The hunting motion of the vehicle increases the wear of the wheel tracks and affects the lateral stability of the vehicle system and safety, so the hunting motion of the vehicle needs to be recognized. However, the existing recognition methods ignore the small-amplitude hunting motion that precedes the onset of the running motion. In addition, due to the scarcity of real hunting data of high-speed trains, there is a problem of underfitting when training with traditional deep learning methods. In this paper, first, the dynamics model of a high-speed train is established, and the normal, small-amplitude hunting and hunting motions of high-speed trains in the process are simulated. Second, this paper proposes a transfer learning-based method for high-speed train hunting motion recognition. The method uses easily collected normal data samples in the training process, does not use real data samples of small-amplitude hunting and hunting motions, and completes the high-speed train running motions recognition task by transferring from simulation data (source domain) to real data (target domain). Finally, the validation is carried out using the real data, which proves that the method-related approach has some engineering application value in the intelligent monitoring of high-speed trains.
2008/232/EC (2008) Concerning a Technical specification for interoperability relating to ‘rolling stock’ sub-system of the Trans- European high-speed rail system.
2.
AlabsiMLiaoYNabulsiA, et al. (2021) Bearing fault diagnosis using deep learning techniques coupled with handcrafted feature extraction: a comparative study. Journal of Vibration and Control27(3–4): 404–414.
3.
ChenHJiangB (2020) A review of fault detection and diagnosis for the traction system in high-speed trains. IEEE Transactions on Intelligent Transportation Systems21(2): 450–465.
4.
ChenHJiangBStevenX, et al. (2020) Data-driven fault diagnosis for traction systems in high-speed trains: a survey, challenges, and perspectives. IEEE Transactions on Intelligent Transportation Systems23: 1–17.
5.
FRA Vehicle/Track interaction safety standards (2013) High-Speed and High cant Deficiency Operations. College Park: National archives and records administration.
6.
GanD (2016) Recognition method and real-time online monitoring device for lateral stability of high speed train based on Bayesian clustering. China Railway Science37(04): 139–144.
7.
GaninYUstinovaEAjakanH, et al. (2016) Domain-adversarial training of neural networks. Journal of Machine Learning Research17(1): 1–13.
8.
GuoLLeiYXingS, et al. (2018) Deep convolutional transfer learning network: a new method for intelligent fault diagnosis of machines with unlabeled data. IEEE Transactions on Industrial Electronics66(9): 7316–7325.
9.
HanTLiuCWuR, et al. (2021) Deep transfer learning with limited data for machinery fault diagnosis. Applied Soft Computing103: 107150.
10.
LiXZhangW (2020) Deep learning-based partial domain adaptation method on intelligent machinery fault diagnostics. IEEE Transactions on Industrial Electronics68(5): 4351–4361.
11.
LiXZhangWDingQ, et al. (2020) Diagnosing rotating machines with weakly supervised data using deep transfer learning. IEEE Transactions on Industrial Informatics16(3): 1688–1697.
12.
LiFTangTTangB, et al. (2021) Deep convolution domain-adversarial transfer learning for fault diagnosis of rolling bearings. Measurement169: 108339.
13.
MaSGaoLLiuX, et al. (2019) Deep learning for track quality evaluation of high-speed railway based on vehicle-body vibration prediction. IEEE Access7: 185099–185107.
14.
NajehTLundbergJKerroucheA, et al. (2021) Deep-learning and vibration-based system for wear size estimation of railway switches and crossings. Sensors21(15): 5217.
15.
NingJCuiWChongC, et al. (2019) Feature recognition of small amplitude hunting signals based on the MPE-LTSA in high-speed trains. Measurement131: 452–460.
16.
NingJFangMRanW, et al. (2020) Rapid multi-sensor feature fusion based on non-stationary kernel JADE for the small-amplitude hunting monitoring of high-speed trains. Sensors20(12): 3457–3473.
17.
PanSJYangQ (2009) A survey on transfer learning. IEEE Transactions on Knowledge and Data Engineering22(10): 1345–1359.
18.
PolachO (2005) Influence of wheel/rail contact geometry on the behaviour of a railway vehicle at stability limit. In: Proceedings ENOC-2005 2203-2210, Eindhoven, The Netherlands, University of Technology.
19.
PolachO (2009) Application of nonlinear stability analysis in railway vehicle industry. In: Non-smooth Problems in Vehicle Systems Dynamics. Berlin, Heidelberg: Springer, 15–27.
20.
PolachOVuittonJ (2019) Which parameters determine the type of bogie hunting bifurcation. In: The IAVSD International Symposium on Dynamics of Vehicles on Roads and Tracks. Cham. August: Springer, 483–490.
21.
SantamariaJVadilloEGGomezJ, et al. (2009) Influence of creep forces on the risk of derailment of railway vehicles. Vehicle System Dynamics47: 721–752.
22.
SedighiHShiraziK (2012) A survey of Hopf bifurcation analysis in nonlinear railway wheelset dynamics. Journal of Vibroengineering14(1): 344–351.
23.
SresakoolchaiJKaewunruenS (2021) Detection and severity evaluation of combined rail defects using deep learning. Vibrations4(2): 341–356.
24.
SunJMeliECaiW, et al. (2020) A signal analysis based hunting instability detection methodology for high-speed railway vehicles. Vehicle System Dynamics59(10): 1–23.
25.
Tb/T 3188 (2007) Technical specification for railway car safety monitor and diagnosis system.
26.
TB10761 (2013) Technical regulations for dynamic acceptance for high-speed railways construction.
27.
TzengEHoffmanJZhangN, et al. (2019) Deep domain confusion: Maximizing for domain invariance. arXiv 2014 arXiv preprint arXiv:1412.3474.
28.
WenLGaoLLiX, et al. (2019) A new deep transfer learning based on sparse auto-encoder for fault diagnosis. IEEE Transactions on Systems, Man, and Cybernetics: Systems49(1): 136–144.
29.
YanY (2019) Hopf bifurcation study of hunting behavior of vehicle systems. China: Dissertation, Southwest Jiaotong University.
30.
YeYNingJ (2019) Small-amplitude hunting diagnosis method of high-speed trains based on bogie frame’s lateral-longitudinal-vertical data fusion, independent mode function reconstruction and linear local tangent space alignment, Proceedings of the Institution of Mechanical Engineers. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit233(10): 1050–1067.
31.
YounesianDJafariASerajianR (2011) Effects of the bogie and body inertia on the nonlinear wheel-set hunting recognized by the hopf bifurcation theory. Automotive Science and Engineering1(3): 186–196.
32.
ZengYZhangWSongD, et al. (2020) A new strategy for hunting alarm and stability evaluation for railway vehicles based on nonlinear dynamics analysis. Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit234(1): 54–64.
33.
ZhangWHLiYSongDL (2013) Design methods for motion stability of high-speed trains. Southwest Jiaotong University48: 1–9.
34.
ZhangLGuoLGaoH, et al. (2020) Instance-based ensemble deep transfer learning network: a new intelligent degradation recognition method and its application on ball screw. Mechanical Systems and Signal Processing140: 106681.
