Article(id=1295068070586904837, tenantId=1146029695717560320, journalId=1210938733613449225, issueId=1295068070071005445, articleNumber=null, orderNo=null, doi=10.19666/j.rlfd.202510030, pmid=null, cstr=null, oa=null, hot=null, price=null, onlineType=0, articleFormat=0, articleType=null, articleTypeStr=null, receivedDate=1760457600000, receivedDateStr=2025-10-15, revisedDate=1766937600000, revisedDateStr=2025-12-29, acceptedDate=1767542400000, acceptedDateStr=2026-01-05, onlineDate=1786697889229, onlineDateStr=2026-08-14, pubDate=1779638400000, pubDateStr=2026-05-25, doiRegisterDate=null, doiRegisterDateStr=null, onlineIssueDate=1786697889229, onlineIssueDateStr=2026-08-14, onlineJustAcceptDate=null, onlineJustAcceptDateStr=null, onlineFirstDate=null, onlineFirstDateStr=null, sourceXml=null, magXml=null, createTime=1786697889229, creator=13701087609, updateTime=1786697889229, 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=21, endPage=32, ext={EN=ArticleExt(id=1295068070838563079, articleId=1295068070586904837, tenantId=1146029695717560320, journalId=1210938733613449225, language=EN, title=Selection and estimation of multi-point feature wind speeds for large-scale wind turbines, columnId=1295068070763065606, journalTitle=Thermal Power Generation, columnName=Energy storage and renewable energy technology, runingTitle=null, highlight=null, articleAbstract=
[Objective]

With the continuous development of the wind power industry toward high power and large capacity, the soaring unit capacity and expanding blade radius of large-scale wind turbines have resulted in increasingly complex spatial distributions of the inflow wind field in front of the turbine and significantly enhanced vertical wind shear effects. The conventional method of characterizing wind conditions using single-point wind speed at hub height can no longer fully reflect the wind speed distribution differences and dynamic patterns within the ultra-large rotor swept area, which is prone to causing issues such as wind power prediction deviations and inadequate adaptability of operation control strategies. To address these challenges, this study proposes a multi-point feature wind speed selection and estimation method for large-scale wind turbines, which can accurately capture key wind speed information in the rotor swept area, overcome the limitations of single-point feature wind speed, and provide data support for the optimal operation of wind turbines.

[Methods]

To achieve the aforementioned research objective, this study adopts a step-by-step technical approach for systematic investigation. Firstly, based on high-precision grid data of the inflow wind field in front of the turbine, a two-stage stepwise feature selection algorithm is proposed, which first carries out preliminary selection with random forest and then implements refined selection via Boruta (RF-Boruta). The Boruta algorithm is employed to conduct significance tests on the feature importance scores output by the random forest model, thereby eliminating redundant and irrelevant wind speed grid points and realizing stable and accurate selection of feature wind speed points within the ultra-large rotor swept area. Secondly, for the selected feature wind speed points, the extended long short-term memory neural network (xLSTM-Mixer) algorithm is introduced, combined with an embedded feature engineering strategy that accounts for input-output delay orders. This strategy fully exploits the temporal correlation and spatial correlation of wind speed sequences, and constructs a unit dynamics-driven ultra-short-term multi-step dynamic estimation model for multi-point feature wind speed points. Finally, to verify the effectiveness and superiority of the proposed method, large eddy simulation (LES) of a 10 MW wind turbine is performed on the SOWFA platform. Meanwhile, 7 typical wind conditions covering the full wind speed range specified in the IEC standards (including complex wind conditions such as shear wind and turbulent wind) are configured for numerical simulation and flow field data collection. The feature selection performance and speed estimation accuracy of the proposed method are comprehensively validated based on the collected high-fidelity data.

[Results]

The numerical simulation and verification results demonstrate that four representative feature wind speed points, including the hub center, are identified via the RF-Boruta stepwise algorithm. These feature points are arranged at a radius of 50~60 m with an angular interval of 120°, which can effectively cover the key regions of the rotor swept area and fully characterize the spatial distribution features of the inflow wind field. The constructed xLSTM-Mixer model exhibits excellent performance in the multi-point feature wind speed estimation task: the relative error of 80-step-ahead (second-level) prediction for multi-point wind speeds is ≤2.8%, achieving second-level high-precision estimation. Statistical characteristic analysis shows that the Kolmogorov-Smirnov (KS) statistic between the model estimation results and the actual wind speed data is ≤0.2, and the structural similarity index (SSIM) is ≥0.96, indicating a high degree of consistency in both distribution characteristics and structural features between the two datasets. Comparative experiments with mainstream time-series prediction models such as the conventional LSTM and Transformer reveal that the estimation accuracy of the xLSTM-Mixer model is improved by approximately 10%, with distinct advantages in wind speed distribution matching and spatial structure capture capabilities.

[Conclusion]

The multi-point feature wind speed selection and estimation method proposed in this study effectively breaks through the limitations of conventional single-point feature wind speed, realizing accurate selection and efficient estimation of key wind speed information within the ultra-large rotor swept area. The high-precision multi-point wind speed data provided by this method can reliably support wind power prediction, operation control optimization, and power generation evaluation of wind turbines, helping to enhance the operational stability and energy utilization efficiency of wind turbines. It holds important theoretical significance and engineering application value for promoting the high-quality development of the wind power industry.

, authors=Shanshan SHEN1, 2, Yang HU1, 2, Jiheng WANG1, 2, Ziqiu SONG1, 2, authorsList=Shanshan SHEN, Yang HU, Jiheng WANG, Ziqiu SONG, authorCompany=null, correspAuthors=Yang HU, 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=1295068073938153749, articleId=1295068070586904837, tenantId=1146029695717560320, journalId=1210938733613449225, language=CN, title=大型风电机组多点特征风速选择及估计, columnId=1295068072533061896, journalTitle=热力发电, columnName=储能与可再生能源技术, runingTitle=null, highlight=null, articleAbstract=
【目的】

针对大型风电机组容量增大、机组叶片半径急剧增加、机前入流风速场分布及垂直风切变效应更为复杂,轮毂高度处单点有效风速难以充分表征入流风况的问题,提出了一种大型风电机组多点特征风速选择及估计方法。

【方法】

首先,基于机前入流风速场网格数据,提出随机森林结合Boruta(RF-Boruta)分步算法,实现超大风轮扫掠面内特征风速格点的稳定筛选;然后,引入混合多变量长短时记忆(xLSTM-Mixer)神经网络算法,结合计及输入-输出延迟阶次的嵌入式特征工程策略,构建机组动力学特性驱动的多点特征风速超短期多步动态估计模型;最后,在SOWFA平台完成10 MW风电机组大涡模拟及IEC标准下全风速范围内7种风况的数值仿真与流场数据采集,对所提方法进行验证。

【结果】

结果表明:筛选得到含轮毂中心在内的4个代表性特征风速点(半径50~60 m、120°角度间隔布置),xLSTM-Mixer模型对多点风速的当前时刻滤波及未来80步超前预测相对误差均≤2.8%,实现秒级高精度估计,科尔莫戈罗夫-斯米尔诺夫(KS)统计量≤0.2,结构相似性指数(SSIM)≥0.96,相较于传统LSTM、Transformer模型,精确度提升约10%,且在分布匹配与结构捕捉能力上优势显著。

【结论】

该方法突破了单点风速表征的局限性,为风功率预测、机组运行控制及发电量评估提供了可靠技术支撑。

, authors=申珊珊1, 2, 胡阳1, 2, 王继恒1, 2, 宋子秋1, 2, authorsList=申珊珊, 胡阳, 王继恒, 宋子秋, authorCompany=null, correspAuthors=胡阳, authorNote=

申珊珊(1998),女,硕士,主要研究方向为风力发电过程建模及控制等,

, correspAuthorsNote=
胡阳(1986),男,博士,副教授,主要研究方向为新能源发电建模及控制等,
, copyrightStatement=null, copyrightOwner=null, extLink=null, articleAbsUrl=null, sourceXml=VQ12s3NtZ9EjrbztmPHb3Q==, magXml=g3JEJce/MPFSasVwsELUxA==, pdfUrl=null, pdf=YVn5O5W6ydScHnjuC0OmmQ==, pdfFileSize=1899063, pdfExtLink=null, richHtmlUrl=null, mobilePdfUrl=null, reviewReport=null, pdfFirstPage=null, abstractGraph=9P0jjWusklHvmVwBDV4WMg==, abstractGraphContent=null, abstractVideo=null, citation=null, cebUrl=null, magXmlContent=tzp+4Rg+NBy9hDFfF6C0Rg==, mapNumber=null, fund=null)}, authors=[Author(id=1295068074328224029, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=18831831705@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1295068074424693024, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068074328224029, language=EN, stringName=Shanshan SHEN, firstName=Shanshan, middleName=null, lastName=SHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China
2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068074504384801, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068074328224029, language=CN, stringName=申珊珊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206
2.华北电力大学控制与计算机工程学院,北京 102206, bio={"content":"

申珊珊(1998),女,硕士,主要研究方向为风力发电过程建模及控制等,

"}, bioImg=null, bioContent=

申珊珊(1998),女,硕士,主要研究方向为风力发电过程建模及控制等,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068074160451862, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=1., ext=[AuthorCompanyExt(id=1295068074168840471, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074177229080, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206)]), AuthorCompany(id=1295068074248532249, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=2., ext=[AuthorCompanyExt(id=1295068074256920858, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074265309467, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.华北电力大学控制与计算机工程学院,北京 102206)])]), Author(id=1295068074575687971, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hooyoung@ncepu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1295068074667962662, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068074575687971, language=EN, stringName=Yang HU, firstName=Yang, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China
2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068074756043047, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068074575687971, language=CN, stringName=胡阳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206
2.华北电力大学控制与计算机工程学院,北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068074160451862, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=1., ext=[AuthorCompanyExt(id=1295068074168840471, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074177229080, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206)]), AuthorCompany(id=1295068074248532249, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=2., ext=[AuthorCompanyExt(id=1295068074256920858, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074265309467, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.华北电力大学控制与计算机工程学院,北京 102206)])]), Author(id=1295068074814763305, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, 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=1295068074877677868, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068074814763305, language=EN, stringName=Jiheng WANG, firstName=Jiheng, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China
2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068074948981037, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068074814763305, language=CN, stringName=王继恒, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206
2.华北电力大学控制与计算机工程学院,北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068074160451862, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=1., ext=[AuthorCompanyExt(id=1295068074168840471, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074177229080, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206)]), AuthorCompany(id=1295068074248532249, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=2., ext=[AuthorCompanyExt(id=1295068074256920858, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074265309467, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.华北电力大学控制与计算机工程学院,北京 102206)])]), Author(id=1295068075028672815, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, 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=1295068075091587378, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068075028672815, language=EN, stringName=Ziqiu SONG, firstName=Ziqiu, middleName=null, lastName=SONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China
2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068075162890547, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068075028672815, language=CN, stringName=宋子秋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206
2.华北电力大学控制与计算机工程学院,北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068074160451862, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=1., ext=[AuthorCompanyExt(id=1295068074168840471, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074177229080, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206)]), AuthorCompany(id=1295068074248532249, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=2., ext=[AuthorCompanyExt(id=1295068074256920858, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074265309467, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.华北电力大学控制与计算机工程学院,北京 102206)])])], keywords=[Keyword(id=1295068075271942452, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=EN, orderNo=1, keyword=wind power generation), Keyword(id=1295068075339051317, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=EN, orderNo=2, keyword=spatiotemporal feature selection), Keyword(id=1295068077033550134, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=EN, orderNo=3, keyword=xLSTM-Mixer neural network), Keyword(id=1295068077092270391, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=EN, orderNo=4, keyword=multi-step time series dynamic estimation), Keyword(id=1295068077180350776, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=CN, orderNo=1, keyword=风力发电), Keyword(id=1295068077251653945, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=CN, orderNo=2, keyword=时空特征选择), Keyword(id=1295068077335540026, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=CN, orderNo=3, keyword=xLSTM-Mixer神经网络), Keyword(id=1295068077402648891, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=CN, orderNo=4, keyword=多步时间序列动态估计)], refs=[Reference(id=1295068079218782544, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2007, volume=75, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[1], rfOrder=0, authorNames=ØSTERGAARD K Z, BRATH P, STOUSTRUP J, journalName=Journal of Physics: Conference Series, refType=null, unstructuredReference=ØSTERGAARD K Z, BRATH P, STOUSTRUP J. Estimation of effective wind speed[J]. Journal of Physics: Conference Series, 2007, 75: 012082., articleTitle=Estimation of effective wind speed, refAbstract=null), Reference(id=1295068079285891409, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=7, pageStart=9, pageEnd=16, url=null, language=null, rfNumber=[2], rfOrder=1, authorNames=李颖峰, 许瑾, 刘美岑, journalName=热力发电, refType=null, unstructuredReference=李颖峰,许瑾,刘美岑,. 基于机舱激光雷达的风力机增益预置前馈控制方法研究[J]. 热力发电202251(7):9-16., articleTitle=基于机舱激光雷达的风力机增益预置前馈控制方法研究, refAbstract=null), Reference(id=1295068079361388882, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=7, pageStart=9, pageEnd=16, url=null, language=null, rfNumber=[2], rfOrder=2, authorNames=LI Yingfeng, XU Jin, LIU Meicen, journalName=Thermal Power Generation, refType=null, unstructuredReference=LI Yingfeng, XU Jin, LIU Meicen, et al. Research on gain scheduled feedforward control method of wind turbine based on nacelle LIDAR[J]. Thermal Power Generation, 2022, 51(7): 9-16., articleTitle=Research on gain scheduled feedforward control method of wind turbine based on nacelle LIDAR, refAbstract=null), Reference(id=1295068079436886355, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2025, volume=46, issue=8, pageStart=78, pageEnd=83, url=null, language=null, rfNumber=[3], rfOrder=3, authorNames=牛洪涛, 杨从新, 刘文杰, journalName=太阳能学报, refType=null, unstructuredReference=牛洪涛,杨从新,刘文杰. 来流风剪切及其对风力机性能影响的实验研究[J]. 太阳能学报202546(8):78-83., articleTitle=来流风剪切及其对风力机性能影响的实验研究, refAbstract=null), Reference(id=1295068079508189524, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2025, volume=46, issue=8, pageStart=78, pageEnd=83, url=null, language=null, rfNumber=[3], rfOrder=4, authorNames=NIU Hongtao, YANG Congxin, LIU Wenjie, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=NIU Hongtao, YANG Congxin, LIU Wenjie. Experimental study of incoming flow shear and its influence on performance of wind turbine[J]. Acta Energiae Solaris Sinica, 2025, 46(8): 78-83., articleTitle=Experimental study of incoming flow shear and its influence on performance of wind turbine, refAbstract=null), Reference(id=1295068079579492693, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2013, volume=6, issue=12, pageStart=6352, pageEnd=6372, url=null, language=null, rfNumber=[4], rfOrder=5, authorNames=TAN J, HU W H, WANG X R, journalName=Energies, refType=null, unstructuredReference=TAN J, HU W H, WANG X R, et al. Effect of tower shadow and wind shear in a wind farm on AC tie-line power oscillations of interconnected power systems[J]. Energies, 2013, 6(12): 6352-6372., articleTitle=Effect of tower shadow and wind shear in a wind farm on AC tie-line power oscillations of interconnected power systems, refAbstract=null), Reference(id=1295068079650795862, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2006, volume=47, issue=18/19, pageStart=2846, pageEnd=2858, url=null, language=null, rfNumber=[5], rfOrder=6, authorNames=CAMBLONG H, MARTINEZ DE ALEGRIA I, RODRIGUEZ M, journalName=Energy Conversion and Management, refType=null, unstructuredReference=CAMBLONG H, MARTINEZ DE ALEGRIA I, RODRIGUEZ M, et al. Experimental evaluation of wind turbines maximum power point tracking controllers[J]. Energy Conversion and Management, 2006, 47(18/19): 2846-2858., articleTitle=Experimental evaluation of wind turbines maximum power point tracking controllers, refAbstract=null), Reference(id=1295068079730487639, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2022, volume=null, issue=null, pageStart=5, pageEnd=null, url=null, language=null, rfNumber=[6], rfOrder=7, authorNames=null, journalName=null, refType=null, unstructuredReference=Wind energy generation systems: Part 12-1: Power performance measurements of electricity producing wind turbines: IEC 61400-12-1: 2022, Edition 3.0[S]. Geneva, Switzerland: International Electrotechnical Commission, 2022: 5., articleTitle=null, refAbstract=null), Reference(id=1295068079805985112, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=3, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=8, authorNames=null, journalName=null, refType=null, unstructuredReference=风力发电机组功率特性测试:GB/T 18451.2—2021[S]. 北京:中国标准出版社,2021:3., articleTitle=null, refAbstract=null), Reference(id=1295068081487901017, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=null, pageStart=3, pageEnd=null, url=null, language=null, rfNumber=[7], rfOrder=9, authorNames=null, journalName=null, refType=null, unstructuredReference=Wind turbines: power performance testing of electricity producing wind turbines: GB/T 18451.2 — 2021[S]. Beijing: China Standards Press, 2021: 3., articleTitle=null, refAbstract=null), Reference(id=1295068081571787098, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=2, pageStart=415, pageEnd=423, url=null, language=null, rfNumber=[8], rfOrder=10, authorNames=陈文婷, 张铂炅, 林勇刚, journalName=太阳能学报, refType=null, unstructuredReference=陈文婷,张铂炅,林勇刚,. 基于激光雷达的风力机分离测风独立变桨控制策略[J]. 太阳能学报202243(2):415-423., articleTitle=基于激光雷达的风力机分离测风独立变桨控制策略, refAbstract=null), Reference(id=1295068081659867483, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=2, pageStart=415, pageEnd=423, url=null, language=null, rfNumber=[8], rfOrder=11, authorNames=CHEN Wenting, ZHANG Bojiong, LIN Yonggang, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=CHEN Wenting, ZHANG Bojiong, LIN Yonggang, et al. Separated wind measurement individual pitch control of wind turbine based on lidar[J]. Acta Energiae Solaris Sinica, 2022, 43(2): 415-423., articleTitle=Separated wind measurement individual pitch control of wind turbine based on lidar, refAbstract=null), Reference(id=1295068081743753564, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=2, pageStart=63, pageEnd=67, url=null, language=null, rfNumber=[9], rfOrder=12, authorNames=李颖, 雷熠, 莫尔兵, journalName=东方汽轮机, refType=null, unstructuredReference=李颖,雷熠,莫尔兵,. 风力发电机组机舱式激光测风雷达可用性评价[J]. 东方汽轮机2021(2):63-67., articleTitle=风力发电机组机舱式激光测风雷达可用性评价, refAbstract=null), Reference(id=1295068081836028253, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2021, volume=null, issue=2, pageStart=63, pageEnd=67, url=null, language=null, rfNumber=[9], rfOrder=13, authorNames=LI Ying, LEI Yi, MO Erbing, journalName=Dongfang Turbine, refType=null, unstructuredReference=LI Ying, LEI Yi, MO Erbing, et al. Availability of LIDAR used in wind turbine[J]. Dongfang Turbine, 2021(2): 63-67., articleTitle=Availability of LIDAR used in wind turbine, refAbstract=null), Reference(id=1295068081919914334, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2014, volume=555, issue=null, pageStart=12011, pageEnd=null, url=null, language=null, rfNumber=[10], rfOrder=14, authorNames=BOSSANYI E A, KUMAR A, HUGUES S O, journalName=Journal of Physics: Conference Series, refType=null, unstructuredReference=BOSSANYI E A, KUMAR A, HUGUES S O. Wind turbine control applications of turbine-mounted LIDAR[J]. Journal of Physics: Conference Series, 2014, 555: 12011., articleTitle=Wind turbine control applications of turbine-mounted LIDAR, refAbstract=null), Reference(id=1295068081987023199, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=9, pageStart=5, pageEnd=7, url=null, language=null, rfNumber=[11], rfOrder=15, authorNames=迟林, 刘智超, 姜禹含, journalName=电力系统装备, refType=null, unstructuredReference=迟林,刘智超,姜禹含,. 机舱式激光雷达在风电后市场领域的应用[J]. 电力系统装备2023(9):5-7., articleTitle=机舱式激光雷达在风电后市场领域的应用, refAbstract=null), Reference(id=1295068082054132064, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2023, volume=null, issue=9, pageStart=5, pageEnd=7, url=null, language=null, rfNumber=[11], rfOrder=16, authorNames=CHI Lin, LIU Zhichao, JIANG Yuhan, journalName=Electric Power System Equipment, refType=null, unstructuredReference=CHI Lin, LIU Zhichao, JIANG Yuhan, et al. Application of cabin lidar in the wind power aftermarket[J]. Electric Power System Equipment, 2023(9): 5-7., articleTitle=Application of cabin lidar in the wind power aftermarket, refAbstract=null), Reference(id=1295068082133823841, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2025, volume=45, issue=4, pageStart=544, pageEnd=581, url=null, language=null, rfNumber=[12], rfOrder=17, authorNames=曲晨志, 林忠伟, 刘吉臻, journalName=动力工程学报, refType=null, unstructuredReference=曲晨志,林忠伟,刘吉臻,. 多源数据驱动的风电机组偏航稳态误差校准方法及现场应用测试[J]. 动力工程学报202545(4):544-581., articleTitle=多源数据驱动的风电机组偏航稳态误差校准方法及现场应用测试, refAbstract=null), Reference(id=1295068082209321314, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2025, volume=45, issue=4, pageStart=544, pageEnd=581, url=null, language=null, rfNumber=[12], rfOrder=18, authorNames=QU Chenzhi, LIN Zhongwei, LIU Jizhen, journalName=Journal of Chinese Society of Power Engineering, refType=null, unstructuredReference=QU Chenzhi, LIN Zhongwei, LIU Jizhen, et al. Multi-source data-driven yaw steady-state error calibration method for wind turbines and field application testing[J]. Journal of Chinese Society of Power Engineering, 2025, 45(4): 544-581., articleTitle=Multi-source data-driven yaw steady-state error calibration method for wind turbines and field application testing, refAbstract=null), Reference(id=1295068082289013091, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2020, volume=38, issue=4, pageStart=43, pageEnd=46, url=null, language=null, rfNumber=[13], rfOrder=19, authorNames=王立强, 曹斌, 王琪, journalName=内蒙古电力技术, refType=null, unstructuredReference=王立强,曹斌,王琪,. 基于RT-LAB的双馈风电机组建模与仿真[J]. 内蒙古电力技术202038(4):43-46., articleTitle=基于RT-LAB的双馈风电机组建模与仿真, refAbstract=null), Reference(id=1295068082360316260, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2020, volume=38, issue=4, pageStart=43, pageEnd=46, url=null, language=null, rfNumber=[13], rfOrder=20, authorNames=WANG Liqiang, CAO Bin, WANG Qi, journalName=Inner Mongolia Electric Power, refType=null, unstructuredReference=WANG Liqiang, CAO Bin, WANG Qi, et al. Modeling and simulation of doubly fed wind turbine based on RT-LAB[J]. Inner Mongolia Electric Power, 2020, 38(4): 43-46., articleTitle=Modeling and simulation of doubly fed wind turbine based on RT-LAB, refAbstract=null), Reference(id=1295068082440008037, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=4, pageStart=102, pageEnd=105, url=null, language=null, rfNumber=[14], rfOrder=21, authorNames=刘坤, 卓锡鑫, 余高阳, journalName=机电工程技术, refType=null, unstructuredReference=刘坤,卓锡鑫,余高阳,. 等效风速与轮毂风速对风电机组功率曲线的评估对比分析[J]. 机电工程技术202251(4):102-105., articleTitle=等效风速与轮毂风速对风电机组功率曲线的评估对比分析, refAbstract=null), Reference(id=1295068082532282726, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2022, volume=51, issue=4, pageStart=102, pageEnd=105, url=null, language=null, rfNumber=[14], rfOrder=22, authorNames=LIU Kun, ZHUO Xixin, YU Gaoyang, journalName=Mechanical & Electrical Engineering Technology, refType=null, unstructuredReference=LIU Kun, ZHUO Xixin, YU Gaoyang, et al. Evaluation and comparative analysis of equivalent wind speed and hub wind speed on wind turbine power curve[J]. Mechanical & Electrical Engineering Technology, 2022, 51(4): 102-105., articleTitle=Evaluation and comparative analysis of equivalent wind speed and hub wind speed on wind turbine power curve, refAbstract=null), Reference(id=1295068082716832103, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2022, volume=12, issue=14, pageStart=6949, pageEnd=null, url=null, language=null, rfNumber=[15], rfOrder=23, authorNames=RYU G H, KIM D, KIM D Y, journalName=Applied Sciences, refType=null, unstructuredReference=RYU G H, KIM D, KIM D Y, et al. Analysis of vertical wind shear effects on offshore wind energy prediction accuracy applying rotor equivalent wind speed and the relationship with atmospheric stability[J]. Applied Sciences, 2022, 12(14): 6949., articleTitle=Analysis of vertical wind shear effects on offshore wind energy prediction accuracy applying rotor equivalent wind speed and the relationship with atmospheric stability, refAbstract=null), Reference(id=1295068082783940968, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2022, volume=306, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[16], rfOrder=24, authorNames=WU C, LUO K, WANG Q, journalName=Applied Energy, refType=null, unstructuredReference=WU C, LUO K, WANG Q, et al. A refined wind farm parameterization for the weather research and forecasting model[J]. Applied Energy, 2022, 306: 118082., articleTitle=A refined wind farm parameterization for the weather research and forecasting model, refAbstract=null), Reference(id=1295068082851049833, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=1, pageStart=269, pageEnd=274, url=null, language=null, rfNumber=[17], rfOrder=25, authorNames=万庆祝, 吴开聪, journalName=太阳能学报, refType=null, unstructuredReference=万庆祝,吴开聪. 基于随机森林分类的直流微电网孤岛检测[J]. 太阳能学报202243(1):269-274., articleTitle=基于随机森林分类的直流微电网孤岛检测, refAbstract=null), Reference(id=1295068082918158698, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2022, volume=43, issue=1, pageStart=269, pageEnd=274, url=null, language=null, rfNumber=[17], rfOrder=26, authorNames=WAN Qingzhu, WU Kaicong, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=WAN Qingzhu, WU Kaicong. Islanding detection for dc microgrid based on random forest classification[J]. Acta Energiae Solaris Sinica, 2022, 43(1): 269-274., articleTitle=Islanding detection for dc microgrid based on random forest classification, refAbstract=null), Reference(id=1295068083186594155, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2021, volume=9, issue=null, pageStart=166695, pageEnd=166708, url=null, language=null, rfNumber=[18], rfOrder=27, authorNames=LAKMINI PRARTHANA JAYASINGHE W J M, DEO R C, GHAHRAMANI A, journalName=IEEE Access, refType=null, unstructuredReference=LAKMINI PRARTHANA JAYASINGHE W J M, DEO R C, GHAHRAMANI A, et al. Deep multi-stage reference evapotranspiration forecasting model: multivariate empirical mode decomposition integrated with the boruta-random forest algorithm[J]. IEEE Access, 2021, 9: 166695-166708., articleTitle=Deep multi-stage reference evapotranspiration forecasting model: multivariate empirical mode decomposition integrated with the boruta-random forest algorithm, refAbstract=null), Reference(id=1295068083270480236, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2024, volume=154, issue=null, pageStart=1, pageEnd=22, url=null, language=null, rfNumber=[19], rfOrder=28, authorNames=LI J, LIU Y K, GONG H F, journalName=Applied Soft Computing, refType=null, unstructuredReference=LI J, LIU Y K, GONG H F, et al. Stock price series forecasting using multi-scale modeling with boruta feature selection and adaptive denoising[J]. Applied Soft Computing, 2024, 154: 1-22., articleTitle=Stock price series forecasting using multi-scale modeling with boruta feature selection and adaptive denoising, refAbstract=null), Reference(id=1295068083362754925, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2004, volume=92, issue=3, pageStart=401, pageEnd=422, url=null, language=null, rfNumber=[20], rfOrder=29, authorNames=JULIER S J, UHLMANN J K, journalName=Proceedings of the IEEE, refType=null, unstructuredReference=JULIER S J, UHLMANN J K. Unscented filtering and nonlinear estimation[J]. Proceedings of the IEEE, 2004, 92(3): 401-422., articleTitle=Unscented filtering and nonlinear estimation, refAbstract=null), Reference(id=1295068083538915694, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2013, volume=5, issue=6, pageStart=533, pageEnd=538, url=null, language=null, rfNumber=[21], rfOrder=30, authorNames=陈兴鹃, 周杰, 李家强, journalName=南京信息工程大学学报, refType=null, unstructuredReference=陈兴鹃,周杰,李家强,. 基于非线性滤波的风廓线雷达数据处理[J]. 南京信息工程大学学报20135(6):533-538., articleTitle=基于非线性滤波的风廓线雷达数据处理, refAbstract=null), Reference(id=1295068083635384687, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2013, volume=5, issue=6, pageStart=533, pageEnd=538, url=null, language=null, rfNumber=[21], rfOrder=31, authorNames=CHEN Xingjuan, ZHOU Jie, LI Jiaqiang, journalName=Journal of Nanjing University of Information Science and Technology, refType=null, unstructuredReference=CHEN Xingjuan, ZHOU Jie, LI Jiaqiang, et al. Data processing of wind profiler radar based on nonlinear filtering[J]. Journal of Nanjing University of Information Science and Technology, 2013, 5(6): 533-538., articleTitle=Data processing of wind profiler radar based on nonlinear filtering, refAbstract=null), Reference(id=1295068083710882160, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2015, volume=null, issue=null, pageStart=90, pageEnd=112, url=null, language=null, rfNumber=[22], rfOrder=32, authorNames=GEORGE E P B, GWILYM M J, GREGORY C R, journalName=Time series analysis: forecasting and control, refType=null, unstructuredReference=GEORGE E P B, GWILYM M J, GREGORY C R, et al. Time series analysis: forecasting and control[M]. 5th ed. Wiley, 2015: 90-112., articleTitle=null, refAbstract=null), Reference(id=1295068083949957489, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=69, pageEnd=72, url=null, language=null, rfNumber=[23], rfOrder=33, authorNames=易丹辉, journalName=时间序列分析:方法与应用, refType=null, unstructuredReference=易丹辉. 时间序列分析:方法与应用[M]. 2版. 北京:中国人民大学出版社,2018:69-72., articleTitle=null, refAbstract=null), Reference(id=1295068084029649266, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2018, volume=null, issue=null, pageStart=69, pageEnd=72, url=null, language=null, rfNumber=[23], rfOrder=34, authorNames=YI Danhui, journalName=Time series analysis: methods and application, refType=null, unstructuredReference=YI Danhui. Time series analysis: methods and application[M]. 2th ed. Beijing: China Renmin University Press, 2018: 69-72., articleTitle=null, refAbstract=null), Reference(id=1295068084109341043, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=1998, volume=2, issue=null, pageStart=121, pageEnd=167, url=null, language=null, rfNumber=[24], rfOrder=35, authorNames=CHRISTOPHER J C, BURGES A, journalName=Data Mining and Knowledge Discovery, refType=null, unstructuredReference=CHRISTOPHER J C, BURGES A. Tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998, 2: 121-167., articleTitle=Tutorial on support vector machines for pattern recognition, refAbstract=null), Reference(id=1295068084184838516, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2024, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[25], rfOrder=36, authorNames=BECK M, PÖPPEL K, SPANRING M, journalName=Computer Science, refType=null, unstructuredReference=BECK M, PÖPPEL K, SPANRING M, et al. xLSTM: extended long short-term memory[J/OL]. Computer Science, 2024. https://proceedings.neurips.cc/paper_files/paper/2024/hash/c2ce2f2701c10a2b2f2ea0bfa43cfaa3-Abstract-Conference.html., articleTitle=xLSTM: extended long short-term memory, refAbstract=null), Reference(id=1295068084256141685, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2013, volume=null, issue=null, pageStart=null, pageEnd=null, url=null, language=null, rfNumber=[26], rfOrder=37, authorNames=BAK C, ZAHLE F, journalName=The DTU 10-MW reference wind turbine, refType=null, unstructuredReference=BAK C, ZAHLE F, et al. The DTU 10-MW reference wind turbine[R/OL]. Roskilde: DTU Wind Energy, 2013. [2025-10-15]. https://dtuwindenergy.dk/publications/the-dtu-10-mw-reference-wind-turbine/., articleTitle=null, refAbstract=null), Reference(id=1295068085975806326, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2019, volume=null, issue=null, pageStart=10, pageEnd=null, url=null, language=null, rfNumber=[27], rfOrder=38, authorNames=null, journalName=null, refType=null, unstructuredReference=Wind energy generation systems: Part 3-1: Design requirements for fixed offshore wind turbines: IEC 61400-3-1: 2019[S]. Geneva, Switzerland: International Electrotechnical Commission, 2019: 10., articleTitle=null, refAbstract=null), Reference(id=1295068086072275319, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2018, volume=39, issue=11, pageStart=3224, pageEnd=3230, url=null, language=null, rfNumber=[28], rfOrder=39, authorNames=王渊博, 李春, 缪维跑, journalName=太阳能学报, refType=null, unstructuredReference=王渊博,李春,缪维跑,. 基于致动线方法的风力机组尾迹控制策略研究[J]. 太阳能学报201839(11):3224-3230., articleTitle=基于致动线方法的风力机组尾迹控制策略研究, refAbstract=null), Reference(id=1295068086147772792, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2018, volume=39, issue=11, pageStart=3224, pageEnd=3230, url=null, language=null, rfNumber=[28], rfOrder=40, authorNames=WANG Yuanbo, LI Chun, MIAO Weipao, journalName=Acta Energiae Solaris Sinica, refType=null, unstructuredReference=WANG Yuanbo, LI Chun, MIAO Weipao, et al. Research of control strategies for wind turbines wake based on ALM[J]. Acta Energiae Solaris Sinica, 2018, 39(11): 3224-3230., articleTitle=Research of control strategies for wind turbines wake based on ALM, refAbstract=null), Reference(id=1295068086231658873, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, doi=null, pmid=null, pmcid=null, year=2012, volume=15, issue=5, pageStart=811, pageEnd=825, url=null, language=null, rfNumber=[29], rfOrder=41, authorNames=SHEN W Z, ZHU W J, SØRENSEN J N, journalName=Wind Energy, refType=null, unstructuredReference=SHEN W Z, ZHU W J, SØRENSEN J N. Actuator line/Navier-Stokes computations for the MEXICO rotor: comparison with detailed measurements[J]. Wind Energy, 2012, 15(5): 811-825., articleTitle=Actuator line/Navier-Stokes computations for the MEXICO rotor: comparison with detailed measurements, refAbstract=null)], funds=[Fund(id=1295068079030038862, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, awardId=62473152, language=EN, fundingSource=National Natural Science Foundation of China(62473152), fundOrder=null, country=null), Fund(id=1295068079113924943, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, awardId=62473152, language=CN, fundingSource=国家自然科学基金项目(62473152), fundOrder=null, country=null)], companyList=[AuthorCompany(id=1295068074160451862, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=1., ext=[AuthorCompanyExt(id=1295068074168840471, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074177229080, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206)]), AuthorCompany(id=1295068074248532249, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=2., ext=[AuthorCompanyExt(id=1295068074256920858, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074265309467, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.华北电力大学控制与计算机工程学院,北京 102206)])], figs=[ArticleFig(id=1295068077524283708, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=EN, label=Fig.1, caption=The architecture of the xLSTM-Mixer model, figureFileSmall=oVpTl9bhJIZt5qYawBM9ww==, figureFileBig=9P0jjWusklHvmVwBDV4WMg==, tableContent=null), ArticleFig(id=1295068077587198269, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=CN, label=图1, caption=xLSTM-Mixer模型架构, figureFileSmall=oVpTl9bhJIZt5qYawBM9ww==, figureFileBig=9P0jjWusklHvmVwBDV4WMg==, tableContent=null), ArticleFig(id=1295068077754970430, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=EN, label=Fig.2, caption=Time series estimation process with dynamic delayed inputs, figureFileSmall=nRGRDE5sIEUHoZWylw7kyg==, figureFileBig=cEzOYQk6uWbUIbdOc63sKg==, tableContent=null), ArticleFig(id=1295068077813690687, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=CN, label=图2, caption=具有动态延迟输入的时间序列估计过程, figureFileSmall=nRGRDE5sIEUHoZWylw7kyg==, figureFileBig=cEzOYQk6uWbUIbdOc63sKg==, tableContent=null), ArticleFig(id=1295068077872410944, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=EN, label=Fig.3, caption=Distributions of finely selected feature wind speed measurement points under different wind conditions, figureFileSmall=BsLg6NFEhSDyASG2aAvzRQ==, figureFileBig=VG1Hh9WuhNr8FsJePY4JEQ==, tableContent=null), ArticleFig(id=1295068077931131201, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=CN, label=图3, caption=不同风况下精细选择后特征风速点位分布, figureFileSmall=BsLg6NFEhSDyASG2aAvzRQ==, figureFileBig=VG1Hh9WuhNr8FsJePY4JEQ==, tableContent=null), ArticleFig(id=1295068078006628674, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=EN, label=Fig.4, caption=Comparative spatio-temporal distribution map of feature wind speed points under different wind conditions, figureFileSmall=rvdkBDsJKoyW2COiDsk0ZA==, figureFileBig=F7VMDTY24yNxplFcWtfoxg==, tableContent=null), ArticleFig(id=1295068078077931843, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=CN, label=图4, caption=不同风况下特征风速点时空分布对比, figureFileSmall=rvdkBDsJKoyW2COiDsk0ZA==, figureFileBig=F7VMDTY24yNxplFcWtfoxg==, tableContent=null), ArticleFig(id=1295068078153429316, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=EN, label=Fig.5, caption=Model comparison under wind condition 1 (average wind speed: 7:13 m/s; turbulence intensity: 12%), figureFileSmall=+ti+X50cgHO2WwYLZZd/cA==, figureFileBig=YwKBc5OysnPUDwW+CDNLBw==, tableContent=null), ArticleFig(id=1295068078233121093, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=CN, label=图5, caption=风况1(平均风速7.13 m/s,湍流强度12%)条件下模型对比, figureFileSmall=+ti+X50cgHO2WwYLZZd/cA==, figureFileBig=YwKBc5OysnPUDwW+CDNLBw==, tableContent=null), ArticleFig(id=1295068078296035654, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=EN, label=Fig.6, caption=Model comparison under wind condition 2 (average wind speed: 11:12 m/s; turbulence intensity: 14%), figureFileSmall=5/fKbLQ/QrdseaI0/EKiJw==, figureFileBig=+rUsCPv7AB9+elUhpF5bQQ==, tableContent=null), ArticleFig(id=1295068078392504647, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=CN, label=图6, caption=风况2(平均风速11.12 m/s,湍流强度14%)条件下模型对比, figureFileSmall=5/fKbLQ/QrdseaI0/EKiJw==, figureFileBig=+rUsCPv7AB9+elUhpF5bQQ==, tableContent=null), ArticleFig(id=1295068078472196424, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=EN, label=Tab.1, caption=

Configuration parameters of a 10 MW wind turbine

, figureFileSmall=null, figureFileBig=null, tableContent=
项目数值
叶片数量3
额定功率/MW10
切入、额定、切出风速/(m·s–14.0、11.4、25.0
发电机额定转速/(r·min–1493
轮毂直径、高度/m5.6、119.0
风轮扫掠面直径/m178.3
), ArticleFig(id=1295068078535110985, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=CN, label=表1, caption=

10 MW风电机组配置参数

, figureFileSmall=null, figureFileBig=null, tableContent=
项目数值
叶片数量3
额定功率/MW10
切入、额定、切出风速/(m·s–14.0、11.4、25.0
发电机额定转速/(r·min–1493
轮毂直径、高度/m5.6、119.0
风轮扫掠面直径/m178.3
), ArticleFig(id=1295068078631579978, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=EN, label=Tab.2, caption=

Selection results and stability evaluation of feature wind speed points under seven wind conditions

, figureFileSmall=null, figureFileBig=null, tableContent=
风况快速选择对应精细选择特征风速点数量/个绝对波动变异系数/%
1 0002 0003 0004 0005 000
平均风速7.13 m/s
湍流强度12%
309305310300305101.30
平均风速9.08 m/s
湍流强度12%
393375391373371222.77
平均风速11.12 m/s
湍流强度12%
321323350335335293.49
平均风速11.12 m/s
湍流强度14%
321323350345335293.49
平均风速11.12 m/s
湍流强度16%
336334338331328101.19
平均风速14.12 m/s
湍流强度12%
590581591585583100.74
平均风速16.00 m/s
湍流强度12%
556507509499495614.79
), ArticleFig(id=1295068078719660363, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=CN, label=表2, caption=

7种风况下特征风速点选择结果及稳定性评估

, figureFileSmall=null, figureFileBig=null, tableContent=
风况快速选择对应精细选择特征风速点数量/个绝对波动变异系数/%
1 0002 0003 0004 0005 000
平均风速7.13 m/s
湍流强度12%
309305310300305101.30
平均风速9.08 m/s
湍流强度12%
393375391373371222.77
平均风速11.12 m/s
湍流强度12%
321323350335335293.49
平均风速11.12 m/s
湍流强度14%
321323350345335293.49
平均风速11.12 m/s
湍流强度16%
336334338331328101.19
平均风速14.12 m/s
湍流强度12%
590581591585583100.74
平均风速16.00 m/s
湍流强度12%
556507509499495614.79
), ArticleFig(id=1295068078811935052, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=EN, label=Tab.3, caption=

Results of model evaluation

, figureFileSmall=null, figureFileBig=null, tableContent=
风况风速点平均相对误差/%KSSSIM
xLSTM-MixerLSTMTransformerxLSTM-MixerLSTMTransformerxLSTM-MixerLSTMTransformer
平均风速7.13 m/s
湍流强度12%
point10.514.654.220.112 50.462 50.212 50.991 600.042 8
point21.127.198.250.087 50.437 50.287 50.985 200
point31.236.788.030.100 00.500 00.312 50.983 300
point40.936.476.530.112 50.550 00.237 50.982 500
平均风速9.08 m/s
湍流强度12%
point10.174.704.660.178 50.425 00.250 00.991 600.032 8
point21.468.237.580.067 50.500 00.275 00.975 200
point32.747.797.370.165 50.462 50.387 50.983 500
point42.378.638.890.166 50.500 00.225 00.985 300
平均风速11.12 m/s
湍流强度12%
point10.455.555.550.062 50.300 00.262 50.993 500
point20.959.009.110.050 00.337 50.325 00.989 800
point31.228.979.280.112 50.337 50.250 00.977 500
point41.0310.7911.430.062 50.175 00.150 00.987 800
平均风速11.12 m/s
湍流强度14%
point10.455.555.550.062 50.300 00.262 50.993 500
point20.959.009.110.050 00.337 50.325 00.989 800
point31.228.979.280.112 50.337 50.250 00.977 500
point41.0310.7911.430.062 50.175 00.150 00.987 800
平均风速11.12 m/s
湍流强度16%
point11.266.245.360.082 50.500 00.162 50.983 500
point22.455.444.230.060 00.537 50.225 00.998 800
point32.437.657.240.122 50.537 50.350 00.988 800
point42.0610.5112.350.062 50.275 00.250 00.975 500
平均风速14.12 m/s
湍流强度12%
point10.335.275.860.087 50.125 00.150 00.994 100
point20.385.155.880.062 50.500 00.375 00.995 50.162 90.023 4
point30.375.846.430.062 50.462 50.387 50.996 900
point40.598.519.060.062 50.500 00.425 00.996 100
平均风速16.00 m/s
湍流强度12%
point11.385.304.810.078 50.225 00.250 00.993 500
point22.644.014.430.067 50.500 00.275 00.978 800
point32.783.954.100.065 50.562 50.287 50.968 800
point42.605.755.890.066 50.600 00.325 00.985 500
), ArticleFig(id=1295068078908404045, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, language=CN, label=表3, caption=

模型评估结果

, figureFileSmall=null, figureFileBig=null, tableContent=
风况风速点平均相对误差/%KSSSIM
xLSTM-MixerLSTMTransformerxLSTM-MixerLSTMTransformerxLSTM-MixerLSTMTransformer
平均风速7.13 m/s
湍流强度12%
point10.514.654.220.112 50.462 50.212 50.991 600.042 8
point21.127.198.250.087 50.437 50.287 50.985 200
point31.236.788.030.100 00.500 00.312 50.983 300
point40.936.476.530.112 50.550 00.237 50.982 500
平均风速9.08 m/s
湍流强度12%
point10.174.704.660.178 50.425 00.250 00.991 600.032 8
point21.468.237.580.067 50.500 00.275 00.975 200
point32.747.797.370.165 50.462 50.387 50.983 500
point42.378.638.890.166 50.500 00.225 00.985 300
平均风速11.12 m/s
湍流强度12%
point10.455.555.550.062 50.300 00.262 50.993 500
point20.959.009.110.050 00.337 50.325 00.989 800
point31.228.979.280.112 50.337 50.250 00.977 500
point41.0310.7911.430.062 50.175 00.150 00.987 800
平均风速11.12 m/s
湍流强度14%
point10.455.555.550.062 50.300 00.262 50.993 500
point20.959.009.110.050 00.337 50.325 00.989 800
point31.228.979.280.112 50.337 50.250 00.977 500
point41.0310.7911.430.062 50.175 00.150 00.987 800
平均风速11.12 m/s
湍流强度16%
point11.266.245.360.082 50.500 00.162 50.983 500
point22.455.444.230.060 00.537 50.225 00.998 800
point32.437.657.240.122 50.537 50.350 00.988 800
point42.0610.5112.350.062 50.275 00.250 00.975 500
平均风速14.12 m/s
湍流强度12%
point10.335.275.860.087 50.125 00.150 00.994 100
point20.385.155.880.062 50.500 00.375 00.995 50.162 90.023 4
point30.375.846.430.062 50.462 50.387 50.996 900
point40.598.519.060.062 50.500 00.425 00.996 100
平均风速16.00 m/s
湍流强度12%
point11.385.304.810.078 50.225 00.250 00.993 500
point22.644.014.430.067 50.500 00.275 00.978 800
point32.783.954.100.065 50.562 50.287 50.968 800
point42.605.755.890.066 50.600 00.325 00.985 500
)], 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.202510030, detailUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/10.19666/j.rlfd.202510030, pdfUrlCn=https://castjournals.cast.org.cn/joweb/rlfd/CN/PDF/10.19666/j.rlfd.202510030, pdfUrlEn=https://castjournals.cast.org.cn/joweb/rlfd/EN/PDF/10.19666/j.rlfd.202510030, 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
大型风电机组多点特征风速选择及估计
收藏切换
PDF下载
申珊珊 1, 2 , 胡阳 1, 2 , 王继恒 1, 2 , 宋子秋 1, 2
热力发电 | 储能与可再生能源技术 2026,55(5): 21-32
收起
收藏切换
热力发电 |储能与可再生能源技术 2026 , 55 (5) : 21 -32
大型风电机组多点特征风速选择及估计
全屏
[Author(id=1295068074328224029, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, orderNo=0, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=18831831705@163.com, emailSecond=null, emailThird=null, correspondingAuthor=0, authorType=1, ext={EN=AuthorExt(id=1295068074424693024, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068074328224029, language=EN, stringName=Shanshan SHEN, firstName=Shanshan, middleName=null, lastName=SHEN, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China
2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068074504384801, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068074328224029, language=CN, stringName=申珊珊, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206
2.华北电力大学控制与计算机工程学院,北京 102206, bio={"content":"

申珊珊(1998),女,硕士,主要研究方向为风力发电过程建模及控制等,

"}, bioImg=null, bioContent=

申珊珊(1998),女,硕士,主要研究方向为风力发电过程建模及控制等,

, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068074160451862, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=1., ext=[AuthorCompanyExt(id=1295068074168840471, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074177229080, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206)]), AuthorCompany(id=1295068074248532249, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=2., ext=[AuthorCompanyExt(id=1295068074256920858, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074265309467, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.华北电力大学控制与计算机工程学院,北京 102206)])]), Author(id=1295068074575687971, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, orderNo=1, firstName=null, middleName=null, lastName=null, nameCn=null, orcid=null, stid=null, country=null, authorPic=null, dead=0, email=hooyoung@ncepu.edu.cn, emailSecond=null, emailThird=null, correspondingAuthor=1, authorType=1, ext={EN=AuthorExt(id=1295068074667962662, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068074575687971, language=EN, stringName=Yang HU, firstName=Yang, middleName=null, lastName=HU, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China
2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068074756043047, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068074575687971, language=CN, stringName=胡阳, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206
2.华北电力大学控制与计算机工程学院,北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068074160451862, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=1., ext=[AuthorCompanyExt(id=1295068074168840471, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074177229080, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206)]), AuthorCompany(id=1295068074248532249, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=2., ext=[AuthorCompanyExt(id=1295068074256920858, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074265309467, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.华北电力大学控制与计算机工程学院,北京 102206)])]), Author(id=1295068074814763305, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, 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=1295068074877677868, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068074814763305, language=EN, stringName=Jiheng WANG, firstName=Jiheng, middleName=null, lastName=WANG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China
2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068074948981037, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068074814763305, language=CN, stringName=王继恒, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206
2.华北电力大学控制与计算机工程学院,北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068074160451862, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=1., ext=[AuthorCompanyExt(id=1295068074168840471, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074177229080, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206)]), AuthorCompany(id=1295068074248532249, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=2., ext=[AuthorCompanyExt(id=1295068074256920858, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074265309467, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.华北电力大学控制与计算机工程学院,北京 102206)])]), Author(id=1295068075028672815, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, 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=1295068075091587378, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068075028672815, language=EN, stringName=Ziqiu SONG, firstName=Ziqiu, middleName=null, lastName=SONG, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China
2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null), CN=AuthorExt(id=1295068075162890547, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, authorId=1295068075028672815, language=CN, stringName=宋子秋, firstName=null, middleName=null, lastName=null, prefix=null, suffix=null, authorComment=null, nameInitials=null, affiliation=null, department=null, xref=1, 2, address=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206
2.华北电力大学控制与计算机工程学院,北京 102206, bio=null, bioImg=null, bioContent=null, aboutCorrespAuthor=null)}, companyList=[AuthorCompany(id=1295068074160451862, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=1., ext=[AuthorCompanyExt(id=1295068074168840471, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074177229080, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074160451862, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=1.新能源电力系统全国重点实验室(华北电力大学),北京 102206)]), AuthorCompany(id=1295068074248532249, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, xref=2., ext=[AuthorCompanyExt(id=1295068074256920858, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=EN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China), AuthorCompanyExt(id=1295068074265309467, tenantId=1146029695717560320, journalId=1210938733613449225, articleId=1295068070586904837, companyId=1295068074248532249, language=CN, country=null, province=null, city=null, postcode=null, companyName=null, departmentName=null, remark=2.华北电力大学控制与计算机工程学院,北京 102206)])])]
申珊珊1, 2 , 胡阳1, 2 , 王继恒1, 2, 宋子秋1, 2
作者信息
  • 1.新能源电力系统全国重点实验室(华北电力大学),北京 102206
  • 2.华北电力大学控制与计算机工程学院,北京 102206
通讯作者:
胡阳(1986),男,博士,副教授,主要研究方向为新能源发电建模及控制等,
作者简介:

申珊珊(1998),女,硕士,主要研究方向为风力发电过程建模及控制等,

Selection and estimation of multi-point feature wind speeds for large-scale wind turbines
Shanshan SHEN1, 2 , Yang HU1, 2 , Jiheng WANG1, 2, Ziqiu SONG1, 2
Affiliations
  • 1.State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources, North China Electric Power University, Beijing 102206, China
  • 2.School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China
出版时间: 2026-05-25 doi: 10.19666/j.rlfd.202510030
文章导航
收藏切换
【目的】

针对大型风电机组容量增大、机组叶片半径急剧增加、机前入流风速场分布及垂直风切变效应更为复杂,轮毂高度处单点有效风速难以充分表征入流风况的问题,提出了一种大型风电机组多点特征风速选择及估计方法。

【方法】

首先,基于机前入流风速场网格数据,提出随机森林结合Boruta(RF-Boruta)分步算法,实现超大风轮扫掠面内特征风速格点的稳定筛选;然后,引入混合多变量长短时记忆(xLSTM-Mixer)神经网络算法,结合计及输入-输出延迟阶次的嵌入式特征工程策略,构建机组动力学特性驱动的多点特征风速超短期多步动态估计模型;最后,在SOWFA平台完成10 MW风电机组大涡模拟及IEC标准下全风速范围内7种风况的数值仿真与流场数据采集,对所提方法进行验证。

【结果】

结果表明:筛选得到含轮毂中心在内的4个代表性特征风速点(半径50~60 m、120°角度间隔布置),xLSTM-Mixer模型对多点风速的当前时刻滤波及未来80步超前预测相对误差均≤2.8%,实现秒级高精度估计,科尔莫戈罗夫-斯米尔诺夫(KS)统计量≤0.2,结构相似性指数(SSIM)≥0.96,相较于传统LSTM、Transformer模型,精确度提升约10%,且在分布匹配与结构捕捉能力上优势显著。

【结论】

该方法突破了单点风速表征的局限性,为风功率预测、机组运行控制及发电量评估提供了可靠技术支撑。

风力发电  /  时空特征选择  /  xLSTM-Mixer神经网络  /  多步时间序列动态估计
[Objective]

With the continuous development of the wind power industry toward high power and large capacity, the soaring unit capacity and expanding blade radius of large-scale wind turbines have resulted in increasingly complex spatial distributions of the inflow wind field in front of the turbine and significantly enhanced vertical wind shear effects. The conventional method of characterizing wind conditions using single-point wind speed at hub height can no longer fully reflect the wind speed distribution differences and dynamic patterns within the ultra-large rotor swept area, which is prone to causing issues such as wind power prediction deviations and inadequate adaptability of operation control strategies. To address these challenges, this study proposes a multi-point feature wind speed selection and estimation method for large-scale wind turbines, which can accurately capture key wind speed information in the rotor swept area, overcome the limitations of single-point feature wind speed, and provide data support for the optimal operation of wind turbines.

[Methods]

To achieve the aforementioned research objective, this study adopts a step-by-step technical approach for systematic investigation. Firstly, based on high-precision grid data of the inflow wind field in front of the turbine, a two-stage stepwise feature selection algorithm is proposed, which first carries out preliminary selection with random forest and then implements refined selection via Boruta (RF-Boruta). The Boruta algorithm is employed to conduct significance tests on the feature importance scores output by the random forest model, thereby eliminating redundant and irrelevant wind speed grid points and realizing stable and accurate selection of feature wind speed points within the ultra-large rotor swept area. Secondly, for the selected feature wind speed points, the extended long short-term memory neural network (xLSTM-Mixer) algorithm is introduced, combined with an embedded feature engineering strategy that accounts for input-output delay orders. This strategy fully exploits the temporal correlation and spatial correlation of wind speed sequences, and constructs a unit dynamics-driven ultra-short-term multi-step dynamic estimation model for multi-point feature wind speed points. Finally, to verify the effectiveness and superiority of the proposed method, large eddy simulation (LES) of a 10 MW wind turbine is performed on the SOWFA platform. Meanwhile, 7 typical wind conditions covering the full wind speed range specified in the IEC standards (including complex wind conditions such as shear wind and turbulent wind) are configured for numerical simulation and flow field data collection. The feature selection performance and speed estimation accuracy of the proposed method are comprehensively validated based on the collected high-fidelity data.

[Results]

The numerical simulation and verification results demonstrate that four representative feature wind speed points, including the hub center, are identified via the RF-Boruta stepwise algorithm. These feature points are arranged at a radius of 50~60 m with an angular interval of 120°, which can effectively cover the key regions of the rotor swept area and fully characterize the spatial distribution features of the inflow wind field. The constructed xLSTM-Mixer model exhibits excellent performance in the multi-point feature wind speed estimation task: the relative error of 80-step-ahead (second-level) prediction for multi-point wind speeds is ≤2.8%, achieving second-level high-precision estimation. Statistical characteristic analysis shows that the Kolmogorov-Smirnov (KS) statistic between the model estimation results and the actual wind speed data is ≤0.2, and the structural similarity index (SSIM) is ≥0.96, indicating a high degree of consistency in both distribution characteristics and structural features between the two datasets. Comparative experiments with mainstream time-series prediction models such as the conventional LSTM and Transformer reveal that the estimation accuracy of the xLSTM-Mixer model is improved by approximately 10%, with distinct advantages in wind speed distribution matching and spatial structure capture capabilities.

[Conclusion]

The multi-point feature wind speed selection and estimation method proposed in this study effectively breaks through the limitations of conventional single-point feature wind speed, realizing accurate selection and efficient estimation of key wind speed information within the ultra-large rotor swept area. The high-precision multi-point wind speed data provided by this method can reliably support wind power prediction, operation control optimization, and power generation evaluation of wind turbines, helping to enhance the operational stability and energy utilization efficiency of wind turbines. It holds important theoretical significance and engineering application value for promoting the high-quality development of the wind power industry.

wind power generation  /  spatiotemporal feature selection  /  xLSTM-Mixer neural network  /  multi-step time series dynamic estimation
申珊珊, 胡阳, 王继恒, 宋子秋. 大型风电机组多点特征风速选择及估计. 热力发电, 2026 , 55 (5) : 21 -32 . DOI: 10.19666/j.rlfd.202510030
Shanshan SHEN, Yang HU, Jiheng WANG, Ziqiu SONG. Selection and estimation of multi-point feature wind speeds for large-scale wind turbines[J]. Thermal Power Generation, 2026 , 55 (5) : 21 -32 . DOI: 10.19666/j.rlfd.202510030
在全球能源向可再生能源加速转型的大背景下,风能凭借其清洁、可再生的显著优势,已然成为能源领域的核心组成部分,其装机容量和发电量均呈现出迅猛的增长态势。风电机组作为将风能转化为电能的关键设备,其控制策略制定、功率优化以及设备安全运行,在很大程度上取决于对风轮扫掠面内风速的精准把握[1-2]。然而,风速具有极强的随机性和动态性,且随着10 MW大型风电机组塔架高度提升、叶片半径延长,风轮扫掠面内风剪切效应和湍流特性显著增强,导致扫掠面内风速分布存在明显差异[3-4],这使得直接对其进行精确测量在实际操作中面临着巨大的挑战[5]
当前10 MW机组工程化的风速测量主要依赖以下几种核心方式:1)近轮毂高度单点风速计测量,作为应用最广泛的传统方式,通过在轮毂附近安装杯式或超声风速计获取数据[6-7],虽成本低、维护简便,但单点测量结果无法反映全扫掠面风速的差异,易导致功率评估偏差和控制策略适配性不足。2)机舱式激光雷达测量,可远程扫描上游风场,实时捕捉风速、风向及湍流变化,精度较高且能为前馈控制提供提前量[8-10],部分案例可提升偏航校正效益[11-12],但因设备成本高而限制大规模普及,且恶劣环境易影响测量稳定性,长期维护成本较高。3)多高度点位加权测量,通过在扫掠面内不同高度部署多个风速计,以加权平均算法拟合整体风速[613-14],虽能改善单点测量局限,但多点部署增加安装、校准复杂度,且加权系数缺乏统一标准,精度易受风况波动影响。
现有研究中,文献[15-16]对比了轮毂高度风速与等效风速的发电量计算结果,发现等效风速更接近实际值,但未解决全扫掠面风速表征问题;文献[13-14]提出的多点加权方法虽然考虑风速分布特性,却仍存在前文提及的工程应用短板。总体而言,当前研究仍存在明显缺口,现有测量方式难以同时满足精准性、经济性与便捷性需求,亟需探究更优方法为风功率预测、机组发电量评估及运行控制提供理论支撑。
本文围绕超大风轮扫掠面内特征风速点展开研究,提出了一种大型风电机组多点特征风速选择及估计方法。通过随机森林结合Boruta(RF-Boruta)分步算法,对超大风轮扫掠面内特征风速点进行合理选择;采用混合多变量长短时记忆(xLSTM-Mixer)神经网络算法,对选择的多点位特征风速进行动态估计;最后,利用SOWFA对10 MW风电机组进行大涡模拟(LES),产生全风速范围7个风况的网格数据,并进行仿真验证。
超大风轮扫掠面内风速具有高维度、强冗余性、非线性、易受湍流与尾流干扰等特点,单一的传统特征选择方法(过滤法、单一包装法、单一嵌入法、启发式搜索法等)无法匹配风速数据的场景特殊性。因此,提出了RF-Boruta分步算法,该算法能捕捉数据间的非线性和交互特征。首先,利用RF算法对特征风速点快速选择,排除纯噪声特征,将特征维度从高维压缩至中低维,降低Boruta算法的计算成本;其次采用Boruta算法精细选择,修正对冗余特征的误判,精准识别真正与目标相关的风速特征,得到所需的重要数据集,实验结果表明这是一种高效、可靠的特征选择方式。
RF是一种基于决策树的集合学习算法,先捕捉强非线性特征,快速处理大型数据集,同时初步识别出高贡献的交互特征[17]。建模步骤如下:
步骤1 基于研究内容,研究对象为10 MW超大风轮扫掠面,特征矩阵X和目标变量y的表达式为:
X=[x11x12x1nx21x22x2nxijxm1xm2xmn]y=[y1y2ym]
式中:xiji时刻第j个网格位置处的风速值;mn分别为采样总时间和风轮扫掠面内网格总数;yii时刻风轮扫掠面内风速平均值,表达式为:
yi=1nj=1nxij
特征矩阵X的每一列代表一个特征f(即单个网格位置的风速序列),特征f与目标变量y的关联紧密程度,直接决定其在特征选择中的重要性排序。
步骤2 采用平均减少不纯度(MDI)指标来量化特征变量的重要性,通过统计特征在决策树分裂过程中对节点不纯度的降低贡献,实现特征重要性的客观评估。初始设置决策树数量Ntree=200,计算步骤如下:
1)使用均方误差(MSE)衡量节点的不纯度。
2)对于第n棵决策树,将特征矩阵X和目标变量y作为输入,在节点分裂时,得到由特征f引起的不纯度减少量ΔIn,f,表达式为:
ΔIn,f=nMSE(np)m1mpnMSE(n1)mrmpnMSE(nr)
式中:nMSE为一个节点的均方误差;n1nrnp分别为分裂后的左子节点、右子节点和父节点;m1mrmp分别为左子节点、右子节点和父节点的样本数量。
3)每个特征f的重要性分数表达式为:
GMDIf=1Ntreen=1NtreeΔIn,f
GMDIf值越大,表示特征f对于目标变量y的重要性越高,应优先保留。
Boruta是一种包装式算法,通过机器学习对数据的特征进行重要性迭代评估,在初步筛选的基础上,进一步验证交互特征的真实贡献,进行精细选择,从而保留对目标变量最有用的特征[18-19]。建模步骤如下:
步骤1数据准备 RF快速选择得到的特征变量作为输入A
步骤2创建影子特征 对数据A中的每个特征进行随机洗牌,洗牌后的特征称为“虚拟特征”,即影子特征。将影子数据帧追加到原始数据集中,形成一个新的特征矩阵Aboruta,特征数量是原始特征矩阵A的2倍。
步骤3模型训练 步骤如下:
1)计算重要性得分,采用MDI指标计算所有特征的重要性得分,将得分进行标准化处理(转换为Z值),消除不同特征维度差异的干扰。
2)对比重要性,每个特征与它的影子特征进行比较,记录原始特征的Z值是否超过其对应影子特征的Z值。
步骤4标记原始特征,循环迭代 将每个原始特征标记为“暂定”,循环迭代过程如下:
1)每轮模型训练后,统计每个原始特征在当前轮次中“Z值超过对应影子特征”的结果。
2)累积多轮结果,若某原始特征在多数迭代中持续优于其影子特征,则标记为“接受”;若多数迭代中劣于其影子特征,则标记为“拒绝”;结果不稳定则维持“暂定”。
3)剔除“拒绝”特征及其对应影子特征,更新Aboruta并进入下一轮训练,聚焦剩余特征的验证。
步骤5终止条件 所有特征归类完成后停止。Boruta算法会输出“接受”的特征作为选择结果。
步骤6特征评估 对最终选择的特征风速点进行评估,从绝对波动(AV)和相对波动(RV)两方面综合考虑,相对波动评估指标为变异系数(CV),表达式为:
BAV=mmaxmminBCV=sm¯×100%
式中:mmaxmmin分别为最终选择的特征风速点数量的最大值和最小值;sm-分别为最终选择的特征风速点数量的标准差和均值。工程中稳定阈值(BCV)为5%。
风速估计需要覆盖历史数据的平滑、当前数据的滤波及未来数据预测等多时间场景需求。受风速强随机性与数据规模大的特性影响,传统估计方法面临显著局限:卡尔曼滤波对非线性风速序列的适配性不足[20-21],自回归滑动平均模型(ARMA)在处理长时序依赖时易出现参数爆炸[22-23],支持向量机(SVM)则因计算复杂度随数据量呈指数级增长,导致计算成本与时间开销大幅攀升[24]。为此,扩展长短时记忆(xLSTM)神经网络模型成为高效替代方案[25]。该模型采用了一组专门设计的长短时记忆(sLSTM)模块,在每个LSTM单元内部引入跳过连接,使信息能够直接在不同时间步之间传递,增强了网络内部的信息流动性。这一设计通过并行化计算与梯度优化,将大规模风速数据的处理效率提升数倍,在时间成本上实现突破;通过跳过连接有效缓解了梯度消失问题,使模型能深度挖掘风速序列的长期依赖关系,在预测精度上展现明显优势,对风速突变、多模态分布等复杂模式的捕捉能力显著优于传统方法。
xLSTM-Mixer是一种基于递归深度学习的混合多变量时间序列预测方法,通过精心设计时间、变量和多视图的混合,来捕捉复杂的时间依赖关系和变量间关系。xLSTM-Mixer模型架构如图1所示。由图1可见,本文xLSTM-Mixer模型由3个阶段组成。
1)初始的NLinear预测
输入为程序预处理后标准化的多变量时序xnorm,不同变量对应独立特征通道,通过NLinear模块实现时间维度的特征混合——采用线性变换对输入序列的180步信息进行加权聚合,完成“时间混合”,捕捉单一变量的短期时间关联,生成初步的单变量时间特征xinitial。为打破变量独立限制,程序通过跨变量共享全连接层FCupxinitial进行维度提升,将特征维度映射至128维,得到嵌入特征xup,为后续联合混合提供高维特征。
2)后续的联合混合与sLSTM跨维度建模
嵌入特征xup直接输入sLSTM块堆栈S,sLSTM块通过递归结构同时建模180步序列的时间依赖与128维特征的变量耦合关联,输出中间特征后,通过线性映射将序列长度从180步压缩至80步,得到中间预测y′。对嵌入特征xup执行视图反转操作,即按变量维度对特征张量进行转置与逆序排列,得到反转特征x^up,同样输入sLSTM块堆栈,经时间-变量联合建模与序列长度转换,输出中间预测y″。双视图设计通过程序中并行计算逻辑实现,确保模型从“原始时序”与“反转时序”2个视角捕捉特征,提升对复杂波动模式(如风速突变)的适应能力,避免单一视角的特征遗漏。
3)最终的视图混合(多视图自适应融合)
输入为双视图中间预测y′和y″,引入自适应权重系数α,该系数由模型训练过程动态学习(基于验证集损失反馈实时调整),对预测精度更优的视图赋予更高权重,实现双视图信息的差异化融合。采用加权求和策略在全连接层FCview完成视图融合,融合公式为:y=α·y+(1–α)·y″,融合后得到最终预测结果y。融合过程采用矩阵向量化运算优化,在保证融合精度的同时提升预测推理效率,避免批量计算中的维度不匹配问题。
原始数据集添加均值为0、方差为0.01的高斯噪声,在模型训练过程中,增加了对数据波动的鲁棒性,防止过拟合现象的发生,从而提高了模型的泛化能力。初始设置:批量大小为16,隐藏层维度为128,优化器为Adam,损失函数为MSE,学习率为0.000 5。xLSTM-Mixer模型的时间序列动态估计过程如图2所示,场景生成流程如下。
步骤1嵌入式特征工程 输入变量为激光雷达测风、机舱风速、桨距角和风轮转速,输出变量为最终选择的多点位特征风速数据。对输入数据做动态延迟,与输出数据在时间上对齐,表达式为:
t=t+ττ=200ν¯i
式中:ν¯ii时刻风轮扫掠面内风速平均值;τ为延迟阶次;t′和t分别为动态延迟前、后的时间。
步骤2最优预测步长选择 动态延迟后的输入数据和高斯噪声作为xLSTM-Mixer模型输入进行训练,目标是确定最优历史时间步长和最优预测时间步长。赤池信息准则(AIC)倾向于选择拟合效果好的模型预测未来数据,贝叶斯信息准则(BIC)倾向于选择简单模型拟合现有数据。选权重比例为1:1的评估指标S综合评价,表达式为:
S=w×SAIC+(1w)×SBICSAIC=2k2ln(L)SBIC=kln(L)2ln(L)
式中:w为权重;k为模型中参数的数量;L为模型的极大似然估计值。SAICSBIC的值越小,模型在拟合数据的同时能够保持较好的简洁性,避免过拟合的风险。
步骤3模型训练 采用最优参数对模型进行重新训练,根据最小验证损失,选择最优模型,进行多步预测。
步骤4模型评估 对训练完成的模型性能进行评估,评估指标为相对误差(RE)、科尔莫戈罗夫-斯米尔诺夫(KS)统计量及结构相似性指数(SSIM),表达式分别为:
ERE=|yxx|×100%
EKS=maxx|FX(x)FY(x)|
ESSIM=(2μxμy+C1)(2σxy+C2)(μx2+μy2+C1)(σx2+σy2+C2)
式中:x为真实值;y为预测值;X={x1x2,…,xn}为真实值时间序列;Y={y1y2,…,yn}为预测值时间序列;FXx)和FYx)分别为真实风速值和预测风速值的经验累积分布函数;μxμy分别为真实值与预测值的均值;σx2σy2分别为真实值与预测值的方差;σxy为真实值与预测值的协方差;C1C2为稳定系数。
ERE的值越小,表明模型的精度越高。EKS的值越接近0,表明预测值分布与真实值分布匹配度越高。ESSIM的值越接近1,表明预测值序列与实际值序列结构越相似。
以SOWFA精细化大涡模拟代替机组实际运行进行仿真实验和性能验证。硬件系统采用浪潮NF5280M6高性能计算机,软件环境部署Ubuntu 16.04操作系统,集成OpenFOAM-v9开源CFD求解器,并行计算依托OpenMPI4.0.3接口实现48核分布式并行任务调度。模型训练实验平台采用NVIDIA Tesla A100 GPU作为核心计算设备,在PyTorch 1.1.0深度学习框架下进行模型开发与训练,配合CUDA 11.3实现并行计算。
基于丹麦技术大学研发的10 MW风电机组配置模型参数[26],风电机组配置参数如表1所示。
计算域采用多级嵌套网格策略。背景网格分辨率5 m,全局域尺寸为2 000 m×1 000 m×300 m;局部加密域围绕风电机组布置,尺寸为500 m×600 m×250 m,网格逐级加密至叶尖最小尺寸。边界条件设置遵循IEC 61400-3-1标准[27]:入口采用Dirichlet速度边界V=4~22 m/s,出口为Neumann压力边界,顶部及侧面施加滑移壁面,地面采用粗糙壁面模型,粗糙度zQ=0.6 m。湍流入口由Mann盒模型生成,涵盖A/B/C 3类湍流:16%、14%、12%。湍流积分尺度Lk=340 m。
流体求解器采用大涡模拟,亚格子模型为动态Smagorinsky-Lilly模型,时间推进采用二阶隐式Crank-Nicolson格式,时间步长Δt=1 s,满足库朗数CFL<0.5。风电机组模拟通过致动线模型(ALM)实现[28-29],叶片离散为50个升阻力单元,升阻力系数表来源于NREL Airfoil数据库(S809系列翼型)。叶片结构动力学耦合欧拉-伯努利梁理论,刚度矩阵K由材料属性定义(E=38 GPa,ρ=1 800 kg/m3),气动载荷与结构形变通过强耦合迭代求解,收敛残差<10–4。翼型在根部区域厚度约35%,该部分主要提高高升阻比和结构强度。翼型的中部区域厚度约21%,用于平衡气动性能和结构性能。翼型的尖部区域厚度约14%,用于优化雷诺数性能,其采用非线性扭角设计,根部扭角≈15°,尖部扭角≈–2°,以匹配轴向入流条件。
在全风速范围下,进行7个风况模拟,并采集机前入流风速场网格数据,涵盖额定风速以上及以下的风速场景。
风轮扫掠面的边界为X:290、Y:405~595、Z:26.5~210.0,仿真总时长600 s,时间步长1 s。部分风况精细选择后特征风速点位分布如图3所示,表2为特征风速点选择结果及稳定性评估结果。
观察和分析图3表2可得下列结论。
1)相同风况下,无论快速选择的初始样本数量(1 000~5 000个)如何变化,精细选择后的特征风速点数量波动幅度小,基本保持不变,时空分布处于相同位置,稳定性极强,同时所有风况场景下的变异系数均<5%,低于工程稳定阈值,证明了精细选择特征风速点的唯一性。
2)不同风况下,分2类场景。
①湍流强度固定,平均风速变化。在低风速启动区(额定风速以下7~11 m/s),此阶段风轮采用恒转速控制,叶尖线速度随平均风速的增大而增大,风轮扫掠面风速的径向梯度与圆周周期性波动显著增强,气动有效特征点增多,因此精细选择后的特征风速点数量随平均风速递增;在额定功率临界区(11~14 m/s),风轮从恒转速控制切换为变桨距控制,桨距角增大,部分原有效点因攻角突变失去气动意义,被筛选剔除,因此精细选择后的特征风速点数量会先减少;在额定功率稳定区(14~16 m/s):变桨距控制进入平稳调整状态,高风速使风轮扫掠面气动信号更丰富,有效点数量大幅回升,精细选择后的特征风速点数量会再增加。
②平均风速不变,湍流强度改变精细选择后的特征风速点数量差异微弱,仅高湍流有影响,由于高湍流的强扰动,使特征风速点位分布边缘化。
因此,在不同风况下,平均风速主导特征风速点数量差异,湍流强度仅边际干扰,证明了精细选择特征风速点的有效性。结果表明,最终选择的特征风速点具有较强的稳定性、唯一性和有效性。
7种风况特征风速点位分布如图4所示,对比分析确定特征风速点的位置、轮毂中心,半径区间为50~60 m,角度间隔120°(30°方位角、150°方位角、270°方位角)处的3点,共4点作为风轮扫掠面特征风速的代表点。在这4点位置处选取长20 m宽18 m区域,区域内平均风速值作为多步风速估计的4个输出变量,分别为point 1、point 2、point 3和point 4。输入变量为机舱风速、桨距角、风轮转速和激光雷达所测机前200 m风速值。
最优历史时间步长为180 s,最优预测时间步长为80 s,在7种风况下进行多点特征风速超短期多步动态估计。为验证本文所提出模型的可行性,将xLSTM-Mixer模型与传统LSTM、Transformer模型进行对比,部分风况对比结果如图5图6所示。
模型评估结果见表3,由图5图6表3可见:
1)数值精准性(平均相对误差)
xLSTM-Mixer模型的数值估计误差(0.17%~2.78%)显著低于LSTM模型(3.95%~10.79%)与Transformer模型(4.22%~12.35%),精确度提高了约10%,主要源于其混合结构优势:xLSTM模型通过改进门控机制缓解梯度消失,稳定学习多风况下风速趋势,Mixer模块借助跨特征交互精准捕捉湍流局部波动,避免过度平滑或敏感。而LSTM模型传统门控易过滤湍流有效信号,Transformer模型自注意力机制在小样本时间序列中易过拟合局部噪声,均导致数值预测稳定性不足、误差波动显著。
2)分布匹配度(KS统计量)
相同风况、湍流组合下,风速数据的均值、方差及分位数等分布特征具有稳定性,KS统计量验证了xLSTM-Mixer模型(KS值0.050 0~0.178 5)的全局统计规律适配性,预测分布与真实分布高度相似,可稳定复现数据统计特性。LSTM、Transformer模型的KS值显著偏高(0.150 0~0.600 0),主要原因是LSTM模型在小样本任务中,受高参数冗余度制约,模型无法有效分离真实分布与噪声分布,其过拟合噪声的特性会随迭代过程加剧预测分布与真实分布的偏差,Transformer模型自注意力计算放大局部异常值影响,引发预测分布偏态偏移。
3)结构捕捉能力(SSIM)
SSIM指标量化风速数据动态趋势连续性,xLSTM-Mixer模型的SSIM值在0.968 8~0.994 1,表明其预测序列与真实序列在趋势形态、峰谷位置及波动节奏上高度契合,可精准复现风速动态变化规律。LSTM、Transformer模型的SSIM值趋近于0,本质是结构与数据特性不匹配,LSTM模型隐藏层状态更新对趋势转折敏感性不足,难以跟随风速快速变化。Transformer模型自注意力权重分配缺乏时间序列局部关联性约束,导致预测序列无规律波动,与真实结构完全脱节。
数据结果表明xLSTM-Mixer模型不仅数值预测精准,而且能匹配数据的分布规律与结构特征。在特征风速预测方面,xLSTM-Mixer模型优于传统LSTM、Transformer模型。
本文针对轮毂高度单点风速难以表征入流风速的局限,提出了面向大型风电机组的多点特征风速选择方法及基于xLSTM-Mixer的动态估计模型。结论如下:
1)创新提出了RF-Boruta分步算法,实现10 MW致动线型风电机组超大风轮扫掠面内特征风速点的稳定筛选,特征点数量在同一风况下波动小(BCV<5%),空间分布固定,满足工程的稳定性与唯一性要求;不同风况下,平均风速主导特征点数量,湍流强度仅产生边际影响,验证了所选特征点的有效性。
2)4点代表性特征风速点(轮毂中心及以半径50~60 m、方位角30°、150°、270°的3点)成功克服单点风速的局部性与片面性,为风功率预测和机组运行控制提供了可靠的风场信息支撑。
3)构建xLSTM-Mixer模型,对上述4点风速进行超短期多步估计,精度达97.2%(秒级响应),相较于传统LSTM、Transformer模型精度提升约10%,同时更能匹配数据的分布规律与结构特征,显著提升了风能利用效率和发电量评估的可靠性。
  • 国家自然科学基金项目(62473152)
参考文献 引证文献
排序方式:
[1]
ØSTERGAARD K Z, BRATH P, STOUSTRUP J. Estimation of effective wind speed[J]. Journal of Physics: Conference Series, 2007, 75: 012082.
[2]
李颖峰,许瑾,刘美岑,. 基于机舱激光雷达的风力机增益预置前馈控制方法研究[J]. 热力发电202251(7):9-16.
LI Yingfeng, XU Jin, LIU Meicen, et al. Research on gain scheduled feedforward control method of wind turbine based on nacelle LIDAR[J]. Thermal Power Generation, 2022, 51(7): 9-16.
[3]
牛洪涛,杨从新,刘文杰. 来流风剪切及其对风力机性能影响的实验研究[J]. 太阳能学报202546(8):78-83.
NIU Hongtao, YANG Congxin, LIU Wenjie. Experimental study of incoming flow shear and its influence on performance of wind turbine[J]. Acta Energiae Solaris Sinica, 2025, 46(8): 78-83.
[4]
TAN J, HU W H, WANG X R, et al. Effect of tower shadow and wind shear in a wind farm on AC tie-line power oscillations of interconnected power systems[J]. Energies, 2013, 6(12): 6352-6372.
[5]
CAMBLONG H, MARTINEZ DE ALEGRIA I, RODRIGUEZ M, et al. Experimental evaluation of wind turbines maximum power point tracking controllers[J]. Energy Conversion and Management, 2006, 47(18/19): 2846-2858.
[6]
Wind energy generation systems: Part 12-1: Power performance measurements of electricity producing wind turbines: IEC 61400-12-1: 2022, Edition 3.0[S]. Geneva, Switzerland: International Electrotechnical Commission, 2022: 5.
[7]
风力发电机组功率特性测试:GB/T 18451.2—2021[S]. 北京:中国标准出版社,2021:3.
Wind turbines: power performance testing of electricity producing wind turbines: GB/T 18451.2 — 2021[S]. Beijing: China Standards Press, 2021: 3.
[8]
陈文婷,张铂炅,林勇刚,. 基于激光雷达的风力机分离测风独立变桨控制策略[J]. 太阳能学报202243(2):415-423.
CHEN Wenting, ZHANG Bojiong, LIN Yonggang, et al. Separated wind measurement individual pitch control of wind turbine based on lidar[J]. Acta Energiae Solaris Sinica, 2022, 43(2): 415-423.
[9]
李颖,雷熠,莫尔兵,. 风力发电机组机舱式激光测风雷达可用性评价[J]. 东方汽轮机2021(2):63-67.
LI Ying, LEI Yi, MO Erbing, et al. Availability of LIDAR used in wind turbine[J]. Dongfang Turbine, 2021(2): 63-67.
[10]
BOSSANYI E A, KUMAR A, HUGUES S O. Wind turbine control applications of turbine-mounted LIDAR[J]. Journal of Physics: Conference Series, 2014, 555: 12011.
[11]
迟林,刘智超,姜禹含,. 机舱式激光雷达在风电后市场领域的应用[J]. 电力系统装备2023(9):5-7.
CHI Lin, LIU Zhichao, JIANG Yuhan, et al. Application of cabin lidar in the wind power aftermarket[J]. Electric Power System Equipment, 2023(9): 5-7.
[12]
曲晨志,林忠伟,刘吉臻,. 多源数据驱动的风电机组偏航稳态误差校准方法及现场应用测试[J]. 动力工程学报202545(4):544-581.
QU Chenzhi, LIN Zhongwei, LIU Jizhen, et al. Multi-source data-driven yaw steady-state error calibration method for wind turbines and field application testing[J]. Journal of Chinese Society of Power Engineering, 2025, 45(4): 544-581.
[13]
王立强,曹斌,王琪,. 基于RT-LAB的双馈风电机组建模与仿真[J]. 内蒙古电力技术202038(4):43-46.
WANG Liqiang, CAO Bin, WANG Qi, et al. Modeling and simulation of doubly fed wind turbine based on RT-LAB[J]. Inner Mongolia Electric Power, 2020, 38(4): 43-46.
[14]
刘坤,卓锡鑫,余高阳,. 等效风速与轮毂风速对风电机组功率曲线的评估对比分析[J]. 机电工程技术202251(4):102-105.
LIU Kun, ZHUO Xixin, YU Gaoyang, et al. Evaluation and comparative analysis of equivalent wind speed and hub wind speed on wind turbine power curve[J]. Mechanical & Electrical Engineering Technology, 2022, 51(4): 102-105.
[15]
RYU G H, KIM D, KIM D Y, et al. Analysis of vertical wind shear effects on offshore wind energy prediction accuracy applying rotor equivalent wind speed and the relationship with atmospheric stability[J]. Applied Sciences, 2022, 12(14): 6949.
[16]
WU C, LUO K, WANG Q, et al. A refined wind farm parameterization for the weather research and forecasting model[J]. Applied Energy, 2022, 306: 118082.
[17]
万庆祝,吴开聪. 基于随机森林分类的直流微电网孤岛检测[J]. 太阳能学报202243(1):269-274.
WAN Qingzhu, WU Kaicong. Islanding detection for dc microgrid based on random forest classification[J]. Acta Energiae Solaris Sinica, 2022, 43(1): 269-274.
[18]
LAKMINI PRARTHANA JAYASINGHE W J M, DEO R C, GHAHRAMANI A, et al. Deep multi-stage reference evapotranspiration forecasting model: multivariate empirical mode decomposition integrated with the boruta-random forest algorithm[J]. IEEE Access, 2021, 9: 166695-166708.
[19]
LI J, LIU Y K, GONG H F, et al. Stock price series forecasting using multi-scale modeling with boruta feature selection and adaptive denoising[J]. Applied Soft Computing, 2024, 154: 1-22.
[20]
JULIER S J, UHLMANN J K. Unscented filtering and nonlinear estimation[J]. Proceedings of the IEEE, 2004, 92(3): 401-422.
[21]
陈兴鹃,周杰,李家强,. 基于非线性滤波的风廓线雷达数据处理[J]. 南京信息工程大学学报20135(6):533-538.
CHEN Xingjuan, ZHOU Jie, LI Jiaqiang, et al. Data processing of wind profiler radar based on nonlinear filtering[J]. Journal of Nanjing University of Information Science and Technology, 2013, 5(6): 533-538.
[22]
GEORGE E P B, GWILYM M J, GREGORY C R, et al. Time series analysis: forecasting and control[M]. 5th ed. Wiley, 2015: 90-112.
[23]
易丹辉. 时间序列分析:方法与应用[M]. 2版. 北京:中国人民大学出版社,2018:69-72.
YI Danhui. Time series analysis: methods and application[M]. 2th ed. Beijing: China Renmin University Press, 2018: 69-72.
[24]
CHRISTOPHER J C, BURGES A. Tutorial on support vector machines for pattern recognition[J]. Data Mining and Knowledge Discovery, 1998, 2: 121-167.
[25]
BECK M, PÖPPEL K, SPANRING M, et al. xLSTM: extended long short-term memory[J/OL]. Computer Science, 2024. https://proceedings.neurips.cc/paper_files/paper/2024/hash/c2ce2f2701c10a2b2f2ea0bfa43cfaa3-Abstract-Conference.html.
[26]
BAK C, ZAHLE F, et al. The DTU 10-MW reference wind turbine[R/OL]. Roskilde: DTU Wind Energy, 2013. [2025-10-15]. https://dtuwindenergy.dk/publications/the-dtu-10-mw-reference-wind-turbine/.
[27]
Wind energy generation systems: Part 3-1: Design requirements for fixed offshore wind turbines: IEC 61400-3-1: 2019[S]. Geneva, Switzerland: International Electrotechnical Commission, 2019: 10.
[28]
王渊博,李春,缪维跑,. 基于致动线方法的风力机组尾迹控制策略研究[J]. 太阳能学报201839(11):3224-3230.
WANG Yuanbo, LI Chun, MIAO Weipao, et al. Research of control strategies for wind turbines wake based on ALM[J]. Acta Energiae Solaris Sinica, 2018, 39(11): 3224-3230.
[29]
SHEN W Z, ZHU W J, SØRENSEN J N. Actuator line/Navier-Stokes computations for the MEXICO rotor: comparison with detailed measurements[J]. Wind Energy, 2012, 15(5): 811-825.
2026年第55卷第5期
PDF下载
220
95
引用本文
BibTeX
文章信息
doi: 10.19666/j.rlfd.202510030
  • 接收时间:2025-10-15
  • 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:2025-10-15
  • 修回日期:2025-12-29
  • 录用日期:2026-01-05
基金
National Natural Science Foundation of China(62473152)
国家自然科学基金项目(62473152)
作者信息
    1.新能源电力系统全国重点实验室(华北电力大学),北京 102206
    2.华北电力大学控制与计算机工程学院,北京 102206

通讯作者:

胡阳(1986),男,博士,副教授,主要研究方向为新能源发电建模及控制等,
参考文献
分享链接
https://castjournals.cast.org.cn/joweb/rlfd/CN/10.19666/j.rlfd.202510030
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