Article(id=1154428674284704343, tenantId=1146029695717560320, journalId=1146119893612605453, issueId=1154428668001636939, articleNumber=null, orderNo=null, doi=null, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1705248000000, receivedDateStr=2024-01-15, revisedDate=null, revisedDateStr=null, acceptedDate=null, acceptedDateStr=null, onlineDate=1753166844196, onlineDateStr=2025-07-22, pubDate=1734624000000, pubDateStr=2024-12-20, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1753166844196, onlineIssueDateStr=2025-07-22, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1753166844196, creator=13701087609, updateTime=1753166844196, updator=13701087609, issue=Issue{id=1154428668001636939, tenantId=1146029695717560320, journalId=1146119893612605453, year='2024', volume='42', issue='12', pageStart='1563', pageEnd='1704', issueExtLink='null', onlineDate='null', pubDate='null', beforeIssueId=null, nextIssueId=null, price=null, status=1, issueComplete=1, articleOrder=1, issueType=-1, specialIssue=null, createTime=1753166842699, creator=13701087609, updateTime=1753694519077, updator=13701087609, preIssue=null, nextIssue=null, ext={EN=IssueExt(id=1156641903186666331, tenantId=1146029695717560320, journalId=1146119893612605453, issueId=1154428668001636939, language=EN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=), CN=IssueExt(id=1156641903186666332, tenantId=1146029695717560320, journalId=1146119893612605453, issueId=1154428668001636939, language=CN, specialIssueTitle=, coverIllustrator=, specialIssueEditor=, specialIssueAbout=)}, issueFiles=null}, startPage=1627, endPage=1634, ext={EN=ArticleExt(id=1154428675018707545, articleId=1154428674284704343, tenantId=1146029695717560320, journalId=1146119893612605453, language=EN, title=The yaw control strategy optimization based on ultra-short time wind forecast, columnId=null, journalTitle=Renewable Energy Resources, columnName=null, runingTitle=null, highlight=null, articleAbstract=

In order to solve the problem of unified setting of yaw control parameters of wind turbines and the delay of yaw startup of wind operation, a yaw control parameter optimization method based on wind direction fluctuation characteristic evaluation and multiobjective particle swarm optimization algorithm was proposed. The yaw control parameters under different wind speed ranges were optimized by taking the power generation of the unit and the rotation Angle of the engine room under yaw control as optimization objectives. A yaw control strategy optimization method based on VMDEEMD –LSTM –LSSVM wind condition prediction model is proposed. Through predicting the average wind speed in a period of time, the optimized yaw control parameters are set in advance, and through predicting the wind direction, whether yaw starts in advance to the wind action is judged and controlled. The results of example analysis show that this strategy can effectively improve the power generation of wind turbines and reduce the cabin rotation Angle under yaw control, which is beneficial to the economic benefit of wind farms.

, correspAuthors=null, authorNote=null, correspAuthorsNote=null, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=null, magXml=null, pdfUrl=null, pdf=null, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=null, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=Shaoxiong Lu, Yingming Liu, Xiaodong Wang, Mingshun Sun), CN=ArticleExt(id=1154428706945749760, articleId=1154428674284704343, tenantId=1146029695717560320, journalId=1146119893612605453, language=CN, title=基于超短时风况预测的偏航控制策略优化, columnId=null, journalTitle=可再生能源, columnName=null, runingTitle=null, highlight=null, articleAbstract=

为解决风电机组偏航控制参数统一设定与偏航对风动作启动滞后的问题,文章提出了一种基于风向波动特征评估与多目标粒子群算法的偏航控制参数优化方法。以一段时间内机组的发电量与偏航控制下机舱转过角度为优化目标,对不同风速区间下的偏航控制参数进行优化。基于VMDEEMDLSTMLSSVM 风况预测模型的偏航控制策略优化方法,通过对一段时间内平均风速的预测,提前设定优化后的偏航控制参数,通过风向的预测,判断并控制偏航对风动作是否提前启动。算例分析结果表明,该策略可以有效地提高风电机组的发电量,减少偏航控制下的机舱转过角度,有利于提高风电场的经济效益。

, correspAuthors=null, authorNote=null, correspAuthorsNote=
刘颖明(1973-),男,博士,教授,博士生导师,研究方向为风力发电并网技术。E-mail:
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=FLMOaz5EZUOJ30NJZlX8RQ==, magXml=Va+1EmQ7tcbqFHyMzBnfeQ==, pdfUrl=null, pdf=CvdYztmq5K82PaJOZm2mvg==, pdfFileSize=null, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=null, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=6lqWi9kTkFPatE/9/HeDrA==, mapNumber=null, authorCompany=null, fund=null, authors=null, authorsList=卢少雄, 刘颖明, 王晓东, 孙明顺)}, authors=[Author(id=1154428708384396067, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, orderNo=0, 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=1154428708434727717, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, authorId=1154428708384396067, language=EN, stringName=Shaoxiong Lu, firstName=Shaoxiong, middleName=null, lastName=Lu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154428708480865063, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, authorId=1154428708384396067, language=CN, stringName=卢少雄, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=null), Author(id=1154428708531196714, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=13555730215@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154428708581528364, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, authorId=1154428708531196714, language=EN, stringName=Yingming Liu, firstName=Yingming, middleName=null, lastName=Liu, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154428708644442926, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, authorId=1154428708531196714, language=CN, stringName=刘颖明, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=null), Author(id=1154428708703163186, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, 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=1154428708770272053, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, authorId=1154428708703163186, language=EN, stringName=Xiaodong Wang, firstName=Xiaodong, middleName=null, lastName=Wang, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154428708837380918, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, authorId=1154428708703163186, language=CN, stringName=王晓东, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=null), Author(id=1154428708896101176, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, orderNo=3, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=null, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1154428708954821433, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, authorId=1154428708896101176, language=EN, stringName=Mingshun Sun, firstName=Mingshun, middleName=null, lastName=Sun, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1154428709034513211, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, authorId=1154428708896101176, language=CN, stringName=孙明顺, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=null, address=null, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=null)], keywords=[Keyword(id=1154428709407806271, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=EN, orderNo=1, keyword=wind turbine), Keyword(id=1154428709462332224, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=EN, orderNo=2, keyword=wind direction fluctuation characteristic assessment), Keyword(id=1154428709512663873, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=EN, orderNo=3, keyword=multiobjective particle swarm), Keyword(id=1154428709588161346, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=EN, orderNo=4, keyword=wind direction and speed prediction), Keyword(id=1154428709642687300, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=EN, orderNo=5, keyword=yaw control parameter optimization), Keyword(id=1154428709701407559, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=CN, orderNo=1, keyword=风电机组), Keyword(id=1154428709760127816, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=CN, orderNo=2, keyword=风向波动特征评估), Keyword(id=1154428709810459466, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=CN, orderNo=3, keyword=多目标粒子群), Keyword(id=1154428709864985420, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=CN, orderNo=4, keyword=风向与风速预测), Keyword(id=1154428709932094286, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=CN, orderNo=5, keyword=偏航控制参数优化)], refs=[Reference(id=1154428713149125615, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, doi=null, pmid=null, pmcid=null, year=2014, volume=34, issue=29, pageStart=5029, pageEnd=5040, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=薛禹胜, 雷兴, 薛峰, journalName=中国电机工程学报, refType=null, unstructuredReference=薛禹胜, 雷兴, 薛峰, 等. 关于风电不确定性对电力系统影响的评述[J]. 中国电机工程学报, 2014, 34(29): 5029-5040., articleTitle=关于风电不确定性对电力系统影响的评述, refAbstract=null), Reference(id=1154428713199457266, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, doi=null, pmid=null, pmcid=null, year=2019, volume=12, issue=8, pageStart=1508, pageEnd=1531, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=Liu Y, Wang Y, Wang X, journalName=Energies, refType=null, unstructuredReference=Liu Y, Wang Y, Wang X, et al. Active power dispatchfor supporting grid frequency regulation in wind farmsconsideringfatigue load[J]. Energies, 2019, 12(8): 1508-1531., articleTitle=Active power dispatchfor supporting grid frequency regulation in wind farmsconsideringfatigue load, refAbstract=null), Reference(id=1154428713283343347, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, doi=null, pmid=null, pmcid=null, year=2017, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[3], rfOrder=2, authorNames=高峰, 吕跃刚, 郭鹏, journalName=中国专利: CN106286130A, refType=null, unstructuredReference=高峰, 吕跃刚, 郭鹏, 等. 基于 SCADA 数据的风电机组偏航控制参数优化方法[P]. 中国专利: CN106286130A, 2017-01-04., articleTitle=基于 SCADA 数据的风电机组偏航控制参数优化方法, refAbstract=null), Reference(id=1154428713400783862, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, doi=null, pmid=null, pmcid=null, year=2023, volume=126, issue=null, pageStart=107036, pageEnd=null, url=null, language=null, rfNumber=[4], rfOrder=3, authorNames=Han J, Wang X, Yang X, journalName=Engineering Applications of Artificial Intelligence, refType=null, unstructuredReference=Han J, Wang X, Yang X, et al. Yaw system restart strategy optimization of wind turbines in mountain wind farms based on operational data mining and multi objective optimization[J]. Engineering Applications of Artificial Intelligence, 2023, 126: 107036., articleTitle=Yaw system restart strategy optimization of wind turbines in mountain wind farms based on operational data mining and multi objective optimization, refAbstract=null), Reference(id=1154428713484669945, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, doi=null, pmid=null, pmcid=null, year=2017, volume=15, issue=4, pageStart=1720, pageEnd=1728, url=null, language=null, rfNumber=[5], rfOrder=4, authorNames=Song D, Yang J, Liu Y, journalName=International Journal of Control Automation and Systems, refType=null, unstructuredReference=Song D, Yang J, Liu Y, et al. Wind direction prediction for yaw control of wind turbines[J]. International Journal of Control Automation and Systems, 2017, 15(4): 1720-1728., articleTitle=Wind direction prediction for yaw control of wind turbines, refAbstract=null), Reference(id=1154428713564361724, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, doi=null, pmid=null, pmcid=null, year=2021, volume=15, issue=1, pageStart=237, pageEnd=250, url=null, language=null, rfNumber=[6], rfOrder=5, authorNames=Dong X, Wang Y, Wang H, journalName=IET Renewable Power Generation, refType=null, unstructuredReference=Dong X, Wang Y, Wang H, et al. Optimised yaw model for adaptive wind direction characteristic based on a data -driven approach[J]. IET Renewable Power Generation, 2021, 15(1): 237-250., articleTitle=Optimised yaw model for adaptive wind direction characteristic based on a data -driven approach, refAbstract=null), Reference(id=1154428713627276287, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, doi=null, pmid=null, pmcid=null, year=2020, volume=38, issue=4, pageStart=491, pageEnd=496, url=null, language=null, rfNumber=[7], rfOrder=6, authorNames=宋鹏, 柳玉, 郭鹏, journalName=可再生能源, refType=null, unstructuredReference=宋鹏, 柳玉, 郭鹏, 等. 风电机组风向波动概率特性研究[J]. 可再生能源, 2020, 38(4): 491-496., articleTitle=风电机组风向波动概率特性研究, refAbstract=null), Reference(id=1154428713690189824, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, doi=null, pmid=null, pmcid=null, year=2018, volume=129, issue=null, pageStart=168, pageEnd=182, url=null, language=null, rfNumber=[8], rfOrder=7, authorNames=Gugliani GK, Sarkar A, Ley C, journalName=Renewable Energy, refType=null, unstructuredReference=Gugliani GK, Sarkar A, Ley C, et al. Newmethods to assess wind resources in terms of wind speed, load, power and direction[J]. Renewable Energy, 2018, 129: 168-182., articleTitle=Newmethods to assess wind resources in terms of wind speed, load, power and direction, refAbstract=null), Reference(id=1154428713774075906, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, doi=null, pmid=null, pmcid=null, year=2023, volume=31, issue=3, pageStart=1191, pageEnd=1207, url=null, language=null, rfNumber=[9], rfOrder=8, authorNames=Long H, Chen Z, Huang H, journalName=Engineering Letters, refType=null, unstructuredReference=Long H, Chen Z, Huang H, et al. Research on multi -objective optimization power flow of power system based on improved remora optimization algorithm[J]. Engineering Letters, 2023, 31(3): 1191-1207., articleTitle=Research on multi -objective optimization power flow of power system based on improved remora optimization algorithm, refAbstract=null), Reference(id=1154428713853767685, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, doi=null, pmid=null, pmcid=null, year=2018, volume=41, issue=1, pageStart=236, pageEnd=253, url=null, language=null, rfNumber=[10], rfOrder=9, authorNames=王丽萍, 章鸣雷, 邱飞岳, journalName=计算机学报, refType=null, unstructuredReference=王丽萍, 章鸣雷, 邱飞岳, 等. 基于角度惩罚距离精英选择策略的偏好高维目标优化算法[J]. 计算机学报, 2018, 41(1): 236-253., articleTitle=基于角度惩罚距离精英选择策略的偏好高维目标优化算法, refAbstract=null), Reference(id=1154428713916682247, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, doi=null, pmid=null, pmcid=null, year=2023, volume=213, issue=null, pageStart=112716, pageEnd=null, url=null, language=null, rfNumber=[11], rfOrder=10, authorNames=Guo L L, Ya J L, Yue J, journalName=Measurement, refType=null, unstructuredReference=Guo L L, Ya J L, Yue J, et al. Mid-infrared acetone sensor for exhaled gas using fwa-lssvm and empirical mode decomposition algorithm[J]. Measurement, 2023, 213: 112716., articleTitle=Mid-infrared acetone sensor for exhaled gas using fwa-lssvm and empirical mode decomposition algorithm, refAbstract=null)], funds=[Fund(id=1154428713069433831, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, awardId=2021JH1/10400009, language=CN, fundingSource=辽宁省揭榜挂帅科技攻关专项(2021JH1/10400009), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1154428708321481502, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, xref=1, ext=[AuthorCompanyExt(id=1154428708325675807, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, companyId=1154428708321481502, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 School of Electrical Engineering Shenyang University of Technology Shenyang 110870 China), AuthorCompanyExt(id=1154428708329870112, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, companyId=1154428708321481502, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1 沈阳工业大学 电气工程学院 辽宁 沈阳 110870)])], figs=[ArticleFig(id=1154428711697896331, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=EN, label=Fig. 1, caption=Flow chart of multi-objective particle swarm optimization yaw control parameters, figureFileSmall=/bGTMzhxgnTU4LY6qIOQVg==, figureFileBig=+fkRkyxcP8quwQDKUHV6MA==, tableContent=null), ArticleFig(id=1154428711756616590, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=CN, label=图 1, caption=多目标粒子群优化偏航控制参数流程图, figureFileSmall=/bGTMzhxgnTU4LY6qIOQVg==, figureFileBig=+fkRkyxcP8quwQDKUHV6MA==, tableContent=null), ArticleFig(id=1154428711811142545, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=EN, label=Fig. 2, caption=VMD-EEMD-LSTM-LSSVM prediction model schematic diagram, figureFileSmall=Plm02lPWgCssmIrhOQ73Sg==, figureFileBig=48kt2TQw4enG36XYBTtABQ==, tableContent=null), ArticleFig(id=1154428711890834323, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=CN, label=图 2, caption=VMD-EEMD-LSTM-LSSVM 预测模型原理, figureFileSmall=Plm02lPWgCssmIrhOQ73Sg==, figureFileBig=48kt2TQw4enG36XYBTtABQ==, tableContent=null), ArticleFig(id=1154428711945360278, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=EN, label=Fig. 3, caption=Flow chart of yaw control optimization strategy based on wind condition prediction, figureFileSmall=IjD4m3oeujpoGH5gob5XVg==, figureFileBig=bKRaC86mp2OVECw6RTAsBg==, tableContent=null), ArticleFig(id=1154428712012469147, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=CN, label=图 3, caption=基于风况预测的偏航控制优化策略流程图, figureFileSmall=IjD4m3oeujpoGH5gob5XVg==, figureFileBig=bKRaC86mp2OVECw6RTAsBg==, tableContent=null), ArticleFig(id=1154428712066995103, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=EN, label=Fig. 4, caption=DBSCAN and K-Means filter Weibull parameters of wind direction, figureFileSmall=bAZJ1F6r+PiNzNep5SAGpQ==, figureFileBig=ZRFSno3u1RCDg5TU0z2AIQ==, tableContent=null), ArticleFig(id=1154428712125715365, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=CN, label=图 4, caption=DBSCAN 与 K-Means 筛选后的风向 Weibull 参数, figureFileSmall=bAZJ1F6r+PiNzNep5SAGpQ==, figureFileBig=ZRFSno3u1RCDg5TU0z2AIQ==, tableContent=null), ArticleFig(id=1154428712213795754, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=EN, label=Fig. 5, caption=Pareto optimal solution set of yaw control parameters in each wind speed range, figureFileSmall=DKuPdmMR++7x2uTHbdeTbQ==, figureFileBig=SSaS4a4eqPVFKS2rO9eaiA==, tableContent=null), ArticleFig(id=1154428712272516012, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=CN, label=图 5, caption=各风速区间下偏航控制参数的 Pareto 最优解集, figureFileSmall=DKuPdmMR++7x2uTHbdeTbQ==, figureFileBig=SSaS4a4eqPVFKS2rO9eaiA==, tableContent=null), ArticleFig(id=1154428712335430575, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=EN, label=Fig. 6, caption=Yaw control parameter optimization and cabin position comparison before and after yaw early start, figureFileSmall=O2Y7+5BVZ50eSjTqFiH8eQ==, figureFileBig=2iDiWP8DF5+6WxENOAVJ1Q==, tableContent=null), ArticleFig(id=1154428712394150833, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=CN, label=图 6, caption=偏航控制参数优化与偏航提前启动前、后机舱位置对比, figureFileSmall=O2Y7+5BVZ50eSjTqFiH8eQ==, figureFileBig=2iDiWP8DF5+6WxENOAVJ1Q==, tableContent=null), ArticleFig(id=1154428712452871095, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=EN, label=Table 1, caption=The number of wind data in each wind speed interval, figureFileSmall=null, figureFileBig=null, tableContent=
风速/m 数据组数 区间 数据组数
0~3 814 7~9 487
3~5 717 9~11 287
5~7 712 11 以上 346
), ArticleFig(id=1154428712515785660, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=CN, label=表 1, caption=各风速区间的风数据组数, figureFileSmall=null, figureFileBig=null, tableContent=
风速/m 数据组数 区间 数据组数
0~3 814 7~9 487
3~5 717 9~11 287
5~7 712 11 以上 346
), ArticleFig(id=1154428712574505919, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=EN, label=Table 2, caption=Yaw control parameters are optimized for each wind speed range, figureFileSmall=null, figureFileBig=null, tableContent=
风速/m
3~5 15 25
5~7 16 20
7~9 10 15
9~11 8 15
), ArticleFig(id=1154428712641614789, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=CN, label=表 2, caption=各风速区间优化后偏航控制参数, figureFileSmall=null, figureFileBig=null, tableContent=
风速/m
3~5 15 25
5~7 16 20
7~9 10 15
9~11 8 15
), ArticleFig(id=1154428712708723658, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=EN, label=Table 3, caption=Prediction accuracy index of wind speed and wind direction of three forecasting models, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型 单步风速预测指标 12 步风向预测指标
MAE RMSE MAE RMSE
VMD-LSTM 0.23 0.31 0.73 0.85
VMD-EEMD 0.13 0.16 0.54 0.61
VMD-EEMD- LSTM-LSSVM 0.11 0.13 0.31 0.39
), ArticleFig(id=1154428712767443918, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=CN, label=表 3, caption=3 种预测模型风速与风向预测精度指标, figureFileSmall=null, figureFileBig=null, tableContent=
预测模型 单步风速预测指标 12 步风向预测指标
MAE RMSE MAE RMSE
VMD-LSTM 0.23 0.31 0.73 0.85
VMD-EEMD 0.13 0.16 0.54 0.61
VMD-EEMD- LSTM-LSSVM 0.11 0.13 0.31 0.39
), ArticleFig(id=1154428712851330005, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=EN, label=Table 4, caption=Data comparison before and after yaw control strategy optimization, figureFileSmall=null, figureFileBig=null, tableContent=
数据 序号 风速 m/s 参数优化前 发电量 参数优化后 发电量 偏航提前启 动后发电量 参数优化前 机舱转过 角度/(°) 参数优化后 机舱转过 角度/(°) 偏航提前启 动后机舱转 过角度/(°) 参数优化前 偏航启动 次数 参数优化后 偏航启动 次数 偏航提前 启动后偏航 启动次数
1 9~11 762.185 9 770.368 5 776.3625 132.992 5 81.130 0 52.125 0 16 12 9
2 9~11 867.986 4 877.197 9 877.201 3 10.502 5 7.8375 10.2375 2 2 2
3 9~11 685.589 2 694.482 3 697.316 5 93.645 0 86.262 5 46.662 5 9 14 7
4 7~9 675.506 6 681.615 6 686.857 8 5.3150 69.955 0 63.220 0 1 9 10
5 3~5 43.4120 43.296 7 43.583 2 95.420 0 51.235 0 87.930 0 9 3 7
6 5~7 208.250 5 211.004 1 213.872 4 101.235 0 80.475 0 94.9875 6 5 7
7 7~9 432.334 4 436.215 4 439.983 2 0 58.232 5 51.4950 0 9 9
8 5~7 253.718 0 255.168 8 256.003 1 74.880 0 14.675 0 15.2750 8 2 2
), ArticleFig(id=1154428712918438877, tenantId=1146029695717560320, journalId=1146119893612605453, articleId=1154428674284704343, language=CN, label=表 4, caption=偏航控制策略优化前、后数据对比, figureFileSmall=null, figureFileBig=null, tableContent=
数据 序号 风速 m/s 参数优化前 发电量 参数优化后 发电量 偏航提前启 动后发电量 参数优化前 机舱转过 角度/(°) 参数优化后 机舱转过 角度/(°) 偏航提前启 动后机舱转 过角度/(°) 参数优化前 偏航启动 次数 参数优化后 偏航启动 次数 偏航提前 启动后偏航 启动次数
1 9~11 762.185 9 770.368 5 776.3625 132.992 5 81.130 0 52.125 0 16 12 9
2 9~11 867.986 4 877.197 9 877.201 3 10.502 5 7.8375 10.2375 2 2 2
3 9~11 685.589 2 694.482 3 697.316 5 93.645 0 86.262 5 46.662 5 9 14 7
4 7~9 675.506 6 681.615 6 686.857 8 5.3150 69.955 0 63.220 0 1 9 10
5 3~5 43.4120 43.296 7 43.583 2 95.420 0 51.235 0 87.930 0 9 3 7
6 5~7 208.250 5 211.004 1 213.872 4 101.235 0 80.475 0 94.9875 6 5 7
7 7~9 432.334 4 436.215 4 439.983 2 0 58.232 5 51.4950 0 9 9
8 5~7 253.718 0 255.168 8 256.003 1 74.880 0 14.675 0 15.2750 8 2 2
)], attaches=null, journal=Journal(id=1146118781765529606, delFlag=0, nameCn=可再生能源, nameEn=Renewable Energy Resources, nameHistory1=null, nameHistory2=null, issn=1671-5292, eissn=, cn=21-1469/TK, 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=JwZjzvOuLF6gg7XdYa5wzg==, journalPrice=null, startedYear=null, abbrevIsoEn=Renew Energy Res, journalRemark=null, publicationField=null, createdTime=null, updatedTime=1755588886026, createdBy=null, updatedBy=15831073675, firstLetterCn=R, firstLetterEn=R, subjectCode=Engineering, subjectName=工程, subjectCodeEn=Engineering, subjectNameEn=null, picCn=JwZjzvOuLF6gg7XdYa5wzg==, picEn=JbD+CPZ3qeyTMjY1NLqExg==, jcr=null, cjcr=null, exts=[JournalExt(id=1164587454112678277, language=CN, name=可再生能源, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=http://kzsny.com/, createdTime=1755588886049, updatedTime=1755588886049, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=https://ncny.cbpt.cnki.net/EditorEN/PromptPageInfo.aspx?t=v&c=1, submissionAuthorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=1, submissionEditorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=3, submissionReviewUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=2, submissionCeEditorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=3, submissionAeEditorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=3, option={"copyright":""}), JournalExt(id=1164587454167204230, language=EN, name=Renewable Energy Resources, nameHistory1=null, nameHistory2=null, managedBy=, sponsoredBy=, publishedBy=, editorOffice=, officeProv=null, officeCity=null, officeAddr=, officeZip=, editDirector=null, officeDirector=null, officePhone=null, coverPicUrl=null, journalRemark=, submitArticleUrl=null, websiteUrl=, createdTime=1755588886062, updatedTime=1755588886062, createdBy=15831073675, updatedBy=15831073675, submissionGuidelinesUrl=, submissionAuthorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=1, submissionEditorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=3, submissionReviewUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=2, submissionCeEditorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=3, submissionAeEditorUrl=https://ncny.cbpt.cnki.net/EditorEN/index.aspx?t=3, option={"copyright":""})], databaseList=null, tenantJournalId=1146119893612605453, websiteList=[Website(id=1148243202370429360, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146119893612605453, 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/kzsny/CN, language=CN, createTime=1751692112772, createBy=18614031015, updateTime=1753519535151, updateBy=18614031015, name=《可再生能源》-中文站点, tplId=1146099689490845704, title=可再生能源, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1148619523667816493, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202370429360, code=articleTextType, value=kx, createTime=1751781834761, updateTime=1751781834761, creator=18614031015, updator=18614031015), WebsiteProps(id=1148619523642650666, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202370429360, code=banner, value=null, createTime=1751781834755, updateTime=1751781834755, creator=18614031015, updator=18614031015), WebsiteProps(id=1148619523634262057, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202370429360, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=y1rtJt0tFAqUB4W3g4tlSw==, createTime=1751781834753, updateTime=1751781834753, creator=18614031015, updator=18614031015), WebsiteProps(id=1148619523659427884, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202370429360, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1751781834759, updateTime=1751781834759, creator=18614031015, updator=18614031015), WebsiteProps(id=1148619523651039275, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1148243202370429360, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1751781834757, updateTime=1751781834757, creator=18614031015, updator=18614031015)]), Website(id=1155908164001353748, webName=null, webTitle=null, webDomain=null, webCopyrigh=null, webIpcNo=null, seoTitle=null, seoKeywords=null, seoDescription=null, tenantJournalId=null, journalId=1146119893612605453, 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/kzsny/EN, language=EN, createTime=1753519582037, createBy=18614031015, updateTime=1753519582037, updateBy=18614031015, name=《可再生能源》-英文站点, tplId=1146101810881728533, title=Renewable Energy Resources, delFlag=0, indexPage=/home, props=[WebsiteProps(id=1155908456914739359, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155908164001353748, code=articleTextType, value=kx, createTime=1753519651869, updateTime=1753519651869, creator=18614031015, updator=18614031015), WebsiteProps(id=1155908456893767836, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155908164001353748, code=banner, value=null, createTime=1753519651864, updateTime=1753519651864, creator=18614031015, updator=18614031015), WebsiteProps(id=1155908456885379227, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155908164001353748, code=logo, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic?fileId=y1rtJt0tFAqUB4W3g4tlSw==, createTime=1753519651862, updateTime=1753519651862, creator=18614031015, updator=18614031015), WebsiteProps(id=1155908456906350750, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155908164001353748, code=picServerUrl, value=https://castjournals.cast.org.cn/joweb/kjdb/CN/file/pic, createTime=1753519651867, updateTime=1753519651867, creator=18614031015, updator=18614031015), WebsiteProps(id=1155908456902156445, tenantId=1146029695717560320, journalId=null, journalGroupId=null, siteId=1155908164001353748, code=staticResourcePath, value=https://castjournals.cast.org.cn/joweb/cast_kjdb_cn_619/, createTime=1753519651866, updateTime=1753519651866, creator=18614031015, updator=18614031015)])], journalTitle=可再生能源, weixinUrl=null, journalUrl=null, iacademicId=null, status=0, seqNo=null, journalTitleEn=Renewable Energy Resources, journalPhotoCn=JwZjzvOuLF6gg7XdYa5wzg==, journalPhotoEn=JbD+CPZ3qeyTMjY1NLqExg==, 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), detailUrlCn=https://castjournals.cast.org.cn/joweb/kzsny/CN/Y2024/V42/I12/1627, detailUrlEn=https://castjournals.cast.org.cn/joweb/kzsny/EN/Y2024/V42/I12/1627, pdfUrlCn=https://castjournals.cast.org.cn/joweb/kzsny/CN/PDF/Y2024/V42/I12/1627, pdfUrlEn=https://castjournals.cast.org.cn/joweb/kzsny/EN/PDF/Y2024/V42/I12/1627, aliStartDate=null, aliEndDate=null, collectionFlag=false, citedCount=null, citedUrl=null, reference=null)
收藏切换
基于超短时风况预测的偏航控制策略优化
收藏切换
PDF下载
卢少雄 , 刘颖明 , 王晓东 , 孙明顺
可再生能源 | 2024,42(12): 1627-1634
收起
收藏切换
可再生能源 | 2024, 42(12): 1627-1634
基于超短时风况预测的偏航控制策略优化
全屏
卢少雄, 刘颖明 , 王晓东, 孙明顺
作者信息
  • 1 沈阳工业大学 电气工程学院 辽宁 沈阳 110870

通讯作者:

刘颖明(1973-),男,博士,教授,博士生导师,研究方向为风力发电并网技术。E-mail:
The yaw control strategy optimization based on ultra-short time wind forecast
Shaoxiong Lu, Yingming Liu , Xiaodong Wang, Mingshun Sun
Affiliations
  • 1 School of Electrical Engineering Shenyang University of Technology Shenyang 110870 China
出版时间: 2024-12-20
文章导航
收藏切换

为解决风电机组偏航控制参数统一设定与偏航对风动作启动滞后的问题,文章提出了一种基于风向波动特征评估与多目标粒子群算法的偏航控制参数优化方法。以一段时间内机组的发电量与偏航控制下机舱转过角度为优化目标,对不同风速区间下的偏航控制参数进行优化。基于VMDEEMDLSTMLSSVM 风况预测模型的偏航控制策略优化方法,通过对一段时间内平均风速的预测,提前设定优化后的偏航控制参数,通过风向的预测,判断并控制偏航对风动作是否提前启动。算例分析结果表明,该策略可以有效地提高风电机组的发电量,减少偏航控制下的机舱转过角度,有利于提高风电场的经济效益。

风电机组  /  风向波动特征评估  /  多目标粒子群  /  风向与风速预测  /  偏航控制参数优化

In order to solve the problem of unified setting of yaw control parameters of wind turbines and the delay of yaw startup of wind operation, a yaw control parameter optimization method based on wind direction fluctuation characteristic evaluation and multiobjective particle swarm optimization algorithm was proposed. The yaw control parameters under different wind speed ranges were optimized by taking the power generation of the unit and the rotation Angle of the engine room under yaw control as optimization objectives. A yaw control strategy optimization method based on VMDEEMD –LSTM –LSSVM wind condition prediction model is proposed. Through predicting the average wind speed in a period of time, the optimized yaw control parameters are set in advance, and through predicting the wind direction, whether yaw starts in advance to the wind action is judged and controlled. The results of example analysis show that this strategy can effectively improve the power generation of wind turbines and reduce the cabin rotation Angle under yaw control, which is beneficial to the economic benefit of wind farms.

wind turbine  /  wind direction fluctuation characteristic assessment  /  multiobjective particle swarm  /  wind direction and speed prediction  /  yaw control parameter optimization
卢少雄, 刘颖明, 王晓东, 孙明顺. 基于超短时风况预测的偏航控制策略优化. 可再生能源, 2024 , 42 (12) : 1627 -1634 .
Shaoxiong Lu, Yingming Liu, Xiaodong Wang, Mingshun Sun. The yaw control strategy optimization based on ultra-short time wind forecast[J]. Renewable Energy Resources, 2024 , 42 (12) : 1627 -1634 .
风电机组偏航系统的主要功能为控制风轮实现准确对风动作, 有效提高风能利用率, 并在风速低于切入、超出切出风速时,降低偏航频率以减小损耗,从而保证机组的安全运行 [ 1 , 2 ] 。风电场多处于山地、荒漠地区,受不同地形条件影响,同一个风电场内,不同机组所处位置的风况也不尽相同。 因此, 针对每台风电机组在不同风速区间下的偏航参数进行单独优化与设定, 具有重要的实际意义。
近些年,学者对偏航系统控制优化相关问题做了许多研究。文献[ 3 ]根据应用粒细菌群优化算法优化控制参数, 以最大限度地提高发电量。文献 [ 4 ] 提出了一种基于非支配排序遗传算法的偏航参数优化方法, 在发电量损失最小的情况下, 减少偏航次数。以上研究主要侧重于发电量的最大化或偏航次数的最小化问题,旨在将多目标优化转换为单目标优化问题, 在发电量与偏航损耗两个优化目标的平衡上仍有进步空间。
上述研究对偏航控制参数进行了优化, 但并未结合对未来风况的预测, 无法改善偏航启动滞后带来的不利影响, 因此仍具有很大的优化空间。随着预测算法的进一步发展, 文献[ 5 ]提出了一种将自回归移动平均 (ARIMA) 集成到卡尔曼滤波 (KF) 中的混合模型, 用于预测风向优化偏航控制。文献[ 6 ]提出了基于BP 神经网络预测风向并结合历史风向变化概率统计的偏航控制优化策略,有效减小了偏航滞后对发电量的影响。 上述基于预测模型的偏航控制策略主要是针对风向的预测, 实现了提前启动偏航对风动作的目的, 但忽略了对风速的预测, 未结合偏航控制参数的优化, 因此在不同风速区间下的偏航表现也有待提高。
为提高风电机组偏航系统的自适应水平,使其在不同风速区间均有更优的偏航表现, 本文提出了一种基于偏航控制参数优化与超短时风况预测的偏航控制策略。首先,基于 Weibull 分布建立风向波动特征评估模型, 并结合基于密度的聚类算法(DBSCAN)与 K-均值(K-Means)聚类算法完成对 Weibull 分布参数的聚类, 实现对不同风速区间风向波动特征的提取; 然后, 基于多目标粒子群优化算法, 以发电量与机舱转过角度为目标, 对不同风速区间下的偏航控制参数进行优化; 最后, 基于变分模态分解-集合经验模态分解-长短期记忆-最小二乘支持向量机(VMD-EEMD-LSTM-LSSVM)的风况预测模型, 完成对短期风速与风向的精确预测。
通过对风速的预测, 实现机组在未来处于不同风速区间时, 能够提前设定优化后的偏航控制参数。通过对风向的预测, 实现偏航对风动作的提前启动, 减少偏航滞后性带来的不利影响。基于所提出的优化后的偏航控制策略, 可以有效提高风电机组的发电量, 并降低偏航动作时机舱转过角度, 减少偏航机械结构的损耗, 实现风电场降本增效的目标。
风电机组偏航系统的两个主要控制参数为偏航误差角度阈值 ${T}_{\text{angle }}$ 和偏航误差持续时间阈值 ${T}_{\text{time }}$ 。当风轮与来风方向的角度超过设定的 ${T}_{\text{angle }}$ , 且持续时间超过 ${T}_{\text{time }}$ 时,机组开始进行偏航对风动作 [ 7 ] 。本文通过风向波动评估与聚类算法选择符合各风速区间主体风向波动的历史风数据, 基于多目标粒子群算法进行偏航控制参数的优化, 旨在提高机组在各风速区间下的偏航表现, 提高发电量,并减少偏航动作时的机舱转过角度。
风向角度向一侧的持续变化过程被记为一次风向波动,风向变化幅值记为 $A$ ,变化持续时间记为 $T$ ,根据上述对风向波动的定义,可以得到一组二维随机变量(A, T)。
Weibull 分布在描述风资源特性方面表现良好,利用其对 $A, T$ 两个变量进行边缘分布概率密度函数拟合,拟合方法选择最大似然估计法 [ 8 ] ,分别得到 $A$$T$ 的 Weibull 分布参数,以表征风向波动特性。Weibull 分布概率密度函数为
$ f\left( x\right)= \frac{K}{C}{\left(\frac{x}{C}\right)}^{K - 1}{\mathrm{e}}^{{\left(-\frac{x}{C}\right)}^{K}}$
式中: $K$ 为形状参数; $C$ 为尺度参数。
Weibull 分布参数中的 $K$ 主要决定拟合概率密度曲线的形状:当 $K < 1$ 时,曲线呈 “驼峰” 形状; 当 $K > 1$ 时,曲线呈指数分布形状。而 $C$ 决定概率密度曲线的分布情况: 当 $C$ 值越大时,曲线整体越平缓,后端占比越大;当 $C$ 值越小时,曲线整体越陡峭,后端占比越小。
当进行不同风速区间的偏航控制参数优化时, 由于每台风电机组均会时刻记录下海量的风数据, 不可能运用所有的数据进行参数优化, 因此, 须要选择一部分符合各风速区间主体风向波动特征的数据进行偏航参数优化工作。对每组风数据进行风向波动评估后, 得到代表此组数据风向波动特征的 Weibull 风向分布参数, 之后基于两种聚类算法进行风数据的筛选。
首先,采取 ${3\sigma }$ 准则筛除异常点,并筛除处于边界上的点, 这些数据往往是异常数据或是完全不符合此风速区间风向波动特征的数据;然后,基于 DBSCAN 算法对不同风速区间数据的 Weibull 分布参数进行聚类, 筛除密度较小代表与此风速区间风向波动特征差距较大的数据;最后,基于 K-Means 算法对不同风速区间数据的 Weibull 分布参数进行聚类中心的计算, 将最靠近聚类中心的风数据作为代表此风速区间主体风向波动特征的数据。
多目标粒子群算法是为求解多目标优化问题,将传统粒子群算法与 Pareto 排序相结合,通过对比粒子之间的支配关系, 以网格划分与轮盘赌选择来更新粒子的个体最优解与全局最优解, 最终得到 Pareto 最优解集 [ 9 , 10 ]
多目标粒子群算法优化偏航控制参数流程如 图 1 所示。
经优化算法计算后,可以得到各风速区间偏航控制参数的 Pareto 最优解集, 通过对比参数优化前的发电量与机舱转过角度, 在最优解集中选择两者表现更优的参数作为优化后的偏航控制参数。
基于信号分解方法能够有效提取风数据的特征, 提高预测模型的精度, VMD 在此方面表现优异, 然而经 VMD 分解后剩余的残差信息在过去的研究中往往被丢弃, 造成部分信息的丢失。因此利用 EEMD 对残差信息进行进一步的提取, 有助于预测模型精度的提升。
LSTM 网络可以提取长时间序列和短时间序列的复杂特征关系, 在处理时间序列数据方面具有优异的性能。LSSVM 是一种小批量数据建模算法, 将低维空间中的线性不可分问题转入高维空间中解决,具有很好的拟合能力 [ 11 ]
图 2 为 VMD-EEMD-LSTM-LSSVM 预测模型原理图。
整体预测模型建模流程如下:
①确定 VMD 分解子序列的数量 $K$ ,分解得到 $K$ 个子序列与残差;
②将①中分解得的残差数据经 EEMD 分解得到 $N$ 个子序列与残差;
③利用 LSTM 网络对分解得到的每个子序列建模并进行训练与预测;
④利用 LSSVM 网络对③中预测模型训练的误差建模,并进行训练与预测;
⑤将每个子序列经误差修正后的预测结果相加, 得到最终的预测结果。
本文中 ${T}_{\text{angle }}$ 的优化范围为 $\left({{5}^{\circ },{6}^{\circ },{7}^{\circ },\cdots }\right.$ , $\left.{30}^{\circ }\right),{T}_{\text{time }}$ 的优化范围为 $\left({5,{10},{15},\cdots ,{60}\mathrm{\;s}}\right)$ ,偏航控制策略以 ${30}\mathrm{\;{min}}$ 的平均风速作为设置偏航控制参数的依据,以每 $5\mathrm{\;s}$ 的平均风向作为判断偏航是否提前动作的依据。选择平均风向可以起到平滑秒级风向数据小范围、无规律波动的效果,能够有效提高预测模型的精确度与偏航动作判断的准确度。
图 3 为优化后的偏航控制策略流程图。
为验证本文提出的偏航控制参数优化策略的有效性,选取东北某风电场共 ${280}\mathrm{\;d}$ 、采样间隔为 $1\mathrm{\;s}$ 的历史风速与风向数据进行算例分析。
${30}\mathrm{\;{min}}$ 为一组,将 ${280}\mathrm{\;d}$ 的历史风数据共划分为 3 363 组数据, 计算每组数据的平均风速, 共分为 6 个风速区间, 各风速区间的数据组数如 表 1 所示。
当风速处于 $0 \sim 3\mathrm{\;m}/\mathrm{s}$ 时,风电机组未达到切入风速,当风速处于 ${11}\mathrm{\;m}/\mathrm{s}$ 以上时,风电机组功率受偏航系统影响较小, 因此本文不涉及这两个风速区间的偏航参数优化。
首先,采取 ${3\sigma }$ 准则筛除异常点并筛除处于边界上的点, 此类数据属于异常数据或完全不符合各风速区间主体风向波动特征的数据, 应首先筛除;然后,通过 DBSCAN 与 K-Means 聚类方法对风向 Weibull 分布参数的聚类进行选择, 根据 DBSCAN 算法对低密度数据的识别, 筛除各风速区间下的离群数据, 并根据 K-Means 算法计算各风速区间下的 30 个聚类中心,选取 Weibull 参数最接近聚类中心的 30 组数据作为表征本风速区间风向波动特征的风数据, 进行之后的偏航参数优化环节。
各风速区间下经 DBSCAN 与 K-Means 聚类算法进行数据选择之后的风向 Weibull 分布参数如 图 4 所示。
基于多目标粒子群优化算法, 以发电量与机舱转过角度为优化目标, 将 3.2 中选择得到的历史风数据带入风电机组仿真模型中计算适应度值, 得到各风速区间下偏航控制参数的 Pareto 最优解集。为将最大化问题转换为最小化问题, 横坐标取发电量的倒数, 各风速区间优化后得到的 Pareto 最优解集如 图 5 所示。
在偏航控制参数未优化之前, ${T}_{\text{angle }}$${T}_{\text{time }}$ 统一设定为 $\left\lbrack {{10}^{\circ },{20}\mathrm{\;s}}\right\rbrack$ ,优化后得到 Pareto 最优解集。若出现多个发电量与机舱转过角度表现均优于优化前的解,当风速为 $3 \sim 5\mathrm{\;m}/\mathrm{s}$$5 \sim 7\mathrm{\;m}/\mathrm{s}$ 时, 更多偏航动作对发电量的提高较小, 因此选择机舱转过角度更小的解;当风速为 $7 \sim 9\mathrm{\;m}/\mathrm{s}$$9 \sim {11}$ $\mathrm{m}/\mathrm{s}$ 时,更多的偏航动作对发电量的提高较大,因此选择发电量更多的解。
各风速区间经优化后的偏航控制参数如 表 2 所示。
选取共 ${40}\mathrm{\;h}$ 的历史风速与风向数据,训练集与测试集按 9:1 划分, 分别采用 VMD-LSTM, VME-EEMD-LSTM, VMD-EEMD-LSTM-LSSVM 3 种预测模型对风速与风向进行预测, 验证在预测模型中加入 EEMD 残差分解与 LSSVM 误差修正环节是否能够有效提高预测模型的精度。预测精度验证指标选用平均绝对误差(MAE)与均方根误差(RMSE)。
${30}\mathrm{\;{min}}$ 平均风速预测中,共 80 个数据,以前 72 个数据训练集, 后 8 个数据作为测试集。在 12 步 5 s 平均风向预测中,共 28800 个数据,以前 25920 个数据作为训练集, 后 2880 个数据作为测试集。 表 3 为各模型的预测精度指标。
表 3 可知, VMD-EEMD-LSTM-LSSVM 预测模型可以更为精确地预测单步平均风速与多步平均风向。VMD-EEMD-LSTM-LSSVM 预测模型可以为偏航控制策略的优化提供可靠的预测数据。
前文中的测试集为 $4\mathrm{\;h}$ 的历史风数据,即 8 组 ${30}\mathrm{\;{min}}$ 的数据,通过 MATLAB/Simulink 风电机组仿真模型验证本文所提出的偏航控制策略的有效性。 图 6 为偏航控制参数优化前、提前设置优化后的偏航控制参数、偏航控制参数优化后且提前启动偏航的机舱位置对比图。
偏航控制策略优化前、后各项数据如 表 4 所示。由 表 4 可知:在进行参数优化且提前启动偏航后, 8 组数据整体发电量相较于仅进行参数优化时提高了 ${21.8307}\mathrm{\;{kW}}\cdot \mathrm{h}$ ,机舱转过角度减少了 ${27.8700}^{\circ }$ ; 相较于参数优化前,发电量提高了 ${62.1970}\mathrm{\;{kW}}\cdot \mathrm{h}$ ,机舱转过角度减少了 ${92.0575}^{\circ }$ ; 仅进行参数优化时, 发电量较参数未优化时提高了 1.03%,机舱转过角度减少了 12.49%;加入风向预测, 提前启动偏航后较参数未优化时, 发电量提高了 1.58%,机舱转过角度减少了 17.91%。
由算例分析的结果可知, 本文提出的偏航控制优化策略能够有效地提高各风速区间下风电机组的发电量并减少偏航控制下的机舱转过角度, 降低了对偏航机构的损耗, 实现了降本增效, 对风电场经济效益的提高具有实际意义。
本文对风电机组偏航控制策略的优化问题进行了深入研究, 提出了基于风向波动评估与多目标粒子群优化算法的偏航控制参数优化方法结合 VMD-EEMD-LSTM-LSSVM 预测模型的偏航控制优化策略, 运用预测的风速与风向数据提前设定优化后的偏航控制参数, 并判断是否提前启动偏航对风动作,经过算例分析,得到以下结论。
①基于 Weibull 分布的风向波动评估模型能够有效描述风数据的风向波动特征, 结合 DB-SCAN 与 K-Means 聚类算法能够得到准确描述不同风速区间主体风向波动特征的多组风数据。
②基于多目标粒子群优化算法的偏航控制参数优化方法, 能够得到各风速区间下偏航表现均优于未优化前的偏航控制参数。在算例分析中, 整体偏航次数增加了 2 次, 但是机舱转过角度明显减少,表明相较于偏航次数作为优化目标,机舱转过角度更能代表偏航系统结构的损耗量。
③相较于单分解与未加入误差修正的预测模型,基于 VMD-EEMD-LSTM-LSSVM 的风况预测模型能够更为准确地预测单步平均风速与多步平均风向数据。使用优化的偏航控制策略后,多组数据的整体发电量得到了提高, 且机舱转过角度得到了降低。
  • 辽宁省揭榜挂帅科技攻关专项(2021JH1/10400009)
参考文献 引证文献
排序方式:
[1]
薛禹胜, 雷兴, 薛峰, 等. 关于风电不确定性对电力系统影响的评述[J]. 中国电机工程学报, 2014, 34(29): 5029-5040.
[2]
Liu Y, Wang Y, Wang X, et al. Active power dispatchfor supporting grid frequency regulation in wind farmsconsideringfatigue load[J]. Energies, 2019, 12(8): 1508-1531.
[3]
高峰, 吕跃刚, 郭鹏, 等. 基于 SCADA 数据的风电机组偏航控制参数优化方法[P]. 中国专利: CN106286130A, 2017-01-04.
[4]
Han J, Wang X, Yang X, et al. Yaw system restart strategy optimization of wind turbines in mountain wind farms based on operational data mining and multi objective optimization[J]. Engineering Applications of Artificial Intelligence, 2023, 126: 107036.
[5]
Song D, Yang J, Liu Y, et al. Wind direction prediction for yaw control of wind turbines[J]. International Journal of Control Automation and Systems, 2017, 15(4): 1720-1728.
[6]
Dong X, Wang Y, Wang H, et al. Optimised yaw model for adaptive wind direction characteristic based on a data -driven approach[J]. IET Renewable Power Generation, 2021, 15(1): 237-250.
[7]
宋鹏, 柳玉, 郭鹏, 等. 风电机组风向波动概率特性研究[J]. 可再生能源, 2020, 38(4): 491-496.
[8]
Gugliani GK, Sarkar A, Ley C, et al. Newmethods to assess wind resources in terms of wind speed, load, power and direction[J]. Renewable Energy, 2018, 129: 168-182.
[9]
Long H, Chen Z, Huang H, et al. Research on multi -objective optimization power flow of power system based on improved remora optimization algorithm[J]. Engineering Letters, 2023, 31(3): 1191-1207.
[10]
王丽萍, 章鸣雷, 邱飞岳, 等. 基于角度惩罚距离精英选择策略的偏好高维目标优化算法[J]. 计算机学报, 2018, 41(1): 236-253.
[11]
Guo L L, Ya J L, Yue J, et al. Mid-infrared acetone sensor for exhaled gas using fwa-lssvm and empirical mode decomposition algorithm[J]. Measurement, 2023, 213: 112716.
2024年第42卷第12期
PDF下载
265
160
引用本文
BibTeX
文章信息
  • 接收时间:2024-01-15
  • 首发时间:2025-07-22
  • 出版时间:2024-12-20
补充材料
相关文章
文章信息
作者
出版历史
  • 收稿日期:2024-01-15
基金
辽宁省揭榜挂帅科技攻关专项(2021JH1/10400009)
作者信息
    1 沈阳工业大学 电气工程学院 辽宁 沈阳 110870

通讯作者:

刘颖明(1973-),男,博士,教授,博士生导师,研究方向为风力发电并网技术。E-mail:
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/kzsny/CN/1154428674284704343
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