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

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

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.

Key words: high-speed train bogie, fault identification, few-shot learning, siamese network

CLC Number:

TP277

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.

References

[1] LeCun Y, Bengio Y, Hinton G. Deep learning[J]. Nature (S1476-4687), 2015, 521(7553): 436.
[2] Schmidhuber J.Deep learning in neural networks: An overview[J]. Neural networks (S1879-2782), 2015, 61: 85-117.
[3] Liu R, Yang B, Zio E, et al.Artificial intelligence for fault diagnosis of rotating machinery: A review[J]. Mechanical Systems and Signal Processing (S1096-1216), 2018, 108: 33-47.
[4] 吴昀璞, 金炜东, 黄颖坤. 基于多域融合CNN的高速列车转向架故障检测[J]. 系统仿真学报, 2018, 30(11): 4492-4497.
Wu Yunpu, Jin Weidong, Huang Yingkun.High Speed Train Bogie Fault Diagnosis Based on Multi-domain Fusion CNN[J]. Journal of System Simulation, 2018, 30(11): 4492-4497.
[5] Hu H, Tang B, Gong X, et al.Intelligent fault diagnosis of the high-speed train with big data based on deep neural networks[J]. IEEE Transactions on Industrial Informatics (S1941-0050), 2017, 13(4): 2106-2116.
[6] Peng D, Liu Z, Wang H, et al.A Novel Deeper One-Dimensional CNN With Residual Learning for Fault Diagnosis of Wheelset Bearings in High-Speed Trains[J]. IEEE Access (S2169-3536), 2019, 7: 10278-10293.
[7] Wu Y, Jin W, Ren J, et al. A multi-perspective architecture for high-speed train fault diagnosis based on variational mode decomposition and enhanced multi-scale structure[J/OL]. Applied Intelligence (S1573-7497), 2019. https://link.springer.com/article/ 10.1007/s10489-019-01483-8.
[8] Wang Y, Yao Q.Generalizing from a Few Examples: A Survey on Few-Shot Learning[J]. arXiv preprint (S2331-8422) arXiv: 1904.05046, 2019.
[9] Lake B, Salakhutdinov R, Gross J, et al.One shot learning of simple visual concepts[C]. Proceedings of the Annual Meeting of the Cognitive Science Society. Boston, USA: Curran Associates, Inc, 2011.
[10] Lake B M, Salakhutdinov R R, Tenenbaum J.One-shot learning by inverting a compositional causal process[C]. Advances in neural information processing systems. Lake Tahoe, USA: Curran Associates, Inc., 2013: 2526-2534.
[11] Mao J, Wei X, Yang Y, et al.Learning like a child: Fast novel visual concept learning from sentence descriptions of images[C]. Proceedings of the IEEE international conference on computer vision. Santiago, Chile: IEEE, 2015: 2533-2541.
[12] Koch G, Zemel R, Salakhutdinov R.Siamese neural networks for one-shot image recognition[C]. ICML deep learning workshop. Lille, France: ICML, 2015: 2.
[13] Latorre Iglesias E, Thompson D J, Smith M, et al.Anechoic wind tunnel tests on high-speed train bogie aerodynamic noise[J]. International Journal of Rail Transportation (S2324-8386), 2017, 5(2): 87-109.
[14] Lu Y, Xiang P, Dong P, et al.Analysis of the effects of vibration modes on fatigue damage in high-speed train bogie frames[J]. Engineering Failure Analysis (S1350-6307), 2018, 89: 222-241.
[15] Haixiang G, Yijing L, Shang J, et al.Learning from class-imbalanced data: Review of methods and applications[J]. Expert Systems with Applications (S1873-6793), 2017, 73: 220-239.
[16] Bromley J, Guyon I, LeCun Y, et al. Signature verification using a" siamese" time delay neural network[C]. Advances in neural information processing systems. London, England: MIT press, 1994: 737-744.
[17] He K, Zhang X, Ren S, et al.Deep residual learning for image recognition[C]. Proceedings of the IEEE conference on computer vision and pattern recognition. Las Vegas, USA: IEEE, 2016: 770-778.
[18] Zhang W, Li C, Peng G, et al.A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load[J]. Mechanical Systems and Signal Processing (S1096-1216), 2018, 100: 439-453.