A comprehensive data-driven approach to estimate track longitudinal level from inertial measurements

Abstract

Infrastructure managers rely on diagnostic trains that periodically measure track geometry and vehicle accelerations to ensure the safety of the railway network. Their runs are scheduled depending on the line priority, in order to safely monitor the evolution of track defects. However, sudden and unpredictable defect growth may happen and be missed between successive runs. Therefore, condition monitoring systems have been installed on in-service vehicles. In fact, these trains run every day along the same line, so they can provide additional information useful for maintenance practices. When trains run along conventional lines, their speed significantly changes depending on the line characteristics, and vehicle accelerations strongly depend on speed. Therefore, monitoring systems that rely on vehicle accelerations should carefully take this effect into account. In this paper, a methodology to estimate the track longitudinal level using bogie accelerations from an in-service vehicle is presented. The recorded accelerations were double-integrated to account for the speed variation, and a model-based strategy was adopted to reduce the filtering action of the primary suspension. Data were recorded during a two-year monitoring campaign along an Italian railway line. The methodology allowed for the estimation of the longitudinal level along specific track sections, considering statistical measures like the peak value. A maximum error of 1 mm was found between the estimated values and those measured by the diagnostic train (considering a defect with magnitude of 7.5 mm). Therefore, the results showed that it is possible to estimate the peak longitudinal level between the two rails using one single vertical accelerometer installed on the bogie of an in-service vehicle. The results of this research may be used to support the current maintenance strategy with daily estimations of track longitudinal level. It should be noted that specific attention was given only to this type of track geometry parameter, since it often drives maintenance operations. In the future, the possibility to extend the methodology to the estimation of different type of defects, like cross-level and twist, could be considered.

Keywords

Rolling stock-based diagnostic system / Railway track monitoring / Railway infrastructure / Track condition / Condition-based maintenance / Predictive maintenance

References

[1] Weston P, Roberts C, Yeo Get al.. Perspectives on railway track geometry condition monitoring from in-service railway vehicles. Veh Syst Dyn, 2015, 53(7): 1063-1091

[2] Yan TH, Hoelzl C, Corman Fet al.. Integration of on-board monitoring data into infrastructure management for effective decision-making in railway maintenance. Railw Eng Sci, 2025, 33(1): 151-168

[3] Jarillo JM, Moreno J, Alfi Set al.. Novel technology concepts and architecture for on-board condition-based monitoring of railway running gear: the RUN2Rail vision. Proc Inst Mech Eng F J Rail Rapid Transit, 2021, 235(5): 616-630

[4] Liu X Y, Alfi S, Bruni S (2016) An efficient condition monitoring strategy of railway vehicle suspension based on recursive least-square algorithm. In: The Dynamics of Vehicles on Roads and Tracks—Proceedings of the 24th Symposium of the International Association for Vehicle System Dynamics, IAVSD 2015. pp. 861–870

[5] Tsunashima H, Ono H, Takata Tet al.. Development and operation of track condition monitoring system using in-service train. Appl Sci, 2023, 13(6): 3835

[6] Araya Reyes CE, Zanelli F, Castelli-Dezza Fet al.. Monitoring the bogie lateral dynamics of a high-speed train through wireless sensor nodes. Proc Inst Mech Eng F J Rail Rapid Transit, 2024, 23891121-1132

[7] Weston PF, Li P, Ling CSet al.. Track and vehicle condition monitoring during normal operation using reduced sensor sets. Trans Hong Kong Inst Eng, 2006, 13: 47-53

[8] Ward CP, Weston PF, Stewart EJCet al.. Condition monitoring opportunities using vehicle-based sensors. Proc Inst Mech Eng F J Rail Rapid Transit, 2011, 225(2): 202-218

[9] Real J, Montalbán L, Bueno M. Determination of rail vertical profile through inertial methods. Proc Inst Mech Eng F J Rail Rapid Transit, 2011, 225(1): 14-23

[10] OBrien EJ, Bowe C, Quirke Pet al.. Determination of longitudinal profile of railway track using vehicle-based inertial readings. Proc Inst Mech Eng F J Rail Rapid Transit, 2017, 231(5): 518-534

[11] Sun X, Yang F, Shi Jet al.. On-board detection of longitudinal track irregularity via axle box acceleration in HSR. IEEE Access, 2021, 9: 14025-14037

[12] De Rosa A, Kulkarni R, Qazizadeh Aet al.. Monitoring of lateral and cross level track geometry irregularities through onboard vehicle dynamics measurements using machine learning classification algorithms. Proc Inst Mech Eng F J Rail Rapid Transit, 2021, 235(1): 107-120

[13] Hao X, Yang J, Yang Fet al.. Track geometry estimation from vehicle–body acceleration for high-speed railway using deep learning technique. Veh Syst Dyn, 2023, 61(1): 239-259

[14] Molodova M, Li Z, Núnez Aet al.. Automatic detection of squats in railway infrastructure. IEEE Trans Intell Transp Syst, 2014, 15(5): 1980-1990

[15] Molodova M, Oregui M, Núñez Aet al.. Health condition monitoring of insulated joints based on axle box acceleration measurements. Eng Struct, 2016, 123(15): 225-235

[16] Weston PF, Ling CS, Roberts Cet al.. Monitoring vertical track irregularity from in-service railway vehicles. Proc Inst Mech Eng F J Rail Rapid Transit, 2007, 221(1): 75-88

[17] Weston PF, Ling CS, Roberts Cet al.. Monitoring lateral track irregularity from in-service railway vehicles. Proc Inst Mech Eng F J Rail Rapid Transit, 2007, 221(1): 89-100

[18] Alfi S, De Rosa A, Bruni S (2016) Estimation of lateral track irregularities from on-board measurement: Effect of wheel-rail contact model. In: 7th IET Conference on Railway Condition Monitoring 2016 (RCM 2016), Birmingham, 2016, pp 1–7

[19] Rosano G, Massini D, Bocciolini Let al.. Diagnostics of the railway track-possibility of development through the measurement of accelerations and contact forces (La diagnostica dell’armamento ferroviario-Possibilità di sviluppo attraverso la misura di accelerazioni e forze di contatto). Ingegneria Ferroviaria, 2024, 79(2): 81-102

[20] Yeo GJ, Weston PF, Roberts C (2014) The utility of Continual Monitoring of track geometry from an in-service vehicle. In: 6th IET Conference on Railway Condition Monitoring (RCM 2014), Birmingham, pp 1–6,

[21] Grassie SL. Measurement of railhead longitudinal profiles: a comparison of different techniques. Wear, 1996, 191(1): 245-251

[22] McAnaw HE. The system that measures the system. NDT & E Int, 2003, 36(3): 169-179

[23] Lee JS, Choi S, Kim S-Set al.. A mixed filtering approach for track condition monitoring using accelerometers on the axle box and bogie. IEEE Trans Instrum Meas, 2012, 61(3): 749-758

[24] Nicks S (1998) Condition monitoring of the train/track interface. In: Proceedings of the IEEE Seminar–Condition Monitoring for Rail Transport System, London, 10 November 1998.

[25] Bocciolone M, Caprioli A, Cigada Aet al.. A measurement system for quick rail inspection and effective track maintenance strategy. Mech Syst Signal Process, 2007, 21(3): 1242-1254

[26] Tsunashima H, Yagura N. Railway track irregularity estimation using car body vibration: a data-driven approach for regional railway. Vibration, 2024, 7(4): 928-948

[27] Tsunashima H, Naganuma Y, Kobayashi T. Track geometry estimation from car-body vibration. Veh Syst Dyn, 2014, 52: 207-219

[28] European Committee for Standardization (2017) EN 13848–5:2017. Railway applications–Track–Track geometry quality. Part 5: geometry quality levels– plain line, switches and crossings

[29] Karis T, Berg M, Stichel Set al.. Correlation of track irregularities and vehicle responses based on measured data. Veh Syst Dyn, 2018, 56(6): 967-981

[30] La Paglia I, Carnevale M, Corradi Ret al.. Condition monitoring of vertical track alignment by bogie acceleration measurements on commercial high-speed vehicles. Mech Syst Signal Process, 2023, 186: 109869

[31] La Paglia I, Di Gialleonardo E, Facchinetti A et al (2023) A methodology to estimate railway track conditions from vehicle accelerations based on multiple regression. In: Limongelli MP, Giordano PF, Quqa S et al (Eds.) Experimental Vibration Analysis for Civil Engineering Structures. EVACES 2023. Lecture Notes in Civil Engineering, vol 432. Springer, Cham

[32] La Paglia I, Di Gialleonardo E, Facchinetti Aet al.. Acceleration-based condition monitoring of track longitudinal level using multiple regression models. Proc Inst Mech Eng F J Rail Rapid Transit, 2024, 238(5): 479-488

[33] La Paglia I, Araya Reyes CE, Di Gialleonardo E et al (2025). A speed-dependent condition monitoring system for track geometry estimation using inertial measurements. In: Huang W, Ahmadian M (eds) Advances in Dynamics of Vehicles on Roads and Tracks III. IAVSD 2023. Lecture Notes in Mechanical Engineering. Springer, Cham

[34] European Committee for Standardization (2019) EN 13848–1:2019. Railway applications–Track–Track geometry quality. Part 1: Characterisation of track geometry

[35] Carnevale M, La Paglia I, Pennacchi P. An algorithm for precise localization of measurements in rolling stock-based diagnostic systems. Proc Inst Mech Eng F J Rail Rapid Transit, 2021, 235(7): 827-839

[36] Aravanis TCI, Sakellariou JS, Fassois SD. Spectral analysis of railway vehicle vertical vibration under normal operating conditions. Int J Rail Transp, 2016, 4(4): 193-207

Funding

Ministero dell'Università e della Ricerca(DOT1316301-3)

RIGHTS & PERMISSIONS

The Author(s)