提出基于风电机组监控与数据采集系统（SCADA）运行数据的分析和挖掘提升风电机组出力性能。通过风电机组运行状态和异常数据分析,采用改进的基于密度聚类识别算法（DBSCAN）,对环境变化引起的异常数据进行清洗和检测。再通过改进的移动最小二乘法B样条曲线回归模型,识别不同风速下最大机组出力对应的控制特性参数并反馈机组控制系统。在机组仿真验证的基础上,开展真实机组实际运行工况下的验证和分析,实际测试表明该方法对额定风速下系统效率提升较明显。
Abstract
This article proposes the analysis and mining of SCADA operation data to improve the output performance of wind turbines. By analyzing the operating status and abnormal data types of wind turbines, an improved DBSCAN clustering method is adopted to clean and detect abnormal data caused by environmental changes. By using an improved moving least squares B-spline regression model, the control characteristic parameters corresponding to the maximum unit output at different wind speeds are identified and fed back to the unit control system. On the basis of unit simulation verification, validation and analysis were carried out under actual operating conditions of real units. Actual tests show that this method significantly improved system efficiency at rated wind speed.
关键词
风电机组 /
运行数据 /
数据挖掘 /
DBSCAN算法 /
移动最小二乘法 /
控制特性参数
Key words
wind turbines /
operation data /
data mining /
DBSCAN algorithm /
moving least square method /
control characteristic parameters
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 金晓航, 泮恒拓, 徐正国. 数据驱动的风电机组变桨系统状态监测[J]. 太阳能学报, 2022, 43(4): 409-417.
JIN X H, PAN H T, XU Z G.Condition monitoring of wind turbine pitch system using data-driven approach[J]. Acta energiae solaris sinica, 2022, 43(4): 409-417.
[2] 韩万里, 茅大钧, 蔡晔, 等. 基于数据融合的风电变桨系统故障预警研究[J]. 太阳能学报, 2022, 43(12): 236-241.
HAN W L, MAO D J, CAI Y, et al.Research on fault warning of wind power pitch system based on data fusion[J]. Acta energiae solaris sinica, 2022, 43(12): 236-241.
[3] KUSIAK A, ZHENG H Y, SONG Z.Models for monitoring wind farm power[J]. Renewable energy, 2009, 34(3): 583-590.
[4] WANG Y, INFIELD D G, STEPHEN B, et al.Copula-based model for wind turbine power curve outlier rejection[J]. Wind energy, 2014, 17(11): 1677-1688.
[5] 赵永宁, 叶林, 朱倩雯. 风电场弃风异常数据簇的特征及处理方法[J]. 电力系统自动化, 2014, 38(21): 39-46.
ZHAO Y N, YE L, ZHU Q W.Characteristics and processing method of abnormal data clusters caused by wind curtailments in wind farms[J]. Automation of electric power systems, 2014, 38(21): 39-46.
[6] 马良玉, 孙佳明, 於世磊, 等. 基于DBSCAN和SDAE的风电机组异常工况预警研究[J]. 动力工程学报, 2021, 41(9): 786-793, 808.
MA L Y, SUN J M, YU S L, et al.DBSCAN and SDAE-based abnormal condition early warning for a wind turbine unit[J]. Journal of Chinese Society of Power Engineering, 2021, 41(9): 786-793, 808.
[7] KHALFALLAH M G, KOLIUB A M.Suggestions for improving wind turbines power curves[J]. Desalination, 2007, 209(1-3): 221-229.
[8] PELLETIER F, MASSON C, TAHAN A.Wind turbine power curve modelling using artificial neural network[J]. Renewable energy, 2016, 89: 207-214.
[9] 饶日晟, 叶林, 任成, 等. 基于实际运行数据的风电场功率曲线优化方法[J]. 中国电力, 2016, 49(3): 148-153.
RAO R S, YE L, REN C, et al.Wind farm power curve optimization based on actual operating data[J]. Electric power, 2016, 49(3): 148-153.
[10] WAN S T, CHENG L F, SHENG X L.Effects of yaw error on wind turbine running characteristics based on the equivalent wind speed model[J]. Energies, 2015, 8(7): 6286-6301.
PDF(1884 KB)
