IMPROVING METHODS FOR DETECTING AND DIAGNOSING RAILWAY BEARING FAULTS USING VIBRATION SENSORS
Keywords:
railway axlebox bearing, vibration sensor, fault diagnosis, envelope analysis, sensor positioning, condition monitoring.Abstract
Railway axlebox bearings operate under variable loads, wheel–rail impacts and changing rotational speeds, which complicate the early detection of local defects. This review evaluates vibration-based approaches to identifying inner-race, outer-race and rolling-element faults and examines how sensor location influences diagnostic reliability. A targeted comparative analysis of published railway studies, foundational bearing-diagnostics research and openly documented benchmark datasets was conducted. Root-mean-square (RMS) amplitude and kurtosis are useful for screening, whereas spectral analysis and envelope demodulation provide stronger links to characteristic defect frequencies when speed and bearing geometry are known. Time–frequency and adaptive-band methods can improve interpretability under non-stationary conditions, but their effectiveness depends on signal quality and validation conditions. The review identifies mounting repeatability, transmission-path attenuation, speed variation and domain shift between laboratory and railway data as major obstacles. A three-stage improvement framework is proposed: standardize measurement conditions; compare candidate sensor positions using signal-quality and fault-separability criteria; and apply speed-aware, multi-domain signal analysis before fault classification. This is a literature-based methodological proposal, not a report of newly measured diagnostic accuracy. The study offers a transparent basis for subsequent experimental development of an adaptive sensor-positioning mechatronic system for railway bearing inspection.
References
M. Entezami, C. Roberts, P. Weston, E. Stewart, A. Amini, and M. Papaelias, “Perspectives on railway axle bearing condition monitoring,” Proc. IMechE Part F: J. Rail Rapid Transit, vol. 234, no. 1, pp. 17–31, 2020. doi: 10.1177/0954409719831822.
M. Abtane, K. Dahi, H. Martinez, M. Sedki, H. El Kimi, C. Dahhassi, C. Hlib, and L. F. Borges, “Axle bearing fault diagnosis for high-speed trains: A comprehensive review of methodologies, technologies, challenges and emerging trends,” Measurement, vol. 251, art. 117098, 2025. doi: 10.1016/j.measurement.2025.117098.
R. B. Randall and J. Antoni, “Rolling element bearing diagnostics—A tutorial,” Mech. Syst. Signal Process., vol. 25, no. 2, pp. 485–520, 2011. doi: 10.1016/j.ymssp.2010.07.017.
N. Tandon and A. Choudhury, “A review of vibration and acoustic measurement methods for the detection of defects in rolling element bearings,” Tribol. Int., vol. 32, no. 8, pp. 469–480, 1999. doi: 10.1016/S0301-679X(99)00077-8.
J. Antoni, “Fast computation of the kurtogram for the detection of transient faults,” Mech. Syst. Signal Process., vol. 21, no. 1, pp. 108–124, 2007. doi: 10.1016/j.ymssp.2005.12.002.
A. Amini, M. Entezami, Z. Huang, H. Rowshandel, and M. Papaelias, “Wayside detection of faults in railway axle bearings using time spectral kurtosis analysis on high-frequency acoustic emission signals,” Adv. Mech. Eng., vol. 8, no. 11, 2016. doi: 10.1177/1687814016676000.
G. Vaičiūnas, G. Bureika, and S. Steišūnas, “Rail vehicle axle-box bearing damage detection considering the intensity of heating alteration,” Eksploatacja i Niezawodność – Maintenance and Reliability, vol. 22, no. 4, pp. 724–729, 2020. doi: 10.17531/ein.2020.4.16.
Y. Bai, H. Xue, and J. Chen, “Train Axlebox Bearing Fault Diagnosis Based on MSC–SGMD,” Sensors, vol. 24, no. 1, art. 254, 2024. doi: 10.3390/s24010254.
Z. Wang, Z. Zheng, D. Song, and X. Xu, “A High-Speed Train Axle Box Bearing Fault Diagnosis Method Based on Dimension Reduction Fusion and the Optimal Bandpass Filtering Demodulation Spectrum of Multi-Dimensional Signals,” Machines, vol. 12, no. 8, art. 571, 2024. doi: 10.3390/machines12080571.
Z. Liu, L. Zhang, Q. Xiao, H. Huang, and G. Xiong, “Performance Degradation Assessment of Railway Axle Box Bearing Based on Combination of Denoising Features and Time Series Information,” Sensors, vol. 23, no. 13, art. 5910, 2023. doi: 10.3390/s23135910.
Case Western Reserve University, “Bearing Data Center,” Case School of Engineering, online data repository. Available: https://engineering.case.edu/bearingdatacenter (accessed Oct. 2026).
Universität Paderborn, “Bearing DataCenter: Data Sets and Download,” online data repository. Available: https://mb.uni-paderborn.de/kat/forschung/bearing-datacenter/data-sets-and-download (accessed Oct. 2026).
C. Lessmeier, J. K. Kimotho, D. Zimmer, and W. Sextro, “Condition Monitoring of Bearing Damage in Electromechanical Drive Systems by Using Motor Current Signals of Electric Motors: A Benchmark Data Set for Data-Driven Classification,” PHM Society European Conf., vol. 3, no. 1, 2016. doi: 10.36001/phme.2016.v3i1.1577.
