Onboard monitoring system for railway infrastructure: design, implementation, and anomaly detection

Abstract

This paper presents the development and validation of an automatic onboard monitoring system installed on a locomotive for railway infrastructure condition assessment. The system integrates a strategic layout of accelerometers mounted on axles, bogies, and the carbody, combined with triggering mechanisms for accurate structural monitoring of track sections. Real-time solutions for data acquisition, storage, and transmission enabled long-term deployment under operational conditions. A case study was conducted on a 450-m track section on Ferrovia Tereza Cristina, in Brazil, comprising both intact rails and areas with spalling, squats, and severe wear with plastic deformation. Two defect detection methodologies were evaluated: one based on time-frequency domain features using continuous time wavelet transform, and another relying on time-domain autoencoder modeling. Both methods effectively distinguished damaged from intact sections and demonstrated sensitivity to defect severity, with higher damage indices observed for severely damaged rail sections. The results confirm the robustness of the monitoring system and the potential of data-driven approaches for accurate and continuous railway condition assessment.

Keywords

Onboard monitoring / Track damage detection / Vibration measurements / Structural health monitoring / Machine learning

References

[1] Bressi S, Santos J, Losa M. Optimization of maintenance strategies for railway track-bed considering probabilistic degradation models and different reliability levels. Reliab Eng Syst Saf, 2021, 207 107359

[2] Soleimani-Chamkhorami K, Garmabaki AHS, Kasraei A, et al. . Life cycle cost assessment of railways infrastructure asset under climate change impacts. Transp Res Part D Transp Environ, 2024, 127 104072

[3] Davari N, Veloso B, de Assis CG, et al. . A survey on data-driven predictive maintenance for the railway industry. Sensors, 2021, 21(17): 5739

[4] Ghiasi R, Malekjafarian A. Monitoring of railway tracks maintenance needs using dynamic responses collected by an in-service train. Railw Eng Sci, 2025, 33(4): 553-580

[5] Bravo I, Alvarado U, Nieto J, et al. . On-board accelerometers in railway track condition monitoring. A systematic review. Transp Res Interdiscip Perspect, 2025, 33101572

[6] Lederman G, Chen S, Garrett J, et al. . Track-monitoring from the dynamic response of an operational train. Mech Syst Signal Process, 2017, 87: 1-16

[7] Naganuma Y, Suzuki W, Itaya K et al (2000) A complete digital inertial measurement system for railway track geometry. In: Seventh international conference on computers in railways. Bologna, pp 75–84

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

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

[10] Caprioli A, Cigada A, Raveglia D. Rail inspection in track maintenance: a benchmark between the wavelet approach and the more conventional Fourier analysis. Mech Syst Signal Process, 2007, 21(2): 631-652

[11] Li Z, Dollevoet R, Molodova M, et al. . Squat growth—some observations and the validation of numerical predictions. Wear, 2011, 271(1/2): 148-157

[12] Li Z, Zhao X, Esveld C, et al. . An investigation into the causes of squats—correlation analysis and numerical modeling. Wear, 2008, 265(9/10): 1349-1355

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

[14] Hoelzl C, Dertimanis V, Landgraf M et al (2022) On-board monitoring for smart assessment of railway infrastructure: a systematic review. In: The rise of smart cities, Elsevier, Butterworth-Heinemann, pp 223–259

[15] Malekjafarian A, OBrien E, Quirke P, et al. . Railway track monitoring using train measurements: an experimental case study. Appl Sci (Basel), 2019, 9(22 4859

[16] Matsuoka K, Kawasaki K, Tanaka H, et al. . Development and validation of drive-by detection method for resonant bridges. Q Rep RTRI, 2022, 632): 133-138

[17] Wei Z, Núñez A, Li Z, et al. . Evaluating degradation at railway crossings using axle box acceleration measurements. Sensors, 2017, 17(10 2236

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

[19] Xie Q, Peng F, Tao G, et al. . Monitoring track irregularities using multi-source on-board measurement data. Railw Eng Sci, 2025, 334): 746-765

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

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

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

[23] Phusakulkajorn W, Zeng Y, Li Z, et al. . Unsupervised representation learning for monitoring rail infrastructures with high-frequency moving vibration sensors. IEEE Trans Intell Transport Syst, 2025, 26(8): 12746-12760

[24] Sohn H. Effects of environmental and operational variability on structural health monitoring. Phil Trans R Soc A, 2007, 365(1851): 539-560

[25] Bragança C, Souza EF, Ribeiro D, et al. . Drive-by methodologies applied to railway infrastructure subsystems: a literature review: Part II: track and vehicle. Appl Sci, 2023, 13(12 6982

[26] Weston P, Roberts C, Yeo G, et al. . Perspectives on railway track geometry condition monitoring from in-service railway vehicles. Veh Syst Dyn, 2015, 537): 1063-1091

[27] Fernandes TM, Lopez RH, Ribeiro DRF, et al. . Early multi-damage classification in railway bridges using drive-by numerical measurements with piecewise aggregate approximation and convolutional neural networks. Int J Str Stab Dyn, 2025

[28] Comércio e Serviços de Equipamentos Ferroviários SA (2025) Locomotiva G12 Modernizada/Microprocessada. https://www.locofer.com.br/equipamentos/locomotiva-g12-modernizada-microprocessada. Accessed 5 February 2025

[29] Chen A (2024) Ultimate guide to choose the right UHF RFID antennas. https://www.sannytelecom.com/ultimate-guide-to-choose-the-right-uhf-rfid-antennas/. Accessed 6 February 2025

[30] Fernandes T, Lopez R, Ribeiro D. Drive-by scour damage detection in railway bridges using deep autoencoder and different sensor placement strategies. J Civ Struct Health Monit, 2024, 14(8): 1895-1916

[31] Bragança C, Bittencourt T, Souza E et al (2025) AI-driven unsupervised damage detection on warren truss railway bridges using drive-by monitoring. In: Life-cycle performance of structures and infrastructure systems in diverse environments. CRC Press, London, pp 833

[32] Braganca C, De Souza ED, Ribeiro D, et al. . Drive-by early damage detection in railway bridges using wavelets and autoencoders. Proc Sixth Int Conf Railw Technol Res Dev Maint, 2024, 7: 1-12

[33] Associação Brasileira de Normas Técnicas (2012) Trilho Vignole—Requisitos. NBR 7590

[34] Google. Earth Versions—Google Earth. Google Earth Pro 2022

[35] Bao X, Li J, Wu W, et al. . Damage identification of offshore wind turbine blades based on graph neural networks and successive variational mode decomposition. Ocean Eng, 2025, 340 122310

[36] Li X, Wang Y, Wang Z, et al. . A lightweight multi-scale time-frequency fusion model for motor fault diagnosis. Eng Res Express, 2025, 7(4 045245

[37] Song M, Zhang Z, Xiao S, et al. . Bearing fault diagnosis method using a spatio-temporal neural network based on feature transfer learning. Meas Sci Technol, 2023, 341 015119

[38] Olhede SC, Walden AT. Generalized morse wavelets. IEEE Trans Signal Process, 2002, 5011): 2661-2670

[39] Lilly JM, Olhede SC. Higher-order properties of analytic wavelets. IEEE Trans Signal Process, 2009, 57(1): 146-160

[40] Wang Z, Bovik AC, Sheikh HR, et al. . Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process, 2004, 13(4): 600-612

[41] Singh D, Singh B. Investigating the impact of data normalization on classification performance. Appl Soft Comput, 2020, 97 105524

[42] Jones DR, Schonlau M, Welch WJ. Efficient global optimization of expensive black-box functions. J Glob Optim, 1998, 13(4): 455-492

[43] Sarwar MZ, Cantero D. Deep autoencoder architecture for bridge damage assessment using responses from several vehicles. Eng Struct, 2021, 246 113064

Funding

Fundação de Amparo à Pesquisa do Estado de São Paulo(grant #2022/13045-1)

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior(Finance Code 001)

Conselho Nacional de Desenvolvimento Científico e Tecnológico(grants 403540/2024-0)

Fundação para a Ciência e a Tecnologia(Base Funding - UIDB/04708/2020)

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.