Clustering Method of High-dimensional Time Series SCADA Data from Wind Turbines Based on Operational Laws and TICC Algorithm

doi:10.3901/JME.2022.23.196

Abstract

Abstract: Aiming at the working condition identification of high-dimensional SCADA time series data from wind turbines, a new time series clustering method is proposed by combining the operational laws of wind turbines and the TICC algorithm. A small set of key parameters such as wind velocity, rotational speed and pitch angle are selected from the high-dimensional SCADA data as the cluster datasets. The repeated patterns in temporal data of the key parameters and the theoretical operational conditions of wind turbines are analyzed. Some historical data of key parameters are used to obtain the optimal feature parameters by the TICC algorithm. The optimal feature parameters are then taken as the input of the TICC algorithm which clusters new time series data of the key parameters. Finally, the SCADA time series data of non-key parameters are segmented and clustered based on the clustering results of the key parameters. The SCADA data of 2.5 MW doubly-fed induction generator wind turbine are used to validate the present method. Performance comparison of TICC algorithm, FCM algorithm, GMM algorithm and K-Means algorithm with respect to SCADA data cluster are analyzed. The validation example and comparative study show that the proposed method takes full advantage of the theoretical knowledge and the TICC algorithm. It can efficiently segment and cluster high-dimensional time series SCADA data while the clustering results are consistent with the theoretical results.

Key words: wind turbine, SCADA data, TICC algorithm, time series clustering

CLC Number:

TM614

XIAO Zhao, DENG Jiewen, LIU Xiaoming, DUAN Shuyong, XU Shouliang. Clustering Method of High-dimensional Time Series SCADA Data from Wind Turbines Based on Operational Laws and TICC Algorithm[J]. Journal of Mechanical Engineering, 2022, 58(23): 196-207.

References

[1] ENEVOLDSEN P,JACOBSON M Z. Data investigation of installed and output power densities of onshore and offshore wind turbines worldwide[J]. Energy for Sustainable Development,2021,60:40-51.
[2] 秦海岩. "十四五",大力发展风电正当时[J]. 风能,2021,11:1-2. QIN Haiyan. A good opportunity to develop wind energy during the 14th Five-Year Plan period[J]. Wind Energy,2021,11:1-2.
[3] 金晓航,孙毅,单继宏,等. 风力发电机组故障诊断与预测技术研究综述[J]. 仪器仪表学报,2017,385:1041-1053. JIN Xiaohang,SUN Yi,SHAN Jihong,et al. Review of wind turbine fault diagnosis and prediction technology research[J]. Chinese Journal of Scientific Instrument,2017,385:1041-1053.
[4] 张帆,刘德顺,戴巨川,等. 一种基于SCADA参数关系的风电机组运行状态识别方法[J]. 机械工程学报,2019,55(4):1-9. ZHANG Fan,LIU Deshun,DAI Juchuan,et al. A method for identifying the operating state of wind turbines based on SCADA parameter relationship[J]. Journal of Mechanical Engineering,2019,55(4):1-9.
[5] CHEN Hansi,LIU Hang,CHU Xuening,et al. Anomaly detection and critical SCADA parameters identification for wind turbines based on LSTM-AE neural network[J]. Renewable Energy,2021,1721:1.
[6] 董兴辉,李佳,高迪,等. 风电机组效能和性能统一评估模型研究[J]. 机械工程学报,2021,57(14):253-260. DONG Xinghui,LI Jia,GAO Di,et al. Research on unified assessment model of wind turbine efficiency and performance[J]. Journal of Mechanical Engineering,2021,57(14):253-260.
[7] 刘帅,刘长良,甄成刚. 基于数据分类重建的风电机组故障预警方法[J]. 仪器仪表学报,2019,40(8):1-11. LIU Shuai,LIU Changliang,ZHEN Chenggang. A fault early warning method for wind turbines based on data classification and reconstruction[J]. Chinese Journal of Scientific Instrument,2019,40(8):1-11.
[8] PANG Yanhua,HE Qun,JIANG Guoqian,et al. Spatio-temporal fusion neural network for multi-class fault diagnosis of wind turbines based on SCADA data[J]. Renewable Energy,2020,161:510-524.
[9] LI Yanting,LIU Shujun. Wind turbine fault diagnosis based on Gaussian process classifiers applied to operational data[J]. Renewable Energy,2018,134:1.
[10] YANG Wenxian,COURT R,JIANG Jiesheng. Wind turbine condition monitoring by the approach of SCADA data analysis[J]. Renewable Energy,2013,539:365-376.
[11] 郭慧东,王玮,夏明超. 基于数据挖掘的风电机组变桨系统劣化状态在线辨识方法[J]. 中国电机工程学报,2016,369:9. GUO Huidong,WANG Wei,XIA Mingchao. On-line identification method of wind turbine pitch system degradation state based on data mining[J]. Chinese Journal of Electrical Engineering,2016,369:9.
[12] 董玉亮,李亚琼,曹海斌,等. 基于运行工况辨识的风电机组健康状态实时评价方法[J]. 中国电机工程学报,2013,33(11):88-95. DONG Yuliang,LI Yaqiong,CAO Haibin,et al. Real-time evaluation method of wind turbine health status based on operating condition identification[J]. Chinese Journal of Electrical Engineering,2013,33(11):88-95.
[13] LAPIRA E,BRISSET D,ARDAKANI H D,et al. Wind turbine performance assessment using multi-regime modeling approach[J]. Renewable Energy,2012,45:86-95.
[14] JIA Xiaodong,CHAO Jin,BUZZA M,et al. Wind turbine performance degradation assessment based on a novel similarity metric for machine performance curves[J]. Renewable Energy,2016,99:1191-1201.
[15] XIAO Zhao,ZHAO Qiancheng,YANG Xuebing,et al. A power performance online assessment method of a wind turbine based on the probabilistic area metric[J]. Applied Sciences,2020,10:1.
[16] ZHU Anfeng,XIAO Zhao,ZHAO Qiancheng. Power data preprocessing method of mountain wind farm based on POT-DBSCAN[J]. Energy Engineering,2021,118(3):549-563.
[17] BECKER E,POSTE P. Keeping the blades turning:Condition monitoring of wind turbine gears[J]. Wind Energy,2006,7(2):26-32.
[18] 刘永前,王飞,时文刚,等. 基于支持向量机的风电机组运行工况分类方法[J]. 太阳能学报,2010,31(9):1191-1197. LIU Yongqian,WANG Fei,SHI Wengang,et al. Operation condition classification method for wind turbine based on support vector machine[J]. Acta Energiae Solaris Sinica,2010,31(9):1191-1197.
[19] HIMBERG J,KORPIAHO K,MANNILA H,et al. Time series segmentation for context recognition in mobile devices[C]//IEEE International Conference on Data Mining. IEEE,2002:1.
[20] BEGUM N,ULANOVA L,WANG Jun,et al. Accelerating dynamic time warping clustering with a novel admissible pruning strategy[C]//ACM Sigkdd International Conference on Knowledge Discovery & Data Mining. ACM,2015:49-58.
[21] HALLAC D,NYSTRUP P,BOYD S. Greedy gaussian segmentation of multivariate time series[J]. Advances in Data Analysis and Classification,2016,13:727-751.
[22] HALLAC D,VARE S,BOYD S,et al. Toeplitz inverse covariance-based clustering of multivariate time series data[C]//The 23rd ACM SIGKDD International Conference. ACM,2017:1.