Fault Diagnosis of High Speed Train Bogie Based on Multi-domain Fusion CNN

doi:10.16182/j.issn1004731x.joss.201811053

Abstract

Abstract: The performance degradation and failures of high-speed train bogie components directly threaten the operation security of train. A fault detection method based on multi-domain fusion convolutional neural network is proposed to address the high complexity, high coupling and strong nonlinearity of vibration signals. Noise injection for time domain signal is used to enhance noise robustness and generalization of the model. Signal time-frequency representation information is obtained through embedded time-frequency transformation layer. Adaptive weight-based fusion is implemented through intrinsic characteristics of the convolutional neural network to handle the multi-domain multi-channel information. The experimental results show that the proposed method improves the accuracy of fault diagnosis of high-speed train bogies with good noise robustness and adaptability to work condition.

Key words: high speed train bogie, fault diagnosis, multi-domain fusion, convolutional neural network

CLC Number:

TP277

Wu Yunpu, Jin Weidong, Huang Yingkun. Fault Diagnosis of High Speed Train Bogie Based on Multi-domain Fusion CNN[J]. Journal of System Simulation, 2018, 30(11): 4492-4497.

References

[1] 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.
[2] Iglesias E L, Thompson D J, Smith M, et al.Anechoic wind tunnel tests on high-speed train bogie aerodynamic noise[J]. International Journal of Rail Transportation (S2324-8378), 2017, 5(2): 87-109.
[3] Qin N, Jin W D, Huang J, et al. High Speed Train Bogie Fault Signal Analysis Based on Wavelet Entropy Feature[J]. Advanced Materials Research (S1662-8985), 2013, 753/754/755: 2286-2289.
[4] Wu Z, Jin W, Qin N.Fault feature analysis of high-speed train suspension system based on multivariate multi-scale sample entropy[C]//2016 35th Chinese Control Conference (CCC), 2016: 3913-3918.
[5] Du J, Jin W, Cai Z, et al.A New Feature Evaluation Algorithm and Its Application to Fault of High-Speed Railway[C]//Proceedings of the Second International Conference on Intelligent Transportation. Springer, Singapore, 2016: 1-14.
[6] Lecun Y, Bengio Y, Hinton G.Deep learning[J]. Nature (S1476-4687), 2015, 521(7553): 436-444.
[7] Jia F, Lei Y, Lin J, et al. Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data[J]. Mechanical Systems and Signal Processing (S0888-3270), 2016, 72/73(Supplement C): 303-315.
[8] Janssens O, Slavkovikj V, Vervisch B, et al.Convolutional Neural Network Based Fault Detection for Rotating Machinery[J]. Journal of Sound and Vibration (S0022-460X), 2016, 377(Supplement C): 331-345.
[9] Karim F, Majumdar S, Darabi H, et al.LSTM fully convolutional networks for time series classification[J]. IEEE Access (S2169-3536), 2018, 6: 1662-1669.
[10] Chen Z, Li W.Multisensor Feature Fusion for Bearing Fault Diagnosis Using Sparse Autoencoder and Deep Belief Network[J]. IEEE Transactions on Instrumentation and Measurement (S0018-9456), 2017, 66(7): 1693-1702.
[11] Jing L, Wang T, Zhao M, et al.An Adaptive Multi-Sensor Data Fusion Method Based on Deep Convolutional Neural Networks for Fault Diagnosis of Planetary Gearbox[J]. Sensors (S1424-8220), 2017, 17(2): 414-415.
[12] 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 (S1551-3203), 2017, 13(4): 2106-2116.
[13] Zhao Y, Guo Z H, Yan J M.Vibration signal analysis and fault diagnosis of bogies of the high-speed train based on deep neural networks[J]. Journal of Vibroengineering (S2538-8460), 2017, 19(4): 2456-2474.
[14] Noh H, You T, Mun J, et al.Regularizing Deep Neural Networks by Noise: Its Interpretation and Optimization[G]//Guyon I, Luxburg U V, Bengio S, et al. Advances in Neural Information Processing Systems 30. Curran Associates, Inc., 2017: 5109-5118.
[15] Kingma D P, Welling M. Auto-encoding variational bayes [J]. arXiv preprint (S2331-8422) arXiv:1312.6114, 2013.
[16] Zheng Y.Methodologies for Cross-Domain Data Fusion: An Overview[J]. IEEE Transactions on Big Data (S2332-7790), 2015, 1(1): 16-34.
[17] Stutz D.Understanding convolutional neural networks [R]. InSeminar Report, Fakultät für Mathematik, Informatik und Naturwissenschaften Lehr-und Forschungsgebiet Informatik VIII Computer Vision, 2014.
[18] 鞠萍华. 旋转机械早期故障特征提取的时频分析方法研究[D]. 重庆: 重庆大学, 2010.
Ju Pinghua.Research on the Time-frequency Analysis Method to Extract Early Fault Features of Rotating Machinery[D]. Chongqing: Chongqing University, 2010.