A Wind Turbine Fault Diagnosis Method Based on Siamese Deep Neural Network

Authors

Jiarui Liu, College of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China;Follow
Guotian Yang, College of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China;Follow
Xiaowei Wang, College of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China;

Abstract

Abstract: In order to effectively extract the fault features of time series data in supervisory control and data acquisition (SCADA), considering the advantages of one-dimensional convolutional neural network (1-D CNN) for extracting local time series features and the advantages of long-term memory (LSTM) which can extract long-term dependent features, a method for fault diagnosis of wind turbines based on 1-D CNN-LSTM is proposed. To solve the problem of the scarcity of fault samples of wind turbines based on the siamese network architecture, a wind fault diagnosis method based on siamese 1-D CNN-LSTM is proposed. The proposed siamese 1-D CNN-LSTM method relies on a small amount of sample data to effectively extract the fault features of the wind turbine. The results show that 1-D CNN-LSTM is better than other existing deep learning methods. When the training samples are insufficient, the proposed siamese 1-D CNN-LSTM can significantly improve the fault diagnosis results.

Recommended Citation

Liu, Jiarui; Yang, Guotian; and Wang, Xiaowei (2022) "A Wind Turbine Fault Diagnosis Method Based on Siamese Deep Neural Network," Journal of System Simulation: Vol. 34: Iss. 11, Article 4.
DOI: 10.16182/j.issn1004731x.joss.21-0261
Available at: https://dc-china-simulation.researchcommons.org/journal/vol34/iss11/4

First Page

2348

Revised Date

2021-05-11

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.21-0261

Last Page

2358

CLC

TM315;TP391

Recommended Citation

Jiarui Liu, Guotian Yang, Xiaowei Wang. A Wind Turbine Fault Diagnosis Method Based on Siamese Deep Neural Network[J]. Journal of System Simulation, 2022, 34(11): 2348-2358.

Corresponding Author

Guotian Yang,ygt@ncepu.edu.cn

DOI

10.16182/j.issn1004731x.joss.21-0261