, officeEmpNum=null, coverPicUrl=YWgAUXbKXZzTw3c+kJbAIA==, journalPrice=null, startedYear=null, abbrevIsoEn=Thermal Power Generation, journalRemark=null, publicationField=null, createdTime=1766639718774, updatedTime=1766640759031, createdBy=18614031015, updatedBy=13701087609, firstLetterCn=T, firstLetterEn=T, subjectCode=Engineering, subjectName=null, subjectCodeEn=Engineering, subjectNameEn=null, picCn=YWgAUXbKXZzTw3c+kJbAIA==, picEn=jfJjUlYAGfUZwuOMQZ6AHQ==, jcr=null, cjcr=null, exts=[JournalExt(id=1210942369256575009, language=CN, name=热力发电, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1766640759052, updatedTime=1766640759052, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=1, submissionEditorUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=3, submissionReviewUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""}), JournalExt(id=1210942369315295266, language=EN, name=Thermal Power Generation, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1766640759066, updatedTime=1766640759066, createdBy=13701087609, updatedBy=13701087609, submissionGuidelinesUrl=, submissionAuthorUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=1, submissionEditorUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=3, submissionReviewUrl=https://rlfd.chinajournal.net.cn/index.aspx?t=2, submissionCeEditorUrl=, submissionAeEditorUrl=, option={"copyright":""})], databaseList=null, tenantJournalId=1210938733613449225, websiteList=[Website(id=1210941118787744741, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1210938733613449225, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/rlfd/CN, language=CN, createTime=1766640460918, createBy=18614031015, updateTime=1766640511525, updateBy=18614031015, name=热力发电-中文, tplId=1146099689490845704, title=热力发电, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1210944690380214659, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=articleTextType, value=kx, createTime=1766641312451, updateTime=1766641312451, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690359243136, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=banner, value=null, createTime=1766641312446, updateTime=1766641312446, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690401186182, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=grayFlag, value=0, createTime=1766641312456, updateTime=1766641312456, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690346660223, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=logo, value=https://castjournals.cast.org.cn/joweb/rlfd/CN/file/pic?fileId=ToFA0Lu4b/CNocENDvNjHA==, createTime=1766641312443, updateTime=1766641312443, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690409574792, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=minRunFlag, value=0, createTime=1766641312458, updateTime=1766641312458, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690371826050, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/rlfd/CN/file/pic, createTime=1766641312449, updateTime=1766641312449, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690405380487, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=silenceFlag, value=0, createTime=1766641312457, updateTime=1766641312457, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690367631745, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1766641312448, updateTime=1766641312448, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690388603268, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=themeColor, value=null, createTime=1766641312453, updateTime=1766641312453, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944690392797573, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118787744741, code=themeStyle, value=null, createTime=1766641312454, updateTime=1766641312454, creator=18614031015, updator=18614031015)]), Website(id=1210941118926156777, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1210938733613449225, journalNameCn=null, journalNameEn=null, grayFlag=null, tenantId=1146029695717560320, platformId=null, journalGroupId=null, journalGroupNameCn=null, journalGroupNameEn=null, type=1, domain=https://castjournals.cast.org.cn/joweb/rlfd/EN, language=EN, createTime=1766640460950, createBy=18614031015, updateTime=1766640598724, updateBy=18614031015, name=热力发电-英文, tplId=1146101810881728533, title=Thermal Power Generation, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1210944709317489283, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=articleTextType, value=kx, createTime=1766641316966, updateTime=1766641316966, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709296517760, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=banner, value=null, createTime=1766641316961, updateTime=1766641316961, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709334266502, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=grayFlag, value=0, createTime=1766641316970, updateTime=1766641316970, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709288129151, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=logo, value=https://castjournals.cast.org.cn/joweb/rlfd/CN/file/pic?fileId=ToFA0Lu4b/CNocENDvNjHA==, createTime=1766641316959, updateTime=1766641316959, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709346849416, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=minRunFlag, value=0, createTime=1766641316973, updateTime=1766641316973, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709309100674, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/rlfd/EN/file/pic, createTime=1766641316964, updateTime=1766641316964, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709338460807, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=silenceFlag, value=0, createTime=1766641316971, updateTime=1766641316971, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709300712065, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_en_623/, createTime=1766641316962, updateTime=1766641316962, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709321683588, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=themeColor, value=null, createTime=1766641316967, updateTime=1766641316967, creator=18614031015, updator=18614031015), WebsiteProps(id=1210944709330072197, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1210941118926156777, code=themeStyle, value=null, createTime=1766641316969, updateTime=1766641316969, creator=18614031015, updator=18614031015)])], journalTitle=热力发电, weixinUrl=null, journalUrl=null, iacademicId=null, status=1, seqNo=null, journalTitleEn=Thermal Power Generation, journalPhotoCn=YWgAUXbKXZzTw3c+kJbAIA==, journalPhotoEn=jfJjUlYAGfUZwuOMQZ6AHQ==, journalFirstLetter=T, journalRecommend=null, journalNew=null, journalCollection=null, jcrJf=null, cjcrJf=null, jcrJfStr=null, cjcrJfStr=null, submissionFirstDecision=null, sciSubjectClassification=null, casSubjectClassification=null, citeScore=null, totalCitationFrequency=null, icpCode=null, psCode=null, advertisingLicenseCode=null, copyrightInformation=null, country=null, option=, provinceCode=null, provinceName=null, collectFlag=false), detailUrlCn=https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202306390, detailUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/10.19666/j.rlfd.202306390, pdfUrlCn=https://castjournals.cast.org.cn/joweb/rlfd/CN/PDF/10.19666/j.rlfd.202306390, pdfUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/PDF/10.19666/j.rlfd.202306390, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于融合驱动的余热阀门控制优化方法
收藏切换
PDF下载
刘晶 1, 2 , 李超然 1 , 张建楠 1 , 赵佳 3, 4
热力发电 | 发电技术论坛 2023,52(10): 176-186
收起
收藏切换
热力发电 | 发电技术论坛 2023, 52(10): 176-186
基于融合驱动的余热阀门控制优化方法
全屏
刘晶1, 2 , 李超然1, 张建楠1, 赵佳3, 4
作者信息
  • 1.河北工业大学人工智能与数据科学学院,天津 300400
  • 2.河北省数据驱动工业智能工程研究中心,天津 300400
  • 3.天津开发区精诺瀚海数据科技有限公司,天津 300400
  • 4.河北工业大学理学院,天津 300400
  • 刘晶(1979),女,博士,研究员,主要研究方向为工业人工智能,

通讯作者:

赵佳(1989),女,博士,副教授,主要研究方向为数据挖掘和微分算子谱理论,
Optimization method of waste heat valve control based on fusion drive
Jing LIU1, 2 , Chaoran LI1, Jiannan ZHANG1, Jia ZHAO3, 4
Affiliations
  • 1.School of Artificial Intelligence, Hebei University of Technology, Tianjin 300400, China
  • 2.Hebei Data Driven Industrial Intelligent Engineering Research Center, Tianjin 300400, China
  • 3.Tianjin Development Zone Jingnuo Data Technology Co., Ltd., Tianjin 300400, China
  • 4.School of Science, Hebei University of Technology, Tianjin 300400, China
出版时间: 2023-10-25 doi: 10.19666/j.rlfd.202306390
文章导航
收藏切换

传统余热阀门控制技术主要分为机理建模和数据驱动2种方法,但在实际的应用中前者因机理复杂,难以准确描述,后者要求数据质量高、工况样本全,难以短时间满足。针对上述问题,提出一种基于融合驱动的余热阀门控制优化方法,该方法首先融合机理知识与数据知识构建基于模糊集合的知识图谱模型,将阀门开度知识实体化;其次,建立基于时间保护机制的长短时记忆(long short-term memory,LSTM)神经网络阀门开度优化模型,并提出时间保护机制算法,确定阀门最优调节频率;最后,通过知识推理得到推荐阀门开度。经实验分析验证,该方法通过融合余热回收机理等定性知识和设备运行数据等定量知识,在提升设备安全性的同时,产生的高温饱和蒸汽焓值提升概率为94%,平均每天可提升8 640 kJ,实现了余热回收阀门开度的智慧决策。

融合驱动  /  余热回收  /  阀门控制  /  知识图谱  /  LSTM神经网络

The traditional waste heat valve control technology is mainly divided into two methods, mechanism modeling and data-driven. However, in practical applications, the former is difficult to accurately describe due to the complex mechanism. The latter requires high data quality and full working condition samples, which is difficult to meet in a short time. Aiming at the above problems, a fusion-driven optimization method for waste heat valve control is proposed. Firstly, the mechanism knowledge and data knowledge are fused to construct a knowledge graph model based on fuzzy sets, and the valve opening knowledge is materialized. Secondly, the LSTM valve opening optimization model based on time protection mechanism is established, and the time protection mechanism algorithm is proposed to determine the optimal adjustment frequency of the valve. Finally, the recommended valve opening is obtained by knowledge reasoning. Through experimental analysis and verification, this method integrates qualitative knowledge such as waste heat recovery mechanism and quantitative knowledge such as equipment operation data. While improving the safety of equipment, the probability of generating high-temperature saturated steam enthalpy is increased by 94%, and the average daily increase is 8 640 kJ, which realizes the intelligent decision of waste heat recovery valve opening.

fusion drive  /  waste heat recovery  /  valve control  /  knowledge graph  /  LSTM neural network
刘晶, 李超然, 张建楠, 赵佳. 基于融合驱动的余热阀门控制优化方法. 热力发电, 2023 , 52 (10) : 176 -186 . DOI: 10.19666/j.rlfd.202306390
Jing LIU, Chaoran LI, Jiannan ZHANG, Jia ZHAO. Optimization method of waste heat valve control based on fusion drive[J]. Thermal Power Generation, 2023 , 52 (10) : 176 -186 . DOI: 10.19666/j.rlfd.202306390
余热是工业生产中分布最广、潜力最大的一种能源[1-5]。现阶段我国工业产生余热的30%~60%随着废气排放到大气中,其余热回收率仅为发达国家的50%左右。传统余热回收控制技术分为机理建模方法和数据驱动方法。机理建模方法解决了阀门调节过度依赖人工的问题,但随着系统复杂度的提高,存在建模困难,知识难存储的问题;数据驱动方法可进一步挖掘参数之间的关系,提高余热回收率,但其要求工况样本全,在实际应用中收集数据时间较长。因此,如何将机理建模方法和数据驱动方法相融合成为关注的焦点问题。
针对上述问题,本文以知识图谱为载体将机理建模和数据驱动相融合,提出基于融合驱动的余热阀门控制优化方法(optimization method of waste heat valve control based on fusion drive,OWF),该方法通过提取设备机理、余热回收机理、专家经验等非结构化信息和设备运行的历史数据等结构化信息构建图谱,将阀门开度知识实体化,并通过构建基于时间保护机制的长短时记忆(long short-term memory,LSTM)神经网络阀门开度优化模型,确定阀门调节频率,减少阀门损耗。该方法在保证余热回收设备安全运行的前提下,进行阀门调节以提高余热回收率。
余热的能量与篦式冷却机(air quenching cooler,AQC)中的废气温度和流量正相关,余热回收原理如图1所示。熟料在篦冷机被冷却产生余热废气,余热废气进入AQC锅炉、悬浮预热器(suspension preheater,SP)及分解炉进行热量交换,随后多余的空气经除尘后通过烟囱排出。旁通阀位于篦冷机中,开度可调节,当旁通阀关闭时,篦冷机中的低温气体与高温气体一起送入AQC锅炉,AQC锅炉温度下降,气体流量上升;当旁通阀打开时,篦冷机中的低温气体排出,仅高温气体送入AQC锅炉,AQC锅炉温度上升,气体流量下降。同时,AQC锅炉的温度过高会造成一定的安全隐患,冷风阀的作用是给AQC锅炉降温,起到保护锅炉的目的。冷风阀开度越大,外界进入到AQC锅炉的冷空气越多,AQC锅炉温度越低,气体流量越大。可以看出,阀门调节对AQC锅炉中废气温度和流量的影响方向相反,因此,如何在设备安全运行的前提下,调节阀门控制温度与流量,提高其余热回收率是一个关键性问题。
传统余热回收控制技术中的机理建模是根据工业过程的物理、化学反应原理,依据热力学定律、物料平衡等理论建立相关模型。Yin等人[6]通过推导热回收系统的多目标优化模型,得到最优设计参数,减少了热损失。Chen等人[7]提出单个热交换器和换热器网络的能量流模型,应用该模型得到了整个系统的约束条件,优化热管理系统。Ahmad等人[8]建立基于第一原理的模型模拟气体、固体温度、壁温损失的变化,用于理解各种设计参数对水泥余热回收的影响,通过仿真实验验证了模型的有效性。王义涵等[9]采用水泥窑炉排冷却器排出空气和旋风预热器废气的热量加热燃煤机组的部分凝结水,从而节省汽轮机抽汽,增加汽轮机做功,余热系统的发电效率提升了18.25个百分点。上述方法取得了较好的效果,但随着系统复杂度的提高,不确定性因素增加,机理建模越来越困难。
随着工业互联网等技术的快速发展,设备产生并存储了海量的运行数据,基于数据驱动的系统控制优化方法成为研究热点[10-12]。基于数据驱动的系统控制优化方法主要通过深度挖掘历史数据之间的内在关系,调整优化设备参数[13-16]。常用的数据驱动方法有神经网络、遗传算法等。刘强等[17]将BP神经网络应用于低温余热系统建模中,可提升低温余热的使用效率。Ali等人[18]使用BPNN神经网络开发了一种基于回归的预测模型预测余热回收系统产生的发电功率,得出数据科学可以作为热力学建模的替代方案,以避免大量的计算。Alcoforado等人[19]提出一种基于遗传算法的工艺蒸汽分配网络的数学模型,最大限度地提高钢铁厂的能源利用率。刘晶等[20]提出一种数据融合驱动的余热锅炉阀门调节方法,该方法基于AQC余热锅炉阀门调节历史数据建模,以达到余热再利用的最大化。上述方法都取得了较好的效果,但是基于数据驱动的方法要求数据覆盖工况全面,在实际的应用中有效数据积累时间长,数据质量难以满足建模需求。
本文结合知识图谱技术[21],结构化阀门开度分类结果,实现锅炉参数特征、分类关系等信息的知识图存储,建立基于模糊集合的知识图谱模型和融合卷积神经网络的LSTM预测算法,使余热回收率得到明显提升。
本文提出了一种基于融合驱动的余热阀门控制优化方法,方法框架如图2所示。该方法整体结构分为基于模糊集合的知识图谱模型(knowledge graph model based on fuzzy sets,KM-FS)和基于时间保护机制的LSTM阀门开度优化模型(optimization model of LSTM valve opening based on time protection mechanism,OV-LSTM)2部分。首先,针对余热回收机理知识与设备运行数据难融合的问题,构建KM-FS模型,该模型分别从机理知识抽取规则,从历史数据提取属性,规则与属性共同形成初始实体;其次,为了加快图谱检索速度,提出基于模糊集合的专家经验算法(expert experience algorithm based on fuzzy sets,EAF),将部分实体聚合形成集合实体,以减少实体数量;然后,提出基于热学机理知识的评判标准(evaluation standard based on thermal mechanism,EST),依托该标准从历史数据中筛选出优质数据,挖掘实体之间的关系,从而建立基于模糊集合的知识图谱模型;最后,针对频繁调节造成锅炉阀门易损耗的问题,构建OV-LSTM模型,该模型提出时间保护机制算法,用于判断阀门调节的最优频率,进一步提出融合卷积神经网络的LSTM预测算法(LSTM prediction algorithm based on convolutional neural network,LSTM-CNN)预测余热锅炉参数的变化趋势,减少调节阀门到温度变化的延时,及时调节阀门,降低设备风险。
针对传统余热回收技术机理知识与设备运行数据难融合的问题,提出一种基于模糊集合[22]的知识图谱模型,通过数据驱动解决建模难的问题,并利用机理建模弥补工况样本不全的限制,为阀门调节提供辅助决策。该模型包括基于EAF算法的实体抽取和融合EST标准的决策树关系抽取2部分。
基于EAF算法的实体抽取需要基于余热回收原理和相关性分析,得到影响阀门开度的特征,从历史数据中依次提取这些特征的属性,根据特征和特征属性形成初始实体,并将初始实体存入高性能的NOSQL图形数据库neo4j中,然而AQC锅炉数据复杂多变,实体数量庞大,图谱检索效率低,因此本文提出EAF算法,运用集合的思想分析专家经验,将实体划分为普通实体和集合实体。由于专家经验中存在大量的不确定性表达,所以引入模糊集合的概念,将专家经验模糊集合化,特征与特征示意如图3所示。
模糊集合是用来表达模糊性概念的集合,把待考察的模糊对象和介绍其的模糊概念组合成为模糊集合,建立适当的隶属函数,通过模糊集合的关系运算和变换,对模糊对象进行分析。比如,根据专家经验中存在较多的词汇确定状态集V={“高”,“较高”,“较低”,“低”},根据特征取值,通过隶属度函数确定状态集对应的最优值集合。隶属度函数不仅应该体现出该实体与最优状态值的距离,又应该体现出在历史数据中,该实体属于该模糊集的概率。
为介绍隶属度函数,引入概率函数pi(x),x为特征的实测值,pi(x)为历史数据中该实体属于第i个状态的概率,历史数据中特征值取值为x的总次数为nx,当前数据阀门操作与第i个状态经验描述相同情况为ni,则计算公式为:
pi(x)=ninx
判断实体属于状态为“高”的模糊集合的隶属度函数为:
A1(x)={1,xchigh(e(xahigh)2+p1(x))/2,bhighxchigh0,xbhigh
式中:ahigh为状态值“高”对应的最优值;bhigh为状态为“高”可以接受的特征最低值;chigh为状态为“高”可以接受的特征最高值,其中bhigh<ahigh=chigh
判断实体属于状态为“较高”的集合的隶属度函数为式(3):
A2(x)={0,xcrelHigh(e(xarelHigh)2+p2(x))/2,    brelHighxcrelHigh0,xbrelHigh
式中:arelHigh为状态值“较高”对应的最优值;brelHigh为状态为“较高”可以接受的特征最低值;crelHigh为状态为“较高”可以接受的特征最高值,其中brelHigh<arelHigh<crelHigh<。
判断实体属于状态为“较低”的集合的隶属度函数为:
A3(x)={0,xcrelLow(e(xarelLow)2+p3(x))/2,brelLowxcrelLow0,xbrelLow
式中:areLow为状态值“较低”对应的最优值;breLow为状态为“较低”可以接受的特征最低值;creLow为状态为“较低”可以接受的特征最高值,其中breLow<areLow<creLow
判断实体属于状态为“低”的集合的隶属度函数为(5):
A4(x)={0,xclow(e(xalow)2+p4(x))/2,blowxclow1,xblow
式中:alow为状态值“低”对应的最优值;blow为状态为“低”可以接受的特征最低值;clow为状态为“低”可以接受的特征最高值,其中blow=alow<clow
计算实体属于各个模糊集合的隶属度,根据隶属度值判断实体所处的状态。接下来,根据实体之间的相似度整合实体。设式(6)、式(7)为2个维度均为n的实体,计算AiAj的欧氏距离为式(8):
Ai=(ai1,ai2,ai3,...,aik,...,ain)
Aj=(aj1,aj2,aj3,...,ajk,...,ajn)
d(Ai,Aj)=k=1n(aikajk)2
AiAj之间的相似公式SAiAj如式(8)所示,SAiAj越大,二者的相似度越高。
SAiAj=11+d(Ai,Aj)
式中:aikajk分别为AiAj的第k个特征值,1≤kn
综上,聚合实体的EAF算法具体步骤如下:
步骤1:读取当前neo4j图数据库中的所有初始实体;
步骤2:根据专家经验对实体特征进行模糊判断,根据隶属度函数确定所属状态;
步骤3:设定实体相似度阈值为α,实体集为U={A1, A2, A3, …, Ak, …, AN},N为节点总数,AkU的第k个实体,1≤kN
步骤4:计算实体之间的相似度SAiAj(i<j,1≤i<N),1<jN);
步骤5:若所有实体间的相似度均小于α,则停止;否则,转步骤6;
步骤6:相似度小于α的2个实体合并成为一个集合实体,集合实体的特征向量为2个旧实体向量的平均值。将旧实体从U中剔除,添加新集合实体到U中,转步骤4。
传统的阀门开度由人工决定,存在经验及操作水平的差异,为得到高质量、高可靠性的数据,需要对数据进行筛选。目前对余热质量好坏的评价标准一般是焓利用和能量利用系数等指标,但这些指标仅从能量的数量考察,并不包含能量的品质属性,因此本文提出EST标准,在原评价指标的基础上添加㶲值作为余热品质好坏的指标,并根据博弈论思想将二者进行组合,得到“质”与“量”均优的数据。依托该标准建立决策树从历史数据中抽取关系,具体过程如图4所示。
本文将高温饱和蒸汽的焓作为参与热量交换的余热热量高低的评价指标。焓的计算公式为式(10):
h=u+pv
式中:h为工质的焓;u为物质的内能;p为压强;v为体积。
余热评价不仅需要关注余热能量的数值,还需要关注能量的品质。根据热力学第二定律规定,能量在利用和传递过程中,只能沿着不可逆的方向“熵增”,余热回收应该减慢“熵增”的进度。本文将㶲作为余热品质的评价标准,其计算公式为:
e=cp(TT0)(1T0TT0ln(TT0))
式中:e为工质的㶲;T为工质温度;T0为环境温度;cp为工质的比热容。
综上,余热的量由焓表示,质由㶲表示,EST标准挑选出相似工况下质与量均优的阀门开度。设“质量”由㶲表示,计算公式为:
Q=λ1H+λ2E
式中:λ1λ2为线性组合系数;H为相似工况下数据的焓;E为相似工况下数据的㶲。
根据博弈论思想,建立目标函数,以指标组合权重QHE离差之和最小为目标,寻求最优的线性组合系数λ1*λ2*,此时的指标组合权重即为最优组合权重Q*。目标函数和约束条件为:
minQH2+QE2
s.t.   λ1+λ2=1λ1λ20
根据微分原理,式(13)取得最小值的一阶导数条件为:
{λ1HTH+λ2HTE=HTHλ1HTE+λ2ETE=ETE
由于HE已知,根据式(15)可以求得λ1λ2的值。将λ1λ2进行归一化处理为:
{λ1*=λ1λ1+λ2λ2*=λ2λ1+λ2
进而得到评估指标的最优组合权重为式(17):
Q*=λ1*H+λ2*E
根据“质量”的优劣筛选数据并将优质数据保存备用作为知识图谱关系抽取的依据。关系抽取主要用到决策树ID3算法[23],该算法以信息熵为分类的依据,选择信息增益最大的属性作为分裂点,而信息增益的值与属性的属性值数量有关。由于工厂实时数据均为连续值,且不同属性间属性值的数量差距较大,因此先将各维数据进行k均值聚类,使各个属性的原始属性值数量接近以减少信息增益与属性值数量的相关性。k均值聚类的主要难点在于k值,即聚类的个数。由于方差拟合优度(goodness of variance fit,GVF)更容易发现断点,因此本文k值参照GVF选取。随着k值增大,GVF曲线由陡峭变得越来越平缓,GVF曲线由陡峭变平缓的转折点为聚类中心数量的最优值,然而转折点受人为因素影响比较大,客观性不强,因此转折点的选择参考轮廓系数确定。
针对频繁调节阀门造成的阀门易损耗问题,提出基于时间保护机制的LSTM阀门开度优化模型,模型构建过程如图5所示。传统方法受限于参数波动频率,短时间内需要多次调节阀门,该模型提出时间保护机制确定阀门调节频率,减少阀门调节次数,更进一步提出融合卷积神经网络的LSTM预测模型预测参数变化趋势,抵抗阀门调节到参数变化的延时。
由于现场参数更新频繁,若参数更新立刻执行知识查询并调节阀门,会加剧阀门损耗;反之,若数据急剧变化但未及时调整阀门则会对设备造成不可逆的损伤。针对上述问题,本文提出时间保护机制。根据现场需求以及温度变化确定时间保护窗口时间,在时间保护窗口内若温度度数和变化速度均未超过规定阈值,则继续监测;否则跳出时间保护期,通过融合卷积神经网络的LSTM预测模型预测参数变化,匹配基于模糊集合的知识图谱模型得到阀门开度,时间保护期重新计时。时间保护机制流程图如图6所示。
由于阀门变化对锅炉参数的影响存在延时,若延时为t,则此时的阀门开度影响t时刻后的锅炉参数,为了更有效的调节阀门,需要预测未来t时刻的锅炉参数,得到相应的阀门开度。与其他神经网络相比,LSTM是一种带有长短时记忆单元的时间序列模型,能够很好的解决常规RNN中存在的梯度消失和梯度爆炸问题[24-25],而且拥有多个记忆单元,使得该网络可以更好的处理多个不同时间尺度的信息,因此选择LSTM作为本文时间序列预测方法更加有优势。理论上其步长越长,挖掘出的信息量越多,然而在步长超出一定长度时,仍旧会出现远距离记忆丢失及梯度消失的问题[26-27],因此加入CNN网络,能更有效的剔除子序列中的干扰信息,将有用的信息传递给LSTM模型以作为输入进行处理。之后,可以重新调整输入数据的格式以适应所需的结构,为了解决过拟合以及迭代速度慢问题分别使用Dropout和BN层进行优化,具体模型参数见表1
本实验主要分为数据集描述、KM-FS构建、OV-LSTM模型构建和对比实验4部分。数据集描述主要说明本文实验数据来源;KM-FS首先根据机理知识划分实体,再根据专家经验将部分实体聚合形成集合实体,然后应用融合EST标准的决策树根据历史数据进行关系抽取,最后采用Neo4j图数据库存储;OV-LSTM使用TensorFlow-CPU和keras包对模型进行训练;对比实验通过进行仿真实验验证OWF方法的有效性。
实验采用某水泥厂余热回收系统采集的真实数据,采集时间为2020年8月3日至2020年8月27日,采集时间间隔为5 ms,共计397 766个样本。数据分为篦冷机数据、AQC锅炉数据和发电机数据3个部分。篦冷机数据包括旁通阀开度;AQC锅炉数据主要包括AQC锅炉混风烟道调节阀(冷风阀)、AQC炉联合过热器前烟气温度(AQC温度)、AQC炉出口烟道烟气压力和AQC联合过热器前烟气压力(AQC压差);发电机数据包括发电机功率、主蒸汽温度、AQC高压蒸汽流量。选取部分数据如图7所示。
KM-FS构建包括基于EAF算法的实体抽取和融合EST标准的决策树关系抽取2部分。
根据余热回收原理选取与阀门调节有关的相关特征,如温度、压差等,选取结果见表2
其中调节阀门到饱和蒸汽变化的延时不能从数据库中直接取到,通过皮尔逊相关系数计算二者的延时,相关系数曲线如图8所示。当延时为125~150 s时,相关系数最高且趋于平缓,因此认为二者的延时为150 s。根据特征与特征属性建立初始实体,初始实体共有397 766个。
为减少实体数量,根据EAF算法对实体特征进行模糊判断。与AQC联合过热器前烟气温度有关的4个专家经验为:AQC联合过热器前烟气温度较高且变化趋于平稳或者温度下降时,阀门保持不变;AQC联合过热器前烟气温度高时,需要打开冷风阀;AQC联合过热器前烟气温度较低且呈上升趋势时,阀门保持不变;AQC联合过热器前烟气温度低且趋于平稳时,打开旁通阀。
根据专家经验和隶属度函数,将与上述经验有关的实体加上特征“温度状态值”,该特征取值为{“高”,“较高”,“较低”,“低”},根据实体之间的相似度进行进一步整合,实体数量减少20 420个,下降了5.1%,提高了检索效率。
根据方差拟合优度与轮廓系数确定k值的取值,具体如图9所示。由图9可知,AQC联合过热器前烟气温度和主蒸汽温度曲线在12、13、14、15趋于平缓,AQC压差曲线在14、15、16、17趋于平缓。接下来分别计算这几个点的轮廓系数,结果如图10所示。由此可以确定联合过热器前烟气温度分为13类,主蒸汽温度分为15类,AQC压差分为16类。
用于关系抽取的样本为经EST标准筛选的工厂数据。样本数量为164 185个,样本中包含4个条件属性和2个决策属性。决策属性是离散的,而条件属性的AQC温度、AQC压差和主蒸汽温度为连续的。通过k-means算法对条件属性的连续值聚合为离散值。
为验证方法的有效性,将融合EST标准的决策树与传统ID3决策树进行比较,结果见表3。实验证明,融合EST标准的决策树算法的训练集与测试集的准确性均高于传统算法。
根据实体与关系构建图谱如图11所示。
蓝色节点为阀门开度,橙色节点为设备状态。建立图谱后,可以对图谱进行检索,信息检索主要以实时数据的特征属性作为依据,如AQC联合过热器前温度、AQC联合过热器前压差等,然后利用Neo4j的Cypher语言进行检索,得到当前条件下相应的阀门调节开度。
为验证OV-LSTM时间序列预测的有效性,设计实验对比该模型与传统LSTM模型的预测结果,结果如图12所示。由图12可以看出,OV-LSTM的预测值明显比LSTM的预测值更接近于真实值,而且OV-LSTM的预测值随真实值的波动效果由于传统LSTM技术,由此证明OV-LSTM的有效性。
本文使用平均绝对误差(mean absolute error,MAE)和均方根误差(root mean square error,RMSE)来检验OV-LSTM预测的准确性,分别计算OV-LSTM和LSTM的δMAEδRMSE值,结果见表4。由表4可以看出,OV-LSTM的δMAEδRMSE值均低于LSTM,可进一步确定OV-LSTM时间序列预测的有效性。
为验证OWF在实际应用中提高余热回收率的有效性,计算应用OWF方法前后余热回收情况,此处用高温饱和蒸汽的焓值表示,对比结果如图13所示。由图13可以看出,应用OWF后,除8月14日外,应用OWF后焓值均高于应用OWF前,该方法可提升焓值的概率为94%,平均每5 s提升4 kJ左右,每天提升8 460 kJ,证明了OWF可明显提高余热回收率。
为验证OWF保护设备的有效性,作对比实验比较该方法推荐的阀门开度与人工调节阀门开度的区别,结果如图14图15所示。
图14可以看出,温度低于安全阈值时,除8月4日外,该方法打开阀门升温的概率高于人工调节,OWF方法减少设备低温的概率平均提高52.12个百分点。由图15可以看出,温度高于安全阈值时,除8月5日外,该方法打开阀门降温的概率均大于等于人工调节,OWF方法减少设备高温的概率平均提高43.88个百分点。该实验验证了OWF保护设备的有效性。
接下来验证时间保护机制在实际应用中减少阀门损耗的有效性,对8月数据进行仿真实验,实验结果见表5。添加时间保护机制后阀门调节次数明显下降。添加时间保护机制后,对输入的数据进行分析预测,判断阀门是否需要调节,减少了阀门不必要的调节次数。
针对传统的余热阀门控制技术存在机理知识与数据知识难融合等问题,本文提出一种基于融合驱动的余热阀门控制优化方法。该方法一方面借助知识图谱技术和模糊集合概念将阀门开度知识实体化,另一方面提出时间保护机制算法并通过融合卷积神经网络的LSTM预测模型预测参数的变化趋势,及时调节阀门,降低设备风险。实验结果表明该方法有效融合机理知识与数据知识,能达到管理决策和生产制造的高效化和绿色化。
  • 京津冀基础研究合作专项项目(G2021202013)
  • 河北省自然科学基金资助项目(F2022202021)
参考文献 引证文献
排序方式:
[1]
时国华,刘彦琛,李晓静,等.天然气烟气余热高效回收技术研究进展[J].热力发电202049(2):1-9.
SHI Guohua, LIU Yanchen, LI Xiaojing, et al. Research advances on waste heat recovery technology of natural gas-fired flue gas[J]. Thermal Power Generation, 2020, 49(2): 1-9.
[2]
JOUHARA H, KHORDEHGAH N, ALMAHMOUD S, et al. Waste heat recovery technologies and applications[J]. Thermal Science and Engineering Progress, 2018, 6: 268-289.
[3]
XIAO Y, ZHANG Y, ZHOU W, et al. Research on algorithm fusion for the control of a roots-type waste heat power generation system[J]. IEEE Access, 2021, 9: 111062-111071.
[4]
JOUHARA H, KHORDEHGAH N, ALMAHMOUD S, et al. Waste heat recovery technologies and applications[J]. Thermal Science and Engineering Progress, 2018, 6: 268-289.
[5]
王金平,安连锁,张学镭.燃煤锅炉烟气余热深度回收及脱水性能分析[J].热力发电201847(4):48-54.
WANG Jinping, AN Liansuo, ZHANG Xuelei. Performance analysis on heat and water recovery from flue gas of coal-fired boiler[J]. Thermal Power Generation, 2018, 47(4): 48-54.
[6]
YIN Q, DU W J, CHENG L. Optimization design of heat recovery systems on rotary kilns using genetic algorithms[J]. Applied Energy, 2017, 202: 153-168.
[7]
CHEN Q, HAO J H, ZHAO T. An alternative energy flow model for analysis and optimization of heat transfer systems[J]. International Journal of Heat and Mass Transfer, 2017, 108: 712-720.
[8]
AHMAD R, KHAN T A, AGARWAL V. Mass and energy balance in grate cooler of cement plant[J]. International Journal of Scientific Engineering and Technology, 2013, 2(7): 631-637.
[9]
王义函,李镓睿,陈衡,等.耦合燃煤机组的水泥窑余热利用系统热力学性能分析[J].热力发电202251(6):111-121.
WANG Yihan, LI Jiarui, CHEN Heng, et al. Thermomechanical performance analysis for waste heat recovery and utilization system of cement kiln coupled with coal-fired power plant[J]. Thermal Power Generation, 2022, 51(6): 111-121.
[10]
XU B, RATHOD D, YEBI A, et al. Real-time realization of dynamic programming using machine learning methods for IC engine waste heat recovery system power optimization[J]. Applied Energy, 2020, 262: 114514.
[11]
YANG F, CHO H, ZHANG H, et al. Artificial neural network(ANN) based prediction and optimization of an organic Rankine cycle (ORC) for diesel engine waste heat recovery[J]. Energy conversion and management, 2018, 164: 15-26.
[12]
GARUD K S, SEO J H, CHO C P, et al. Artificial neural network and adaptive neuro-fuzzy interface system modelling to predict thermal performances of thermoelectric generator for waste heat recovery[J]. Symmetry, 2020, 12(2): 259.
[13]
李松柏,耿志敏,江乐新,等.空压机余热回收解耦控制算法研究[J].计算机仿真201734(5):295-299.
LI Songbai, GENG Zhimin, JIANG Lexin, et al. Research on heat recovery of air compressor control based on BP neural network[J]. Computer Simulation, 2017, 34(5): 295-299.
[14]
张军,曹俊雅,曾齐斌,等.基于ASPEN PLUS和MATLAB遗传算法工具箱对天然气锅炉烟气冷凝换热器的设计与优化[J].计算机与应用化学201633(1):64-68.
ZHANG Jun, CAO Junya, ZENG Qibin, et al. Design and optimization for the flue gas heat exchanger of natural gas boiler based on ASPEN PLUS and MATLAB genetic algorithm tool[J]. Computers and Applied Chemistry, 2016, 33(1): 64-68.
[15]
XI H, LI M J, XU C, et al. Parametric optimization of regenerative organic Rankine cycle(ORC) for low grade waste heat recovery using genetic algorithm[J]. Energy, 2013, 58: 473-482.
[16]
KHADSE A, BLANCHETTE L, KAPAT J, et al. Optimization of supercritical CO2 Brayton cycle for simple cycle gas turbines exhaust heat recovery using genetic algorithm[J]. Journal of energy resources technology, 2018, 140(7): 071601.
[17]
刘强,付文成,尚小科.基于BP神经网络策略的中低温余热发电系统性能优化[J].化工管理2019(1):109-110.
LIU Qiang, FU Wencheng, SHANG Xiaoke. The performance optimization of medium and low temperature waste heat power generation system based on BP neural network strategy[J]. Chemical Management, 2019(1): 109-110.
[18]
ALI A, KAMAL K, RATLAMWALA T A H, et al. Power prediction of waste heat recovery system for a cement plant using back propagation neural network and its thermodynamic modeling[J]. International Journal of Energy Research, 2021, 45(6): 9162-9178.
[19]
ALCOFORADO G N G, DE OLIVEIRA V B, DE ALMEIDA G M, et al. A model of process steam network in a steel plant with identification of parameters by a genetic algorithm[C]//2016 12th IEEE International Conference on Industry Applications (INDUSCON). IEEE, 2016: 1-8.
[20]
刘晶,秦国帅,孟德凯,等.数据融合驱动的余热锅炉阀门调节方法[J].燕山大学学报202145(1):76-86.
LIU Jing, QIN Guoshuai, MENG Dekai, et al. Data fusion driven waste heat bolier valve adjustment method[J]. Journal of Yanshan University, 2021, 45(1): 76-86.
[21]
SINGHAL A. Introducing the knowledge graph: things, not strings[EB/OL]. (2012-05-16)[2022-11-01]. https://blog.google/products/search/introducing-knowledge-graph-things-not/.
[22]
ZEDEH L A. Fuzzy sets[J]. Information and Control, 1965, 8(3): 338-353.
[23]
CHAN P P K, ZHENG J, LIU H, et al. Robustness analysis of classical and fuzzy decision trees under adversarial evasion attack[J]. Applied Soft Computing, 2021, 107: 107311.
[24]
PASCANU R, MIKOLOV T, BENGIO Y. On the difficulty of training recurrent neural networks[C]. //International conference on machine learning. Pmlr, 2013: 1310-1318.
[25]
王万良,胡明志,张仁贡,等.改进时间卷积网络和长短时记忆网络的泸水河流域月径流量预测模型[J].计算机集成制造系统202228(11):3558-3575.
WANG Wanliang, HU Mingzhi, ZHANG Rengong, et al. Monthly runoff prediction model of Lushui river basin based on improved TCN and LSTM[J]. Computer Integrated Manufacturing Systems, 2022, 28(11): 3558-3575.
[26]
YAN X, WEIHAN W, CHANG M. Research on financial assets transaction prediction model based on LSTM neural network[J]. Neural Computing and Applications, 2021, 33(1): 257-270.
[27]
王英伟,马树才.基于ARIMA和LSTM混合模型的时间序列预测[J].计算机应用与软件202138(2):291-298.
WANG Yingwei, MA Shucai. Time series forecasting based on ARIMA_DLSTM hybrid model[J]. Computer Applications and Software, 2021, 38(2): 291-298.
2023年第52卷第10期
PDF下载
96
37
引用本文
BibTeX
文章信息
doi: 10.19666/j.rlfd.202306390
  • 首发时间:2026-01-26
  • 出版时间:2023-10-25
补充材料
相关文章
文章信息
作者
出版历史
  • 修回日期:2023-06-07
基金
Beijing-Tianjin-Hebei Cooperation Special Foundation for Basic Research(G2021202013)
京津冀基础研究合作专项项目(G2021202013)
Natural Science Foundation of Hebei Province(F2022202021)
河北省自然科学基金资助项目(F2022202021)
作者信息
    1.河北工业大学人工智能与数据科学学院,天津 300400
    2.河北省数据驱动工业智能工程研究中心,天津 300400
    3.天津开发区精诺瀚海数据科技有限公司,天津 300400
    4.河北工业大学理学院,天津 300400

通讯作者:

赵佳(1989),女,博士,副教授,主要研究方向为数据挖掘和微分算子谱理论,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202306390
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