大型风力机异常功率数据清洗方法

兰州理工大学学报 ›› 2022, Vol. 48 ›› Issue (3): 65-70.

大型风力机异常功率数据清洗方法

李琳^*1, 董博², 郑玉巧²

1.甘肃省特种设备检验检测研究院, 甘肃兰州 730050;
2.兰州理工大学机电工程学院, 甘肃兰州 730050

收稿日期:2022-01-19 出版日期:2022-06-28 发布日期:2022-10-09
通讯作者: 李琳(1964-),女,陕西宝鸡人,高级工程师.Email:292550607@qq.com

Abnormal power data cleaning method of the wind turbine based on improved DBSCAN

LI Lin¹, DONG Bo², ZHENG Yu-qiao²

1. Gansu Province Special Equipment Inspection and Testing Institute, Lanzhou 730050, China;
2. School of Mechanical and Electrical Engineering, Lanzhou Univ. of Tech., Lanzhou 730050, China

Received:2022-01-19 Online:2022-06-28 Published:2022-10-09

摘要/Abstract

摘要： 针对风力机异常功率数据难以有效清洗的问题,提出改进的DBSCAN方法.首先将数据集离散分割,然后在各离散区间内自适应粗估DBSCNA算法参数并聚类,最后计算统计特征相似性修正聚类结果.以某风场2.5 MW风力机SCADA系统实测数据验证所提方法,结果表明:改进方法的召回率为97.97%,准确率为97.97%,F₁值可达97.85%,可有效清洗风力机功率数据集,且变更数据集时改进方法结果更稳定.

关键词: 风力机, 异常功率, 数据清洗, 清洗质量, 改进DBSCAN方法

Abstract: The anomalous power data of wind turbine are difficult to clean effectively, an improved DBSCAN method was proposed. Firstly, the data set was segmented discretely. Then, the parameters of DBSCNA algorithm were estimated adaptively and clustered in each discrete interval. Ultimately, the statistical feature similarity was calculated to correct the clustering results. The proposed method is validated with the measured data of the wind turbine SCADA system in a wind field of 2.5 MW. The findings indicate that the recall rate, accuracy rate and F1 value of the improved method are 97.97%, 97.97% and 97.85%, respectively. The improved method can effectively clean the wind turbine power data set, and the improved method is more stable when the data set is changed.

Key words: wind turbine, abnormal power, data cleaning, cleaning quality, improved DBSCAN

中图分类号:

TK83

李琳, 董博, 郑玉巧. 大型风力机异常功率数据清洗方法[J]. 兰州理工大学学报, 2022, 48(3): 65-70.

LI Lin, DONG Bo, ZHENG Yu-qiao. Abnormal power data cleaning method of the wind turbine based on improved DBSCAN[J]. Journal of Lanzhou University of Technology, 2022, 48(3): 65-70.

参考文献

[1] WANG Y,HU Q H,LI L H,et al.Approaches to wind power curve modeling: A review and discussion [J].Renewable and Sustainable Energy Reviews,2019,116:109422.
[2] 杨茂,杨琼琼.风电机组风速-功率特性曲线建模研究综述 [J].电力自动化设备,2018,38(2):34-43.
[3] 董兴辉,张鑫淼,张光,等.基于云模型的风电机组输出功率特性分析 [J].机械工程学报,2017,53(22):212-219.
[4] 李航涛,郭鹏,杨锡运.基于离散度分析的风电机组功率曲线绘制方法研究 [J].太阳能学报,2019,40(1):237-241.
[5] DE ANDRADE VIEIRA R J,SANZ-BOBI M A,KATO S.Wind turbine condition assessment based on changes observed in its power curve [C]//International Conference on Renewable Energy Research and Applications.[S.l.]:IEEE,2014.
[6] 娄建楼,胥佳,陆恒,等.基于功率曲线的风电机组数据清洗算法 [J].电力系统自动化,2016,40(10):116-121.
[7] TASLIMI-RENANI E,MODIRI-DELSHAD M,ELIAS M F M,et al.Development of an enhanced parametric model for wind turbine power curve [J].Applied Energy,2016,177:544-552.
[8] 沈小军,付雪姣,周冲成,等.风电机组风速-功率异常运行数据特征及清洗方法 [J].电工技术学报,2018,33(14):3353-3361.
[9] 邹同华,高云鹏,伊慧娟,等.基于Thompson tau-四分位和多点插值的风电功率异常数据处理 [J].电力系统自动化,2020,44(15):156-162.
[10] 杨茂,杨春霖,杨琼琼,等.计及风向信息的风电功率异常数据识别研究 [J].太阳能学报,2019,40(11):3265-3272.
[11] OUYANG T H,KUSIAK A,HE Y S.Modeling wind-turbine power curve:A data partitioning and mining approach [J].Renewable Energy,2017,102(Mar.Pt.A):1-8.
[12] ZHAO Y N,YE L,WANG W S,et al.Data-driven correction approach to refine power curve of wind farm under wind curtailment [J].IEEE Transactions on Sustainable Energy,2017,9(1):95-105.
[13] ESTER M,KRIEGEL H P,SANDER J,et al.A density-based algorithm for discovering clusters in large spatial databases with noise [C]//Proceedings of 2nd International Conference on Knowledge Discovery and Data Mining.[S.l.]:AAAI,1996.
[14] 郝爽,李国良,冯建华,等.结构化数据清洗技术综述 [J].清华大学学报(自然科学版),2018,58(12):1037-1050.