Skip to main content
SpringerLink
Log in

Application of neural networks in evaluation of railway track quality condition

  • Published:
Journal of Mechanical Science and Technology Aims and scope Submit manuscript

Abstract

Due to the significant costs and time consumed for track visual inspections, most railway industries rely only on geometry data obtained from automated inspections for the assessments of railway track quality conditions. This is the main limitation of the current practices, which may lead to inappropriate determinations of maintenance and repair schedules. This research attempts to rectify this deficiency by developing a methodology for the establishment of correlations between the track structural conditions and the data obtained from automated inspections. The aim is to provide the possibility of having a rational understanding of the structural defects of track (the causes of track irregularities) without conducting visual inspections. Neural network technique is implemented for this purpose. A vast amount of field data obtained from comprehensive visual and automated inspections of different railways are utilized to develop the neural network models. The results obtained in this research reveals that the neural network technique has a very good capability in establishing correlations between track geometrical defects and track structural problems. The application of the developed models in a number of railway tracks indicates that the proposed methodology is an effective approach in the prediction of track structural defects.

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

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. M. N. S. Hadi, Neural networks applications in concrete structures, The International Journal of Computers and Structures, 81(6) (2003) 373–381.

    Article  Google Scholar 

  2. T. M. S. Elhag and A. H. Boussabaine, Tender price estimation using artificial neural networks, II: Modeling.” Journal of Finan. Mange. Property Constr, 7(1) (2002) 49–64.

    Google Scholar 

  3. T. M. S. Elhag, Cost modeling: Neural networks vs. regression techniques, Int. Conf. on Construction Information Technology (INCITE), Construction Industry Development Board (CIDB), Langkawi, Malaysia (2004).

  4. J. Sadeghi, Development of railway track geometry indexes based on statistical distribution of geometry data, Journal of Transportation Engineering, American Society of Civil Engineers (ASCE), 136(8) (2010) 693–700.

    Article  MathSciNet  Google Scholar 

  5. J. Madejski and J. Grabczyk, Continuous geometry measurement for diagnostics of tracks and switches, Proceedings of the International Conference on Switches, Delft University of Technology, Delft, the Netherlands (2002).

    Google Scholar 

  6. M. Anderson, Strategic planning of track maintenance, Ph.D thesis, Royal Institute of Technology, Department of Infrastructure, Borlänge, Sweden (2002).

    Google Scholar 

  7. International Union of Railways (ORE), Quantitative evaluation of geometric track parameters determining vehicle behavior, Office of Research and Experiments, C152, RP1 (1981).

    Google Scholar 

  8. J. S. Mundrey, Railway track engineering, Tata McGrew-Hill publishing: New Delhi (2003).

    Google Scholar 

  9. J. Sadeghi and H. Askarinejad, Development of improved railway track degradation models, Journal of Structure and Infrastructure Engineering, 3(4) (2008) 1–14.

    Google Scholar 

  10. J. Sadeghi, M. Fathali and N. Boloukian, Development of new Track Geometry Assessment Technique Incorporating Rail cant Factor, Proceedings of the Institution of Mechanical Engineers (UK), Part F Journal of Rail and Rapid Transit, 223(3) (2009) 255–263.

    Article  Google Scholar 

  11. D. R. Uzarski, Development of condition indexes for low volume railroad track, Technical Report No.FM-93/14, USACER (1993).

  12. J. Sadeghi and H. Askarinejad, Investigation on effects of track structural conditions on railway track geometry deviations, Proceedings of the Institution of Mechanical Engineers (UK), Part F: J. Rail and Rapid Transit, 223(4) (2009) 415–425.

    Article  Google Scholar 

  13. International Union of Railways (UIC), Classification of lines for purpose of track maintenance, Third edition, 717R (1989).

  14. American Railway Engineering and Maintenance-of-Way Association (AREMA), Manual for railway engineering, USA (2006).

  15. PBO, Railway Track Superstructure General Technical Specifications, No. 301 Leaflet, Plan and Budget Organization, Iran Technical Affairs and the Office of Standards (2004).

  16. I. Flood and N. Kartam, Neural networks in civil engineering. I: Principles and understanding, J. Computing in Civil Engineering, ASCE, 8(2) (1994) 131–148.

    Article  Google Scholar 

  17. S. Haykin, Neural networks-A comprehensive foundation, Mc-Millan College Publishing Company, New York (1994).

    MATH  Google Scholar 

  18. S. Freitag, M. Beer, W. Graf and M. Kaliske, Lifetime prediction using accelerated test data and neural networks, Computers & Structures, 87(19–20) (2009) 1187–1194.

    Article  Google Scholar 

  19. H. White, Some asymptotic results for learning in single hidden layer feed forward network models, J. Am. Statistical Assn: Theory and methods, 84(408) (1989) 1003–1012.

    Article  MATH  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. School of Railway Engineering, Iran University of Science and Technology, Narmak, 16844, Tehran, Iran

    Javad Sadeghi & Hossein Askarinejad

Authors
  1. Javad Sadeghi
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hossein Askarinejad
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Javad Sadeghi.

Additional information

This paper was recommended for publication in revised form by Associate Editor Tae Hee Lee

Javad Sadeghi received his ME and Ph.D degrees in Civil Engineering from Wollongong University, Australia. Currently he is an associate professor of Civil Engineering at the School of Railway Engineering, Iran University of Science and Technology. He has been awarded more than 1.5 million US dollars research grants from industries since 2005. He has published more than 20 ISI journal papers and 70 conference papers in the field of road and railway infrastructures. He is the author of a book entitled “Principles of analysis and design of ballasted railway track” selected as the best book of the year (in the third national book celebration, Tehran, February 2009). Recently he was the chair of ICRARE 2009, the Second International Conference on Recent Advances in Railway Engineering, held in Tehran.

Hossein Askarinejad received his B.S. in Civil Engineering in 2004. He achieved his M.S. in Civil-Rail Track Engineering at Iran University of Science and Technology (IUST) in 2008. From 2005 till 2009, he was the key research team member in IUST and has received several research awards from Iranian industries and IUST. As a Ph.D candidate, he is currently doing research at centre for railway engineering in Central Queensland University, Australia.

Rights and permissions

Reprints and permissions

About this article

Cite this article

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

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12206-011-1016-5

Keywords

Search

Navigation