The Recent Applications of Machine Learning in Rail Track Maintenance: A Survey | SpringerLink
Skip to main content
Springer Nature Link
Log in

The Recent Applications of Machine Learning in Rail Track Maintenance: A Survey

  • Conference paper
  • First Online:
Reliability, Safety, and Security of Railway Systems. Modelling, Analysis, Verification, and Certification (RSSRail 2019)

Part of the book series: Lecture Notes in Computer Science ((LNPSE,volume 11495))

Abstract

Railway systems play a vital role in the world’s economy and movement of goods and people. Rail tracks are one of the most critical components needed for the uninterrupted operation of railway systems. However, environmental conditions or mechanical forces can accelerate the degradation process of rail tracks. Any fault in rail tracks can incur enormous costs or even results in disastrous incidents such as train derailment. Over the past few years, the research community has adopted the use of machine learning (ML) algorithms for diagnosis and prognosis of rail defects in order to help the railway industry to carry out timely responses to failures. In this paper, we review the existing literature on the state-of-the-art machine learning-based approaches used in different rail track maintenance tasks. As one of our main contributions, we also provide a taxonomy to classify the existing literature based on types of methods and types of data. Moreover, we present the shortcomings of current techniques and discuss what research community and rail industry can do to address these issues. Finally, we conclude with a list of recommended directions for future research in the field.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 6634
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 8293
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

References

  1. Sharma, S., Cui, Y., He, Q., Mohammadi, R., Li, Z.: Data-driven optimization of railway maintenance for track geometry. Trans. Res. Part C: Emerg. Technol. 90, 34–58 (2018)

    Article  Google Scholar 

  2. Zhuang, L., Wang, L., Zhang, Z., Tsui, K.L.: Automated vision inspection of rail surface cracks: a double-layer data-driven framework. Transp. Res. Part C Emerg. Technol. 92, 258–277 (2018). https://doi.org/10.1016/j.trc.2018.05.007

    Article  Google Scholar 

  3. Liu, X., Saat, M., Barkan, C.: Analysis of causes of major train derailment and their effect on accident rates. Transp. Res. Rec. J. Transp. Res. Board. 2289, 154–163 (2012). https://doi.org/10.3141/2289-20

    Article  Google Scholar 

  4. Lasisi, A., Attoh-Okine, N.: Principal components analysis and track quality index: a machine learning approach. Transp. Res. Part C Emerg. Technol. 91, 230–248 (2018). https://doi.org/10.1016/j.trc.2018.04.001

    Article  Google Scholar 

  5. Durazo-Cardenas, I., et al.: An autonomous system for maintenance scheduling data-rich complex infrastructure: fusing the railways’ condition, planning and cost. Transp. Res. Part C Emerg. Technol. 89, 234–253 (2018). https://doi.org/10.1016/j.trc.2018.02.010

    Article  Google Scholar 

  6. Gibert, X., Patel, V.M., Chellappa, R.: Deep multitask learning for railway track inspection. IEEE Trans. Intell. Transp. Syst. 18, 153–164 (2017). https://doi.org/10.1109/TITS.2016.2568758

    Article  Google Scholar 

  7. Zoeteman, A., Dollevoet, R., Li, Z.: Dutch research results on wheel/rail interface management: 2001–2013 and beyond. Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit. 228, 642–651 (2014). https://doi.org/10.1177/0954409714524379

    Article  Google Scholar 

  8. Zhao, R., Yan, R., Chen, Z., Mao, K., Wang, P., Gao, R.X.: Deep learning and its applications to machine health monitoring: a survey, 14, 1–14 (2016). https://arxiv.org/abs/1612.07640

  9. Thaduri, A., Galar, D., Kumar, U.: Railway assets: a potential domain for big data analytics. Proc. Comput. Sci. 53, 457–467 (2015). https://doi.org/10.1016/j.procs.2015.07.323

    Article  Google Scholar 

  10. Li, Q., Zhong, Z., Liang, Z., Liang, Y.: Rail inspection meets big data: methods and trends (2015)

    Google Scholar 

  11. Stetco, A., et al.: Machine learning methods for wind turbine condition monitoring: a review. Renew. Energy. 133, 620–635 (2018). https://doi.org/10.1016/j.renene.2018.10.047

    Article  Google Scholar 

  12. Widodo, A., Yang, B.S.: Support vector machine in machine condition monitoring and fault diagnosis. Mech. Syst. Signal Process. 21, 2560–2574 (2007). https://doi.org/10.1016/j.ymssp.2006.12.007

    Article  Google Scholar 

  13. Sun, W., Chen, J., Li, J.: Decision tree and PCA-based fault diagnosis of rotating machinery. Mech. Syst. Signal Process. 21, 1300–1317 (2007). https://doi.org/10.1016/j.ymssp.2006.06.010

    Article  Google Scholar 

  14. Cerrada, M., Zurita, G., Cabrera, D., Sánchez, R.V., Artés, M., Li, C.: Fault diagnosis in spur gears based on genetic algorithm and random forest. Mech. Syst. Signal Process. 70–71, 87–103 (2016). https://doi.org/10.1016/j.ymssp.2015.08.030

    Article  Google Scholar 

  15. Lecun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015). https://doi.org/10.1038/nature14539

    Article  Google Scholar 

  16. LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1, 541–551 (1989)

    Article  Google Scholar 

  17. Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8689, pp. 818–833. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-10590-1_53

    Chapter  Google Scholar 

  18. Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115, 211–252 (2015). https://doi.org/10.1007/s11263-015-0816-y

    Article  MathSciNet  Google Scholar 

  19. Kim, S., Kim, W., Noh, Y.K., Park, F.C.: Transfer learning for automated optical inspection. In: International Joint Conference on Neural Networks (IJCNN), May 2017, pp. 2517–2524 (2017). https://doi.org/10.1109/ijcnn.2017.7966162

  20. Karpathy, A.: What I learned from competing against a convnet on imagenet (2014). http://karpathy.github.io/2014/09/02/what-i-learned-from-competing-against-a-convnet-on-imagenet

  21. Hu, J., Shen, L., Albanie, S., Sun, G., Wu, E.: Squeeze-and-excitation networks, pp. 1–14 (2017). https://doi.org/10.1109/CVPR.2018.00745

  22. Lipton, Z.C., Kale, D.C., Elkan, C., Wetzel, R.: Learning to Diagnose with LSTM Recurrent Neural Networks. 1–18 (2015). https://arxiv.org/abs/1511.03677

  23. Lipton, Z.C., Berkowitz, J., Elkan, C.: A critical review of recurrent neural networks for sequence learning, pp. 1–38 (2015). https://arxiv.org/abs/1506.00019

  24. Hochreiter, S., Urgen Schmidhuber, J.: Ltsm. Neural Comput. 9, 1735–1780 (1997). https://doi.org/10.1162/neco.1997.9.8.1735

    Article  Google Scholar 

  25. Zhang, W., et al.: LSTM-based analysis of industrial iot equipment. IEEE Access. 6, 23551–23560 (2018). https://doi.org/10.1109/ACCESS.2018.2825538

    Article  Google Scholar 

  26. Ghofrani, F., He, Q., Goverde, R.M.P., Liu, X.: Recent applications of big data analytics in railway transportation systems: a survey. Transp. Res. Part C Emerg. Technol. 90, 226–246 (2018). https://doi.org/10.1016/j.trc.2018.03.010

    Article  Google Scholar 

  27. Jamshidi, A., et al.: A decision support approach for condition-based maintenance of rails based on big data analysis ☆. Transp. Res. Part C 95, 185–206 (2018). https://doi.org/10.1016/j.trc.2018.07.007

    Article  Google Scholar 

  28. Soleimanmeigouni, I., Ahmadi, A., Kumar, U.: Track geometry degradation and maintenance modelling: a review. Proc. Inst. Mech. Eng. Part F J. Rail Rapid Transit. 232, 73–102 (2018)

    Article  Google Scholar 

  29. Alahakoon, S., Sun, Y.Q., Spiryagin, M., Cole, C.: Rail flaw detection technologies for safer, reliable transportation: a review. J. Dyn. Syst. Meas. Control 140, 020801 (2017). https://doi.org/10.1115/1.4037295

    Article  Google Scholar 

  30. Papaelias, M.P., Roberts, C., Davis, C.L.: A review on non-destructive evaluation of rails: state-of-the-art and future development. Proc. Inst. Mech. Eng. 222, 367–384 (2008). https://doi.org/10.1243/09544097JRRT209

    Article  Google Scholar 

  31. Jamshidi, A., et al.: A big data analysis approach for rail failure risk assessment. Risk Anal. 37, 1495–1507 (2017). https://doi.org/10.1111/risa.12836

    Article  Google Scholar 

  32. Santur, Y., Karaköse, M., Akın, E.: Condition monitoring approach using 3D-modelling of railway tracks with laser cameras (2017)

    Google Scholar 

  33. Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Pereira, F., Burges, C.J.C., Bottou, L., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems, vol. 25, pp. 1097–1105. Curran Associates, Inc. (2012)

    Google Scholar 

  34. Faghih-Roohi, S., Hajizadeh, S., Nunez, A., Babuska, R., De Schutter, B.: Deep convolutional neural networks for detection of rail surface defects. In: Proceedings International Joint Conference on Neural Networks (IJCNN), October 2016, pp. 2584–2589 (2016). https://doi.org/10.1109/ijcnn.2016.7727522

  35. Xia, Y., Xie, F., Jiang, Z.: Broken railway fastener detection based on adaboost algorithm. In: Proceedings - 2010 International Conference Optoelectronics and Image Processing, ICOIP 2010, vol. 1, pp. 313–316 (2010). https://doi.org/10.1109/icoip.2010.303

  36. Santur, Y., Karakose, M., Akin, E.: Random forest based diagnosis approach for rail fault inspection in railways. In: 2016 National Conference on Electrical, Electronics and Biomedical Engineering (ELECO) (2017)

    Google Scholar 

  37. Gao, S., Szugs, T., Inspection, E., Ahlbrink, R.: Use of combined railway inspection data sources for characterization of rolling contact fatigue (2018)

    Google Scholar 

  38. Sadeghi, J., Askarinejad, H.: Application of neural networks in evaluation of railway track quality condition. J. Mech. Sci. Technol. 26, 113–122 (2012). https://doi.org/10.1007/s12206-011-1016-5

    Article  Google Scholar 

  39. Hu, C., Liu, X.: Modeling track geometry degradation using support vector machine technique (2016)

    Google Scholar 

  40. Famurewa, S.M., Zhang, L., Asplund, M.: Maintenance analytics for railway infrastructure decision support. J. Qual. Maint. Eng. 23, 310–325 (2017). https://doi.org/10.1108/JQME-11-2016-0059

    Article  Google Scholar 

  41. Jiang, Y., Wang, H., Tian, G., Yi, Q., Zhao, J., Zhen, K.: Fast classification for rail defect depths using a hybrid intelligent method. Optik (Stuttg). 180, 455–468 (2019). https://doi.org/10.1016/j.ijleo.2018.11.053

    Article  Google Scholar 

  42. Lee, J.S., Hwang, S.H., Choi, I.Y., Kim, I.K.: Prediction of track deterioration using maintenance data and machine learning schemes. J. Transp. Eng. Part A Syst. 144, 4018045 (2018). https://doi.org/10.1061/JTEPBS.0000173

    Article  Google Scholar 

  43. Hajizadeh, S., Li, Z., Dollevoet, R.P.B.J., Tax, D.M.J.: Evaluating classification performance with only positive and unlabeled samples. In: Fränti, P., Brown, G., Loog, M., Escolano, F., Pelillo, M. (eds.) S+SSPR 2014. LNCS, vol. 8621, pp. 233–242. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-44415-3_24

    Chapter  Google Scholar 

  44. Hajizadeh, S., Núñez, A., Tax, D.M.J.: Semi-supervised rail defect detection from imbalanced image data. IFAC-PapersOnLine. 49, 78–83 (2016). https://doi.org/10.1016/j.ifacol.2016.07.014

    Article  Google Scholar 

  45. Soukup, D., Huber-Mörk, R.: Convolutional neural networks for steel surface defect detection from photometric stereo images. In: Bebis, G., et al. (eds.) ISVC 2014. LNCS, vol. 8887, pp. 668–677. Springer, Cham (2014). https://doi.org/10.1007/978-3-319-14249-4_64

    Chapter  Google Scholar 

  46. Giben, X., Patel, V.M., Chellappa, R.: Material classification and semantic segmentation of railway track images with deep convolutional neural networks. In: Proceedings International Conference Image Processing ICIP, December 2015, pp. 621–625 (2015). https://doi.org/10.1109/icip.2015.7350873

  47. Gibert, X., Patel, V.M., Chellappa, R.: Robust fastener detection for autonomous visual railway track inspection. In: 2015 IEEE Winter Conference on Applications of Computer Vision, pp. 694–701 (2015)

    Google Scholar 

  48. Santur, Y., Karaköse, M., Akin, E.: A new rail inspection method based on deep learning using laser cameras (2017)

    Google Scholar 

  49. Santur, Y., Karakose, M., Akin, E.: An adaptive fault diagnosis approach using pipeline implementation for railway inspection. Turk. J. Electr. Eng. Comput. Sci. 26, 987–998 (2018). https://doi.org/10.3906/elk-1704-214

    Article  Google Scholar 

  50. Rauschmayr, N., Hoechemer, M., Zurkirchen, M., Kenzelmann, S., Gilles, M.: Deep Learning Of Railway Track Faults using GPUs Swiss Federal Railways (SBB) Swiss Center for Electronics and Microtechnology (CSEM) (2018)

    Google Scholar 

  51. Dai, P., Du, X., Wang, S., Gu, Z., Ma, Y.: Rail fastener automatic recognition method in complex background. In: Tenth International Conference Digital Image Processing (ICDIP) 2018, vol. 314, p. 1080625 (2018). https://doi.org/10.1117/12.2503323

  52. Ritika, S., Rao, D.: Data augmentation of railway images for track inspection (2018)

    Google Scholar 

  53. García, V., Sánchez, J.S., Mollineda, R.A.: On the effectiveness of preprocessing methods when dealing with different levels of class imbalance. Knowl.-Based Syst. 25, 13–21 (2012). https://doi.org/10.1016/j.knosys.2011.06.013

    Article  Google Scholar 

  54. He, H., Garcia, E.A.: Learning from imbalanced data. IEEE Trans. Knowl. Data Eng. 21, 1263–1284 (2009). https://doi.org/10.1109/TKDE.2008.239

    Article  Google Scholar 

  55. Nectoux, P., et al.: PRONOSTIA : an experimental platform for bearings accelerated degradation tests. In: IEEE International Conference on Prognostics and Health Management, pp. 1–8 (2012)

    Google Scholar 

  56. Ribeiro, M.T., Guestrin, C.: Why should I trust you ? Explaining the predictions of any classifier (2016)

    Google Scholar 

  57. Jamshidi, A., Nunez, A., Li, Z., Dollevoet, R.: Maintenance decision indicators for treating squats in railway infrastructures. In: Transportation Research Board 94th Annual Meeting (2015)

    Google Scholar 

  58. Ruijters, E., Stoelinga, M.: Fault tree analysis: a survey of the state-of-the-art in modeling, analysis and tools. Comput. Sci. Rev. 15–16, 29–62 (2015). https://doi.org/10.1016/j.cosrev.2015.03.001

    Article  MathSciNet  MATH  Google Scholar 

  59. Nauta, M., Bucur, D., Stoelinga, M.: LIFT: learning fault trees from observational data. In: McIver, Annabelle, Horvath, Andras (eds.) QEST 2018. LNCS, vol. 11024, pp. 306–322. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-99154-2_19

    Chapter  Google Scholar 

Download references

Acknowledgment

This research is supported by ProRail and the Netherlands Organization for Scientific Research (NWO) under the Sequoia project.

Author information

Authors and Affiliations

  1. Data Science, University of Twente, Enschede, The Netherlands

    Muhammad Chenariyan Nakhaee & Djoerd Hiemstra

  2. Formal Methods and Tools, University of Twente, Enschede, The Netherlands

    Mariëlle Stoelinga

  3. Software Science, Radboud University Nijmegen, Nijmegen, The Netherlands

    Mariëlle Stoelinga

  4. ProRail, Utrecht, The Netherlands

    Martijn van Noort

Authors
  1. Muhammad Chenariyan Nakhaee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Djoerd Hiemstra
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Mariëlle Stoelinga
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Martijn van Noort
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Muhammad Chenariyan Nakhaee .

Editor information

Editors and Affiliations

  1. Laboratoire IFSTTAR/ESTAS, Villeneuve d’Ascq , France

    Simon Collart-Dutilleul

  2. ClearSy, Aix en Provence, France

    Thierry Lecomte

  3. Newcastle University, Newcastle-upon-Tyne, UK

    Alexander Romanovsky

Rights and permissions

Reprints and permissions

Copyright information

© 2019 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chenariyan Nakhaee, M., Hiemstra, D., Stoelinga, M., van Noort, M. (2019). The Recent Applications of Machine Learning in Rail Track Maintenance: A Survey. In: Collart-Dutilleul, S., Lecomte, T., Romanovsky, A. (eds) Reliability, Safety, and Security of Railway Systems. Modelling, Analysis, Verification, and Certification. RSSRail 2019. Lecture Notes in Computer Science(), vol 11495. Springer, Cham. https://doi.org/10.1007/978-3-030-18744-6_6

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-18744-6_6

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-18743-9

  • Online ISBN: 978-3-030-18744-6

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics