Multi-sensor system for efficient in-service vehicle-based track monitoring and fault localization: a case study

Abstract

As the requirements for railway operators to offer a safe and economically efficient transportation service have become extremely difficult to met due to the size and complexity of the rail network, vehicle-based track monitoring and fault detection have gained relevance as a way to abate maintenance-related costs via condition-based and predictive approaches. In this work, a cost-effective, permit-free vehicle-based track monitoring system implemented on a regular in-service vehicle is presented. The designed system makes use of inertial sensors mounted on the vehicle’s bogie and car body, as well as positioning technology based on global navigation satellite system (GNSS) to collect monitoring data for detection and spatial localization of track defects. The capabilities of the developed system are exemplified by means of a case study related to a track section with a temporary speed restriction (TSR)—a scenario where traditional acceleration-based detection often fails due to reduced vehicle speed. Here, it is demonstrated that the proposed approach, combining statistical and time-frequency analysis (e.g., wavelets), can effectively lead to the detection and localization of anomalies on the track using onboard inertial measurements, even under reduced vehicle speed.

Keywords

Vehicle-based monitoring / Railway systems / Fault detection and localization / Temporary speed restriction / Time-frequency analysis

References

[1] Baasch B, Roth M, Groos JC. In-service condition monitoring of rail tracks. Int Verkehrswesen, 2018, 70(1): 76-79

[2] Schenkendorf R, Dutschk B, Lüddecke K et al (2016) Improved railway track irregularities classification by a model inversion approach. In: Proceeding of the third european conference of the prognostics and health management society 2016, Bilbao. PHM Society, pp 62–69

[3] Falamarzi A, Moridpour S, Nazem M. A review of rail track degradation prediction models. Aust J Civ Eng, 2019, 17(2): 152-166

[4] Bahamon-Blanco S, Rapp S, Rupp C et al (2019) Recognition of track defects through measured acceleration-part 1 and 2. In: IOP conference series: materials science and engineering, vol. 615. IOP Publishing, pp 012121

[5] Fernández-Bobadilla HA, Martin U. Modern tendencies in vehicle-based condition monitoring of the railway track. IEEE Trans Instrum Meas, 2023, 72: 1-44

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

[7] OBrien EJ, Quirke P, Bowe C, et al.. Determination of railway track longitudinal profile using measured inertial response of an in-service railway vehicle. Struct Health Monit, 2018, 17(6): 1425-1440

[8] van der Kooij RBK, Landmark AD, Seim AA, et al.. The effect of temporary speed restrictions, analyzed by using real train traffic data. Transp Res Proced, 2017, 22: 580-587

[9] Haigermoser A, Luber B, Rauh J, et al.. Road and track irregularities: measurement, assessment and simulation. Veh Syst Dyn, 2015, 53(7): 878-957

[10] Rupp M, Lorenzen S, Hübler C (2024) Indirect continuous monitoring of bridge transitions using the CTM 2.0. In: Bridge maintenance, safety, management, digitalization and sustainability. CRC Press, pp 1736–1744

[11] Wolfs PJ, Bleakley S, Senini ST (2006) An autonomous, low cost, distributed method for observing vehicle track interactions. In: Proceedings of the 2006 IEEE/ASME joint rail conference. IEEE, Atlanta, pp 279–286

[12] Tsunashima H, Naganuma Y, Matsumoto A et al (2011) Japanese railway condition monitoring of tracks using in-service vehicle. In: 5th IET conference on railway condition monitoring and non-destructive testing (RCM 2011), Derby, UK. IET, pp 1–6

[13] Mori H, Sato Y, Ohno H, et al.. Development of compact size onboard device for condition monitoring of railway tracks. J Mech Syst Transp Logist, 2013, 6(2): 142-149

[14] Vanhatalo E, Arasteh-Khouy I, Bergquist B. Assessing the causal and dynamic effects of tamping on railway track geometry using onboard mounted and regular track geometry measurements. Proc Inst Mech Eng Part F J Rail Rapid Transit, 2025, 239(8): 700-709

[15] Balouchi F, Bevan A, Formston R (2016) Detecting railway under-track voids using multi-train in-service vehicle accelerometer. Paper presented at 7th IET Conference on Railway Condition Monitoring 2016 (RCM2016). Birmingham

[16] Lederman G, Chen S, Garrett JH, et al.. Track monitoring from the dynamic response of a passing train: a sparse approach. Mech Syst Signal Process, 2017, 90: 141-153

[17] Lerke O, Bahamon-Blanco S, Metzner M (2021) Vorarbeiten zur Entwicklung eines Gleisfehler-detektionssystems mit Regelzügen und low-cost-sensorik [Preliminary works on the development of a track fault detection system with regular trains and low-cost sensor technology. ZfV-Zeitschrift für Geodäsie.(Geoinformation und Landmanagement (zfv 3/2021)

[18] Hoelzl C, Dertimanis V, Landgraf M (2022) On-board monitoring for smart assessment of railway infrastructure: a systematic review. The Rise of Smart Cities. Elsevier, pp 223–259

[19] Bravo I, Alvarado U, Nieto J. On-board accelerometers in railway track condition monitoring. A systematic review. Transp Res Interdiscip Perspect, 2025, 33: 101572

[20] Tsunashima H, Naganuma Y, Kobayashi T. Track geometry estimation from car-body vibration. Veh Syst Dyn, 2014, 52(sup1): 207-219

[21] Tsunashima H. Condition monitoring of railway tracks from car-body vibration using a machine learning technique. Appl Sci, 2019, 9(13): 2734

[22] Tsunashima H, Hirose R. Condition monitoring of railway track from car-body vibration using time-frequency analysis. Veh Syst Dyn, 2020, 60(4): 1170-1187

[23] Balouchi F, Bevan A, Formston R. Development of railway track condition monitoring from multi-train in-service vehicles. Veh Syst Dyn, 2021, 59(9): 1397-1417

[24] Kojima T, Tsunashima H, Matsumoto A. Fault detection of railway track by multi-resolution analysis. WIT Trans Built Environ, 2006, 88: 955-964

[25] Unsiwilai S, Wang L, Núnez A, et al.. Multiple-axle box acceleration measurements at railway transition zones. Measurement, 2023, 213: 112688

[26] Costa MA, Costa JN, Andrade AR, et al.. Combining wavelet analysis of track irregularities and vehicle dynamics simulations to assess derailment risks. Veh Syst Dyn, 2023, 61(1): 150-176

[27] Podwórna M. Modelling of random vertical irregularities of railway tracks. Int J Appl Mech Eng, 2015, 20(3): 647-655

[28] Fries RH, Coffey BM. A state-space approach to the synthesis of random vertical and crosslevel rail irregularities. J Dyn Syst Meas Control, 1990, 112(1): 83-87

[29] Perrin G, Soize C, Duhamel D, et al.. Track irregularities stochastic modeling. Probab Eng Mech, 2013, 34: 123-130

[30] Zhu M, Cheng X, Miao L, et al.. Random field modeling of track irregularity of Beijing-Guangzhou high-speed railway with Karhunen-Loève expansion. Int J Distrib Sens Netw, 2015, 11(6): 521437

[31] Panunzio AM, Puel G, Cottereau R, et al.. Construction of a stochastic model of track geometry irregularities and validation through experimental measurements of dynamic loading. Veh Syst Dyn, 2017, 55(3): 399-426

[32] Odashima M, Azami S, Naganuma Y et al (2017) Track geometry estimation of a conventional railway from car-body acceleration measurement. Mech Eng J 4(1):16–498

[33] Dertimanis VK, Zimmermann M, Corman F (2020) On-board monitoring of rail roughness via axle box accelerations of revenue trains with uncertain dynamics. In: Model validation and uncertainty quantification, vol 3. Springer International Publishing, pp 167–171

[34] Fernández-Bobadilla HA, Martin U (2024) GAN-based data augmentation of railway track irregularities for fault diagnosis. In: 2024 International joint conference on neural networks (IJCNN), Yokohama

[35] Fernández-Bobadilla HA, Bouchikhi Y, Martin U. GAN-based data augmentation of time series for fault diagnosis in railway track. Railw Eng Sci, 2025, 33(4): 642-683

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

[37] Lasisi A, Attoh-Okine N. Principal components analysis and track quality index: a machine learning approach. Transp Res Part C Emerg Technol, 2018, 91: 230-248

[38] Ghiasi R, Khan MA, Sorrentino D, et al.. An unsupervised anomaly detection framework for onboard monitoring of railway track geometrical defects using one-class support vector machine. Eng Appl Artif Intell, 2024, 133: 108167

[39] Bruzek R, Trosino M, Kreisel L et al (2015) Rail temperature approximation and heat slow order best practices. In: Proceedings of the ASME 2015 joint rail conference (JRC2015), San Jose. American Society of Mechanical Engineers, New York, Paper No JRC2015-5720, pp V001T04A002

[40] Andrade AR, Teixeira PF. Assessing temporary speed restrictions and associated unavailability costs in railway infrastructure. Int J Civ Eng, 2018, 16(2): 219-228

[41] Calderón A. Intermediate spaces and interpolation, the complex method. Stud Math, 1964, 24(2): 113-190

[42] Grossmann A, Morlet J. Decomposition of hardy functions into square integrable wavelets of constant shape. SIAM J Math Anal, 1984, 15(4): 723-736

[43] Mallat S. A wavelet tour of signal processing: the sparse way, 2009, 3, Boston Academic Press

[44] Percival DB, Walden AT. Wavelet methods for time series analysis, 2000, Cambridge, Cambridge University Press 4

[45] Mallat S, Hwang WL. Singularity detection and processing with wavelets. IEEE Trans Inform Theory, 1992, 38(2): 617-643

[46] Mallat SG. A theory for multiresolution signal decomposition: the wavelet representation. IEEE Trans Pattern Anal Machine Intell, 1989, 11(7): 674-693

[47] Percival DB, Mofjeld HO. Analysis of subtidal coastal sea level fluctuations using wavelets. J Am Stat Assoc, 1997, 92(439): 868-880

[48] Kalman RE. A new approach to linear filtering and prediction problems. J Basic Eng, 1960, 82(1): 35-45

[49] Sola J (2017) Quaternion kinematics for the error-state Kalman filter. arXiv:1711.02508

[50] Titterton D, Weston JL. Strapdown inertial navigation technology, 2004, 2, London IET

[51] Groves P. Principles of GNSS, inertial, and multisensor integrated navigation systems, 2013, 2, Boston Artech House

[52] Frolow R, Zhang L, Schwieger V. Precise train positioning with unscented Kalman filter and low-cost sensors. IEEE Open J Intell Transp Syst, 2026, 7: 304-312

[53] Wan EA, van der Merwe R (2000) The unscented Kalman filter for nonlinear estimation. In: Proceedings of the IEEE 2000 adaptive systems for signal processing, communications, and control symposium (AS-SPCC), Lake Louise. IEEE, Piscataway, pp 153–158

[54] Julier SJ, Uhlmann JK. Unscented filtering and nonlinear estimation. Proc IEEE, 2004, 92(3): 401-422

[55] Zhang L, Frolow R, Schwieger V (2025) Cost-effective localization of railway track faults using GNSS antenna under train’s roof. In: Proceedings of the FIG working week 2025, Brisbane. International Federation of Surveyors, Copenhagen

[56] Rodriguez-Bayona LT, Fernández-Bobadilla HA, Martin U (2025) Monitoring data mapping for infrastructure-oriented visualization of railway track condition. In: Proceedings of the 5th international railway symposium aachen (IRSA 2025), Aachen. RWTH Aachen University, Aachen, pp 725–739

[57] González-Muñiz A, Díaz I, Cuadrado AA, et al.. Two-step residual-error based approach for anomaly detection in engineering systems using variational autoencoders. Comput Electr Eng, 2022, 101: 108065

[58] Hsu CC, Frusque G, Fink O (2023) A comparison of residual-based methods on fault detection. arXiv:2309.02274

Funding

Deutsche Forschungsgemeinschaft(515687155)

Rights & permissions

The Author(s)

Just Accepted

This article has successfully passed peer review and final editorial review, and will soon enter typesetting, proofreading and other publishing processes. The currently displayed version is the accepted final manuscript. The officially published version will be updated with format, DOI and citation information upon launch. We recommend that you pay attention to subsequent journal notifications and preferentially cite the officially published version. Thank you for your support and cooperation.