针对风电机组塔架振动监测问题,考虑到风能脉动与机组控制动作等激励对塔架振动的影响,提出一种基于数据驱动的塔架振动监测方法。首先基于K-均值算法对风电机组工况进行辨识,分析各状态参量、机组工况对塔架振动的影响;其次基于极限梯度提升（XGBoost）算法对不同工况下的塔架振动趋势进行建模预测,针对同一风电场不同塔架振动预测残差的差异,提出一种基于Wasserstein距离的塔架振动监测方法;最后使用风电场实际数据验证,以误差平方和为评价指标,考虑机组工况条件的XGBoost预测精度提高了34.6%。基于数据驱动的方法能有效识别风电场中异常振动较频繁的塔架,提升了运维效率。
Abstract
A data-driven tower vibration monitoring method considering the influence of wind pulsation and turbine control action on tower sproposed for solving the problem of tower vibration monitoring. Firstly, the operation conditions of wind turbine are identified based on K-means clustering, and the effects of various state parameters and operation conditions on tower are analyzed. Secondly, the tower vibration trend under different operation conditions is modeled and predicted based on XGBoost algorithm; a tower vibration monitoring method based on Wasserstein distance is proposed according to the difference of preicted residual errors of different towers in the same wind farm. Finally, the actual data of the wind farm is used for verification, taking the sum of squared error as the evaluation index, and the results show that the method considering turbine operation conditions improves the accuracy of the tower vibration prediction by 34.6%. The data-driven method effectively identifies the tower with frequent abnormal vibration in the wind farm and improves the efficiency of operation and maintenance.
关键词
风电机组 /
塔架振动 /
数据驱动 /
XGBoost /
Wasserstein距离
Key words
wind turbines /
tower vibration /
data-driven /
XGBoost /
Wasserstein distance
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] HOANG D T, KANG H J.A survey on deep learning based bearing fault diagnosis[J]. Neurocomputing, 2019, 335: 327-335.
[2] KUSIAK A, ZHANG Z J.Control of wind turbine power and vibration with a data-driven approach[J]. Renewable energy, 2012, 43(7): 73-82.
[3] 王屹立, 朱才朝, 朱永超. 多信号融合的风电齿轮箱异常状态检测[J]. 太阳能学报, 2021, 42(5): 380-386.
WANG Y L, ZHU C C, ZHU Y C.Anomaly detection of wind turbine gearbox based on multi-signal fusion[J]. Acta energiae solaris sinica, 2021, 42(5): 380-386.
[4] 周进, 房宁, 郭鹏. 基于相对主元分析的风电机组塔架振动状态监测与故障诊断[J]. 电力建设, 2014, 35(8): 125-129.
ZHOU J, FANG N, GUO P.Tower vibration fault diagnosis and monitoring for wind turbines based on RPCA[J]. Electric power construction, 2014, 35(8): 125-129.
[5] YU H, JIAN Y, CHARALAMPOS B, et al.Dynamic analysis of offshore steel wind turbine towers subjected to wind, wave and current loading during construction[J]. Ocean engineering, 2020, 216: 108084.
[6] 孙铁雷, 张翔, 许千寿, 等. 基于有限元法的风电机组塔架暂态响应研究[J]. 工业控制计算机, 2018, 31(12): 17-18.
SUN T L, ZHANG X, XU Q S, et al.Research on transient response of wind turbine tower based on finite element method[J]. Industrial control computer, 2018, 31(12): 17-18.
[7] ZHAO Y, PAN J N, HUANG Z Y, et al.Analysis of vibration monitoring data of an onshore wind turbine under different operational conditions[J]. Engineering structures, 2020, 205: 1-15.
[8] KIM H C, KIM M H, CHOE D E.Structural health monitoring of towers and blades for floating offshore wind turbines using operational modal analysis and modal properties with numerical-sensor signals[J]. Ocean engineering, 2019, 188: 1-13.
[9] AHMET U, DILEK A O, FURKAN S, et al.Condition monitoring of wind turbine blades and tower via an automated laser scanning system[J]. Engineering structures, 2019, 189: 25-34.
[10] FANG N, GUO P.Wind generator tower vibration fault diagnosis and monitoring based on PCA[C]//Chinese Control and Decision Conference, Guiyang, China, 2013: 1924-1929.
[11] 朱永超, 朱才朝, 宋朝省, 等. PCA-PSO/GS-SVM组合方法在风电齿轮箱故障预测中的应用研究[J]. 太阳能学报, 2021, 42(3): 36-42.
ZHU Y C, ZHU C C, SONG C S, et al.Application of PCA-PSO/GS-SVM combination method in fault prediction of wind turbine gearbox[J]. Acta energiae solaris sinica, 2021, 42(3): 36-42.
[12] CHEN L T, XU G H, ZHANG Q, et al.Learning deep representation of imbalanced SCADA data for fault detection of wind turbines[J]. Measurement, 2019, 130: 370-379.
[13] FU B, ZHAO J B, LI B Q, et al.Fatigue reliability analysis of wind turbine tower under random wind load[J]. Structural safety, 2020, 87: 101982.
[14] 郑小霞, 李美娜. 基于小波包和并行隐马尔科夫的风力机易损部件健康状态评价[J]. 太阳能学报, 2019, 40(2): 370-379.
ZHENG X X, LI M N.Health state evaluation based on wavelet packet and PCHMM for vulnerable components of wind turbines[J]. Acta energiae solaris sinica, 2019, 40(2): 370-379.
[15] CHEN T Q, GUESTRIN C.XGBoost: a scalable tree boosting system[C]//The 22nd ACM SIGKDD International Conference, ACM, Haliks, Canada, 2016.
[16] 钱晓华, 郭树旭, 李雪妍. 基于Wasserstein距离的局部能量分割模型[J]. 电子学报, 2010, 38(6): 238-242.
QIAN X H, GUO S X, LI X Y.Wasserstein distance based local energy model of segmentation[J]. Acta electronica sinica, 2010, 38(6): 238-242.
[17] BRAULIO B, CYPRIEN H, ELENI C.Applying design knowledge and machine learning to SCADA data for classification of wind turbine operating regimes[C]//2017 IEEE Symposium Series on Computational Intelligence (SSCI), Honlulu, HI, USA, 2017: 1-8.
基金
国防基础研究计划（JCKY2019407C002）
PDF(8280 KB)
