A Method for Abnormal Data Recognition of Wind Turbine Supervisory Control and Data Acquisition Systems

LI Te; WANG Rongxi; GAO Jianmin

doi:10.7652/xjtuxb202403010

您当前的位置：

首页 >

文章列表页 >

A Method for Abnormal Data Recognition of Wind Turbine Supervisory Control and Data Acquisition Systems

更新时间：2025-07-09

- A Method for Abnormal Data Recognition of Wind Turbine Supervisory Control and Data Acquisition Systems
- Vol. 58, Issue 3, Pages: 106-116(2024)
- 作者机构：
  
  西安交通大学机械制造系统国家重点实验室,西安,710049
- 作者简介：
- 基金信息：
- DOI：10.7652/xjtuxb202403010
  CLC： TH17
- Online First：10 March 2024，
  
  Published：2024
- 稿件说明：
移动端阅览
LI Te, WANG Rongxi, GAO Jianmin. A Method for Abnormal Data Recognition of Wind Turbine Supervisory Control and Data Acquisition Systems[J]. 2024, 58(3): 106-116.
DOI：

LI Te, WANG Rongxi, GAO Jianmin. A Method for Abnormal Data Recognition of Wind Turbine Supervisory Control and Data Acquisition Systems[J]. 2024, 58(3): 106-116. DOI： 10.7652/xjtuxb202403010.

摘要

为了解决原始的风电机组数据采集与监控系统(SCADA)中包含大量异常记录的数据、难以准确反映机组运行状态的问题

提出了一种带噪声基于密度的空间聚类(DBSCAN)模型的风电机组SCADA异常数据识别方法。该方法从分析风速-功率曲线的特点出发

采用预测误差和分类准确度来选取关键聚类参数邻域半径和邻域最小样本点数

避免了人工确定聚类参数的主观性

且参数选择过程可以完全自动化

实现了风电机组SCADA异常数据的有效识别。通过某风场中风电机组的监测数据进行实例验证

结果表明:所提方法能够在保证异常数据被剔除的前提下

保留尽可能多的正常数据

异常识别效果好于现有的k-dist图法和基于k-平均最近邻算法的改进算法(KANN-DBSCAN)。该研究可为开展风电机组状态分析提供参考。

Abstract

To address the issue that wind turbines’ supervisory control and data acquisition(SCADA)system contains a significant amount of data about abnormal records

which affects the accurate representation of the turbines’ operational status

a method for identifying abnormal data based on density-based spatial clustering of applications with noise(DBSCAN)is proposed. which affects the accurate representation of the turbines’ operational status

a method for identifying abnormal data based on density-based spatial clustering of applications with noise（DBSCAN）is proposed. Based on the characteristics of the wind speed-power scatter curve

this method involves the use to selec-t the key clustering parameters： of prediction errors and classification accuracy neighborhood radius and minimum number of sample points in the neighborhood. It avoids the subjectivity of manually determining the clustering parameters

allowing for a fully automated parameter selection process. As a result

it achieves effective identification of abnormal data in a wind turbine’s SCADA system. The proposed method is validated using monitoring data from wind turbines in a specific wind farm. The results demonstrate that the method helps to retain as much normal data as possible while ensuring the removal of abnormal data. It also shows superior anomaly identification performance compared to k-distance graph and KANN-DBSCAN

an improved algorithm based on k-nearest neighbors. This study provides valuable insights for the status analysis of wind turbines.

关键词

Keywords

references

符杨, 许伟欣, 刘璐洁, 等. 考虑天气因素的海上风电机组预防性机会维护策略优化方法 [J]. 中国电机工程学报, 2018, 38(20): 5947-5956.

FU Yang, XU Weixin, LIU Lujie, et al.Optimization of preventive opportunistic maintenance strategy for offshore windturbine considering weather conditions [J]. Proceedings of the CSEE, 2018,38(20): 5947-5956.

胡姚刚. 大功率风电机组关键部件健康状态监测与评估方法研究 [D]. 重庆: 重庆大学, 2017.

尹诗, 侯国莲, 于晓东, 等. 基于SCADA数据的风电机组齿轮箱状态监测方法 [J]. 太阳能学报, 2021, 42(1): 324-332.

YIN Shi, HOU Guolian, YU Xiaodong, et al.Condition monitoring method of wind turbine gear box based on SCADA data [J].Acta Energiae Solaris Sinica, 2021, 42(1): 324-332.

DAO P B. Condition monitoring and faultdiagnosis of wind turbines based on structural break detection in SCADA data[J]. Renewable Energy, 2022, 185: 641-654.

RAHIMILARKI R, GAO Zhiwei, JIN Nanlin,et al. Convolutional neural network fault classification based on time-seriesanalysis for benchmark wind turbine machine [J]. Renewable Energy, 2022, 185:916-931.

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 Guoqian, ZHOU Junchao, WU Xin, et al.Wind turbine anomaly detection based on dilated causal convolution network [J].Acta Energiae Solaris Sinica, 2023, 44(5): 368-375.

郭怡, 王荣喜, 高建民. 融合分形特征的风机运行状态辨识方法 [J]. 计算机集成制造系统, 2022, 28(7): 2139-2148.

GUO Yi, WANG Rongxi, GAO Jianmin. Operationstate recognition method based on fractal features of wind turbines [J].Computer Integrated Manufacturing Systems, 2022, 28(7): 2139-2148.

MORRISON R, LIU Xiaolei, LIN Zi.Anomaly detection in wind turbine SCADA data for power curve cleaning [J].Renewable Energy, 2022, 184: 473-486.

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 Yongbin, ZHANG Jianzhong, YUAN Zhengxi,et al. Review on identification and cleaning of abnormal wind power data forwind farms [J]. Power System Technology, 2023, 47(6): 2367-2380.

WANG Yue, INFIELD D G, STEPHEN B, etal. Copula-based mode-l for wind turbine power curve outlier rejection [J]. WindEnergy, 2014, 17(11): 1677-1688.

HAN Shuang, QIAO Yanhui, YAN Ping, etal. Wind turbine power curve mode-ling based on interval extreme probabilitydensity for the integration of renewable energies and electric vehicles [J].Renewable Energy, 2020, 157: 190-203.

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 Xiaojun, FU Xuejiao, ZHOU Chongcheng,et al. Characteristics of outliers in wind speed-power operation data of windturbines and its cleaning method [J]. Transactions of China ElectrotechnicalSociety, 2018, 33(14): 3353-3361.

SHEN Xiaojun, FU Xuejiao, ZHOU Chongcheng.A combined algorithm for cleaning abnormal data of wind turbine power curvebased on change point grouping algorithm and quartile algorithm [J]. IEEETransactions on Sustainable Energy, 2019, 10(1): 46-54.

梅勇, 李霄, 胡在春, 等. 基于风电机组控制原理的风功率数据识别与清洗方法 [J]. 动力工程学报, 2021, 41(4): 316-322.

MEI Yong, LI Xiao, HU Zaichun, et al.Identification and cleaning of wind power data methods based on controlprinciple of wind turbine generator system [J]. Journal of Chinese Society ofPower Engineering,2021, 41(4): 316-322.

LONG Huan, SANG Linwei, WU Zaijun, etal. Image-based abnormal data detection and cleaning algorithm via wind powercurve [J]. IEEE Transactions on Sustainable Energy, 2020, 11(2): 938-946.

WANG Zhongju, WANG Long, HUANG Chao. Afast abnormal data cleaning algorithm for performance evaluation of windturbine [J]. IEEE Transactions on Instrumentation and Measurement, 2021, 70:1-12.

XU Qianyao, HE Dawei, ZHANG Ning, etal. A Short-term wind power forecasting approach with adjustment of numericalweather prediction input by data mining [J]. IEEE Transactions on SustainableEnergy, 2015, 6(4): 1283-1291.

ZHAO Yongning, YE Lin, WANG Weisheng,et al. Data-driven correction approach to refine power curve of wind farm underwind curtailment [J]. IEEE Transactions on Sustainable Energy, 2018, 9(1):95-105.

王一妹, 刘辉, 宋鹏, 等. 基于多阶段递进识别的风电机组异常运行数据清洗方法 [J]. 可再生能源, 2020, 38(11): 1470-1476.

WANG Yimei, LIU Hui, SONG Peng, et al. Anapproach for the cleaning of abnormal wind turbine operation data based onmulti-phase progressive recognition [J]. Renewable Energy Resources, 2020,38(11): 1470-1476.

雷萌, 郭鹏, 刘博嵩. 基于自适应DBSCAN算法的风电机组异常数据识别研究 [J]. 动力工程学报, 2021, 41(10): 859-865.

LEI Meng, GUO Peng, LIU Bosong. Study onabnormal data recognition of wind turbines based on adaptive DBSCAN algorithm[J]. Journal of Chinese Society of Power Engineering, 2021, 41(10): 859-865.

ESTER M, KRIEGEL H P, SANDER J, et al.A density-based algorithm for discovering clusters in large spatial databaseswith noise [C]//Proceedings of the Second International Conference on KnowledgeDiscovery and Data Mining. Palo Alto, CA, USA: AAAI Press, 1996: 226-231.

夏鲁宁, 荆继武.SA-DBSCAN: 一种自适应基于密度聚类算法 [J]. 中国科学院研究生院学报, 2009, 26(4): 530-538.

XIA Luning, JING Jiwu. SA-DBSCAN: aself-adaptive density-based clustering algorithm [J]. Journal of the GraduateSchool of the Chinese Academy of Sciences, 2009, 26(4): 530-538.

李文杰, 闫世强, 蒋莹, 等. 自适应确定DBSCAN算法参数的算法研究 [J]. 计算机工程与应用, 2019, 55(5): 1-7.

LI Wenjie, YAN Shiqiang, JIANG Ying, et al.Research on method of self-adaptive determination of DBSCAN algorithmparameters [J]. Computer Engineering and Applications, 2019, 55(5): 1-7.

周红芳, 王鹏. DBSCAN算法中参数自适应确定方法的研究 [J]. 西安理工大学学报, 2012, 28(3): 289-292.

ZHOU Hongfang, WANG Peng. Research onadaptive parameters determination in DBSCAN algorithm [J]. Journal of Xi’anUniversity of Technology, 2012, 28(3): 289-292.

万佳, 胡大裟, 蒋玉明. 多密度自适应确定DBSCAN算法参数的算法研究 [J]. 计算机工程与应用, 2022, 58(2): 78-85.

WAN Jia, HU Dasha, JIANG Yuming. Researchon method of multi-density self-adaptive determination of DBSCAN algorithmparameters [J]. Computer Engineering and Applications, 2022, 58(2): 78-85.

Views

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Model Predictive Control-Oriented Deep Koopman Global Linear Modeling Method for Wind Turbines

Model Predictive Control-Oriented Deep Koopman Global Linear Modeling Method for Wind Turbine

Integrated and Joint Design Optimization of Centrifugal Compressor Impeller and Casing Treatment at Multiple Working Points

Review of the Application of EBSILON Software in Combined Heat and Power System Optimization

Bi-Level Multi-Obj ective Optimization of a Wind-Solar Coupled Hydrogen Production System Based on the Synergy of Hybrid Electrolyzer Arrays

Related Author

TIAN Runze

KOU Peng

WU Yikun

ZHANG Zhihao

ZHANG Yuanhang

WANG Ruotao

HAO Shouli

LIANG Deliang

Related Institution

School of Electrical Engineering, Xi'an Jiaotong University

Shaanxi Key Laboratory of Smart Grid, Xi'an Jiaotong University

State Key Laboratory of Electrical Insulation and Power Equipment, Xi'an Jiaotong University

Northern Branch, Beijing Jingneng International Holding Co., Ltd.

School of Electrical Engineering, Xi’an Jiaotong University

⁰