基于机器学习的风电机组发电机故障预警

胡 梦浩, 吴 宗明, 刘 　闯
华北水利水电大学电气工程学院

摘要


风电机组发电机的故障运维占据风电场运维的大部分成本，发力发电机运行状态的精准预测是保障风电机组健康
稳定运行的基础。因此，本文提出一种基于 WOA-ELM 的风电机组发电机故障预警方法。首先利用四分位数算法，检测
风电机组 SCADA 数据中的异常数据点，对 SCADA 数据进行预处理；之后构建基于 WOA-ELM 的发电机油箱温度预警模
型；利用滑动窗口法结合预测误差计算发电机的运行状态监测指标；最后利用非参数核密度估计进行报警阈值设置，实现
发电机运行状态故障的动态预警。

关键词


四分位法，WOA-ELM，状态监测指标，非参数核密度估计

全文:

PDF


参考


[1] 姚钢 , 杨浩猛 , 周荔丹等 . 大容量海上风电机组发展

现状及关键技术 [J]. 电力系统自动化 ,2021,45(21):33-47.

[2]Zhang Guangyao, Li Yanting, et al. A novel fault diagnosis

method for wind turbine based on adaptive multivariate time_xfffe_series convolutional network using SCADA data[J]. Advanced

Engineering Informatics,Volume 57,2023,102031

[3]Liu Dongdong, Cui Lingli, et al. Fault diagnosis of wind

turbines under nonstationary conditions based on a novel tacho_xfffe_less generalized demodulation[J]. Renewable Energy, Volume

206,2023,Pages 645-657

[4]Ali Dibaj, Zhen Gao, et al. Fault detection of offshore wind

turbine drivetrains in different environmental conditions through

optimal selection of vibration measurements[J]. Renewable

Energy,Volume 203,2023,Pages 161-176

[5]Omneya Attallah, Rania A. Ibrahim, et al. CAD system

for inter-turn fault diagnosis of offshore wind turbines via

multi-CNNs & feature selection[J]. Renewable Energy,Volume

203,2023,Pages 870-880

[6]Prince Waqas Khan, Chan Yeob Yeun, et al. Fault

detection of wind turbines using SCADA data and genetic

algorithm-based ensemble learning[J]. Engineering Failure

Analysis,Volume 148,2023,107209

[7]Xiang Ling, Xin Yang Xin, et al. Condition monitoring

and anomaly detection of wind turbine based on cascaded and

bidirectional deep learning networks[J]. Applied Energy,Volume

305,2022,117925

[8]Xu Xinhua, Huang Xinyu, et al. Total Process of Fault

Diagnosis for Wind Turbine Gearbox, from the Perspective of

Combination with Feature Extraction and Machine Learning: A

Review[J]. Energy and AI,2023,100318

[9]Phong B. Dao, Condition monitoring and fault diagnosis

of wind turbines based on structural break detection in SCADA

data[J]. Renewable Energy,Volume 185,2022,Pages 641-654

[10]Zeng X.J, Yang M., et al. Gearbox oil temperature

anomaly detection for wind turbine based on sparse Bayesian

probability estimation[J]. International Journal of Electrical Power

& Energy Systems,Volume 123,2020,106233

[11] 苏连成 , 邢美玲 , 张慧 . 基于组合预测模型的风电

机组关键部位故障检测 [J]. 太阳能学报 ,2021,42(10):220-225.

[12] 邓子豪 , 李录平 , 刘瑞等 . 基于 SCADA 数据特征提

取的风电机组偏航齿轮箱故障诊断方法研究 [J]. 动力工程学

报 ,2021,41(01):43-50.

[13]Han Shuang, Qiao Yanhui, et al. Wind turbine power

curve modeling based on interval extreme probability density for

the integration of renewable energies and electric vehicles[J].

Renewable Energy,Volume 157,2020,Pages 190-203.

[14] 慎慧强 . 基于混合预测模型的风光短期功率预测及

不确定性分析 [D].华北水利水电学 ,2022.DOI:10.27144/d.cnki.

ghbsc.2022.000172.

[15]Meng Anbo, Zhu Zibin, et al. A novel wind power

prediction approach using multivariate variational mode

decomposition and multi-objective crisscross optimization

based deep extreme learning machine[J]. Energy,Volume

260,2022,124957.




DOI: http://dx.doi.org/10.12361/2661-3506-05-19-131502

Refbacks

  • 当前没有refback。