基于CNN-LSTM的风电机组异常状态检测

PDF(1694 KB)

振动与冲击 ›› 2021, Vol. 40 ›› Issue (22) : 11-17.

论文

向玲，王朋鹤，李京蓄

作者信息 +

Abnormal state detection of wind turbines based on CNN-LSTM

XIANG Ling，WANG Penghe，LI Jingxu

Author information +

文章历史 +

摘要

风电机组的环境恶劣和工况多变导致风电机组故障频发，为了保障风电机组的可靠运行，基于数据的机组异常状态检测尤为重要。本文提出了一种基于级联深度学习预测模型的风电机组状态检测方法，首先对风电场数据采集与监视控制（supervisory control and data acquisition，SCADA）系统的数据进行预处理，并通过距离相关系数（distance correlation coefficient，DCC）分析选取输入参数；然后结合卷积神经网络（convolution neural network ，CNN）和长短期神经网络（long short-term memory,LSTM）建立观测参数与目标参数之间的逻辑关系，通过均方根误差（root mean square error，RMSE）和样本熵（sample entropy,SE）对齿轮箱轴承温度预测残差进行分析，监测齿轮箱轴承温度异常变化；最后以华北某风场的SCADA数据进行算例验证，结果表明该方法能够准确检测到齿轮箱轴承温度异常，提前发现风电机组的早期故障，为风电机组安全可靠运行提供重要价值。

Abstract

The bad operating environment of wind turbines leads to frequent gearbox failures. Therefore, it is particularly important to improve the reliability of wind turbines.This paper proposes a wind turbine state anomaly detection method based on deep learning prediction model and sample entropy. Firstly, data of wind farm data acquisition and monitoring control (SCADA) system is preprocessed, and input parameters are selected through distance correlation coefficient (DC) analysis.Then, the convolution neural network (CNN) and the long and short term neural network (LSTM) were combined to establish the logical relationship between the observation parameters and the target parameters. By combining the root mean square error (RMSE) and sample entropy, the residual temperature prediction of gear box bearing was analyzed to monitor the abnormal temperature changes of gear box bearing.Finally, the SCADA data of a wind field in north China is used for example verification. The results show that the method can accurately detect the temperature anomaly of the gearbox bearing and find the early faults of the wind turbine in advance, providing reference information for the maintenance of the wind farm staff.

导出引用

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 Ling，WANG Penghe，LI Jingxu. Abnormal state detection of wind turbines based on CNN-LSTM[J]. Journal of Vibration and Shock, 2021, 40(22): 11-17

参考文献

[1] 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 Xue-feng, LI Ji-meng, CHENG Hang, 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.
[2] 2017年中国风电装机容量统计[J]. 风能, 2018(5) : 44-46, 48-57.
Statistics on China's Installed Wind Power Capacity in 2017[J]. Wind Energy, 2018(5): 44-46, 48-57.
[3] 2017年全球风电进展情况[J]. 中外能源, 2018(6)： 103.
Global Wind Power Progress in 2017[J]. Sino-Global Energy, 2018(6): 103.
[4] Zhiwei, Gao, Shuangwen, et al. Real-time monitoring, prognosis, and resilient control for wind turbine systems[J]. Renewable Energy, 2018.
[5] Xiang L, Deng Z, Hu A. Forecasting Short-Term Wind Speed Based on IEWT-LSSVM Model Optimized by Bird Swarm Algorithm[J]. IEEE Access, 2019.
[6] Kumar A, Gandhi C P, Zhou Y, et al. Latest developments in gear defect diagnosis and prognosis: A review[J]. Measurement, 2020, 158:107735.
[7] Yang W X, Court R, Jiang J S. Wind turbine condition monitoring by the approach of SCADA data analysis[J], Renewable Energy, 2013, 53（9）:365-376.
[8] 梁颖, 方瑞明. 基于SCADA和支持向量回归的风电机组状态在线评估方法[J]. 电力系统自动化, 2013, 37(14): 7-12.
LIANG Ying, FANG Rui-ming. An Online Wind Turbine Condition Assessment Method Based on SCADA and Support Vector Regression[J]. Automation of Electric Power Systems, 2013, 37(14): 7-12.
[9] 郭鹏, David Infield, 杨锡运. 风电机组齿轮箱温度趋势状态监测及分析方法[J]. 中国电机工程学报, 2011, 31(32)： 129-136．
GUO Peng, David Infield, YANG Xi-yun. Wind Turbine Gearbox Condition Monitoring Using Temperature Trend Analysis[J]. Proceedings of The Chinese Society for Electrical Engineering | Proc Chin Soc Elect Eng, 2011, 31(32): 129-136.
[10] Ruiming Fang, Rongyan Shang, Shunhui Jiang, et al. A trend cloud model-based approach for the identification of wind turbine gearbox anomalies[J]. Journal of Intelligent & Fuzzy Systems, 2018, 415-421.
[11] Yiyi Zhang, Hanbo Zheng, Jiefeng Liu, et al. An anomaly identification model for wind turbine state parameters[J]. Journal of Cleaner Production, 2018, 1214-1227.
[12] Zhen You Zhang, Ke Sheng Wang. Wind turbine fault detection based on SCADA data analysis using ANN[J]. Advances in Manufacturing, 2014(01): 70-78．
[13] 朱会杰, 王新晴, 芮挺等. 基于平移不变CNN的机械故障诊断研究[J]. 振动与冲击, 2019, 38(05):45-52.
ZHU Hui-jie, WANG Xin-qing, RUI Ting et al. Mechanical fault diagnosis based on shift invariant CNN [J]. Journal of Vibration and Shock, 2019, 38(05):45-52.
[14] 郑小霞, 陈广宁, 任浩翰等. 基于改进VMD和深度置信网络的风机易损部件故障预警[J]. 振动与冲击, 2019, 38(08):153-160+179.
ZHENG Xiao-xia, CHEN Guang-ning, REN Hao-han et al. Fault detection of vulnerable units of wind turbine based on improved VMD and DBN[J]. Journal of Vibration and Shock, 2019, 38(08):153-160+179.
[15] 李海平, 赵建民, 张鑫等. 行星齿轮箱齿轮磨损故障诊断[J]. 振动与冲击, 2019, 38(23):84-89+125.
LI Hai-Ping, ZHAO Jian-min, ZHANG Xing, et al. Fault diagnosis for gear wear of planetary gearbox[J]. Journal of Vibration and Shock, 2019, 38(23):84-89+125.
[16] Jinhao Lei, Chao Liu, Dongxiang Jiang. Fault diagnosis of wind turbine based on Long Short-term memory networks[J]. Renewable Energy, 2019, 133.
[17] 赵洪山, 闫西慧,王桂兰等. 应用深度自编码网络和XGBoost的风电机组发电机故障诊断[J]. 电力系统自动化, 2019, 43(01)： 81-90.
Zhao Hongshan, YAN Xihui, WANG Guilan, et al. Fault Diagnosis of Wind Turbine Generators Based on Deep Autoencoder Network and XGBoost[J]. Automation of Electric Power Systems, 2019, 43(01): 81-90.
[18] Te Han, Chao Liu, Linjiang Wu, et al. An adaptive spatiotemporal feature learning approach for fault diagnosis in complex systems[J]. Mechanical Systems and Signal Processing, 2019, 170-187．
[19] Jiang G, Xie P, He H, et al. Wind Turbine Fault Detection Using Denoising Autoencoder with Temporal Information[J]. IEEE/ASME Transactions on Mechatronics, 2017： 89-100．