FAULT WARNING FOR WIND TURBINE BEARINGS BASED ON PARALLEL NEURAL NETWORK AND IMPROVED DYNAMIC FD-KNN

Xu Boqiang; Wang Biao; Sun Liling; Yin Yanbo

doi:10.19912/j.0254-0096.tynxb.2024-1121

PDF(1806 KB)

Acta Energiae Solaris Sinica ›› 2025, Vol. 46 ›› Issue (10) : 753-765. DOI: 10.19912/j.0254-0096.tynxb.2024-1121

FAULT WARNING FOR WIND TURBINE BEARINGS BASED ON PARALLEL NEURAL NETWORK AND IMPROVED DYNAMIC FD-KNN

Xu Boqiang, Wang Biao, Sun Liling, Yin Yanbo

Author information +

History +

Abstract

Aiming at the current problem of insufficient accuracy and reliability of wind turbine bearing fault warning, a wind turbine bearing fault warning method based on parallel architecture network with improved dynamic fault detection-k-nearest neighbor （FD-KNN） is proposed. Firstly, the correlation analysis of supervisory control and data acquisition （SCADA） of wind turbine is carried out to screen out the variables that are highly correlated with the key variables of wind turbine bearings, and the key variables are decomposed by using the Ensemble empirical mode decomposition （EEMD）, to dig deeply the characteristics of the key variables at different time scales and the potential interactions between key variables and highly correlated covariates. Then, a novel parallel architecture network that combines Self-Attention LSTM and an improved Transformer model is developed to accurately and reliably predict the future states of key variables. Based on the prediction results, the residuals are calculated, and the FD-KNN algorithm is dynamically optimized using the real-time state of wind turbine bearings. This optimization includes adjusting the scale of the nearest neighbors and setting dynamic warning thresholds and conditions to achieve more accurate and reliable fault warnings. Finally, the method is validated using actual SCADA data, and the results demonstrate that it can identify wind turbine bearing faults in advance, excelling in both accuracy and reliability.

Key words

wind turbines / SCADA / bearings / deep learning / fault warning / improved dynamic FD-KNN algorithm / reliability

Cite this article

EndNote

Ris (Procite)

Bibtex

Download Citations

Xu Boqiang, Wang Biao, Sun Liling, Yin Yanbo. FAULT WARNING FOR WIND TURBINE BEARINGS BASED ON PARALLEL NEURAL NETWORK AND IMPROVED DYNAMIC FD-KNN[J]. Acta Energiae Solaris Sinica. 2025, 46(10): 753-765 https://doi.org/10.19912/j.0254-0096.tynxb.2024-1121

References

[1] Global Wind Energy Council. Global wind report 2023[R]. Brussels: GWEC-Global Wind Energy Council, 2024.
[2] FU J, CHU J C, GUO P, et al.Condition monitoring of wind turbine gearbox bearing based on deep learning model[J]. IEEE access, 2019, 7: 57078-57087.
[3] KANDUKURI S T, SENANYAKA J S L, HUYNH V K, et al. A two-stage fault detection and classification scheme for electrical pitch drives in offshore wind farms using support vector machine[J]. IEEE transactions on industry applications, 2019, 55(5): 5109-5118.
[4] 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.
[5] CROSS P, MA X D.Nonlinear system identification for model-based condition monitoring of wind turbines[J]. Renewable energy, 2014, 71: 166-175.
[6] YAMPIKULSAKUL N, BYON E, HUANG S, et al.Condition monitoring of wind power system with nonparametric regression analysis[J]. IEEE transactions on energy conversion, 2014, 29(2): 288-299.
[7] SUN P, LI J, WANG C S, et al.A generalized model for wind turbine anomaly identification based on SCADA data[J]. Applied energy, 2016, 168: 550-567.
[8] SKRIMPAS G A, SWEENEY C W, MARHADI K S, et al.Employment of kernel methods on wind turbine power performance assessment[J]. IEEE transactions on sustainable energy, 2015, 6(3): 698-706.
[9] 向玲, 王朋鹤, 李京蓄. 基于CNN-LSTM的风电机组异常状态检测[J]. 振动与冲击, 2021, 40(22): 11-17.
XIANG L, WANG P H, LI J X.Abnormal state detection of wind turbines based on CNN-LSTM[J]. Journal of vibration and shock, 2021, 40(22): 11-17.
[10] 王依宁, 解大, 王西田, 等. 基于PCA-LSTM模型的风电机网相互作用预测[J]. 中国电机工程学报, 2019, 39(14): 4070-4081.
WANG Y N, XIE D, WANG X T, et al.Prediction of interaction between grid and wind farms based on PCA-LSTM model[J]. Proceedings of the CSEE, 2019, 39(14): 4070-4081.
[11] SUN Z X, SUN H X.Stacked denoising autoencoder with density-grid based clustering method for detecting outlier of wind turbine components[J]. IEEE access, 2019, 7: 13078-13091.
[12] 刘家瑞, 杨国田, 杨锡运. 基于深度卷积自编码器的风电机组故障预警方法研究[J]. 太阳能学报, 2022, 43(11): 215-223.
LIU J R, YANG G T, YANG X Y.Research on wind turbine fault warning method based on deep convolution auto-encoder[J]. Acta energiae solaris sinica, 2022, 43(11): 215-223.
[13] 陈俊生, 李剑, 陈伟根, 等. 采用滑动窗口及多重加噪比堆栈降噪自编码的风电机组状态异常检测方法[J]. 电工技术学报, 2020, 35(2): 346-358.
CHEN J S, LI J, CHEN W G, et al.A method for detecting anomaly conditions of wind turbines using stacked denoising autoencoders with sliding window and multiple noise ratios[J]. Transactions of China Electrotechnical Society, 2020, 35(2): 346-358.
[14] 李东东, 刘宇航, 赵阳, 等. 基于改进生成对抗网络的风机行星齿轮箱故障诊断方法[J]. 中国电机工程学报, 2021, 41(21): 7496-7507.
LI D D, LIU Y H, ZHAO Y, et al.Fault diagnosis method of wind turbine planetary gearbox based on improved generative adversarial network[J]. Proceedings of the CSEE, 2021, 41(21): 7496-7507.
[15] 王桂兰, 赵洪山, 米增强. XGBoost算法在风机主轴承故障预测中的应用[J]. 电力自动化设备, 2019, 39(1): 73-77, 83.
WANG G L, ZHAO H S, MI Z Q.Application of XGBoost algorithm in prediction of wind motor main bearing fault[J]. Electric power automation equipment, 2019, 39(1): 73-77, 83.
[16] 马良玉, 程善珍. 基于支持向量数据描述和XGBoost的风电机组异常工况预警研究[J]. 电工技术学报, 2022, 37(13): 3241-3249.
MA L Y, CHENG S Z.Abnormal state early warning of wind turbine generator based on support vector data description and XGBoost[J]. Transactions of China Electrotechnical Society, 2022, 37(13): 3241-3249.
[17] 赵洪山, 刘辉海. 基于性能改善深度置信网络的风电机组主轴承状态分析[J]. 电力自动化设备, 2018, 38(2): 44-49.
ZHAO H S, LIU H H.Condition analysis of wind turbine main bearing based on deep belief network with improved performance[J]. Electric power automation equipment, 2018, 38(2): 44-49.
[18] 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 S, HOU G L, YU X D, et al.Condition monitoring method of wind turbine gear box based on SCADA data[J]. Acta energiae solaris sinica, 2021, 42(1): 324-332.
[19] 陈尚年, 李录平, 张世海, 等. 基于EEMD-LSTM的汽轮机转子碰磨故障诊断模型及其工程应用[J]. 热能动力工程, 2023, 38(8): 159-168.
CHEN S N, LI L P, ZHANG S H, et al.EEMD-LSTM-based turbine rotor rub-impact fault diagnosis model and its engineering application[J]. Journal of engineering for thermal energy and power, 2023, 38(8): 159-168.
[20] 赵洪山, 林诗雨, 孙承妍, 等. 考虑多时间尺度信息的风力发电机滚动轴承故障预测[J]. 中国电机工程学报, 2024, 44(22): 8908-8920.
ZHAO H S, LIN S Y, SUN C Y, et al.Fault prediction of wind turbine rolling bearing considering multi-time scale information[J]. Proceedings of the CSEE, 2024, 44(22): 8908-8920.
[21] XIANG L, WANG P H, YANG X, et al.Fault detection of wind turbine based on SCADA data analysis using CNN and LSTM with attention mechanism[J]. Measurement, 2021, 175: 109094.
[22] 胡爱军, 连俭, 向玲. 基于ACNN和Bi-LSTM的风电机组故障早期识别[J]. 太阳能学报, 2021, 42(12): 143-149.
HU A J, LIAN J, XIANG L.Early fault identification of wind turbine based on ACNN and Bi-LSTM[J]. Acta energiae solaris sinica, 2021, 42(12): 143-149.
[23] 俞国燕, 李少伟, 董晔弘. 基于XGBoost-LightGBM-LSTM的风机齿轮箱轴承故障预警[J]. 轴承, 2023(6): 140-145.
YU G Y, LI S W, DONG Y H.Fault warning of wind turbine gearbox bearings based on XGBoost-LightGBM-LSTM[J]. Bearing, 2023(6): 140-145.
[24] 庞昊, 高金峰, 杜耀恒. 基于多神经网络融合的短期负荷预测方法[J]. 电力自动化设备, 2020, 40(6): 37-43.
PANG H, GAO J F, DU Y H.Short-term load forecasting method based on fusion of multiple neural networks[J]. Electric power automation equipment, 2020, 40(6): 37-43.
[25] 张书瑶, 王梓齐, 刘长良. 基于改进集成KNN回归算法的风电机组齿轮箱状态监测[J]. 动力工程学报, 2023, 43(6): 759-767.
ZHANG S Y, WANG Z Q, LIU C L.Wind turbine gearbox condition monitoring based on improved ensemble KNN regression algorithm[J]. Journal of Chinese Society of Power Engineering, 2023, 43(6): 759-767.
[26] LIM B, ARıK S Ö, LOEFF N, et al. Temporal fusion Transformers for interpretable multi-horizon time series forecasting[J]. International journal of forecasting, 2021, 37(4): 1748-1764.
[27] VASWANI A, SHAZEER N, PARMAR N, et al.Attention is all you need[J]. Advances in neural information processing systems, 2017, 30: 5998-6008.
[28] 钱小毅, 孙天贺, 姜兴宇, 等. 基于动态邻域指标重构的风电机组故障检测方法[J]. 太阳能学报, 2024, 45(9): 557-563.
QIAN X Y, SUN T H, JIANG X Y, et al.Wind turbine fault detection method based on dynamic neighborhood index reconstruction[J]. Acta energiae solaris sinica, 2024, 45(9): 557-563.