Detection of Isolated Track Defects Using Axle Box Acceleration from Multibody Simulation and Recurrent Neural Network

Kritat Plodphai; Thitiwut Petcharat; Songsak Suthasupradit; Rattapoohm Parichatprecha

doi:10.55003/ETH.430103

Authors

Kritat Plodphai School of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Thailand
Thitiwut Petcharat School of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Thailand
Songsak Suthasupradit School of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Thailand
Rattapoohm Parichatprecha School of Engineering, King Mongkut’s Institute of Technology Ladkrabang, Thailand

DOI:

https://doi.org/10.55003/ETH.430103

Keywords:

Recurrent Neural Network (RNN), Rail Squats, Rail Corrugation, Axle Box Acceleration, Multibody Simulation

Abstract

Railway track inspection is typically conducted cyclically, which is slow, budget-intensive, and time-consuming, as it can only be performed during non-service periods when trains are not in operation. Currently, there are emerging concepts and research studies utilizing railway defect detection through acceleration measurements from axle box mounted on service trains, as this approach offers easier implementation, reduced costs, and time efficiency compared to conventional methods. However, the diagnostic process remains challenging due to the high complexity and large volume of data involved. This research presents a method for applying Recurrent Neural Network (RNN) that works with time-series data in diagnosing railway defects by classifying three specific types of isolated defects: squats and corrugation. The training samples for the neural network were derived from axle box acceleration data obtained through multibody simulation analysis that modeled various railway conditions, speeds, and defect characteristics. A total of 360 samples from the multibody model were used for training, validation, and testing. The study results showed that the Recurrent Neural Network (RNN) achieved an average defects classification accuracy of 91.67%. Furthermore, the study findings revealed that the developed RNN model can accurately predict the location and classify defects, with particularly high accuracy in predicting the location and defects caused by long-pitch corrugation. The study concluded that the developed RNN model can efficiently learn and classify defects from axle box acceleration data obtained from multibody simulation. This approach can be applied as a guideline for railway damage diagnosis in future maintenance applications.

References

A. Malekjafarian, E. J. Obrien and F. Golpayegani, “Indirect monitoring of critical transport infrastructure: Data analytics and signal processing,” in Data Analytics for Smart Cities, A. H. Alavi and W. G. Buttlar, Eds., Boca Raton, FL, USA: CRC Press, 2018, ch. 6, pp. 143–157.

A. R. Andrade and P. F. Teixeira, “Unplanned-maintenance needs related to rail track geometry,” Proceedings of the Institution of Civil Engineers - Transport, vol. 167, no. 6, pp. 400–410, 2014, doi: 10.1680/tran.11.00060.

Z. Wei, A. Núñez, Z. Li and R. Dollevoet, “Evaluating Degradation at Railway Crossing Using Axle Box Acceleration Measurements,” sensors, vol. 17, no. 10, 2017, Art. no. 2236, doi: 10.3390/s17102236.

W. Fu, Q. He, Q. Feng, J. Li, F. Zheng and B. Zhang, “Recent Advances in Wayside Railway Wheel Flat Detection Techniques: A Review,” sensors, vol. 23, no. 8, 2023, Art. no. 3916, doi: 10.3390/s23083916.

P. Salvador, V. Naranjo, R. Insa and P. Teixeira, “Axlebox accelerations: Their acquisition and time-frequency characterisation for railway track monitoring purposes,” Measurement, vol. 82, pp. 301–312, 2016, doi: 10.1016/j.measurement.2016.01.012.

A. Malekjafarian, E. J. Obrien, P. Quirke and F. Golpayagani, “Railway Track Loss-of-Stiffness Detection Using Bogie Filtered Displacement Data Measured on a Passing Train,” infrastructures, vol. 6, no. 6, 2021, Art. no. 93, doi: 10.3390/infrastructures6060093.

E. E. Koks, J. Rozenberg, C. Zorn, M. Tariverdi, M. Vousdoukas, S. A. Fraser, J. W. Hall and S. Hallegatte, “A global multi-hazard risk analysis of road and railway infrastructure assets,” Nature Communications, vol. 10, 2019, Art. no. 2677, doi: 10.1038/s41467-019-10442-3.

P. Quirke, E. J. Obrien, C. Bowe, D. Cantero and A. Malekjafarian, “The calibration challenge when inferring longitudinal track profile from the inertial response of an in-service train,” Canadian Journal of Civil Engineering, vol. 49 no.2, pp. 274–288, 2022, doi: 10.1139/cjce-2020-0069.

M. R. Azim and M. Gül, “Damage detection of steel girder railway bridges utilizing operational vibration response,” Structural Control and Health Monitoring, vol. 26, no. 11, 2019, Art. no. 26:e2447, doi: 10.1002/stc.2447.

Z. Li, M. Molodova, X. Zhao and R. Dollevoet, “Squat treatment by way of minimum action based on early detection to reduce life cycle costs,” in 2010 Joint Rail Conference, Urbana, IL, USA, Apr. 27–29, 2010, pp. 305–311, doi: 10.1115/JRC2010-36184.

Z. Li, R. Dollevoet, M. Molodova and X. Zhao, “Squat Growth—Some observations and the validation of numerical predictions,” Wear, vol. 271, no. 1–2, pp. 148–157, 2011, doi: 10.1016/j.wear.2010.10.051.

Z. Li, X. Zhao, C. Esveld, R. Dollevoet and M. Molodova, “An investigation into the causes of squats—correlation analysis and numerical modelling,” Wear, vol. 265, no. 9–10, pp. 1349–1355, 2008, doi: 10.1016/j.wear.2008.02.037.

M. Molodova, L. Zili, A. Núñez and R. Dollevoet, “Automatic Detection of Squats in Railway Infrastructure,” IEEE Transactions on Intelligent Transportation Systems, vol. 15, no. 5, pp. 1980–1990, 2014, doi: 10.1109/TITS.2014.2307955.

L. Zili, M. Molodova, A. Núñez and R. Dollevoet, “Improvements in Axle Box Acceleration Measurements for the Detection of Light Squats in Railway Infrastructure,” IEEE Transactions on Industrial Electronics, vol. 62, no. 7, pp. 4385–4397, 2015, doi: 10.1109/TIE.2015.2389761.

Z. Li, M. Oregui, R. Carroll, S. Li and J. Moraal, “Detection of Bolt Tightness of Fish-Plated Joints Using Axle Box Acceleration,” in First International Conference on Railway Technology: Research, Development and Maintenance, Las Palmas, Spain, Apr. 18–20, 2012, pp. 84, doi: 10.4203/ccp.98.84.

M. Oregui, Z. Li and R. Dollevoet, “Identification of characteristic frequencies of damaged railway tracks using field hammer test measurements,” Mechanical Systems and Signal Processing, vol. 54–55, pp. 224–242, 2015, doi: 10.1016/j.ymssp.2014.08.024.

Z. Popović, L. Lazarević, L. Brajović and M. Vilotijević, “The Importance of Rail Inspections in the Urban Area – Aspect of Head Checking Rail Defects,” Procedia Engineering, vol. 117, pp. 596–608, 2015, doi: 10.1016/j.proeng.2015.08.220.

M. Molodova, Z. Li and R. Dollevoet, “Axle box acceleration: Measurement and simulation for detection of short track defects,” Wear, vol. 271, pp. 349–356, 2010, doi: 10.1016/j.wear.2010.10.003.

S. Suthasupradit, T. Petcharat, K. D. Kim and R. Parichatprecha, “Application of Multibody Dynamics Simulation in Approximation of Rail Vehicle Dynamic Envelope,” Journal of the Korean Society for Railway, vol. 26, no. 12, pp. 843–855, 2023, doi: 10.7782/jksr.2023.26.12.843.

S. Unsiwilai, W. Phusakulkajorn, C. Shen, A. Zoeteman, R. Dollevoet, A. Núñez and Z. Li, “Enhanced vertical railway track quality index with dynamic responses from moving trains,” Heliyon, vol. 10, no. 19, 2024, Art. no. e38670, doi: 10.1016/j.heliyon.2024.e38670.

R. Tang, L. D. Donato, N. Bes̆nović, F. Flammini, R. M. P. Goverde, Z. Lin, R. Liu, T. Tang, V. Vittorini and Z. Wang, “A literature review of Artificial Intelligence applications in railway systems,” Transportation Research Part C: Emerging Technologies, vol. 140, 2022, Art. no. 103679.

A. Jamshidi, S. Hajizadech, Z. Su, M. Naeimi, A. Núñez, R. Dollevoet, B. D. Schutter and Z. Li, “A decision support approach for condition-based maintenance of rails based on big data analysis,” Transportation Research Part C: Emerging Technologies, vol. 95, pp. 185–206, 2018, doi: 10.1016/j.trc.2018.07.007.

A. Malekjafarian, C. A. Sarrabezolles, M. A. Khan and F. Golpayegani, “A Machine-Learning-Based Approach for Railway Track Monitoring Using Acceleration Measured on an In-Service Train,” sensors, vol. 23, no. 17, 2023, Art. no. 7568, doi: 10.3390/s23177568.

S. Bahamon-Blanco, S. Rapp, Y. Zhang, J. Liu and U. Martin, “Recognition of Track Defects through Measured Acceleration Using A Recurrent Neural Network,” International Journal of Computational Methods and Experimental Measurements, vol. 8, no. 3, pp. 270–280, 2020, doi: 10.2495/cmem-v8-n3-270-280.

S. Iwnick, “Manchester Benchmarks for Rail Vehicle Simulation,” Vehicle System Dynamic, vol. 30, no. 3–4, pp. 295–313, 1998, doi: 10.1080/00423119808969454.

A. R. B. Berawi, “Improving Railway Track Maintenance Using Power Spectral Density (PSD),” Ph.D. dissertation, Faculty of Engineering, Univ. Porto, Porto, Portugal, 2013.