Fault Diagnosis Based on an Approach Combining a Spectrogram and a Convolutional Neural Network with Application to a Wind Turbine System

被引:13
作者
Yu, Wenxin [1 ,2 ]
Huang, Shoudao [1 ]
Xiao, Weihong [3 ]
机构
[1] Hunan Univ, Coll Elect & Informat Engn, Changsha 410082, Hunan, Peoples R China
[2] Hunan Univ Sci & Technol, Sch Informat & Elect Engn, Xiangtan 411201, Peoples R China
[3] Xiangtan Univ, Hunan Prov Cooperat Innovat Ctr Wind Power Equipm, Sch Informat Engn, Xiangtan 411105, Peoples R China
基金
中国博士后科学基金;
关键词
spectrogram; convolutional neural network; wind turbine; fault diagnosis; SUPPORT VECTOR MACHINE; MODEL;
D O I
10.3390/en11102561
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
To investigate problems involving wind turbines that easily occur but are hard to diagnose, this paper presents a wind turbine (WT) fault diagnosis algorithm based on a spectrogram and a convolutional neural network. First, the original data are sampled into a phonetic form. Then, the data are transformed into a spectrogram in the time-frequency domain. Finally, the data are sent into a convolutional neural network (CNN) model with batch regularization for training and testing. Experimental results show that the method is suitable for training a large number of samples and has good scalability. Compared with Back Propagation Neural Network (BPNN), Support Vector Machine (SVM), Extreme Learning Machine (ELM), and other fault diagnosis methods, the average diagnostic correctness rate is higher; so, the method can provide more accurate reference information for wind turbine fault diagnosis.
引用
收藏
页数:11
相关论文
共 50 条
[21]   A transfer convolutional neural network for fault diagnosis based on ResNet-50 [J].
Wen, Long ;
Li, Xinyu ;
Gao, Liang .
NEURAL COMPUTING & APPLICATIONS, 2020, 32 (10) :6111-6124
[22]   Randomization-based neural networks for image-based wind turbine fault diagnosis [J].
Wang, Junda ;
Yang, Yang ;
Li, Ning .
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 121
[23]   Application of SOM neural network in fault diagnosis of the steam turbine regenerative system [J].
Wu, JF ;
Hu, NS ;
Hu, S ;
Zhao, Y .
2002 INTERNATIONAL CONFERENCE ON MACHINE LEARNING AND CYBERNETICS, VOLS 1-4, PROCEEDINGS, 2002, :184-187
[24]   Fault diagnosis strategy of a wind power bearing based on an improved convolutional neural network [J].
Chang M. ;
Shen Y. .
Dianli Xitong Baohu yu Kongzhi/Power System Protection and Control, 2021, 49 (06) :131-137
[25]   Fault diagnosis of gas turbine based on partly interpretable convolutional neural networks [J].
Zhou, Dengji ;
Yao, Qinbo ;
Wu, Hang ;
Ma, Shixi ;
Zhang, Huisheng .
ENERGY, 2020, 200
[26]   Convolutional Neural Network Based on Spiral Arrangement of Features and Its Application in Bearing Fault Diagnosis [J].
Wang, Fengtao ;
Deng, Gang ;
Ma, Linjie ;
Liu, Xiaofei ;
Li, Hongkun .
IEEE ACCESS, 2019, 7 :64092-64100
[27]   Convolutional neural network for gear fault diagnosis based on signal segmentation approach [J].
Kim, Seokgoo ;
Choi, Joo-Ho .
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL, 2019, 18 (5-6) :1401-1415
[28]   A Modified Deep Convolutional Subdomain Adaptive Network Method for Fault Diagnosis of Wind Turbine Systems [J].
Shen, Yijun ;
Chen, Bo ;
Guo, Fanghong ;
Meng, Wenchao ;
Yu, Li .
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT, 2022, 71
[29]   Convolutional Neural Network Based Bearing Fault Diagnosis [J].
Duy-Tang Hoang ;
Kang, Hee-Jun .
INTELLIGENT COMPUTING THEORIES AND APPLICATION, ICIC 2017, PT II, 2017, 10362 :105-111
[30]   Convolutional neural network for wind turbine failure classification based on scada data [J].
Puruncajas B. ;
Alava W. ;
Encalada-Davila ;
Tutivén C. ;
Vidal Y. .
Renewable Energy and Power Quality Journal, 2021, 19 :447-451