Smart Structures and Systems

Techno-Press (테크노프레스)
권호 표지
DOI QR코드

DOI QR Code

Online railway wheel defect detection under varying running-speed conditions by multi-kernel relevance vector machine

  • Wei, Yuan-Hao (Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University) ;
  • Wang, You-Wu (Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University) ;
  • Ni, Yi-Qing (Department of Civil and Environmental Engineering, The Hong Kong Polytechnic University)
  • Received : 2022.06.28
  • Accepted : 2022.07.10
  • Published : 2022.09.25
⟨ Previous Next ⟩

Abstract

The degradation of wheel tread may result in serious hazards in the railway operation system. Therefore, timely wheel defect diagnosis of in-service trains to avoid tragic events is of particular importance. The focus of this study is to develop a novel wheel defect detection approach based on the relevance vector machine (RVM) which enables online detection of potentially defective wheels with trackside monitoring data acquired under different running-speed conditions. With the dynamic strain responses collected by a trackside monitoring system, the cumulative Fourier amplitudes (CFA) characterizing the effect of individual wheels are extracted to formulate multiple probabilistic regression models (MPRMs) in terms of multi-kernel RVM, which accommodate both variables of vibration frequency and running speed. Compared with the general single-kernel RVM-based model, the proposed multi-kernel MPRM approach bears better local and global representation ability and generalization performance, which are prerequisite for reliable wheel defect detection by means of data acquired under different running-speed conditions. After formulating the MPRMs, we adopt a Bayesian null hypothesis indicator for wheel defect identification and quantification, and the proposed method is demonstrated by utilizing real-world monitoring data acquired by an FBG-based trackside monitoring system deployed on a high-speed trial railway. The results testify the validity of the proposed method for wheel defect detection under different running-speed conditions.

Keywords

Acknowledgement

The work described in this paper is supported by a grant from the Research Grants Council of the Hong Kong Special Administrative Region (SAR), China (Grant No. PolyU 152014/18E), and a grant from the Hong Kong, Macao, Taiwan Science and Technology Innovation Cooperation Key Project of Sichuan Province, China (Grant No. 2020YFH0178). The authors would also like to appreciate the funding support by the Innovation and Technology Commission of the Hong Kong SAR Government to the Hong Kong Branch of National Rail Transit Electrification and Automation Engineering Technology Research Center (Grant No. K-BBY1).

References

  1. Aitkin, M. (1991), "Posterior Bayes factors", J. Royal Statist. Soc.: Series B (Methodological), 53(1), 111-128. https://doi.org/10.1111/j.2517-6161.1991.tb01812.x
  2. Asplund, M., Famurewa, S. and Rantatalo, M. (2014), "Condition monitoring and e-maintenance solution of railway wheels", J. Quality Maint. Eng., 20(3), 216-232. https://doi.org/10.1108/JQME-05-2014-0027
  3. Barke, D.W. and Chiu, W.K. (2005), "A review of the effects of out-of-round wheels on track and vehicle components", Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 219(3), 151-175. https://doi.org/10.1243/095440905X8853
  4. Belotti, V., Crenna, F., Michelini, R.C. and Rossi, G.B. (2006), "Wheel-flat diagnostic tool via wavelet transform", Mech. Syst. Signal Process., 20(8), 1953-1966. https://doi.org/10.1016/j.ymssp.2005.12.012
  5. Ben-Hur, A., Ong, C.S., Sonnenburg, S., Scholkopf, B. and Ratsch, G. (2008), "Support vector machines and kernels for computational biology", PLoS Computat. Biol., 4(10), e1000173. https://doi.org/10.1371/journal.pcbi.1000173
  6. Bollas, K., Papasalouros, D., Kourousis, D. and Anastasopoulos, A. (2013), "Acoustic emission monitoring of wheel sets on moving trains", Constr. Build. Mater., 48, 1266-1272. https://doi.org/10.1016/j.conbuildmat.2013.02.013
  7. Dukkipati, R.V. and Dong, R. (1999), "Impact loads due to wheel flats and shells", Vehicle Syst. Dyn., 31(1), 1-22. https://doi.org/10.1076/vesd.31.1.1.2097
  8. Filograno, M.L., Guillen, P.C., Rodriguez-Barrios, A., Martin- Lopez, S., Rodriguez-Plaza, M., Andres-Alguacil, A. and Gonzalez-Herraez, M. (2011), "Real-time monitoring of railway traffic using fiber Bragg grating sensors", IEEE Sensors J., 12(1), 85-92. https://doi.org/10.1109/JSEN.2011.2135848
  9. Filograno, M.L., Corredera, P., Rodriguez-Plaza, M., Andres- Alguacil, A. and Gonzalez-Herraez, M. (2013), "Wheel flat detection in high-speed railway systems using fiber Bragg gratings", IEEE Sensors J., 13(12), 4808-4816. https://doi.org/10.1109/JSEN.2013.2274008
  10. Flyer, N. and Wright, G.B. (2009), "A radial basis function method for the shallow water equations on a sphere", Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences, 465(2106), 1949-1976. https://doi.org/10.1098/rspa.2009.0033
  11. Flyer, N., Barnett, G.A. and Wicker, L.J. (2016), "Enhancing finite differences with radial basis functions: experiments on the Navier-Stokes equations", J. Computat. Phys., 316, 39-62. https://doi.org/10.1016/j.jcp.2016.02.078
  12. Hyndman, R.J. and Koehler, A.B. (2006), "Another look at measures of forecast accuracy", Int. J. Forecast., 22(4), 679-688. https://doi.org/10.1016/j.ijforecast.2006.03.001
  13. Jamshidi, A., Roohi, S.F., Nunez, A., Babuska, R., De Schutter, B., Dollevoet, R. and Li, Z. (2016), "Probabilistic defect-based risk assessment approach for rail failures in railway infrastructure", IFAC-PapersOnLine, 49(3), 73-77. https://doi.org/10.1016/j.ifacol.2016.07.013
  14. Jin, X., Wu, L., Fang, J., Zhong, S. and Ling, L. (2012), "An investigation into the mechanism of the polygonal wear of metro train wheels and its effect on the dynamic behaviour of a wheel/rail system", Vehicle Syst. Dyn., 50(12), 1817-1834. https://doi.org/10.1080/00423114.2012.695022
  15. Johansson, A. and Nielsen, J.C. (2003), "Out-of-round railway wheels-wheel-rail contact forces and track response derived from field tests and numerical simulations", Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 217(2), 135-146. https://doi.org/10.1243/095440903765762878
  16. Kass, R.E. and Raftery, A.E. (1995), "Bayes factors", In: J. Am. Statist. Assoc., 90(430), 773-795. https://doi.org/10.2307/2291091
  17. Kouroussis, G., Connolly, D.P. and Verlinden, O. (2014), "Railway-induced ground vibrations-a review of vehicle effects", Int. J. Rail Transport., 2(2), 69-110. https://doi.org/10.1080/23248378.2014.897791
  18. Krummenacher, G., Ong, C.S., Koller, S., Kobayashi, S. and Buhmann, J.M. (2017), "Wheel defect detection with machine learning", IEEE Transact. Intell. Transport. Syst., 19(4), 1176-1187. https://doi.org/10.1109/TITS.2017.2720721
  19. Lipowsky, H., Staudacher, S., Bauer, M. and Schmidt, K.J. (2010), "Application of Bayesian forecasting to change detection and prognosis of gas turbine performance", J. Eng. Gas Turbines Power, 132(3). https://doi.org/10.1115/1.3159367
  20. Liu, X.Z. and Ni, Y.Q. (2018), "Wheel tread defect detection for high-speed trains using FBG-based online monitoring techniques", Smart Struct. Syst., Int. J., 21(5), 687-694. https://doi.org/10.12989/sss.2018.21.5.687
  21. Liu, X.Z., Ni, Y.Q. and Zhou, L. (2018), "Condition-based maintenance of high-speed railway vehicle wheels through trackside monitoring", Proceedings of the Second International Workshop on Structural Health Monitoring for Railway System, Qingdao, China, October.
  22. Liu, X.Z., Xu, C. and Ni, Y.Q. (2019), "Wayside detection of wheel minor defects in high-speed trains by a Bayesian blind source separation method", Sensors, 19(18), 3981. https://doi.org/10.3390/s19183981
  23. Marin, J.M. and Robert, C. (2007), Bayesian Core: A Practical Approach to Computational Bayesian Statistics, Springer, New York, NY, USA.
  24. Milkovic, D., Simic, G., Jakovljevic, Z., Tanaskovic, J. and Lucanin, V. (2013), "Wayside system for wheel-rail contact forces measurements", Measurement, 46(9), 3308-3318. https://doi.org/10.1016/j.measurement.2013.06.017
  25. Morys, B. (1999), "Enlargement of out-of-round wheel profiles on high speed trains", J. Sound Vib., 227(5), 965-978. https://doi.org/10.1006/jsvi.1999.2055
  26. Ni, Y.Q. and Zhang, Q.H. (2020), "A Bayesian machine learning approach for online detection of railway wheel defects using track-side monitoring", Struct. Health Monitor., 20(4), 1536-1550. https://doi.org/10.1177/1475921720921772
  27. Pau, M. (2005), "Ultrasonic waves for effective assessment of wheel-rail contact anomalies", Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 219(2), 79-90. https://doi.org/10.1243/095440905X8808
  28. Petersson, M. (2000), "Noise-related roughness of railway wheel treads-full-scale testing of brake blocks", Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 214(2), 63-77. https://doi.org/10.1243/0954409001531342
  29. Pohl, R., Erhard, A., Montag, H.J., Thomas, H.M. and Wustenberg, H. (2004), "NDT techniques for railroad wheel and gauge corner inspection", NDT & e Int., 37(2), 89-94. https://doi.org/10.1016/j.ndteint.2003.06.001
  30. Pontius, R.G., Thontteh, O. and Chen, H. (2008), "Components of information for multiple resolution comparison between maps that share a real variable", Environ. Ecol. Statist., 15(2), 111-142. https://doi.org/10.1007/s10651-007-0043-y
  31. Stratman, B., Liu, Y. and Mahadevan, S. (2007), "Structural health monitoring of railroad wheels using wheel impact load detectors", J. Fail. Anal. Prevent., 7(3), 218-225. https://doi.org/10.1007/s11668-007-9043-3
  32. Tipping, M.E. (2001), "Sparse Bayesian learning and the relevance vector machine", J. Mach. Learn. Res., 1(Jun), 211-244. https://doi.org/10.1162/15324430152748236
  33. Uzzal, R.U.A., Ahmed, W. and Rakheja, S. (2008), "Dynamic analysis of railway vehicle-track interactions due to wheel flat with a pitch-plane vehicle model", J. Mech. Eng., 39(2), 86-94. https://doi.org/10.3329/jme.v39i2.1851
  34. Wang, Y.W., Ni, Y.Q. and Wang, X. (2020), "Real-time defect detection of high-speed train wheels by using Bayesian forecasting and dynamic model", Mech. Syst. Signal Process., 139, 106654. https://doi.org/10.1016/j.ymssp.2020.106654
  35. Wang, S.M., Jiang, G.F., Ni, Y.Q., Lu, Y., Lin, G.B., Pan, H.L., Xu, J.Q. and Hao, S. (2022), "Multiple damage detection of maglev rail joints using time-frequency spectrogram and convolutional neural network", Smart Struct. Syst., Int. J., 29(4), 625-640. https://doi.org/10.12989/sss.2022.29.4.625
  36. Wei, C., Xin, Q., Chung, W.H., Liu, S.Y., Tam, H.Y. and Ho, S.L. (2011), "Real-time train wheel condition monitoring by fiber Bragg grating sensors", Int. J. Distrib. Sensor Networks, 8(1), 409048. https://doi.org/10.1155/2012/409048
  37. Wei, B., Xie, N. and Hu, A. (2018), "Optimal solution for novel grey polynomial prediction model", Appl. Mathe. Modell., 62, 717-727. https://doi.org/10.1016/j.apm.2018.06.035
  38. Willmott, C.J. and Matsuura, K. (2006), "On the use of dimensioned measures of error to evaluate the performance of spatial interpolators", Int. J. Geograph. Inform. Sci., 20(1), 89-102. https://doi.org/10.1080/13658810500286976
  39. Wong, S.M., Hon, Y.C. and Golberg, M.A. (2002), "Compactly supported radial basis functions for shallow water equations", Appl. Mathe. Computat., 127(1), 79-101. https://doi.org/10.1016/S0096-3003(01)00006-6
  40. Wu, X. and Chi, M. (2016), "Study on stress states of a wheelset axle due to a defective wheel", J. Mech. Sci. Technol.gy, 30(11), 4845-4857. https://doi.org/10.1007/s12206-016-1003-y
  41. Wu, T.X. and Thompson, D.J. (2002), "A hybrid model for the noise generation due to railway wheel flats", J. Sound Vib., 251(1), 115-139. https://doi.org/10.1006/jsvi.2001.3980
  42. Wu, Y., Du, X., Zhang, H.J., Wen, Z.F. and Jin, X.S. (2017), "Experimental analysis of the mechanism of high-order polygonal wear of wheels of a high-speed train", J. Zhejiang Univ.-Sci. A, 18(8), 579-592. https://doi.org/10.1631/jzus.A1600741
  43. Zhang, Q. (2020), "Sparse Bayesian learning approach for damage detection in a population of nominally identical structures", Ph.D. Dissertation; The Hong Kong Polytechnic University, Hong Kong.
  44. Zhang, L.H., Wang, Y.W., Ni, Y.Q. and Lai, S.K. (2018), "Online condition assessment of high-speed trains based on Bayesian forecasting approach and time series analysis", Smart Struct. Syst., Int. J., 21(5), 705-713. https://doi.org/10.12989/sss.2018.21.5.705