Structural Monitoring and Maintenance

  • 제8권2호
  • /
  • Pages.151-166
  • /
  • 2021
  • /
  • 2288-6605(pISSN)
  • /
  • 2288-6613(eISSN)
테크노프레스 (Techno-Press)
권호 표지
DOI QR코드

DOI QR Code

Machine learning aided rail corrugation monitoring for railway track maintenance

  • 투고 : 2020.09.11
  • 심사 : 2021.01.21
  • 발행 : 2021.06.25
⟨ 이전 논문 다음 논문 ⟩

초록

Urban rail transit is a critical infrastructure system that supports urban economic and social development. It has a significant mass transportation capacity while enables environmental benefits. Public transport is a way to resolve large-scale urban road traffic problems and contributes towards sustainable development. However, with the operations of railway vehicles on curves, unbalanced and undulated wears often appear on rails, especially on the low rail. This rail surface defect, so-called 'rail corrugation', directly affects the service life of rolling stocks and track components. The high-frequency vibrations caused by train-track interaction over rail corrugations also impair passenger ride comfort and generate excessive noises. In severe cases, the defects may even endanger the safe passage of a railway vehicle. In practice, rail corrugation has brought huge challenges to the reliable operations and maintenance of railway networks. With the continuous expansion of railway lines and the increasing traffic demands, any existing rail corrugation test method is not enough to meet the actual needs of track maintainers to promptly identify and mitigate rail surface defects. Therefore, this investigation aims to establish a new technique to prognose and classify rail corrugations efficiently and effectively. This study adopts D-track dynamic simulation package to obtain over thousands of vibration data in the form of axle box accelerations from train-track interactions under different conditions. Neural network models have been developed to recognize the rail corrugations and then classify their severity to aid the planning and prioritization of rail track maintenance activities. The models have been trained and tested using the vibration data, achieving the accuracy of over 90%. The optimal model has then been highlighted. The investigation has demonstrated the potential of the neural network to detect and classify rail corrugations, which can be used practically for curved track condition monitoring and maintenance planning.

키워드

과제정보

Financial support from European Commission is gratefully acknowledged for H2020-MSCA-RISE Project No. 691135 "RISEN: Rail Infrastructure Systems Engineering Network," which enables a global research network that tackles the grand challenge in railway infrastructure resilience and advanced sensing under extreme events (www.risen2rail.eu).

참고문헌

  1. Ajmal, P.C. and Mohammed, A. (2018), "Finite element analysis based fatigue life evaluation approach for railway bridges: a study in Indian scenario", Struct. Monitor. Maint., Int. J., 5(4), 429-443. https://doi.org/10.12989/smm.2018.5.4.429
  2. Cai, Z. (1994), "Modelling of rail track dynamics and wheel/rail interaction."
  3. Cao, B.Y., Ding, Y.L., Zhao, H.W. and Song, Y.S. (2016), "Damage identification for high-speed railway truss arch bridge using fuzzy clustering analysis", Struct. Monitor. Maint., Int. J., 3(4), 315-333. https://doi.org/10.12989/smm.2016.3.4.315
  4. Chen, G.X., Zhou, Z.R., Ouyang, H.J., Jin, X.S., Zhu, M.H. and Liu, Q.Y. (2010), "A finite element study on rail corrugation based on saturated creep force-induced self-excited vibration of a wheelset-track system", J. Sound Vib., 329(22), 4643-4655. https://doi.org/10.1016/j.jsv.2010.05.011
  5. Clark, R.A., Scott, G.A. and Poole, W. (1988), "Short wave corrugations-an explanation based on stick-slip vibrations", Applied Mechanics Rail Transportation Symposium, Vol. 96, pp. 141-148.
  6. CSDN (2019), "Introduction to Artificial Neural Networks", Retrieved 1 July, 2020, from https://blog.csdn.net/htrdchh/article/details/87903720.
  7. Grassie, S.L. and Kalousek, J. (1993), "Rail corrugation: characteristics, causes and treatments", Proceedings of the Institution of Mechanical Engineers, Part F: Journal of Rail and Rapid Transit, 207(1), 57-68. https://doi.org/10.1243/PIME_PROC_1993_207_227_02
  8. Iwnick, S. (1998), "Manchester benchmarks for rail vehicle simulation", Vehicle Syst. Dyn., 30(3-4), 295-313. https://doi.org/10.1080/00423119808969454
  9. Jain, A.K., Mao, J. and Mohiuddin, K.M. (1996), "Artificial neural networks: A tutorial", Computer, 29(3), 31-44. https://doi.org/10.1109/2.485891
  10. Kaewunruen, S. (2014), "Monitoring in-service performance of fibre-reinforced foamed urethane material as sleepers/bearers in railway urban turnout systems", Struct. Monitor. Maint., Int. J., 1(1), 131-157. https://doi.org/10.12989/smm.2014.1.1.131
  11. Kaewunruen, S. (2018), "Monitoring of rail corrugation growth on sharp curves for track maintenance prioritisation", Int. J. Acoust. Vib., 23, 35-43.
  12. Kaewunruen, S. and Chiengson, C. (2018), "Railway track inspection and maintenance priorities due to dynamic coupling effects of dipped rails and differential track settlements", Eng. Fail. Anal., 93, 157-171. https://doi.org/10.1016/j.engfailanal.2018.07.009
  13. Kaewunruen, S., Osman, M.H.B. and Rungskunroch, P. (2019), "The total track inspection", Front. Built Environ., 4, 84. doi: 10.3389/fbuil.2018.00084
  14. Kaewunruen, S., Sresakoolchai, J. and Thamba, A. (2021), "Machine learning-aided identification of train weights from railway sleeper vibration", Insight-Non-Destructive Test. Condition Monitor., 63(3), 151-159. https://doi.org/10.1784/insi.2021.63.3.151
  15. Karsoliya, S. (2012), "Approximating number of hidden layer neurons in multiple hidden layer BPNN architecture", Int. J. Eng. Trends Technol., 3(6), 714-717.
  16. Leong, J. (2007), "Development of a limit state design methodology for railway track", Queensland University of Technology.
  17. Li, H.F. (2014), "Research on the Wave Wear Detection System of Metro Track", Master; Southwest Jiaotong University.
  18. Liu, L. (2018), "Research on rail corrugation detection method based on vehicle axle box vibration acceleration", Master; Southwest Jiaotong University.
  19. Luo, L.Z., Wu, W.G. and Chai, X. (2006), Control of Track Smoothness of Wheel-Rail System, Beijing: China Railway Press.
  20. Matsumoto, A., Sato, Y., Ono, H., Tanimoto, M., Oka, Y. and Miyauchi, E. (2002), "Formation mechanism and countermeasures of rail corrugation on curved track", Wear, 253(1-2), 178-184. https://doi.org/10.1016/S0043-1648(02)00097-2
  21. de Melo, A.L.O., Kaewunruen, S., Papaelias, M., Bernucci, L.L.B. and Motta, R. (2020), "Methods to Monitor and Evaluate the Deterioration of Track and Its Components in a Railway In-Service: A Systemic Review", Front. Built Environ., 6, 118. https://doi.org/10.3389/fbuil.2020.00118
  22. Ngamkhanong, C., Kaewunruen, S. and Baniotopoulos, C. (2017), "A review on modelling and monitoring of railway ballast", Struct. Monitor. Maint., Int. J., 4(3), 195-220. https://doi.org/10.12989/smm.2017.4.3.195
  23. Oscarsson, J. and Dahlberg, T. (1998), "Dynamic train/track/ballast interaction-computer models and full-scale experiments", Vehicle Syst. Dyn., 29(S1), 73-84. https://doi.org/10.1080/00423119808969553
  24. Remennikov, A.M. and Kaewunruen, S. (2008), "A review of loading conditions for railway track structures due to train and track vertical interaction", Structural Control and Health Monitoring: The Official Journal of the International Association for Structural Control and Monitoring and of the European Association for the Control of Structures, 15(2), 207-234. https://doi.org/10.1002/stc.227
  25. Steffens, D.M. (2005), "Identification and development of a model of railway track dynamic behaviour", Queensland University of Technology.
  26. Suda, Y. (1991), "Effects of vibration system and rolling conditions on the development of corrugations", Wear, 144(1-2), 227-242. https://doi.org/10.1016/0043-1648(91)90017-O
  27. Tigdemir, M. (2014), "Re-evaluation of the AASHTO-flexible pavement design equation with neural network modeling", PloS one, 9(11), e113226. https://doi.org/10.1371/journal.pone.0113226
  28. Vadillo, E.G., Tarrago, J., Zubiaurre, G.G. and Duque, C.A. (1998), "Effect of sleeper distance on rail corrugation", Wear, 217(1), 140-145. https://doi.org/10.1016/S0043-1648(97)00239-1
  29. Xia, Y.X., Ni, Y.Q. and Zhang, C. (2014), "Evaluation of torsional response of a long-span suspension bridge under railway traffic and typhoons based on SHM data", Struct. Monitor. Maint., Int. J., 1(4), 371-392. https://doi.org/10.12989/sss.2014.14.5.785
  30. Xu, Y.L. and Dai, Y.H. (2007), Rail Transit Public Affairs Management, Shanghai: Tongji University Press, pp. 25-27.
  31. Yzawa, E. and Takeshita, K. (2002), "Development of measurement device of track irregularity using inertial mid-chord offset method", Quarterly Report of RTRI, 43(3), 125-130. https://doi.org/10.2219/rtriqr.43.125
  32. Zhang, W. (2007), "Research on short-wave track irregularity recognition method based on axle box spectrum", Master; Beijing Jiaotong University.
  33. Zhang, Q., Gao, Y., Zhang, H.X., Xu, F. and Li, F. (2018), "Risk identification, assessment and monitoring design of high cutting loess slope in heavy haul railway", Struct. Monitor. Maint., Int. J., 5(1), 67-78. https://doi.org/10.12989/smm.2018.5.1.067