Article(id=1295068311901983263, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1295068070071005445, articleNumber=null, orderNo=null, doi=10.19666/j.rlfd.202510020, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1760371200000, receivedDateStr=2025-10-14, revisedDate=1762185600000, revisedDateStr=2025-11-04, acceptedDate=1763395200000, acceptedDateStr=2025-11-18, onlineDate=1786697946763, onlineDateStr=2026-08-14, pubDate=1779638400000, pubDateStr=2026-05-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1786697946763, onlineIssueDateStr=2026-08-14, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1786697946763, creator=13701087609, updateTime=1786697946763, updator=13701087609, issue=Issue{id=1295068070071005445, tenantId=1146029695717560320, journalId=1210938733613449225, year='2026', volume='55', issue='5', pageStart='1', pageEnd='186', issueExtLink='null', onlineDate='null', pubDate='1779638400000', pubDateStr='2026-05-25', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1786697889106, creator='13701087609', updateTime=1786698835709, updator='13701087609', preIssue=null, nextIssue=null, articleTotal=null, ext={EN=IssueExt(id=1295072040462078420, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1295068070071005445, language=EN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1295072040462078421, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1295068070071005445, language=CN, specialIssueTitle=, coverIllustrator=null, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null, downloadFileDto=null}, startPage=90, endPage=98, ext={EN=ArticleExt(id=1295068312107504160, articleId=1295068311901983263, tenantId=1146029695717560320, journalId=1210938733613449225, language=EN, title=Main steam temperature prediction and control system for coal-fired units based on hyperparameter transfer modeling, columnId=1295068110525067814, journalTitle=Thermal Power Generation, columnName=Low-carbon thermal power and nuclear power generation technology, runingTitle=null, highlight=null, articleAbstract=

Main steam temperature is a key parameter for the boiler of coal-fired power plants. It is difficult to remain stable under extreme load changes such as deep peak-shaving. To solve this problem, a predictive control model is added to the existing temperature loop. The proposed control system targets an ultra-supercritical boiler. A hybrid long short-term memory (LSTM) network forms the core predictor of the predictive model. A hyper parameter transfer method speeds up global optimization, avoids local optima and cuts optimization calculation amount by 88%. The predictive model gives a root-mean-square error of 0.495 ℃ and a mean absolute percentage error of 0.082%. MATLAB simulations show that the predictive control system reduces peak overshoot by 50% under extreme conditions, while preserving the control-loop stability during normal operation through multi-condition piecewise control. These results demonstrate that the proposed model predictive control system satisfies the main steam temperature regulation requirements across all operating conditions.

, authors=Bijun ZHENG1, 2, Shanhui ZHU2, Bin ZHANG2, Jianguo YANG1, authorsList=Bijun ZHENG, Shanhui ZHU, Bin ZHANG, Jianguo YANG, authorCompany=null, correspAuthors=Jianguo YANG, 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=1295068316222116413, articleId=1295068311901983263, tenantId=1146029695717560320, journalId=1210938733613449225, language=CN, title=基于超参数迁移建模的燃煤机组主蒸汽温度预测控制系统, columnId=1295068110713811496, journalTitle=热力发电, columnName=低碳火电及核电技术, runingTitle=null, highlight=null, articleAbstract=

燃煤电厂的锅炉主蒸汽温度作为一个重要参数,在面临极端工况如深度调峰时,往往难以保持稳定。为了解决这一问题,在原有主蒸汽温度控制系统中引入预测控制模型,来完成控制优化。以某超超临界锅炉为对象构建其主蒸汽温度预测控制系统,以复合长短时记忆(LSTM)神经网络为核心算法构建预测模型,通过超参数迁移方法快速实现全局寻优,在解决神经网络模型易陷入局部最优问题的同时,减少寻优计算量88%。预测模型的均方根误差为0.495 ℃,平均百分比误差0.082%。经MATLAB仿真实验验证,该预测控制系统在面对极端工况时,将主蒸汽温度超调量降低50%,并通过多工况分段控制保持正常工况的控制稳定性,可满足不同工况下的主蒸汽温度调节需求。

, authors=郑必君1, 2, 朱善会2, 张斌2, 杨建国1, authorsList=郑必君, 朱善会, 张斌, 杨建国, authorCompany=null, correspAuthors=杨建国, authorNote=

郑必君(1989),男,硕士,工程师,主要研究方向为智慧能源,

, correspAuthorsNote=
杨建国(1973),男,博士,副研究员,主要研究方向为清洁能源、智慧能源,
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=MyZ0mXh7eZ9bgNi6p7qnkA==, magXml=dZcAPW7s0ORrX3VHQVRRCw==, pdfUrl=null, pdf=GrBTYcce0t4Jd9vNTGaSHg==, pdfFileSize=1317242, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=kJWmUPTUM/BwovMLBhsSdw==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=zzTaCjZumb/4KDfKVgGMXA==, mapNumber=null, fund=null)}, authors=[Author(id=1295068317086143046, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=704824790@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1295068317371355721, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068317086143046, language=EN, stringName=Bijun ZHENG, firstName=Bijun, middleName=null, lastName=ZHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.State Key Laboratory of Clean Energy Utilization, Zhejiang University, Hangzhou 310027, China
2.Zhejiang Zheneng Taizhou Second Electric Power Generation Co., Ltd., Taizhou 317108, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068317593653834, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068317086143046, language=CN, stringName=郑必君, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.浙江大学能源高效清洁利用全国重点实验室,浙江 杭州 310027
2.浙江浙能台州第二发电有限责任公司,浙江 台州 317108, bio={"content":"

郑必君(1989),男,硕士,工程师,主要研究方向为智慧能源,

"}, bioImg=null, bioContent=

郑必君(1989),男,硕士,工程师,主要研究方向为智慧能源,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068316909982271, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, xref=1., ext=[AuthorCompanyExt(id=1295068316918370880, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316909982271, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Key Laboratory of Clean Energy Utilization, Zhejiang University, Hangzhou 310027, China), AuthorCompanyExt(id=1295068316930953793, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316909982271, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.浙江大学能源高效清洁利用全国重点实验室,浙江 杭州 310027)]), AuthorCompany(id=1295068316998062658, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, xref=2., ext=[AuthorCompanyExt(id=1295068317006451267, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316998062658, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Taizhou Second Electric Power Generation Co., Ltd., Taizhou 317108, China), AuthorCompanyExt(id=1295068317014839876, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316998062658, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能台州第二发电有限责任公司,浙江 台州 317108)])]), Author(id=1295068317715288652, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, 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=1295068317794980430, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068317715288652, language=EN, stringName=Shanhui ZHU, firstName=Shanhui, middleName=null, lastName=ZHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Zhejiang Zheneng Taizhou Second Electric Power Generation Co., Ltd., Taizhou 317108, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068317874672207, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068317715288652, language=CN, stringName=朱善会, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.浙江浙能台州第二发电有限责任公司,浙江 台州 317108, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068316998062658, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, xref=2., ext=[AuthorCompanyExt(id=1295068317006451267, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316998062658, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Taizhou Second Electric Power Generation Co., Ltd., Taizhou 317108, China), AuthorCompanyExt(id=1295068317014839876, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316998062658, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能台州第二发电有限责任公司,浙江 台州 317108)])]), Author(id=1295068317950169681, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, 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=1295068318029861459, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068317950169681, language=EN, stringName=Bin ZHANG, firstName=Bin, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Zhejiang Zheneng Taizhou Second Electric Power Generation Co., Ltd., Taizhou 317108, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068318101164628, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068317950169681, language=CN, stringName=张斌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.浙江浙能台州第二发电有限责任公司,浙江 台州 317108, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068316998062658, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, xref=2., ext=[AuthorCompanyExt(id=1295068317006451267, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316998062658, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Taizhou Second Electric Power Generation Co., Ltd., Taizhou 317108, China), AuthorCompanyExt(id=1295068317014839876, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316998062658, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能台州第二发电有限责任公司,浙江 台州 317108)])]), Author(id=1295068318168273494, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yjg@zju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1295068318247965272, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068318168273494, language=EN, stringName=Jianguo YANG, firstName=Jianguo, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.State Key Laboratory of Clean Energy Utilization, Zhejiang University, Hangzhou 310027, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068319950852699, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068318168273494, language=CN, stringName=杨建国, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.浙江大学能源高效清洁利用全国重点实验室,浙江 杭州 310027, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068316909982271, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, xref=1., ext=[AuthorCompanyExt(id=1295068316918370880, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316909982271, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Key Laboratory of Clean Energy Utilization, Zhejiang University, Hangzhou 310027, China), AuthorCompanyExt(id=1295068316930953793, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316909982271, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.浙江大学能源高效清洁利用全国重点实验室,浙江 杭州 310027)])])], keywords=[Keyword(id=1295068320034738780, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, orderNo=1, keyword=main steam temperature), Keyword(id=1295068320097653342, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, orderNo=2, keyword=predictive control), Keyword(id=1295068320152179295, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, orderNo=3, keyword=hyperparameter transfer), Keyword(id=1295068320219288160, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, orderNo=4, keyword=global optimization), Keyword(id=1295068320294785633, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, orderNo=5, keyword=piecewise control), Keyword(id=1295068320357700194, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, orderNo=1, keyword=主蒸汽温度), Keyword(id=1295068320420614755, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, orderNo=2, keyword=预测控制), Keyword(id=1295068320491917924, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, orderNo=3, keyword=超参数迁移), Keyword(id=1295068320554832485, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, orderNo=4, keyword=全局寻优), Keyword(id=1295068320621941350, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, orderNo=5, keyword=分段控制)], refs=[Reference(id=1295068324946268812, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2013, volume=66, issue=null, pageStart=234, pageEnd=245, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=RAY T K, GANGULY R, GUPTA A, journalName=Energy Conversion and Management, refType=null, unstructuredReference=RAY T K, GANGULY R, GUPTA A. Optimal control strategy for minimization of exergy destruction in boiler superheater[J]. Energy Conversion and Management, 2013, 66: 234-245., articleTitle=Optimal control strategy for minimization of exergy destruction in boiler superheater, refAbstract=null), Reference(id=1295068325000794765, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=9, pageStart=3307, pageEnd=3317, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=冯旭刚, 张泽辰, 刘圣晶, journalName=中国电机工程学报, refType=null, unstructuredReference=冯旭刚,张泽辰,刘圣晶,. 基于IGPC的火力发电机组主蒸汽温度预测控制策略[J]. 中国电机工程学报202242(9):3307-3317., articleTitle=基于IGPC的火力发电机组主蒸汽温度预测控制策略, refAbstract=null), Reference(id=1295068325080486542, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2022, volume=42, issue=9, pageStart=3307, pageEnd=3317, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=FENG Xugang, ZHANG Zechen, LIU Shengjing, journalName=Proceedings of the CSEE, refType=null, unstructuredReference=FENG Xugang, ZHANG Zechen, LIU Shengjing, et al. Predictive control strategy for main steam temperature of thermal power unit based on IGPC[J]. Proceedings of the CSEE, 2022, 42(9): 3307-3317., articleTitle=Predictive control strategy for main steam temperature of thermal power unit based on IGPC, refAbstract=null), Reference(id=1295068325151789711, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2003, volume=11, issue=7, pageStart=733, pageEnd=764, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=QIN S J, BADGWELL T A, journalName=Control Engineering Practice, refType=null, unstructuredReference=QIN S J, BADGWELL T A. A survey of industrial model predictive control technology[J]. Control Engineering Practice, 2003, 11(7): 733-764., articleTitle=A survey of industrial model predictive control technology, refAbstract=null), Reference(id=1295068325206315664, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=4, authorNames=HILL E, NEWTON A, GADSDEN S A, journalName=null, refType=null, unstructuredReference=HILL E, NEWTON A, GADSDEN S A. Model predictive control strategies for fault tolerance[D]. Ontario, Canada: University of Guelph, 2021: 1., articleTitle=Model predictive control strategies for fault tolerance, refAbstract=null), Reference(id=1295068325260841617, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2020, volume=206, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[5], rfOrder=5, authorNames=WU X, WANG M, LEE K Y, journalName=Energy, refType=null, unstructuredReference=WU X, WANG M, LEE K Y. Flexible operation of supercritical coal-fired power plant integrated with solvent-based CO2 capture through collaborative predictive control[J]. Energy, 2020, 206: 118105., articleTitle=Flexible operation of supercritical coal-fired power plant integrated with solvent-based CO2 capture through collaborative predictive control, refAbstract=null), Reference(id=1295068325323756178, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=6, authorNames=鲍鹏凯, journalName=null, refType=null, unstructuredReference=鲍鹏凯. 超临界机组中间点汽温预测模型建立与预测控制研究[D]. 北京:华北电力大学,2022:1., articleTitle=超临界机组中间点汽温预测模型建立与预测控制研究, refAbstract=null), Reference(id=1295068325403447955, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=BAO Pengkai, journalName=null, refType=null, unstructuredReference=BAO Pengkai. Establishment of intermediate point temperature prediction model and research on predictive control for supercritical units[D]. Beijing: North China Electric Power University, 2022: 1., articleTitle=Establishment of intermediate point temperature prediction model and research on predictive control for supercritical units, refAbstract=null), Reference(id=1295068325470556820, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2008, volume=null, issue=4, pageStart=395, pageEnd=398, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=刘吉臻, 岳俊红, 谭文, journalName=热能动力工程, refType=null, unstructuredReference=刘吉臻,岳俊红,谭文. 基于多模型集的主汽温多模型预测控制方法[J]. 热能动力工程2008(4):395-398., articleTitle=基于多模型集的主汽温多模型预测控制方法, refAbstract=null), Reference(id=1295068325533471381, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2008, volume=null, issue=4, pageStart=395, pageEnd=398, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=LIU Jizhen, YUE Junhong, TAN Wen, journalName=Journal of Engineering for Thermal Energy and Power, refType=null, unstructuredReference=LIU Jizhen, YUE Junhong, TAN Wen. Main steam temperature multi-model prediction and control method based on a multi-model set[J]. Journal of Engineering for Thermal Energy and Power, 2008(4): 395-398., articleTitle=Main steam temperature multi-model prediction and control method based on a multi-model set, refAbstract=null), Reference(id=1295068325604774550, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2005, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=秦志明, journalName=null, refType=null, unstructuredReference=秦志明. 智能控制算法在主汽温控制中的应用[D]. 保定:华北电力大学,2005:1., articleTitle=智能控制算法在主汽温控制中的应用, refAbstract=null), Reference(id=1295068325671883415, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2005, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=QIN Zhiming, journalName=null, refType=null, unstructuredReference=QIN Zhiming. The application of intelligence control algorithm in main steam temperature control system[D]. Baoding: North China Electric Power University, 2005: 1., articleTitle=The application of intelligence control algorithm in main steam temperature control system, refAbstract=null), Reference(id=1295068325738992280, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2025, volume=56, issue=6, pageStart=2266, pageEnd=2277, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=刘新, 王辉, journalName=中南大学学报(自然科学版), refType=null, unstructuredReference=刘新,王辉. 基于模型预测控制的高精度混合视觉伺服机械臂控制方法[J]. 中南大学学报(自然科学版)202556(6):2266-2277., articleTitle=基于模型预测控制的高精度混合视觉伺服机械臂控制方法, refAbstract=null), Reference(id=1295068325801906841, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2025, volume=56, issue=6, pageStart=2266, pageEnd=2277, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=LIU Xin, WANG Hui, journalName=Journal of Central South University (Science and Technology), refType=null, unstructuredReference=LIU Xin, WANG Hui. High-precision hybrid visual servoing robotic arm control method based on model predictive control[J]. Journal of Central South University (Science and Technology), 2025, 56(6): 2266-2277., articleTitle=High-precision hybrid visual servoing robotic arm control method based on model predictive control, refAbstract=null), Reference(id=1295068325864821402, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2013, volume=46, issue=3, pageStart=386, pageEnd=392, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=方彦军, 易凤飞, 胡文凯, journalName=武汉大学学报(工学版), refType=null, unstructuredReference=方彦军,易凤飞,胡文凯. 基于遗传算法的广义预测PID控制及其在锅炉主汽温系统中的应用[J]. 武汉大学学报(工学版)201346(3):386-392., articleTitle=基于遗传算法的广义预测PID控制及其在锅炉主汽温系统中的应用, refAbstract=null), Reference(id=1295068325957096091, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2013, volume=46, issue=3, pageStart=386, pageEnd=392, url=null, language=null, rfNumber=[10], rfOrder=15, authorNames=FANG Yanjun, YI Fengfei, HU Wenkai, journalName=Engineering Journal of Wuhan University, refType=null, unstructuredReference=FANG Yanjun, YI Fengfei, HU Wenkai. Genetic algorithm-based generalized predictive PID control and its application to main steam temperature control system[J]. Engineering Journal of Wuhan University, 2013, 46(3): 386-392., articleTitle=Genetic algorithm-based generalized predictive PID control and its application to main steam temperature control system, refAbstract=null), Reference(id=1295068326028399260, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2020, volume=17, issue=1, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=SERGIO L, DENIS N, BENJAMIN K, journalName=IEEE Transactions on Industrial Informatics, refType=null, unstructuredReference=SERGIO L, DENIS N, BENJAMIN K, et al. Deep-learning-based model predictive control for resonant power converters[J]. IEEE Transactions on Industrial Informatics, 2020, 17(1): 1., articleTitle=Deep-learning-based model predictive control for resonant power converters, refAbstract=null), Reference(id=1295068326095508125, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=5, pageStart=120, pageEnd=126, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=金志远, 李胜男, 谭鹏, journalName=热力发电, refType=null, unstructuredReference=金志远,李胜男,谭鹏,. 基于长短时记忆神经网络的锅炉多参数协同预测模型[J]. 热力发电202150(5):120-126., articleTitle=基于长短时记忆神经网络的锅炉多参数协同预测模型, refAbstract=null), Reference(id=1295068326171005598, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2021, volume=50, issue=5, pageStart=120, pageEnd=126, url=null, language=null, rfNumber=[12], rfOrder=18, authorNames=JIN Zhiyuan, LI Shengnan, TAN Peng, journalName=Thermal Power Generation, refType=null, unstructuredReference=JIN Zhiyuan, LI Shengnan, TAN Peng, et al. Multi-parameter collaborative prediction model of boilers based on long-short-term memory neural network[J]. Thermal Power Generation, 2021, 50(5): 120-126., articleTitle=Multi-parameter collaborative prediction model of boilers based on long-short-term memory neural network, refAbstract=null), Reference(id=1295068326250697375, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=张凤南, journalName=null, refType=null, unstructuredReference=张凤南. 基于历史数据的主汽温控制系统建模研究[D]. 北京:华北电力大学,2019:1., articleTitle=基于历史数据的主汽温控制系统建模研究, refAbstract=null), Reference(id=1295068326309417632, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=ZHANG Fengnan, journalName=null, refType=null, unstructuredReference=ZHANG Fengnan. Research on modeling of main steam temperature control system based on historical data[D]. Beijing: North China Electric Power University, 2019: 1., articleTitle=Research on modeling of main steam temperature control system based on historical data, refAbstract=null), Reference(id=1295068326376526497, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=212, pageEnd=215, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=张悦, 吴铮, 吕正鑫, journalName=null, refType=null, unstructuredReference=张悦,吴铮,吕正鑫. 基于神经网络预测的锅炉主汽温模糊控制[C]//中国计算机用户协会仿真应用分会. 2019全国仿真技术学术会议论文集. 河北省发电过程仿真与优化控制技术创新中心(华北电力大学),2019:212-215., articleTitle=基于神经网络预测的锅炉主汽温模糊控制, refAbstract=null), Reference(id=1295068326435246754, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=212, pageEnd=215, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=ZHANG Yue, WU Zheng, LYU Zhengxin, journalName=null, refType=null, unstructuredReference=ZHANG Yue, WU Zheng, LYU Zhengxin. Fuzzy control of main steam temperature based on neural network prediction[C]//Proceedings of the 2019 National Conference on Simulation Technology. Simulation Application Branch, China Computer Users Association. Hebei Innovation Center for Simulation & Optimal Control of Power Generation (North China Electric Power University), 2019: 212-215., articleTitle=Fuzzy control of main steam temperature based on neural network prediction, refAbstract=null), Reference(id=1295068326498161315, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=曹鑫炜, journalName=null, refType=null, unstructuredReference=曹鑫炜. 基于深度学习的主汽温预测系统的研究与实现[D]. 北京:华北电力大学,2021:1., articleTitle=基于深度学习的主汽温预测系统的研究与实现, refAbstract=null), Reference(id=1295068326561075876, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=24, authorNames=CAO Xinwei, journalName=null, refType=null, unstructuredReference=CAO Xinwei. Research and implementation of main steam temperature prediction system based on deep learning[D]. Beijing: North China Electric Power University, 2021: 1., articleTitle=Research and implementation of main steam temperature prediction system based on deep learning, refAbstract=null), Reference(id=1295068326619796133, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2024, volume=39, issue=10, pageStart=148, pageEnd=158, url=null, language=null, rfNumber=[16], rfOrder=25, authorNames=周飞燃, 曾德良, 胡勇, journalName=热能动力工程, refType=null, unstructuredReference=周飞燃,曾德良,胡勇. 基于神经网络预测的主蒸汽温度控制方法研究[J]. 热能动力工程202439(10):148-158., articleTitle=基于神经网络预测的主蒸汽温度控制方法研究, refAbstract=null), Reference(id=1295068326674322086, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2024, volume=39, issue=10, pageStart=148, pageEnd=158, url=null, language=null, rfNumber=[16], rfOrder=26, authorNames=ZHOU Feiran, ZENG Deliang, HU Yong, journalName=Journal of Engineering for Thermal Energy and Power, refType=null, unstructuredReference=ZHOU Feiran, ZENG Deliang, HU Yong. Research on main steam temperature control method based on neural network prediction[J]. Journal of Engineering for Thermal Energy and Power, 2024, 39(10): 148-158., articleTitle=Research on main steam temperature control method based on neural network prediction, refAbstract=null), Reference(id=1295068326745625255, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=2603, pageEnd=26127, url=null, language=null, rfNumber=[17], rfOrder=27, authorNames=NGUYEN Q, HEIN M, journalName=null, refType=null, unstructuredReference=NGUYEN Q, HEIN M. The loss surface of deep and wide neural networks[C]//Proceedings of the 34th International Conference on Machine Learning. Sydney: JMLR, 2017: 2603-26127., articleTitle=The loss surface of deep and wide neural networks, refAbstract=null), Reference(id=1295068326804345512, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2024, volume=175, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[18], rfOrder=28, authorNames=XIONG C, ZHANG Y, ZHAO L, journalName=Neural Networks, refType=null, unstructuredReference=XIONG C, ZHANG Y, ZHAO L, et al. A neural network transformation based global optimization algorithm[J]. Neural Networks, 2024, 175: 106448., articleTitle=A neural network transformation based global optimization algorithm, refAbstract=null), Reference(id=1295068326867260073, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2019, volume=1901, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[19], rfOrder=29, authorNames=KAWAGUCHI K, journalName=arXiv, refType=null, unstructuredReference=KAWAGUCHI K. Elimination of all bad local minima in deep learning[J]. arXiv preprint, 2019, 1901: 00279., articleTitle=Elimination of all bad local minima in deep learning, refAbstract=null), Reference(id=1295068326925980330, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2024, volume=25, issue=123, pageStart=1, pageEnd=38, url=null, language=null, rfNumber=[20], rfOrder=30, authorNames=WANG Y, ZHAO H, LIU Y, journalName=Journal of Machine Learning Research, refType=null, unstructuredReference=WANG Y, ZHAO H, LIU Y. Conformal symplectic optimization for stable reinforcement learning[J]. Journal of Machine Learning Research, 2024, 25(123): 1-38., articleTitle=Conformal symplectic optimization for stable reinforcement learning, refAbstract=null), Reference(id=1295068326993089195, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2002, volume=10, issue=2, pageStart=99, pageEnd=127, url=null, language=null, rfNumber=[21], rfOrder=31, authorNames=STANLEY R, MIIKKULAINEN R, journalName=Evolutionary Computation, refType=null, unstructuredReference=STANLEY R, MIIKKULAINEN R. Evolving neural networks through augmenting topologies[J]. Evolutionary Computation, 2002, 10(2): 99-127., articleTitle=Evolving neural networks through augmenting topologies, refAbstract=null), Reference(id=1295068327051809452, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2022, volume=9, issue=4, pageStart=1, pageEnd=15, url=null, language=null, rfNumber=[22], rfOrder=32, authorNames=彭黔荣, 罗小华, 王磊, journalName=OALib Journal, refType=null, unstructuredReference=彭黔荣,罗小华,王磊. 基于混合遗传算法的神经网络全局优化方法[J]. OALib Journal20229(4):1-15., articleTitle=基于混合遗传算法的神经网络全局优化方法, refAbstract=null), Reference(id=1295068327123112621, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2022, volume=9, issue=4, pageStart=1, pageEnd=15, url=null, language=null, rfNumber=[22], rfOrder=33, authorNames=PENG Qianrong, LUO Xiaohua, WANG Lei, journalName=OALib Journal, refType=null, unstructuredReference=PENG Qianrong, LUO Xiaohua, WANG Lei. A global optimization method for neural networks based on hybrid genetic algorithm[J]. OALib Journal, 2022, 9(4): 1-15., articleTitle=A global optimization method for neural networks based on hybrid genetic algorithm, refAbstract=null), Reference(id=1295068327190221486, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2018, volume=6, issue=null, pageStart=12929, pageEnd=12939, url=null, language=null, rfNumber=[23], rfOrder=34, authorNames=ZHAO H, SUN S, JIN B, journalName=IEEE Access, refType=null, unstructuredReference=ZHAO H, SUN S, JIN B. Sequential fault diagnosis based on LSTM neural network[J]. IEEE Access, 2018, 6: 12929-12939., articleTitle=Sequential fault diagnosis based on LSTM neural network, refAbstract=null), Reference(id=1295068327257330351, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2018, volume=11, issue=4, pageStart=1, pageEnd=15, url=null, language=null, rfNumber=[24], rfOrder=35, authorNames=SONG H, DAI J, LUO L, journalName=Energies, refType=null, unstructuredReference=SONG H, DAI J, LUO L, et al. Power transformer operating state prediction method based on an LSTM network[J]. Energies, 2018, 11(4): 1-15., articleTitle=Power transformer operating state prediction method based on an LSTM network, refAbstract=null), Reference(id=1295068328905691824, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2020, volume=49, issue=2, pageStart=52, pageEnd=57, url=null, language=null, rfNumber=[25], rfOrder=36, authorNames=杨新, 高旭东, 李彦苍, journalName=热力发电, refType=null, unstructuredReference=杨新,高旭东,李彦苍,. 基于长短期记忆神经网洛和软投票决策的双流化床气化装置故障诊断模型[J]. 热力发电202049(2):52-57., articleTitle=基于长短期记忆神经网洛和软投票决策的双流化床气化装置故障诊断模型, refAbstract=null), Reference(id=1295068328972800689, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2020, volume=49, issue=2, pageStart=52, pageEnd=57, url=null, language=null, rfNumber=[25], rfOrder=37, authorNames=YANG Xin, GAO Xudong, LI Yancang, journalName=Thermal Power Generation, refType=null, unstructuredReference=YANG Xin, GAO Xudong, LI Yancang, et al. Fault diagnosis model of dual fluidized bed gasification device based on LSTM and voting decision[J]. Thermal Power Generation, 2020, 49(2): 52-57., articleTitle=Fault diagnosis model of dual fluidized bed gasification device based on LSTM and voting decision, refAbstract=null), Reference(id=1295068329035715250, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2024, volume=2401, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[26], rfOrder=38, authorNames=BI X, CHEN D L, CHEN G T, journalName=arXiv, refType=null, unstructuredReference=BI X, CHEN D L, CHEN G T, et al. Deepseek LLM: scaling open-source language models with longtermism[J]. arXiv preprint, 2024, 2401: 02954., articleTitle=Deepseek LLM: scaling open-source language models with longtermism, refAbstract=null), Reference(id=1295068329098629811, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=39, authorNames=THORNTON C, HUTTER F, HOOS H H, journalName=null, refType=null, unstructuredReference=THORNTON C, HUTTER F, HOOS H H, et al. Hyperparameter optimization for long short-term memory networks: a large-scale experiment[C]// Proceedings of the 10th International Conference on Learning Representations. ICLR, 2022: 2110.14778., articleTitle=Hyperparameter optimization for long short-term memory networks: a large-scale experiment, refAbstract=null), Reference(id=1295068329157350068, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[28], rfOrder=40, authorNames=YANG G, HU J E, BABUSCHKIN I, journalName=arXiv, refType=null, unstructuredReference=YANG G, HU J E, BABUSCHKIN I, et al. Tensor programs V: tuning large neural networks via zero-shot hyperparameter transfer[J]. arXiv preprint, 2022: 2203. 03466., articleTitle=Tensor programs V: tuning large neural networks via zero-shot hyperparameter transfer, refAbstract=null), Reference(id=1295068329249624757, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2024, volume=630, issue=8018, pageStart=841, pageEnd=846, url=null, language=null, rfNumber=[29], rfOrder=41, authorNames=NLLB Team, journalName=Nature, refType=null, unstructuredReference=NLLB Team. Scaling neural machine translation to 200 languages[J]. Nature, 2024, 630(8018): 841-846., articleTitle=Scaling neural machine translation to 200 languages, refAbstract=null), Reference(id=1295068329308345014, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=1, pageEnd=null, url=null, language=null, rfNumber=[30], rfOrder=42, authorNames=YANG G, SCHOENHOLZ S S, journalName=null, refType=null, unstructuredReference=YANG G, SCHOENHOLZ S S. Deep mean field theory: layerwise variance and width variation as methods to control gradient explosion[C]//Proceedings of the 6th International Conference on Learning Representations (ICLR 2018). Vancouver, Canada: OpenReview, 2018: 1., articleTitle=Deep mean field theory: layerwise variance and width variation as methods to control gradient explosion, refAbstract=null), Reference(id=1295068329388036791, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2024, volume=12, issue=4, pageStart=705, pageEnd=712, url=null, language=null, rfNumber=[31], rfOrder=43, authorNames=DESWAL V, KUMAR D, journalName=International Journal of Intelligent Systems and Applications in Engineering, refType=null, unstructuredReference=DESWAL V, KUMAR D. Hyperparameter tuning of the LSTM model for stock price prediction[J]. International Journal of Intelligent Systems and Applications in Engineering, 2024, 12(4): 705-712., articleTitle=Hyperparameter tuning of the LSTM model for stock price prediction, refAbstract=null), Reference(id=1295068329463534264, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2020, volume=47, issue=6, pageStart=91, pageEnd=98, url=null, language=null, rfNumber=[32], rfOrder=44, authorNames=于静, 金秀章, journalName=华北电力大学学报(自然科学版), refType=null, unstructuredReference=于静,金秀章. 基于RBF神经网络的PFC-PID主汽温串级预测控制[J]. 华北电力大学学报(自然科学版)202047(6):91-98., articleTitle=基于RBF神经网络的PFC-PID主汽温串级预测控制, refAbstract=null), Reference(id=1295068329522254521, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, doi=null, pmid=null, pmcid=null, year=2020, volume=47, issue=6, pageStart=91, pageEnd=98, url=null, language=null, rfNumber=[32], rfOrder=45, authorNames=YU Jing, JIN Xiuzhang, journalName=Journal of North China Electric Power University (Natural Science Edition), refType=null, unstructuredReference=YU Jing, JIN Xiuzhang. PFC-PID Main steam temperature cascade predictive control based on RBF neural network[J]. Journal of North China Electric Power University (Natural Science Edition), 2020, 47(6): 91-98., articleTitle=PFC-PID Main steam temperature cascade predictive control based on RBF neural network, refAbstract=null)], funds=[Fund(id=1295068324816245386, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, awardId=2022ZFJH04, language=EN, fundingSource=Fundamental Research Funds for the Central Universities(2022ZFJH04), fundOrder=null, country=null), Fund(id=1295068324870771339, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, awardId=2022ZFJH04, language=CN, fundingSource=中央高校基本科研业务费专项资金资助项目(2022ZFJH04), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1295068316909982271, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, xref=1., ext=[AuthorCompanyExt(id=1295068316918370880, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316909982271, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Key Laboratory of Clean Energy Utilization, Zhejiang University, Hangzhou 310027, China), AuthorCompanyExt(id=1295068316930953793, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316909982271, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.浙江大学能源高效清洁利用全国重点实验室,浙江 杭州 310027)]), AuthorCompany(id=1295068316998062658, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, xref=2., ext=[AuthorCompanyExt(id=1295068317006451267, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316998062658, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Taizhou Second Electric Power Generation Co., Ltd., Taizhou 317108, China), AuthorCompanyExt(id=1295068317014839876, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316998062658, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能台州第二发电有限责任公司,浙江 台州 317108)])], figs=[ArticleFig(id=1295068320772936295, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Fig.1, caption=Structure of the LSTM unit, figureFileSmall=1qcw4I0Xq4wPTVXBcaS71Q==, figureFileBig=kJWmUPTUM/BwovMLBhsSdw==, tableContent=null), ArticleFig(id=1295068320844239464, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=图1, caption=LSTM神经网络单元结构, figureFileSmall=1qcw4I0Xq4wPTVXBcaS71Q==, figureFileBig=kJWmUPTUM/BwovMLBhsSdw==, tableContent=null), ArticleFig(id=1295068321024594537, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Fig.2, caption=Modeling flowchart of the prediction model, figureFileSmall=ePUErIFDfgjyysC7Ly+y1Q==, figureFileBig=UrHLkxpACymjFqkhK1614w==, tableContent=null), ArticleFig(id=1295068321087509098, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=图2, caption=预测模型建模流程, figureFileSmall=ePUErIFDfgjyysC7Ly+y1Q==, figureFileBig=UrHLkxpACymjFqkhK1614w==, tableContent=null), ArticleFig(id=1295068321163006571, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Fig.3, caption=Flowchart of the steam and water system, figureFileSmall=Yyez0nRW4sQ4+RKYaajv8Q==, figureFileBig=3NHfOmC1qL8TJVLJ+oS8eg==, tableContent=null), ArticleFig(id=1295068321217532524, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=图3, caption=汽水系统流程, figureFileSmall=Yyez0nRW4sQ4+RKYaajv8Q==, figureFileBig=3NHfOmC1qL8TJVLJ+oS8eg==, tableContent=null), ArticleFig(id=1295068321276252781, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Fig.4, caption=Comparison of prediction accuracy among the models, figureFileSmall=3qy87P0uMcT5h4Ld1TeaPg==, figureFileBig=rqj2N13jGvlCDJ3mPb/IUA==, tableContent=null), ArticleFig(id=1295068321339167342, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=图4, caption=各模型预测精度对比, figureFileSmall=3qy87P0uMcT5h4Ld1TeaPg==, figureFileBig=rqj2N13jGvlCDJ3mPb/IUA==, tableContent=null), ArticleFig(id=1295068321427247727, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Fig.5, caption=Prediction effect of main steam temperature (A side), figureFileSmall=2Bo9KaGnzpO8jG9OtH02kQ==, figureFileBig=j4d2clEB33TQlwlihvs9vQ==, tableContent=null), ArticleFig(id=1295068321494356592, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=图5, caption=主蒸汽温度预测效果(A侧), figureFileSmall=2Bo9KaGnzpO8jG9OtH02kQ==, figureFileBig=j4d2clEB33TQlwlihvs9vQ==, tableContent=null), ArticleFig(id=1295068321574048369, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Fig.6, caption=Prediction effect of main steam temperature (B side), figureFileSmall=hLHzOd/XSPmP0Fe1FdCRqw==, figureFileBig=M8FAn0usUFKM5oaHfvTX4Q==, tableContent=null), ArticleFig(id=1295068321645351538, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=图6, caption=主蒸汽温度预测效果(B侧), figureFileSmall=hLHzOd/XSPmP0Fe1FdCRqw==, figureFileBig=M8FAn0usUFKM5oaHfvTX4Q==, tableContent=null), ArticleFig(id=1295068321704071795, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Fig.7, caption=PID control logic of the primary and secondary desuperheater, figureFileSmall=7Cbqz1FlSUF7JFtPOuvPcw==, figureFileBig=gKKx7gRdf70LWf0C9/J/7g==, tableContent=null), ArticleFig(id=1295068321783763572, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=图7, caption=一、二级减温器PID控制逻辑, figureFileSmall=7Cbqz1FlSUF7JFtPOuvPcw==, figureFileBig=gKKx7gRdf70LWf0C9/J/7g==, tableContent=null), ArticleFig(id=1295068321838289525, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Fig.8, caption=The optimized control logic, figureFileSmall=fsnYV87cAhlitZYkH8B51A==, figureFileBig=qE6se/i7yh2HxWF5Z5BsAw==, tableContent=null), ArticleFig(id=1295068321901204086, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=图8, caption=优化后的控制逻辑, figureFileSmall=fsnYV87cAhlitZYkH8B51A==, figureFileBig=qE6se/i7yh2HxWF5Z5BsAw==, tableContent=null), ArticleFig(id=1295068321959924343, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Fig.9, caption=Simulation configuration diagram of the predictive control system, figureFileSmall=yqLQ4tDV8lA6LukgEy7rkA==, figureFileBig=3URkzljvtNwlc7d8u1kPXQ==, tableContent=null), ArticleFig(id=1295068322018644600, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=图9, caption=预测控制系统仿真组态, figureFileSmall=yqLQ4tDV8lA6LukgEy7rkA==, figureFileBig=3URkzljvtNwlc7d8u1kPXQ==, tableContent=null), ArticleFig(id=1295068322136085113, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Fig.10, caption=The optimized control effect, figureFileSmall=/5RMiz2orLgH/I2nBJ9o3A==, figureFileBig=Lm5rJg6oiVmhUF/s1+keBg==, tableContent=null), ArticleFig(id=1295068322198999674, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=图10, caption=优化后的控制效果, figureFileSmall=/5RMiz2orLgH/I2nBJ9o3A==, figureFileBig=Lm5rJg6oiVmhUF/s1+keBg==, tableContent=null), ArticleFig(id=1295068322274497147, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Fig.11, caption=Piecewise control logic diagram, figureFileSmall=pVidQpZteKfjWQ5iHmr1MQ==, figureFileBig=cNtDmnUrlJbOnOx5C2m0Bg==, tableContent=null), ArticleFig(id=1295068322337411708, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=图11, caption=分段控制逻辑框图, figureFileSmall=pVidQpZteKfjWQ5iHmr1MQ==, figureFileBig=cNtDmnUrlJbOnOx5C2m0Bg==, tableContent=null), ArticleFig(id=1295068322396131965, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Fig.12, caption=Simulation configuration diagram of piecewise control, figureFileSmall=fuZyUVHWXqYcXaKOPaQLew==, figureFileBig=UnwsoBZy8chIh9KXMiyRqA==, tableContent=null), ArticleFig(id=1295068322467435134, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=图12, caption=分段控制的仿真组态, figureFileSmall=fuZyUVHWXqYcXaKOPaQLew==, figureFileBig=UnwsoBZy8chIh9KXMiyRqA==, tableContent=null), ArticleFig(id=1295068322526155391, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Fig.13, caption=Control effect of piecewise optimization, figureFileSmall=P4cxdKH1va41Zd/F7IyzcQ==, figureFileBig=uKqNb7SfBnms2Pp96BY2iw==, tableContent=null), ArticleFig(id=1295068322593264256, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=图13, caption=分段优化的控制效果, figureFileSmall=P4cxdKH1va41Zd/F7IyzcQ==, figureFileBig=uKqNb7SfBnms2Pp96BY2iw==, tableContent=null), ArticleFig(id=1295068322681344641, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Tab.1, caption=

Input and output parameters of the model

, figureFileSmall=null, figureFileBig=null, tableContent=
序号参数名称参数类型
1机组负荷机组全局参数
2总风量燃烧表征参数
3给水量汽水表征参数
4锅炉总煤量燃烧表征参数
5主蒸汽压力汽水表征参数
6低过A侧进口烟气温度燃烧表征参数
7低过B侧进口烟气温度燃烧表征参数
8低过A侧进口蒸汽温度汽水表征参数
9低过A侧出口蒸汽温度汽水表征参数
10低过B侧进口蒸汽温度汽水表征参数
11低过B侧出口蒸汽温度汽水表征参数
12屏过A侧进口蒸汽温度汽水表征参数
13屏过A侧出口蒸汽温度汽水表征参数
14屏过B侧进口蒸汽温度汽水表征参数
15屏过B侧出口蒸汽温度汽水表征参数
16屏过A侧出口烟气温度燃烧表征参数
17屏过B侧出口烟气温度燃烧表征参数
18高过A侧进口蒸汽温度汽水表征参数
19高过B侧进口蒸汽温度汽水表征参数
20高过A侧出口蒸汽温度汽水表征参数
21高过B侧出口蒸汽温度汽水表征参数
22A侧高过出口集箱内壁温度汽水表征参数
23A侧高过出口集箱外壁温度燃烧表征参数
24B侧高过出口集箱内壁温度汽水表征参数
25B侧高过出口集箱外壁温度燃烧表征参数
26高过出口集箱蒸汽压力汽水表征参数
27低再出口烟气挡板阀位燃烧表征参数
28省煤器出口烟气挡板阀位燃烧表征参数
29A过热器一级减温水阀位减温水表征参数
30B过热器一级减温水阀位减温水表征参数
31A过热器二级减温水阀位减温量表征参数
32B过热器二级减温水阀位减温水表征参数
33A侧过热蒸汽温度预测参数
34B侧过热蒸汽温度预测参数
), ArticleFig(id=1295068322769425026, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=表1, caption=

模型输入输出参数

, figureFileSmall=null, figureFileBig=null, tableContent=
序号参数名称参数类型
1机组负荷机组全局参数
2总风量燃烧表征参数
3给水量汽水表征参数
4锅炉总煤量燃烧表征参数
5主蒸汽压力汽水表征参数
6低过A侧进口烟气温度燃烧表征参数
7低过B侧进口烟气温度燃烧表征参数
8低过A侧进口蒸汽温度汽水表征参数
9低过A侧出口蒸汽温度汽水表征参数
10低过B侧进口蒸汽温度汽水表征参数
11低过B侧出口蒸汽温度汽水表征参数
12屏过A侧进口蒸汽温度汽水表征参数
13屏过A侧出口蒸汽温度汽水表征参数
14屏过B侧进口蒸汽温度汽水表征参数
15屏过B侧出口蒸汽温度汽水表征参数
16屏过A侧出口烟气温度燃烧表征参数
17屏过B侧出口烟气温度燃烧表征参数
18高过A侧进口蒸汽温度汽水表征参数
19高过B侧进口蒸汽温度汽水表征参数
20高过A侧出口蒸汽温度汽水表征参数
21高过B侧出口蒸汽温度汽水表征参数
22A侧高过出口集箱内壁温度汽水表征参数
23A侧高过出口集箱外壁温度燃烧表征参数
24B侧高过出口集箱内壁温度汽水表征参数
25B侧高过出口集箱外壁温度燃烧表征参数
26高过出口集箱蒸汽压力汽水表征参数
27低再出口烟气挡板阀位燃烧表征参数
28省煤器出口烟气挡板阀位燃烧表征参数
29A过热器一级减温水阀位减温水表征参数
30B过热器一级减温水阀位减温水表征参数
31A过热器二级减温水阀位减温量表征参数
32B过热器二级减温水阀位减温水表征参数
33A侧过热蒸汽温度预测参数
34B侧过热蒸汽温度预测参数
), ArticleFig(id=1295068324426175108, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Tab.2, caption=

The first step set of hyperparameters for optimization

, figureFileSmall=null, figureFileBig=null, tableContent=
方法batch sizesequece lengthlearning rate/×10–4Loss/℃MAPE/%
PSO1275.121.3800.231
4610.001.5000.265
326.571.6200.268
GA30152.111.6300.275
1671.971.4800.250
5072.872.0800.341
), ArticleFig(id=1295068324484895365, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=表2, caption=

初步寻优的超参数组

, figureFileSmall=null, figureFileBig=null, tableContent=
方法batch sizesequece lengthlearning rate/×10–4Loss/℃MAPE/%
PSO1275.121.3800.231
4610.001.5000.265
326.571.6200.268
GA30152.111.6300.275
1671.971.4800.250
5072.872.0800.341
), ArticleFig(id=1295068324543615622, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Tab.3, caption=

The optimal set of hyperparameters

, figureFileSmall=null, figureFileBig=null, tableContent=
序号batch sizesequence lengthLearning rate/×10–4Loss/℃MAPE/%
1562.001.3070.222
2325.501.2960.221
31275.121.4110.234
), ArticleFig(id=1295068324598141575, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=表3, caption=

最优超参数组

, figureFileSmall=null, figureFileBig=null, tableContent=
序号batch sizesequence lengthLearning rate/×10–4Loss/℃MAPE/%
1562.001.3070.222
2325.501.2960.221
31275.121.4110.234
), ArticleFig(id=1295068324656861832, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=EN, label=Tab.4, caption=

The comparison of prediction effect among the models

, figureFileSmall=null, figureFileBig=null, tableContent=
类型batch sizesequence lengthlearning rate/×10–4Loss/℃MAPE/%单次训练耗时/s
原始模型562.000.9940.167280
325.501.0810.180355
1275.120.7930.132156
LSTM加宽562.001.2030.201345
325.501.0890.182440
1275.120.8130.135190
LSTM加深562.000.5060.085472
325.500.5100.085540
1275.120.5180.086281
LSTM加深宽562.000.5140.086500
325.500.4990.082573
1275.120.5180.086280
增加FCNN562.000.5070.084300
325.500.4950.082370
1275.120.5110.085160
深化LSTM增加FCNN562.000.5190.086600
325.500.5330.089580
1275.120.5280.088370
), ArticleFig(id=1295068324723970697, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, language=CN, label=表4, caption=

各模型预测效果对比

, figureFileSmall=null, figureFileBig=null, tableContent=
类型batch sizesequence lengthlearning rate/×10–4Loss/℃MAPE/%单次训练耗时/s
原始模型562.000.9940.167280
325.501.0810.180355
1275.120.7930.132156
LSTM加宽562.001.2030.201345
325.501.0890.182440
1275.120.8130.135190
LSTM加深562.000.5060.085472
325.500.5100.085540
1275.120.5180.086281
LSTM加深宽562.000.5140.086500
325.500.4990.082573
1275.120.5180.086280
增加FCNN562.000.5070.084300
325.500.4950.082370
1275.120.5110.085160
深化LSTM增加FCNN562.000.5190.086600
325.500.5330.089580
1275.120.5280.088370
)], 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.202510020, detailUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/10.19666/j.rlfd.202510020, pdfUrlCn=https://castjournals.cast.org.cn/joweb/rlfd/CN/PDF/10.19666/j.rlfd.202510020, pdfUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/PDF/10.19666/j.rlfd.202510020, aliStartDate=0, aliEndDate=0, collectionFlag=false, citedCount=null, citedUrl=null, previewStatus=0, delFlag=0, hasFullText=1, orderTime=1779638400000, fullTextJson=null, articleText=null, reference=null)
收藏切换
基于超参数迁移建模的燃煤机组主蒸汽温度预测控制系统
收藏切换
PDF下载
郑必君 1, 2 , 朱善会 2 , 张斌 2 , 杨建国 1
热力发电 | 低碳火电及核电技术 2026,55(5): 90-98
收起
收藏切换
热力发电 |低碳火电及核电技术 2026 , 55 (5) : 90 -98
基于超参数迁移建模的燃煤机组主蒸汽温度预测控制系统
全屏
[Author(id=1295068317086143046, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=704824790@qq.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1295068317371355721, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068317086143046, language=EN, stringName=Bijun ZHENG, firstName=Bijun, middleName=null, lastName=ZHENG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.State Key Laboratory of Clean Energy Utilization, Zhejiang University, Hangzhou 310027, China
2.Zhejiang Zheneng Taizhou Second Electric Power Generation Co., Ltd., Taizhou 317108, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068317593653834, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068317086143046, language=CN, stringName=郑必君, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.浙江大学能源高效清洁利用全国重点实验室,浙江 杭州 310027
2.浙江浙能台州第二发电有限责任公司,浙江 台州 317108, bio={"content":"

郑必君(1989),男,硕士,工程师,主要研究方向为智慧能源,

"}, bioImg=null, bioContent=

郑必君(1989),男,硕士,工程师,主要研究方向为智慧能源,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068316909982271, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, xref=1., ext=[AuthorCompanyExt(id=1295068316918370880, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316909982271, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Key Laboratory of Clean Energy Utilization, Zhejiang University, Hangzhou 310027, China), AuthorCompanyExt(id=1295068316930953793, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316909982271, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.浙江大学能源高效清洁利用全国重点实验室,浙江 杭州 310027)]), AuthorCompany(id=1295068316998062658, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, xref=2., ext=[AuthorCompanyExt(id=1295068317006451267, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316998062658, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Taizhou Second Electric Power Generation Co., Ltd., Taizhou 317108, China), AuthorCompanyExt(id=1295068317014839876, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316998062658, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能台州第二发电有限责任公司,浙江 台州 317108)])]), Author(id=1295068317715288652, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, 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=1295068317794980430, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068317715288652, language=EN, stringName=Shanhui ZHU, firstName=Shanhui, middleName=null, lastName=ZHU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Zhejiang Zheneng Taizhou Second Electric Power Generation Co., Ltd., Taizhou 317108, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068317874672207, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068317715288652, language=CN, stringName=朱善会, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.浙江浙能台州第二发电有限责任公司,浙江 台州 317108, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068316998062658, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, xref=2., ext=[AuthorCompanyExt(id=1295068317006451267, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316998062658, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Taizhou Second Electric Power Generation Co., Ltd., Taizhou 317108, China), AuthorCompanyExt(id=1295068317014839876, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316998062658, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能台州第二发电有限责任公司,浙江 台州 317108)])]), Author(id=1295068317950169681, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, 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=1295068318029861459, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068317950169681, language=EN, stringName=Bin ZHANG, firstName=Bin, middleName=null, lastName=ZHANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.Zhejiang Zheneng Taizhou Second Electric Power Generation Co., Ltd., Taizhou 317108, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068318101164628, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068317950169681, language=CN, stringName=张斌, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=2, address=2.浙江浙能台州第二发电有限责任公司,浙江 台州 317108, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068316998062658, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, xref=2., ext=[AuthorCompanyExt(id=1295068317006451267, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316998062658, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.Zhejiang Zheneng Taizhou Second Electric Power Generation Co., Ltd., Taizhou 317108, China), AuthorCompanyExt(id=1295068317014839876, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316998062658, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.浙江浙能台州第二发电有限责任公司,浙江 台州 317108)])]), Author(id=1295068318168273494, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=yjg@zju.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1295068318247965272, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068318168273494, language=EN, stringName=Jianguo YANG, firstName=Jianguo, middleName=null, lastName=YANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.State Key Laboratory of Clean Energy Utilization, Zhejiang University, Hangzhou 310027, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068319950852699, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, authorId=1295068318168273494, language=CN, stringName=杨建国, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, address=1.浙江大学能源高效清洁利用全国重点实验室,浙江 杭州 310027, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068316909982271, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, xref=1., ext=[AuthorCompanyExt(id=1295068316918370880, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316909982271, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Key Laboratory of Clean Energy Utilization, Zhejiang University, Hangzhou 310027, China), AuthorCompanyExt(id=1295068316930953793, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068311901983263, companyId=1295068316909982271, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.浙江大学能源高效清洁利用全国重点实验室,浙江 杭州 310027)])])]
郑必君1, 2 , 朱善会2, 张斌2, 杨建国1
作者信息
  • 1.浙江大学能源高效清洁利用全国重点实验室,浙江 杭州 310027
  • 2.浙江浙能台州第二发电有限责任公司,浙江 台州 317108
通讯作者:
杨建国(1973),男,博士,副研究员,主要研究方向为清洁能源、智慧能源,
作者简介:

郑必君(1989),男,硕士,工程师,主要研究方向为智慧能源,

Main steam temperature prediction and control system for coal-fired units based on hyperparameter transfer modeling
Bijun ZHENG1, 2 , Shanhui ZHU2, Bin ZHANG2, Jianguo YANG1
Affiliations
  • 1.State Key Laboratory of Clean Energy Utilization, Zhejiang University, Hangzhou 310027, China
  • 2.Zhejiang Zheneng Taizhou Second Electric Power Generation Co., Ltd., Taizhou 317108, China
出版时间: 2026-05-25 doi: 10.19666/j.rlfd.202510020
文章导航
收藏切换

燃煤电厂的锅炉主蒸汽温度作为一个重要参数,在面临极端工况如深度调峰时,往往难以保持稳定。为了解决这一问题,在原有主蒸汽温度控制系统中引入预测控制模型,来完成控制优化。以某超超临界锅炉为对象构建其主蒸汽温度预测控制系统,以复合长短时记忆(LSTM)神经网络为核心算法构建预测模型,通过超参数迁移方法快速实现全局寻优,在解决神经网络模型易陷入局部最优问题的同时,减少寻优计算量88%。预测模型的均方根误差为0.495 ℃,平均百分比误差0.082%。经MATLAB仿真实验验证,该预测控制系统在面对极端工况时,将主蒸汽温度超调量降低50%,并通过多工况分段控制保持正常工况的控制稳定性,可满足不同工况下的主蒸汽温度调节需求。

主蒸汽温度  /  预测控制  /  超参数迁移  /  全局寻优  /  分段控制

Main steam temperature is a key parameter for the boiler of coal-fired power plants. It is difficult to remain stable under extreme load changes such as deep peak-shaving. To solve this problem, a predictive control model is added to the existing temperature loop. The proposed control system targets an ultra-supercritical boiler. A hybrid long short-term memory (LSTM) network forms the core predictor of the predictive model. A hyper parameter transfer method speeds up global optimization, avoids local optima and cuts optimization calculation amount by 88%. The predictive model gives a root-mean-square error of 0.495 ℃ and a mean absolute percentage error of 0.082%. MATLAB simulations show that the predictive control system reduces peak overshoot by 50% under extreme conditions, while preserving the control-loop stability during normal operation through multi-condition piecewise control. These results demonstrate that the proposed model predictive control system satisfies the main steam temperature regulation requirements across all operating conditions.

main steam temperature  /  predictive control  /  hyperparameter transfer  /  global optimization  /  piecewise control
郑必君, 朱善会, 张斌, 杨建国. 基于超参数迁移建模的燃煤机组主蒸汽温度预测控制系统. 热力发电, 2026 , 55 (5) : 90 -98 . DOI: 10.19666/j.rlfd.202510020
Bijun ZHENG, Shanhui ZHU, Bin ZHANG, Jianguo YANG. Main steam temperature prediction and control system for coal-fired units based on hyperparameter transfer modeling[J]. Thermal Power Generation, 2026 , 55 (5) : 90 -98 . DOI: 10.19666/j.rlfd.202510020
现代大型燃煤机组的锅炉主蒸汽温度是一个重要的安全性与经济性指标,正常运行时需将其控制在一个合适范围[1]。常用的主蒸汽温度控制方式是采用减温器结合串级PID控制系统。但随着国家对火电机组灵活性要求的提高,深度调峰逐渐成为常态。在这种极端工况下,由于锅炉系统的多扰动、大迟延等特性,单纯的PID串级控制难以满足控制要求[2]。新形势下,主蒸汽温度调节需要一种更精准、能适应恶劣工况的调节机制。
模型预测控制(model predictive control,MPC)是一种基于预测模型的控制策略,通过预测系统的未来行为来优化控制,从而实现控制系统的性能提升。MPC起源于20世纪60年代,历经多年发展,在工业领域的应用频率上仅次于PID[3]。近年来,MPC在航空航天[4]、火-储协同兼顾碳捕集[5]、电厂控制优化[6]等领域都得到了有效应用。2008年,刘吉臻等提出基于多模型集的主蒸汽温度多模型预测控制方法[7]。彼时主蒸汽温度预测模型主要基于Smith预估[8]、状态空间[9]、遗传算法[10]等方法构建。2015年以后,随着计算机软硬件的进一步发展,深度学习算法在各行各业得到更广泛的应用。而在燃煤电厂锅炉这类大时延非线性系统的参数预测中,相比传统模型,深度学习模型往往能取得更好的预测效果[11]。其中最热门的是以长短时记忆(long short-term memory,LSTM)神经网络为基础的深度学习模型[12]。LSTM神经网络具备捕捉长期依赖能力强、适应非线性工况、对序列长度不敏感等优点,在燃煤电厂主蒸汽温度预测中表现良好[13]。之后的一段时期,主蒸汽温度预测算法主要基于单一类型神经网络[14]。直到2019年后,以LSTM神经网络为基础,结合全连接神经网络(FCNN)、卷积神经网络(CNN)、自注意力机制等复合神经网络的主蒸汽温度预测模型开始涌现[15],预测准确度也进一步得到提高[16]
但包含LSTM神经网络在内的各类神经网络,具有训练中易陷入局部最优的问题[17]。解决方法主要有基于神经网络变换全局优化[18]、增加特殊神经元进行可证凸化[19]、耗散哈密顿系统[20]、优化算法全面寻优[21]等。较常用的解决方法是采用优化算法(如遗传算法)对超参数进行全局寻优,从而获取全局最优解[22]。但模型反复进行超参数寻优又会带来训练计算量过大的问题。
近年来随着大语言模型(large language model,LLM)的兴起,模型规模不断扩大,完整训练LLM需要付出的成本越来越高。算法工程师一般采用超参数迁移方式来降低训练成本。本文将借鉴LLM的训练方式,对预测模型进行超参数迁移,以期解决复杂模型全局寻优计算量大的问题,实现在全局优化的同时,降低计算量。控制系统仍以PID控制回路输出为主,预测输出作为偏置校正,优化主蒸汽温度控制效果。控制回路借助精准的预测模型优化,可实现在极端工况下主蒸汽温度的稳定控制。
预测控制的核心是准确的预测模型。在LSTM神经网络出现前,对于工业时序数据预测采用的基本是传统循环神经网络(RNN),但传统RNN在反向传播中易发生梯度消失现象[23]。为解决梯度消失的问题,LSTM模型被提出。其结构相当于在RNN基础上增加细胞状态c,将上一时刻输出传递的同时,也将历史信息经过滤后进行传递,使下一时刻输出兼顾历史信息[24],通过增加门控单元控制即时信息对历史信息的影响程度,使得模型能长时间保存并传递信息[25],LSTM神经网络单元结构如图1所示。
LSTM神经网络的超参数有2类,分别是架构类与训练类。架构类超参数主要包括:隐含层维度(hidden_size)、层数(num_layers)、层间dropout率(dropout)等。训练类超参数主要包括:学习率(learning_rate)、批大小(batch_size)、序列长度(seq_length)等。由于超参数迁移要求前后模型的类型相同,因此不对架构进行大改动,只针对训练类超参数进行寻优。同时,根据DeepSeek团队的研究[26],对深度学习模型影响明显的超参数主要是learning_rate、batch_size等。而LSTM神经网络作为处理连续时序数据的神经网络,seq_length也是其重要超参数。因此本文围绕这3个超参数进行全局寻优。
Bengio-Yoshua团队在2022年对LSTM神经网络训练类超参数的调优开展了系统性研究,并给出了不同情况下的推荐区间[27],如推荐搜索区间:hiddenSize:{64,128,256};layers:{1,2};dropout:[0.1,0.4];learning_rate:[10–4,10–2]。
常规超参数寻优即在前人的经验寻优区间附近,再采用优化算法在区间内深入寻优。经典优化方法有粒子群优化(particle swarm optimization,PSO)算法和遗传算法(genetic algorithm,GA)等。
理论上,每次超参数寻优都需要对神经网络进行一次完整迭代。这导致对一个复杂的模型进行超参数全局寻优需要的计算量非常庞大。寻找更高效快捷的寻优方法就非常有必要。
超参数迁移就是其中一种方法。但算法人员需要对超参数与模型尺度之间的缩放规律有深入了解。Yang等人研究Transformer类型的LLM超参数(如学习率、批大小等)随模型尺度变化的规律[28],验证了LLM超参数迁移的可行性。LSTM神经网络与Transformer类型的大模型在结构上存在差异。因此其超参数迁移规则,与LLM略有不同。
文献[29]中2019(fairseq scaling study)系统报告指出:当LSTM神经网络缩放后的深度≤6层、宽度≤2 048时,其最优learning_rate与batch_size保持恒定,此时梯度范数与参数量的增长被残差连接、梯度裁剪所抵消,信噪比保持不变;当缩放后的深度>6层时,梯度范数随深度指数增长,最优learning_rate需线性下降10%~20%,此时batch_size仍可不变;当缩放后宽度>2 048时,仅观察到2%~3%的learning_rate漂移,因此认为宽度缩放对LSTM神经网络的超参数影响极小。后续的Mean-Field理论[30]也给出了一致的结果。
Deswal V和Kumar D在研究LSTM神经网络长序列预测时发现[31],增加LSTM神经网络的深度后,网络的“长程记忆”能力显著增加,不必再靠过长输入。因此一般建议序列长度适当缩短。
考虑到锅炉对象的参数时延时间普遍小于1 min,而参数取样周期为5 s,因此seq_length范围一般为2~10步。由于seq_length本身较小,因此不进行缩放。
本文设计的LSTM模型的深度≤3层、宽度≤256,符合learning_rate、batch_size直接迁移的理论要求。seq_length由于锅炉系统特性,因此保留10以下的seq_length,若seq_length值超过10,则降到10来使用。
预测模型的建模流程如图2所示。
根据图2,预测模型的建模流程如下。
1)确定原始模型,为减少总体计算量,原始模型采用结构简单的单层LSTM神经网络,按照Bengio-Yoshua团队的研究,将LSTM神经网络的宽度设为64。
2)通过PSO、GA算法对原始模型的learning_rate、batch_size、seq_length等超参数进行全局寻优。
3)根据规则对超参数进行缩放,形成多个最优超参数组。
4)将最优超参数组迁移到复杂LSTM神经网络。从模型宽度、深度两方面考虑,选用5种不同结构来构造复杂模型。这5种结构分别是宽度增加(×2)的LSTM、深度增加(×2)的LSTM、宽度(×2)深度(×2)均增加的LSTM、增加LSTM后一层FCNN、增加LSTM宽(×2)深(×2)及一层FCNN的结构。
5)将最优超参数组分别赋予上面5种复杂模型,并将复杂模型训练至收敛。最后通过对模型预测准确度、模型复杂度、训练时间等进行综合评估,确定最优预测模型。
目标机组参数为超超临界、一次中间再热、四缸四排汽、双背压、凝汽式汽轮机发电机组。其汽水流程如图3所示。
所采集的数据来源于该燃煤机组的生产系统数据库,选择了与锅炉主蒸汽温度密切相关的所有参数。所采的数据集共包含32个参数,其中既有表征汽水侧特征的蒸汽、给水参数,也有表征燃烧侧特征的烟气、风量、给煤量等参数,以及机组负荷等全局参数。模型输入输出参数清单见表1
数据采样频率为5 s一次,采样时间为50天。数据集包含运行状态下的全负荷工况,机组负荷:[340,1 056] MW;主蒸汽温度范围:[574,612] ℃。经过处理后,数据集内的数据量约85万行,将数据集按照深度学习常用的划分比例(4:1),划分为训练集与验证集。
对于原始模型的参数设置:单层LSTM模型,隐含层节点数目为64。
5种复杂模型的参数设置:
1)宽度增加的LSTM模型 LSTM隐含层节点数增加至128。
2)深度增加的LSTM模型 双层LSTM,隐含层节点数均为64。
3)宽度深度均增加的LSTM模型 双层LSTM,隐含层节点数均为128。
4)LSTM结构不变,增加FCNN层 单层LSTM,隐含层节点数为64,FCNN隐含层节点数为32。
5)宽度深度均增加的LSTM并增加FCNN层 双层LSTM,隐含层节点数均为128,FCNN隐含层节点数为32。
所有模型以主蒸汽温度预测值的均方根误差(RMSE)作为损失函数(Loss),同时选取平均百分比误差(MAPE)作为评价指标,优化器采用Adam算法,预测10 s后的主蒸汽温度。
利用PSO、GA算法分别对原始模型进行超参数全局寻优,每次寻优原始模型仅迭代20次即强制结束迭代,根据迭代过程中模型能达到的最小Loss值及收敛速度进行综合评估,在2种优化算法中各确定3组最优超参数,总共6组。最优超参数的结果见表2
后续以这6组最优超参数为基准,原始模型在其附近领域继续寻优,最终保留预测精度最高的3组最优超参数,具体结果见表3
采用全局优化后筛选出的3组最优超参数,适配2.3.1节的5种不同类型的复杂模型,将所有模型一直迭代到收敛为止。最终得到5个预测模型,其预测效果对比见表4图4则更直观地展示了各模型预测精度。由表4图4可见,只增加LSTM模型宽度,预测效果基本无提升。但增加深度后,模型预测效果均有明显提升。继续拓展模型深度,模型也无法进一步收敛,故不再增加模型复杂度。
虽然用多种方式增加模型的深度后,模型预测效果都有所提升,但从表4可以看出,只增加FCNN层的模型的单次训练耗时最短,对应3个超参数组,分别为300、370、160 s,仅相当于同精度的其他模型的60%。综合考虑模型精度和训练耗时,选取LSTM+FCNN的模型为最优预测模型。图5图6分别展示了原始模型与最优预测模型的主蒸汽温度预测效果对比。
图5图6可以看出,对于同类型神经网络(LSTM),原始模型的最优超参数迁移到复杂模型后,复杂模型取得了良好的拟合效果。这就有效节省了复杂模型的超参数寻优时间。以本文的模型为例,原本需要对5类复杂模型分别进行超参数寻优,借助超参数迁移方法,仅需要利用1个原始模型寻优即可,假设各个模型迭代至收敛的时间相同,则可以减少80%的寻优计算量。
再加上原始模型收敛更快,其收敛耗时仅为复杂模型平均收敛耗时的65%。综合评估,主蒸汽温度预测模型的预测值均方根误差可达0.495 ℃,平均百分比误差0.082%,与未采取超参数迁移,直接进行超参数寻优的系统取得了相同精度,但采用超参数迁移后,预测模型的超参数寻优计算量可降低88%以上。若需要迁移的复杂模型数量更多,则可以进一步节约超参数寻优的时间。
国内超超临界锅炉的主蒸汽温度一般采用两级减温水来控制。第一级减温水设置在低温过热器与屏式过热器之间,第二级减温水设置在屏式过热器与高温过热器之间。一级减温水控制对象为屏式过热器出口温度,二级减温水控制对象为高温过热器出口温度。一、二级减温器的控制系统基本一致,其PID控制结构可简化为图7
机组稳态运行情况下,锅炉的各项参数较稳定,原控制回路可维持主蒸汽温度稳定。但在面对机组RB动作、深度调峰等极端工况,原控制回路就难以满足调节要求。主蒸汽温度会出现剧烈波动,锅炉受热面的安全也受到了严重威胁。
为解决极端工况下主蒸汽温度控制难度大的问题,本文采用预测控制来优化控制逻辑,具体方式如下。
1)预测模型实时计算10 s后的主蒸汽温度预测值,并与当前主蒸汽温度实际值求偏差。若偏差值超过阈值,可认为系统即将面临大的扰动,需要及时干预。
2)预测偏差值作为干预的依据。若将偏差值直接输入系统,会对原系统造成过大扰动。因此采用偏差值占主蒸汽温度设定值的百分比,作为优化输入。
3)将百分比偏差值作为PID1的优化偏置,对PID1的输出进行微调。
至此即完成了对原有控制系统的控制优化。优化后的控制逻辑如图8所示。本文将优化偏置的输入设置在PID1输出之后。主要原因是:
1)若将优化偏置放在PID1输入之前,则设定值叠加偏置后,系统会产生一个难以消除的残差,导致控制效果劣化;
2)若将优化偏置放在PID2输出后,因PID2调节对象是高过入口温度,优化偏置在此相当于微调了高过入口温度,对系统的干预作用不如放在主回路PID1的输出之后明显,可防止控制效果劣化。
在MATLAB软件上对优化后的控制系统进行仿真,图9为预测控制系统仿真组态。
图9中的高过入口实际值来自实际机组的高过入口数据,主蒸汽温度预测值则是在预测模型输出的预测值。系统加入人为扰动后,以上2个数值会有变化,因此在扰动发生的区间,对这2个数值也进行了手动修正,以模拟出与实际工况类似的仿真场景。PID参数设置成与实际系统近似。
被控对象的传递函数无法直接获取。根据于静等的实验[32],结合主蒸汽温度受扰动影响的波动曲线以及现场运行人员经验,将传递函数设置为:
GP(s)=num(s)den(s)=250s+1e10s
待系统运行稳定,加入一个20 ℃的大扰动,控制回路优化前后的效果对比如图10所示。优化后的系统对于突发的大扰动抑制作用明显:原系统超调量为3.3%,优化后系统超调量仅为1.5%,超调量有效降低50%。
在仿真过程中,为了抑制超调量,预测控制对原有控制回路介入程度应随扰动增大而放大。经手动调试,发现对于20 ℃的大扰动,3倍的预测偏置量可以将超调量维持在10 ℃以内,满足运行规程要求。但副作用则是正常运行时控制回路稳定性变差。为消除副作用,本文重新设计了分段优化的控制流程,如图11所示。以预测偏差值作为判断条件,当偏差值大于阈值时,提升预测控制的干预力度,以降低超调量;当偏差值小于阈值,由于原有系统控制效果较好,预测控制回路不介入。
对应的仿真组态如图12所示。预测控制可以在预测偏置量大于阈值时,选择3倍的预测输出,在小于阈值时选择减少预测输出。图12中的变量V表示正常工况下的预测输出倍数,可根据实际情况调整。经仿真试验,V数值取0.1,预测输出对系统稳定性影响就接近0。若正常工况下完全不需要预测输出,则可以将V的数值设置为0。
分段优化后,主蒸汽温度控制效果得到明显改善:当突发大扰动的工况下,预测模型及时介入,主蒸汽温度超调量得到有效抑制;正常工况下,主蒸汽温度预测值与实际值偏差小,优化系统可以少量介入或不介入,保持原有控制系统的稳定性,具体效果如图13所示。在超调量降低50%的基础上,主蒸汽温度历经2个振荡周期即恢复稳定。
至此,锅炉主蒸汽温度预测控制系统实现了“异常工况下稳定主蒸汽温度”的既定目标,有效提升主蒸汽温度控制系统应对不稳定工况的能力,降低锅炉超温的风险,提高锅炉受热面的安全性。而工况分段优化策略则保证了系统既可应对极端工况,也可在正常工况下保持稳定。
本文提出的基于超参数迁移建模的主蒸汽温度预测控制系统,可以有效避免预测模型训练时陷入局部最优,同时节约大量寻优时间。预测控制系统效果显著。
1)主蒸汽温度预测模型的预测值均方根误差可达0.495 ℃,平均百分比误差0.082%,与未采取超参数迁移,直接进行超参数寻优的系统取得了相同精度,但超参数寻优计算量减少88%。
2)仿真试验表明,预测控制可满足极端工况的主蒸汽温度调节需求:面对幅度20 ℃的异常扰动,主蒸汽温度超调量较原控制系统降低50%;而多工况分段控制策略则保持了正常工况的控制稳定性,实现在全工况下有效抑制主蒸汽温度超调,降低燃煤锅炉的超温风险,提高燃煤机组的运行安全性。
  • 中央高校基本科研业务费专项资金资助项目(2022ZFJH04)
参考文献 引证文献
排序方式:
[1]
RAY T K, GANGULY R, GUPTA A. Optimal control strategy for minimization of exergy destruction in boiler superheater[J]. Energy Conversion and Management, 2013, 66: 234-245.
[2]
冯旭刚,张泽辰,刘圣晶,. 基于IGPC的火力发电机组主蒸汽温度预测控制策略[J]. 中国电机工程学报202242(9):3307-3317.
FENG Xugang, ZHANG Zechen, LIU Shengjing, et al. Predictive control strategy for main steam temperature of thermal power unit based on IGPC[J]. Proceedings of the CSEE, 2022, 42(9): 3307-3317.
[3]
QIN S J, BADGWELL T A. A survey of industrial model predictive control technology[J]. Control Engineering Practice, 2003, 11(7): 733-764.
[4]
HILL E, NEWTON A, GADSDEN S A. Model predictive control strategies for fault tolerance[D]. Ontario, Canada: University of Guelph, 2021: 1.
[5]
WU X, WANG M, LEE K Y. Flexible operation of supercritical coal-fired power plant integrated with solvent-based CO2 capture through collaborative predictive control[J]. Energy, 2020, 206: 118105.
[6]
鲍鹏凯. 超临界机组中间点汽温预测模型建立与预测控制研究[D]. 北京:华北电力大学,2022:1.
BAO Pengkai. Establishment of intermediate point temperature prediction model and research on predictive control for supercritical units[D]. Beijing: North China Electric Power University, 2022: 1.
[7]
刘吉臻,岳俊红,谭文. 基于多模型集的主汽温多模型预测控制方法[J]. 热能动力工程2008(4):395-398.
LIU Jizhen, YUE Junhong, TAN Wen. Main steam temperature multi-model prediction and control method based on a multi-model set[J]. Journal of Engineering for Thermal Energy and Power, 2008(4): 395-398.
[8]
秦志明. 智能控制算法在主汽温控制中的应用[D]. 保定:华北电力大学,2005:1.
QIN Zhiming. The application of intelligence control algorithm in main steam temperature control system[D]. Baoding: North China Electric Power University, 2005: 1.
[9]
刘新,王辉. 基于模型预测控制的高精度混合视觉伺服机械臂控制方法[J]. 中南大学学报(自然科学版)202556(6):2266-2277.
LIU Xin, WANG Hui. High-precision hybrid visual servoing robotic arm control method based on model predictive control[J]. Journal of Central South University (Science and Technology), 2025, 56(6): 2266-2277.
[10]
方彦军,易凤飞,胡文凯. 基于遗传算法的广义预测PID控制及其在锅炉主汽温系统中的应用[J]. 武汉大学学报(工学版)201346(3):386-392.
FANG Yanjun, YI Fengfei, HU Wenkai. Genetic algorithm-based generalized predictive PID control and its application to main steam temperature control system[J]. Engineering Journal of Wuhan University, 2013, 46(3): 386-392.
[11]
SERGIO L, DENIS N, BENJAMIN K, et al. Deep-learning-based model predictive control for resonant power converters[J]. IEEE Transactions on Industrial Informatics, 2020, 17(1): 1.
[12]
金志远,李胜男,谭鹏,. 基于长短时记忆神经网络的锅炉多参数协同预测模型[J]. 热力发电202150(5):120-126.
JIN Zhiyuan, LI Shengnan, TAN Peng, et al. Multi-parameter collaborative prediction model of boilers based on long-short-term memory neural network[J]. Thermal Power Generation, 2021, 50(5): 120-126.
[13]
张凤南. 基于历史数据的主汽温控制系统建模研究[D]. 北京:华北电力大学,2019:1.
ZHANG Fengnan. Research on modeling of main steam temperature control system based on historical data[D]. Beijing: North China Electric Power University, 2019: 1.
[14]
张悦,吴铮,吕正鑫. 基于神经网络预测的锅炉主汽温模糊控制[C]//中国计算机用户协会仿真应用分会. 2019全国仿真技术学术会议论文集. 河北省发电过程仿真与优化控制技术创新中心(华北电力大学),2019:212-215.
ZHANG Yue, WU Zheng, LYU Zhengxin. Fuzzy control of main steam temperature based on neural network prediction[C]//Proceedings of the 2019 National Conference on Simulation Technology. Simulation Application Branch, China Computer Users Association. Hebei Innovation Center for Simulation & Optimal Control of Power Generation (North China Electric Power University), 2019: 212-215.
[15]
曹鑫炜. 基于深度学习的主汽温预测系统的研究与实现[D]. 北京:华北电力大学,2021:1.
CAO Xinwei. Research and implementation of main steam temperature prediction system based on deep learning[D]. Beijing: North China Electric Power University, 2021: 1.
[16]
周飞燃,曾德良,胡勇. 基于神经网络预测的主蒸汽温度控制方法研究[J]. 热能动力工程202439(10):148-158.
ZHOU Feiran, ZENG Deliang, HU Yong. Research on main steam temperature control method based on neural network prediction[J]. Journal of Engineering for Thermal Energy and Power, 2024, 39(10): 148-158.
[17]
NGUYEN Q, HEIN M. The loss surface of deep and wide neural networks[C]//Proceedings of the 34th International Conference on Machine Learning. Sydney: JMLR, 2017: 2603-26127.
[18]
XIONG C, ZHANG Y, ZHAO L, et al. A neural network transformation based global optimization algorithm[J]. Neural Networks, 2024, 175: 106448.
[19]
KAWAGUCHI K. Elimination of all bad local minima in deep learning[J]. arXiv preprint, 2019, 1901: 00279.
[20]
WANG Y, ZHAO H, LIU Y. Conformal symplectic optimization for stable reinforcement learning[J]. Journal of Machine Learning Research, 2024, 25(123): 1-38.
[21]
STANLEY R, MIIKKULAINEN R. Evolving neural networks through augmenting topologies[J]. Evolutionary Computation, 2002, 10(2): 99-127.
[22]
彭黔荣,罗小华,王磊. 基于混合遗传算法的神经网络全局优化方法[J]. OALib Journal20229(4):1-15.
PENG Qianrong, LUO Xiaohua, WANG Lei. A global optimization method for neural networks based on hybrid genetic algorithm[J]. OALib Journal, 2022, 9(4): 1-15.
[23]
ZHAO H, SUN S, JIN B. Sequential fault diagnosis based on LSTM neural network[J]. IEEE Access, 2018, 6: 12929-12939.
[24]
SONG H, DAI J, LUO L, et al. Power transformer operating state prediction method based on an LSTM network[J]. Energies, 2018, 11(4): 1-15.
[25]
杨新,高旭东,李彦苍,. 基于长短期记忆神经网洛和软投票决策的双流化床气化装置故障诊断模型[J]. 热力发电202049(2):52-57.
YANG Xin, GAO Xudong, LI Yancang, et al. Fault diagnosis model of dual fluidized bed gasification device based on LSTM and voting decision[J]. Thermal Power Generation, 2020, 49(2): 52-57.
[26]
BI X, CHEN D L, CHEN G T, et al. Deepseek LLM: scaling open-source language models with longtermism[J]. arXiv preprint, 2024, 2401: 02954.
[27]
THORNTON C, HUTTER F, HOOS H H, et al. Hyperparameter optimization for long short-term memory networks: a large-scale experiment[C]// Proceedings of the 10th International Conference on Learning Representations. ICLR, 2022: 2110.14778.
[28]
YANG G, HU J E, BABUSCHKIN I, et al. Tensor programs V: tuning large neural networks via zero-shot hyperparameter transfer[J]. arXiv preprint, 2022: 2203. 03466.
[29]
NLLB Team. Scaling neural machine translation to 200 languages[J]. Nature, 2024, 630(8018): 841-846.
[30]
YANG G, SCHOENHOLZ S S. Deep mean field theory: layerwise variance and width variation as methods to control gradient explosion[C]//Proceedings of the 6th International Conference on Learning Representations (ICLR 2018). Vancouver, Canada: OpenReview, 2018: 1.
[31]
DESWAL V, KUMAR D. Hyperparameter tuning of the LSTM model for stock price prediction[J]. International Journal of Intelligent Systems and Applications in Engineering, 2024, 12(4): 705-712.
[32]
于静,金秀章. 基于RBF神经网络的PFC-PID主汽温串级预测控制[J]. 华北电力大学学报(自然科学版)202047(6):91-98.
YU Jing, JIN Xiuzhang. PFC-PID Main steam temperature cascade predictive control based on RBF neural network[J]. Journal of North China Electric Power University (Natural Science Edition), 2020, 47(6): 91-98.
2026年第55卷第5期
PDF下载
216
100
引用本文
BibTeX
文章信息
doi: 10.19666/j.rlfd.202510020
  • 接收时间:2025-10-14
  • 首发时间:2026-08-14
  • 出版时间:2026-05-25
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2025-10-14
  • 修回日期:2025-11-04
  • 录用日期:2025-11-18
基金
Fundamental Research Funds for the Central Universities(2022ZFJH04)
中央高校基本科研业务费专项资金资助项目(2022ZFJH04)
作者信息
    1.浙江大学能源高效清洁利用全国重点实验室,浙江 杭州 310027
    2.浙江浙能台州第二发电有限责任公司,浙江 台州 317108

通讯作者:

杨建国(1973),男,博士,副研究员,主要研究方向为清洁能源、智慧能源,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202510020
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