王永平;张蕾;张晓琳;徐立;韩朋;张飞;

• 1:内蒙古科技大学信息工程学院

• 2:包头医学院计算机科学与技术系

• 3:华北电力大学可再生与清洁能源学院

• 
  

摘要(Abstract)：

提出一种深度学习检测方法CNN-BiGRU.采用CNN自适应地学习变量之间存在的关联特征，利用BiGRU对时间序列的敏感性，对风机叶片故障分类.对某风电场的SCADA数据进行增强、切片、标准化等预处理，实验结果表明：CNN-BiGRU分类模型能有效对叶片结冰故障进行准确检测，在时间效率和检测准确率方面较其他深度学习模型效果更好.

关键词(KeyWords)： 风机叶片;故障检测;卷积神经网络;双向门控循环单元

基金项目(Foundation): 国家自然科学基金资助项目（61562065）;; 国家重点研发计划基金资助项目（2017YFE0109000）;; 内蒙古自治区自然科学基金资助项目（2019MS06036）;; 内蒙古科技大学创新基金项目（2014QDL046）

作者(Authors): 王永平;张蕾;张晓琳;徐立;韩朋;张飞;

DOI: 10.16559/j.cnki.2095-2295.2022.02.013

参考文献(References)：

• [1]陈长征，赵新光，周勃，等．风电机组叶片裂纹故障特征提取方法[J]．中国电机工程学报，2013,33(02):112.

• [2] Joshuva A,Sugumaran V. Crack detection and localization on wind turbine blade using machine learning algorithms:A data mining approach[J]. Structural Durability&Health Monitoring,2019,13(2):181.

• [3] Peng L,Liu J. Detection and analysis of large-scale WT blade surface cracks based on UAV-taken images[J].IET Image Processing,2018,12(11):2059.

• [4] Carlos Q,Fausto P,Borja H,et al. Structural health monitoring for delamination detection and location in wind turbine blades employing guided waves[J]. Wind Energy,2019,22(5):698.

• [5]邹洁，何超，朱永凯．基于FBG和小波包能量谱的风机叶片无损检测[J]．电子测量技术，2015,38(03):133.

• [6]赵娟，陈斌，李永战，等．复杂背景噪声下风机叶片裂纹故障声学特征提取方法[J]．北京邮电大学学报，2017,40(05):117.

• [7] Glacoppo G,Barbera O,Briguglio N,et al. Thermal study of a SOFC system integration in a fuselage of a hybrid electric mini UAV[J]. International Journal of Hydrogen Energy,2017,42(46):28022.

• [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.

• [9]孟杭，黄细霞，刘娟，等．结合随机森林和SVM的风机叶片结冰预测[J]．电测与仪表，2020,57(17):66.

• [10] Yuan B,Wang C,Jiang F,et al. Wavelet FCNN:A deep time series classification model for wind turbine blade icing detection[EB/OL]. https：//arxiv. org/pdf/1902. 05625vl. pdf. 2019-02-01.

• [11] Li M,He X. An accurate detection method for turbine icing issues using LSTM Network[J]. IOP Conference Series:Earth and Environmental Science,2019,237(12):156.

• [12] Kong Z,Tang B,Deng L,et al. Condition monitoring of wind turbines based on spatio-temporal fusion of SCADA data by convolutional neural networks and gated recurrent units[J]. Renewable Energy,2020,146(10):760.

• [13] Chung J,Gulcehre C,Cho K,et al. Empirical evaluation of gated recurrent neural networks on sequence Modeling[J]. Eprint Arxiv,2014,65(93):662.

• [14] Fan Y,Qian Y,Xie F,et al. TTS synthesis with bidirectional LSTM based recurrent neural Networks[C]//Fifteenth annual conference of the international speech communication association. Red Hook,New York:Curran Associates,Inc.,2014:1964.