基于分布特征的风电异常数据检测方法

苗长新; 周志伟; 杨千禧; 席剑; 韩丽

doi:10.19912/j.0254-0096.tynxb.2024-0443

PDF(10655 KB)

太阳能学报 ›› 2025, Vol. 46 ›› Issue (7) : 395-402. DOI: 10.19912/j.0254-0096.tynxb.2024-0443

第二十七届中国科协年会学术论文

基于分布特征的风电异常数据检测方法

苗长新¹, 周志伟¹, 杨千禧¹, 席剑², 韩丽¹

作者信息 +

ANOMALY DETECTION METHOD FOR WIND POWER BASED ON DISTRIBUTION CHARACTERISTICS

Miao Changxin¹, Zhou Zhiwei¹, Yang Qianxi¹, Xi Jian², Han Li¹

Author information +

文章历史 +

摘要

风电场获取的机组运行数据中存在着大量非正常样本,不能够正确反映机组的工作状态,限制状态评估和功率预测等任务的进行。为此提出一种根据实测风电机组运行数据中不同异常分布特征选择针对性检测手段的识别方法,该方法考虑机组的工作状态,使用自适应的带噪声密度聚类算法,以风速、功率、叶片俯仰角作为输入,最小平均距离作为目标函数,实现算法的参数寻优。以最小二乘法拟合清洗后数据的功率曲线,计算清洗数据与曲线的绝对平均误差,与其他常用算法进行对比,并以中国真实数据集验证模型的有效性。

Abstract

A large amount of abnormal samples are obtained in the operational data collected from wind farms, which prevent the implementation of tasks such as state assessment and power prediction. To overcome this issue, a recognition method which selects targeted detection methods based on different abnormal distribution characteristics in measured wind turbine operational datasets is proposed in the article. The method considers the working state of the unit and uses an adaptive clustering algorithm with noise density, taking wind speed, power, and blade pitch angle as inputs, and the minimum average distance as the objective function to achieve parameter optimization of the algorithm. In order to verify the effectiveness of the model, the power curve of the cleaned data is fitted using the least squares method, and then the absolute average error is calculated and compared with other commonly used algorithms on actual datasets in China.

导出引用

苗长新, 周志伟, 杨千禧, 席剑, 韩丽. 基于分布特征的风电异常数据检测方法[J]. 太阳能学报. 2025, 46(7): 395-402 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0443

Miao Changxin, Zhou Zhiwei, Yang Qianxi, Xi Jian, Han Li. ANOMALY DETECTION METHOD FOR WIND POWER BASED ON DISTRIBUTION CHARACTERISTICS[J]. Acta Energiae Solaris Sinica. 2025, 46(7): 395-402 https://doi.org/10.19912/j.0254-0096.tynxb.2024-0443

中图分类号： TM71

参考文献

[1] 张沛, 左鹏, 谢桦, 等. 风电场异常数据辨识与重构技术综述[J]. 电力信息与通信技术, 2023, 21(4): 16-24.
ZHANG P, ZUO P, XIE H, et al.Review of wind farm abnormal data identification and reconstruction techniques[J]. Electric power information and communication technology, 2023, 21(4): 16-24.
[2] 吴永斌, 张建忠, 袁正舾, 等. 风电场风功率异常数据识别与清洗研究综述[J]. 电网技术, 2023, 47(6): 2367-2380.
WU Y B, ZHANG J Z, YUAN Z X, et al.Review on identification and cleaning of abnormal wind power data for wind farms[J]. Power system technology, 2023, 47(6): 2367-2380.
[3] ZOU M Z, DJOKIC S Z.A review of approaches for the detection and treatment of outliers in processing wind turbine and wind farm measurements[J]. Energies, 2020, 13(16): 4228.
[4] 李莉, 梁袁, 林娜, 等. 考虑时空相关性的风电机组风速清洗方法[J]. 太阳能学报, 2024, 45(6): 461-469.
LI L, LIANG Y, LIN N, ,et al. Data cleaning method considering temporal and spatial correlation for measured wind speed of wind turbines[J]. Acta energiae solaris sinica, 2024, 45(6): 461-469.
[5] PANG G,SHEN C, CAO L,et al.Deep learning for anomaly detection:a review[J]. ACM computing surveys (CSUR), 2021, 54(2):1-38.
[6] 江国乾, 周俊超, 武鑫, 等. 基于空洞因果卷积网络的风电机组异常检测[J]. 太阳能学报, 2023, 44(5): 368-375.
JIANG G Q, ZHOU J C, WU X, et al.Wind turbine anomaly detection based on detailed causal convolution network[J]. Acta energiae solaris sinica, 2023, 44(5):368-375.
[7] MORRISON R, LIU X L, LIN Z.Anomaly detection in wind turbine SCADA data for power curve cleaning[J]. Renewable energy, 2022, 184: 473-486.
[8] 徐昊, 王永生, 许志伟, 等. 基于生成对抗网络多变量风电时间序列异常值处理[J]. 太阳能学报, 2022, 43(12): 300-311.
XU H, WANG Y S, XU Z W, et al.Outlier processing of multivariable wind power time series based on generative adversarial network[J]. Acta energiae solaris sinica, 2022, 43(12): 300-311.
[9] 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, 2018, 9(1): 95-105.
[10] 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.
ZOU T H, GAO Y P, YI H J, et al.Processing of wind power abnormal data based on Thompson tau-quartile and multi-point interpolation[J]. Automation of electric power systems, 2020, 44(15): 156-162.
[11] 李特, 王荣喜, 高建民. 基于改进DBSCAN的风电机组SCADA异常数据识别方法[J]. 西安交通大学学报,2024(3): 1-10.
LI T,WANG R X,GAO J M.A method for wind turbine SCADA abnormal data recognition based on improved DBSCAN[J]. Journal of Xi’an Jiaotong University,2024(3):1-10.
[12] LONG H, SANG L W, WU Z J, et al.Image-based abnormal data detection and cleaning algorithm via wind power curve[J]. IEEE transactions on sustainable energy, 2020, 11(2): 938-946.
[13] LONG H, XU S H, GU W.An abnormal wind turbine data cleaning algorithm based on color space conversion and image feature detection[J]. Applied energy, 2022, 311: 118594.
[14] LUO Z H, FANG C Y, LIU C L, et al.Method for cleaning abnormal data of wind turbine power curve based on density clustering and boundary extraction[J]. IEEE transactions on sustainable energy, 2022, 13(2): 1147-1159.
[15] 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.
YANG M, YANG C L, YANG Q Q, et al.Study on data recognition of wind power abnormality considering wind direction information[J]. Acta energiae solaris sinica, 2019, 40(11): 3265-3272.
[16] 曾祥军, 冯琛, 杨明, 等. 考虑运行状态相似性的风电机组数据异常检测方法[J]. 电力系统自动化, 2022, 46(11): 170-180.
ZENG X J, FENG C, YANG M, et al.Data anomaly detection method for wind turbines considering operation state similarity[J]. Automation of electric power systems, 2022, 46(11): 170-180.
[17] DAO P B.Condition monitoring and fault diagnosis of wind turbines based on structural break detection in SCADA data[J]. Renewable energy, 2022, 185: 641-654.
[18] YAN J, ZHANG H, LIU Y Q, et al.Uncertainty estimation for wind energy conversion by probabilistic wind turbine power curve modelling[J]. Applied energy, 2019, 239: 1356-1370.
[19] 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.
SHEN X J, FU X J, ZHOU C C, et al.Characteristics of outliers in wind speed-power operation data of wind turbines and its cleaning method[J]. Transactions of China Electrotechnical Society, 2018, 33(14): 3353-3361.
[20] FALAHIAZAR Z,BAGHERI A,RESHADI M.Determining the parameters of DBSCAN automatically using the multi-objective genetic algorithm[J]. Journal of information science and engineering, 2021, 37(1):157-183.