Monitoring track irregularities using multi-source on-board measurement data

Abstract

Accurate monitoring of track irregularities is very helpful to improving the vehicle operation quality and to formulating appropriate track maintenance strategies. Existing methods have the problem that they rely on complex signal processing algorithms and lack multi-source data analysis. Driven by multi-source measurement data, including the axle box, the bogie frame and the carbody accelerations, this paper proposes a track irregularities monitoring network (TIMNet) based on deep learning methods. TIMNet uses the feature extraction capability of convolutional neural networks and the sequence mapping capability of the long short-term memory model to explore the mapping relationship between vehicle accelerations and track irregularities. The particle swarm optimization algorithm is used to optimize the network parameters, so that both the vertical and lateral track irregularities can be accurately identified in the time and spatial domains. The effectiveness and superiority of the proposed TIMNet is analyzed under different simulation conditions using a vehicle dynamics model. Field tests are conducted to prove the availability of the proposed TIMNet in quantitatively monitoring vertical and lateral track irregularities. Furthermore, comparative tests show that the TIMNet has a better fitting degree and timeliness in monitoring track irregularities (vertical R² of 0.91, lateral R² of 0.84 and time cost of 10 ms), compared to other classical regression. The test also proves that the TIMNet has a better anti-interference ability than other regression models.

Keywords

Track irregularities / Vehicle accelerations / On-board monitoring / Multi-source data / Deep learning / Information and Computing Sciences / Artificial Intelligence and Image Processing

References

[1.] EkbergA, KaboE, LundénR. Rail and wheel health management. Wear, 2023, 526–527204891

[2.] AsadzadehSM, BarkhordariP, GaleazziR. A model-based approach for joint estimation of track irregularities and track support modulus from trackside measurements in railway turnouts. Int J Rail Transp, 2024.

[3.] ChangC, DingX, LingL, et al. . Mechanism of high-speed train carbody shaking due to degradation of wheel-rail contact geometry. Int J Rail Transp, 2022, 113289-316

[4.] TongF, GaoL, HouB, et al. . Influence of differential deterioration of random track irregularity at different wavelengths on high-speed train safety. Int J Rail Transp, 2023, 123532-554

[5.] WenZ, TaoG, ZhaoX, LiW, et al. . Wear and RCF problems of metro wheel/rail systems: phenomena, causes and countermeasures in China. Wear, 2023, 534–535205118

[6.] XuL, LuT. Influence of track flexibility and spatial coherence of track irregularity on vehicle-slab track interaction: frequency-domain analysis. Int J Rail Transp, 2020, 94342-367

[7.] LiuY, ChenZ, ZhaiW, et al. . Dynamic investigation of traction motor bearing in a locomotive under excitation from track random geometry irregularity. Int J Rail Transp, 2020, 10172-94

[8.] TaoG, WenZ, JinX, et al. . Polygonisation of railway wheels: a critical review. Railw Eng Sci, 2020, 284317-345

[9.] ZhaoW, QiangW, YangF, et al. . Data-driven ballast layer degradation identification and maintenance decision based on track geometry irregularities. Int J Rail Transp, 2023, 124581-603

[10.] TrueH, ChristiansenLE, PlesnerAL, et al. . On the problem of the dynamical reactions of a rolling wheelset to real track irregularities. Railw Eng Sci, 2023, 3111-19

[11.] Xie Q, Wang J, Tao G et al (2024) Intelligent PHM of wheel–rail systems driven by deep learning models with novel targeted loss and directed metric: an application to quantitative detection of rail corrugation. In: Proceedings of the third international conference on rail transportation (ICRT2024), Shanghai.

[12.] KarisT, BergM, StichelS. Analysing the correlation between vehicle responses and track irregularities using dynamic simulations and measurements. Proc Inst Mech Eng Part F J Rail Rapid Transit, 2020, 234: 170-182

[13.] WangQ, ZhaoH, GongD, et al. . Quantitative detection of vertical track irregularities under non-stationary conditions with variable vehicle speed. Sensors, 2024, 24123804

[14.] NingJ, LinJ, ZhangB. Time−frequency processing of track irregularities in high-speed train. Mech Syst Signal Process, 2016, 66–67: 339-348

[15.] LeeJS, ChoiS, KimSS, et al. . A mixed filtering approach for track condition monitoring using accelerometers on the axle box and bogie. IEEE Trans Instrum Meas, 2012, 613749-758

[16.] XieQ, TaoG, HeB, et al. . Rail corrugation detection using one-dimensional convolution neural network and data-driven method. Measurement, 2022, 200111624

[17.] XieQ, TaoG, LoSM, et al. . A data-driven convolutional regression scheme for on-board and quantitative detection of rail corrugation roughness. Wear, 2023, 524–525204770

[18.] YuanZ, LuoJ, ZhuS, et al. . A Wasserstein generative adversarial network-based approach for real-time track irregularity estimation using vehicle dynamic responses. Veh Syst Dyn, 2022, 60124186-4205

[19.] WestonPF, LingCS, RobertsC, et al. . Monitoring vertical track irregularity from in-service railway vehicles. Proc Inst Mech Eng Part F J Rail Rapid Transit, 2007, 221175-88

[20.] WestonPF, LingCS, GoodmanCJ, et al. . Monitoring lateral track irregularity from in-service railway vehicles. Proc Inst Mech Eng Part F J Rail Rapid Transit, 2007, 221189-100

[21.] ChoiIY, UmJH, LeeJS, ChoiHH. The influence of track irregularities on the running behavior of high-speed trains. Proc Inst Mech Eng Part F J Rail Rapid Transit, 2013, 227194-102

[22.] WeiXK, LiuF, JiaLM. Urban rail track condition monitoring based on in-service vehicle acceleration measurements. Measurement, 2016, 80: 217-228

[23.] SkermanD, ColeC, SpiryaginM. The effect of the wavelength of lateral track geometry irregularities on the response measurable by an instrumented freight wagon. Veh Syst Dyn, 2024, 623533-555

[24.] XingZ, ChenY, QingY. On-line monitoring of vertical long wavelength track irregularities using bogie pitch rate. J Vibroengineering, 2015, 171216-228

[25.] Gao J, Zhai W (2011) Effect of track irregularity amplitude on dynamic performance of vehicle system under high-speed operation. In: Proceedings of the 5th international symposium on environmental vibration (ISEV2011), Chengdu, pp 667−673

[26.] Kobayashi T, Naganuma Y, Tsunashima H (2013) Condition monitoring of shinkansen tracks based on inverse analysis. In: Proceedings of the 4th IEEE international conference on prognostics and system health management (PHM), Milan, pp 703−708

[27.] FujimotoH, TanifujiK, MiyamotoM. Comparison between data from test train running on track irregularities artificially set and results of vehicle dynamics simulation (influence of track gauge variation on rail vehicle dynamics). Veh Syst Dyn, 1998, 29157-72

[28.] Zhang X, Ha L, Wei X et al (2015) Railway track condition monitoring based on acceleration measurements. In: proceedings of the 27th Chinese control and decision conference (CCDC), Qingdao, pp 923−928

[29.] Zhang Y, Sun X, Xu X et al (2017) Track irregularities estimation based on the vibration of car-body. In: Proceedings of the 2nd IEEE advanced information technology, electronic and automation control conference (IAEAC), Chongqing, pp 1369−1372

[30.] TsunashimaH, NaganumaY, KobayashiT. Track geometry estimation from car-body vibration. Veh Syst Dyn, 2014, 521207-219

[31.] TsunashimaH, OnoH, TakataT, et al. . Development and operation of track condition monitoring system using in-service train. Appl Sci-Basel, 2023, 1363835

[32.] LiuX, LiZ, WuJ, SongC, et al. . Correlation analysis between rail track geometry and car-body vibration based on fractal theory. Fractal fract, 2022, 612727

[33.] LiC, HeQ, WangP. Estimation of railway track longitudinal irregularity using vehicle response with information compression and Bayesian deep learning. Comput-Aided Civ Inf, 2022, 37101260-1276

[34.] WeiL, ZengJ, LuoR, et al. . Carbody sway behaviour of railway vehicles due to track irregularity from rail alternate side wear. Railw Eng Sci, 2024.

[35.] NiuL, LiuJ. Application status and prospect of track state detection technology based on vehicle dynamic response analysis. China Railway Science, 2021, 426130-142(in Chinese)

[36.] GadhaveR, VyasNS. Rail-wheel contact forces and track irregularity estimation from on-board accelerometer data. Veh Syst Dyn, 2022, 6062145-2166

[37.] LuoR, ShiHDynamics of railway vehicle systems and application, 2018ChengduSouthwest Jiaotong University Press

[38.] ChenG, ZhaiW. Numerical simulation of the stochastic process of railway track irregularities. J Southwest Jiaotong Univ, 1999, 342138-142(in Chinese)

[39.] EichbergerA, HofmannG. TMPT: multi-body package SIMPACK. Veh Syst Dyn, 2007, 45sup1207-216

[40.] HertzBH. On the contact of elastic solids. J Reine Angew Math, 1882, 92: 156-171

[41.] KalkerJJ. A fast algorithm for the simplified theory of rolling contact. Veh Syst Dyn, 1982, 11: 1-13

[42.] Zhai W (2020) Numerical method and computer simulation for analysis of vehicle–track coupled dynamics. In: Vehicle–track coupled dynamics. Springer, Singapore

[43.] XieQ, TaoG, LoSM, et al. . High-speed railway wheel polygon detection framework using improved frequency domain integration. Veh Syst Dyn, 2024, 6261424-1445

[44.] Xie Q, Wang J, Tao G et al (2023) A sparsity-free compressed sensing method for PHM data quality assurance using generative adversarial network. In: Proceedings of the 6th international conference on electrical engineering and information technologies for rail transportation (EITRT2023), Beijing, pp 718–726

Funding

Sichuan Science and Technology Program(2023YFQ0091); National Natural Science Foundation of China(U21A20167); Scientific Research Foundation of the State Key Laboratory of Rail Transit Vehicle System(2024RVL-T08)