Wind Turbine Generator Winding Temperature Prediction Based on XGBoost and LSTM

doi:10.11930/j.issn.1004-9649.202101090

Abstract

Abstract: Generator stator winding temperature is a significant representation of the health status of wind turbines. Accurate prediction of winding overheating can help us timely formulate operation and maintenance plan and find out the fault source. A combined model is proposed to predict the stator winding temperature of wind turbines based on the weighted fusion of XGBoost (eXtreme Gradient Boosting) and LSTM (Long Short-Term Memory), and the difference in model structure between the two methods is used to improve the accuracy of the fusion prediction results. The SCADA data from on-site wind farm verifies that the proposed combined model can effectively predict the winding overheating, which is of great use for further engineering application.

Key words: wind turbine, winding temperature prediction, XGBoost, LSTM

TENG Wei, HUANG Yike, WU Shiming, LIU Yibing. Wind Turbine Generator Winding Temperature Prediction Based on XGBoost and LSTM[J]. Electric Power, 2021, 54(6): 95-103.

Add to citation manager EndNote|Ris|BibTeX

URL: https://www.electricpower.com.cn/EN/10.11930/j.issn.1004-9649.202101090

https://www.electricpower.com.cn/EN/Y2021/V54/I6/95

References

[1] CHU S, MAJUMDAR A. Opportunities and challenges for a sustainable energy future[J]. Nature, 2012, 488(7411):294-303.
[2] 张新旺. 风电机组发电机绕组端温度高故障分析及处理[J]. 风能, 2016(8):66-68
[3] 龙泉, 鲁志平, 张羽. 基于BP神经网络的多变量风力发电机绕组温度预测[C]//2016年中国电机工程学会年会. 2016:1-4.
[4] 霍娟, 唐贵基, 刘大宾, 等. 基于温度信号的风电机组发电机实时可靠性监测新方法[J]. 可再生能源, 2016, 34(3):408-412
HUO Juan, TANG Guiji, LIU Dabin, et al. A novel monitoring method of wind turbine generator real-time reliability based on tempeture signals[J]. Renewable Energy Resources, 2016, 34(3):408-412
[5] 张立鹏, 李忠徽. 双馈风力发电机绕组匝间短路故障诊断综述[J]. 河北电力技术, 2017, 36(5):32-34, 43
ZHANG Lipeng, LI Zhonghui. Summarization on fault diagnosis of turn-to-turn short circuit in DFIG[J]. Hebei Electric Power, 2017, 36(5):32-34, 43
[6] 张正东, 马宏忠, 陈涛涛. 双馈异步发电机转子绕组不对称故障的诊断研究[J]. 微电机, 2014, 47(9):42-45
ZHANG Zhengdong, MA Hongzhong, CHEN Taotao. Diagnosis of doubly-fed induction generator rotor winding asymmetrical faults[J]. Micromotors, 2014, 47(9):42-45
[7] 李俊卿, 于海波, 张立鹏. 基于EEMD-HHT的双馈感应发电机定子匝间短路故障研究[J]. 电机与控制应用, 2015, 42(2):65-72
LI Junqing, YU Haibo, ZHANG Lipeng. Study on stator inter-turn short circuit fault in doubly-fed induction generators based on EEMD-HHT[J]. Electric Machines & Control Application, 2015, 42(2):65-72
[8] 龚天明, 李华. 基于多物理场耦合的直驱永磁同步风力发电机定子绕组优化设计[J]. 电机与控制应用, 2019, 46(7):67-71, 81
GONG Tianming, LI Hua. Optimum design of stator winding of the direct-drive permanent magnet synchronous wind-power generator based on multi-physical-field coupling[J]. Electric Machines & Control Application, 2019, 46(7):67-71, 81
[9] 韩力, 罗张尧, 金钊, 等. 定子双绕组风力感应发电机优化设计方法[J]. 电力自动化设备, 2015, 35(3):33-40
HAN Li, LUO zhangyao, JIN Zhao, et al. Optimal design of dual stator-winding induction generator for wind power[J]. Electric Power Automation Equipment, 2015, 35(3):33-40
[10] 王桂松, 郭鹏, 胥佳, 等. 基于XGBoost建模和Change-Point残差处理的风电机组齿轮箱温度预警[J]. 电力科学与工程, 2018, 34(9):46-53
WANG Guisong, GUO Peng, XU Jia, et al. Temperature warning of wind turbines gearbox based on XGBoost modeling and Change-Point residual processing[J]. Electric Power Science and Engineering, 2018, 34(9):46-53
[11] 曹力, 潘巧波, 王明宇, 等. 基于混合核函数支持向量机的风电机组发电机温度预警方法[J]. 华电技术, 2020, 42(5):43-49
CAO Li, PAN Qiaobo, WANG Mingyu, et al. Early warning method for wind turbine generator temperature based on HK-SVM[J]. Huadian Technology, 2020, 42(5):43-49
[12] 李大中, 常城, 许炳坤. 基于样本优化的风电机组齿轮箱轴承温度预测[J]. 系统仿真学报, 2017, 29(2):374-380
LI Dazhong, CHANG Cheng, XU Bingkun. Wind turbine gearing temperature prediction based on sample optimization[J]. Journal of System Simulation, 2017, 29(2):374-380
[13] 程逸, 胡阳, 马素玲, 等. 基于MIC-LSTM与CKDE的风电机组机舱温度区间预测[J]. 智慧电力, 2020, 48(7):16-23
CHENG Yi, HU Yang, MA Suling, et al. Wind turbine nacelle temperature interval prediction based on MIC-LSTM and CKDE[J]. Smart Power, 2020, 48(7):16-23
[14] 吴琼, 余文铖, 洪海生, 等. 基于XGBoost算法的配网台区低压跳闸概率预测[J]. 中国电力, 2020, 53(4):105-113
WU Qiong, YU Wencheng, HONG Haisheng, et al. Probability prediction of low-voltage tripping failures in distribution transformer station areas based on XGBoost algorithm[J]. Electric Power, 2020, 53(4):105-113
[15] 杨智伟, 刘灏, 毕天姝, 等. 基于长短期记忆网络的PMU不良数据检测方法[J]. 电力系统保护与控制, 2020, 48(7):1-9
YANG Zhiwei, LIU Hao, BI Tianshu,et al. PMU bad data detection method based on long short-term memory network[J]. Power System Protection and Control, 2020, 48(7):1-9
[16] 乔国华, 郭路遥, 吴一敌, 等. 基于遗传优化最小二乘支持向量机的变电站全寿命周期成本预测模型[J]. 中国电力, 2015, 48(11):142-148
QIAO Guohua, GUO Luyao, WU Yidi, et al. Substation life cycle cost prediction model of the least squares support vector machine optimized by genetic algorithm[J]. Electric Power, 2015, 48(11):142-148
[17] QUINLAN J R. Induction of decision trees[J]. Machine Learning, 1986, 1(1):81-106.
[18] FRIEDMAN J H. Stochastic gradient boosting[J]. Computational Statistics & Data Analysis, 2002, 38(4):367-378.
[19] 巢政, 温蜜. 一种基于SMOTE和XGBoost的窃电检测方案[J]. 智慧电力, 2020, 48(11):97-102
CHAO Zheng, WEN Mi. Scheme for Electricity Theft Detection Based on SMOTE and XGBoost[J]. Smart Power, 2020, 48(11):97-102
[20] 武昭旭, 杨岸, 祝龙记. 基于循环神经网络的电能质量扰动识别[J]. 电力系统保护与控制, 2020, 48(18):88-94
WU Zhaoxu, YANG An, ZHU Longji. Power quality disturbance recognition based on a recurrent neural network[J]. Power System Protection and Control, 2020, 48(18):88-94
[21] ZHAO Z, CHEN W H, WU X M, et al. LSTM network:a deep learning approach for short-term traffic forecast[J]. IET Intelligent Transport Systems, 2017, 11(2):68-75.
[22] 李典阳, 张育杰, 王善渊, 等. 基于多预测模型融合的电力变压器安全预判[J]. 中国电力, 2020, 53(1):72-80
LI Dianyang, ZHANG Yujie, WANG Shanyuan, et al. Safety prejudging method for power transformer based on multi-prediction model fusion[J]. Electric Power, 2020, 53(1):72-80
[23] SHAO H, XING D. Short-term wind power forecasting using model structure selection and data fusion techniques[J]. International Journal of Electrical Power & Energy Systems, 2016, 83:79-86.
[24] 李占山, 刘兆赓. 基于XGBoost的特征选择算法[J]. 通信学报, 2019, 40(10):101-108
LI Zhanshan, LIU zhaogeng. Feature selection algorithm based on XGBoost[J]. Journal on Communications, 2019, 40(10):101-108
[25] 马愿, 张倩, 李国丽, 等. 基于频域分解的短期负荷预测研究分析[J]. 中国电力, 2020, 53(4):114-121
MA Yuan, ZHANG Qian, LI Guoli, et al. Research and analysis of short-term load forecasting based on frequency domain decomposition[J]. Electric Power, 2020, 53(4):114-121