Fault Identification of High-Speed Train Bogie Based on Siamese Convolutional Neural Network

Authors

Yunpu Wu, School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China;
Weidong Jin, School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China;
Junxiao Ren, School of Electrical Engineering, Southwest Jiaotong University, Chengdu 610031, China;

Abstract

Abstract: The performance degradation and failure of high-speed train bogie components will threaten the operation security of train. This paper proposes a fault type identification method based on siamese convolutional neural network to address the scarcity of data and the high-dimension of monitoring signals. Deep residual network with one-dimension convolution layers is employed for features extraction and fusion of vibration signals from multiple sensors. The siamese structure is employed to obtain the similarities between samples. Fault types are identified by ranking similarities in the support set. The experimental results show that the proposed method can identify the fault types with only a few training samples and improve the accuracy compared with conventional methods.

Recommended Citation

Wu, Yunpu; Jin, Weidong; and Ren, Junxiao (2019) "Fault Identification of High-Speed Train Bogie Based on Siamese Convolutional Neural Network," Journal of System Simulation: Vol. 31: Iss. 11, Article 44.
DOI: 10.16182/j.issn1004731x.joss.19-FZ0281
Available at: https://dc-china-simulation.researchcommons.org/journal/vol31/iss11/44

First Page

2562

Revised Date

2019-07-04

DOI Link

https://doi.org/10.16182/j.issn1004731x.joss.19-FZ0281

Last Page

2568

CLC

TP277

Recommended Citation

Wu Yunpu, Jin Weidong, Ren Junxiao. Fault Identification of High-Speed Train Bogie Based on Siamese Convolutional Neural Network[J]. Journal of System Simulation, 2019, 31(11): 2562-2568.

DOI

10.16182/j.issn1004731x.joss.19-FZ0281