|
|
|
| Fault Prediction of Wind Turbine Gearbox Based onLong Short-term Memory Network |
| HE Qun,YIN Fei-fei,WU Xin,XIE Ping,JIANG Guo-qian |
| Institute of Electrical Engineering, Yanshan University, Qinhuangdao, Hebei 066004, China |
|
|
|
|
Abstract To capture the characteristics of dynamic temporal-spatial correlation hidden in monitoring data of wind turbine gearbox, a fault prediction method based on long short-term memory (LSTM) network is proposed. The proposed approach mainly consists of two phases: offline training and online detection. First, the oil temperature of the gearbox is taken as the modeling variable and the LSTM-based normal behavior model of wind turbine gearbox oil is built based on historical monitoring data training and learning, which fully takes advantages of the important correlated information between the oil temperature and some relevant input variables. Then, the model residuals are calculated and evaluated to determine the corresponding detection threshold. Furthermore, the well-trained LSTM model is used for online testing.Through model residual analysis and threshold comparison, fault detection and prediction of wind turbine gearbox can be realized.A real motoring data from a wind farm is used to validate the effectiveness of the proposed method. The results show that compared with those traditional methods, the proposed method presents better prediction performance, and can predict the occurrence of gearbox failure earlier.
|
|
Received: 23 November 2018
Published: 10 October 2020
|
|
|
|
|
|
［1］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, 38(5): 1041-1053.
Jin X H, Sun Y, Shan J H, et al. Fault diagnosis and prognosis for wind turbines: An overview［J］. Chinese Journal of Scientific Instrument, 2017, 38(5): 1041-1053.
［2］陈雪峰, 李继猛, 程航, 等. 风力发电机状态监测和故障诊断技术的研究与进展［J］. 机械工程学报, 2011, 47(9): 45-52.
Chen X F, Li J M, Cheng H, et al. Research and application of condition monitoring and fault diagnosis technology in wind turbines［J］. Journal of Mechanical Engineering, 2011, 47(9): 45-52.
［3］Hou Z R. Rolling Bearing Fault Diagnosis Based on Wavelet Packet and Improved BP Neural Network for Wind Turbines［J］. Applied Mechanics & Materials, 2013, 347-350:117-120.
［4］孟宗, 刘东, 岳建辉,等.基于DEMD局部时频熵和SVM的风电齿轮箱故障诊断方法研究［J］. 计量学报, 2017, 38(4): 449-452.
Meng Z, Liu D, Yue J H, et al. Wind Power Gear Box Fault Diagnosis Based on DEMD Local Frequency Entropy and SVM［J］.Acta Metrologica Sinica, 2017, 38(4): 449-452.
［5］Jiang G, He H, Xie P, et al. Stacked Multilevel-Denoising Autoencoders: A New Representation Learning Approach for Wind Turbine Gearbox Fault Diagnosis［J］. IEEE Transactions on Instrumentation & Measurement, 2017, 66(9): 2391-2402.
［6］Tautz-Weinert J, Watson S J. Using SCADA data for wind turbine condition monitoring-a review［J］. IET Renewable Power Generation, 2016, 11(4): 382-394.
［7］Bangalore P, Tjernberg L B. An Artificial Neural Network Approach for Early Fault Detection of Gearbox Bearings［J］. IEEE Transactions on Smart Grid, 2015, 6(2): 980-987.
［8］Song Z, Zhang Z, Jiang Y, et al. Wind Turbine Health State Monitoring Based on a Bayesian Data-driven Approach［J］. Renewable Energy, 2018, 125(2018): 172-181.
［9］何群, 王红, 江国乾, 等. 基于相关主成分分析和极限学习机的风电机组主轴承状态监测研究［J］. 计量学报, 2018, 39(1): 89-93.
He Q, Wang H, Jiang G Q, et al.Research of Wind Turbine Main Bearing Condition Monitoring Based on Correlation PCA and ELM［J］. Acta Metrologica Sinica, 2018, 39(1): 89-93.
［10］Lecun Y, Bengio Y, Hinton G. Deep learning［J］. Nature, 2015, 521(7553): 436-444.
［11］何群,杜硕,王煜文,等, 基于变分模态分解与深度信念网络的运动想象分类识别研究［J］. 计量学报, 2020, 41(1): 90-99.
He Q, Du S, Wang Y W, et al. The Classification of EEG Induced by Motor Imagery Based on Variational Mode Decomposition and Deep Belief Network［J］. Acta Metrologica Sinica, 2020, 41(1): 90-99.
［12］赵洪山, 刘辉海. 基于深度学习网络的风电机组主轴承故障检测［J］. 太阳能学报, 2018, 39(3): 588-595.
Zhao H S, Liu H H. Fault Detection of Wind Turbine Main Bear Based on Deep Learning Network［J］. Acta Energiae Solaris Sinica, 2018, 39(3): 588-595.
［13］Wang L, Zhang Z, Long H, et al. Wind Turbine Gearbox Failure Identification With Deep Neural Networks［J］. IEEE Transactions on Industrial Informatics, 2017, 13(3): 1360-1368.
［14］Jiang G, Xie P, He H, et al. Wind turbine fault detection using a denoising autoencoder with temporal information［J］. IEEE/ASME Transactions on Mechat-ronics, 2018, 23(1): 89-100.
［15］Yang W, Liu C, Jiang D. An unsupervised spatio-temporal graphical modeling approach for wind turbine condition monitoring［J］. Renewable Energy, 2018, 127: 230-241.
［16］Hochreiter S, Schmidhuber J. Long short-term memoty［J］. Neural Computation, 1997, 9(8): 1735-1780.
［17］Zhang W, Qiu Y, Infield D, et al. Applying thermophysics for wind turbine drivetrain fault diagnosis using SCADA data［J］. IET Renewable Power Generation, 2016, 10(5): 661-668.
［18］Touret T, Changenet C, Ville F, et al. On the use of temperature for online condition monitoring of geared systems-A review［J］. Mechanical Systems and Signal Processing, 2018, 101: 197-210.
［19］Zhang S, Xiao J, Liu X, et al. Fusing Geometric Features for Skeleton-Based Action Recognition using Multilayer LSTM Networks［J］. IEEE Transactions on Multimedia, 2018, 20(9): 2330-2343.
［20］Kong W, Dong Z Y, Hill D J, et al. Short-Term Residential Load Forecasting based on Resident Behaviour Learning［J］. IEEE Transactions on Power Systems, 2018, 33(1): 1087-1088.
［21］Prabhu S S, Runger G C. Designing a multivariate EWMA control chart［J］. Journal of Quality Technology, 1997, 29(1): 8-15.
［22］Qiao W, Lu D. A Survey on Wind Turbine Condition Monitoring and Fault Diagnosis—Part Ⅱ: Signals and Signal Processing Methods［J］. IEEE Transactions on Industrial Electronics, 2015, 62(10): 6546-6557. |
|
|
|
2020, Vol. 41 
