Analytical differences between seven prediction models and the description of the rail track deterioration process through these methods

Richard Nagy

Abstract


The quality of the rail track is one of the most important indicators to manage a reliable maintenance system so that plan the costs and the technical interventions. In this study, the track state will be defined by the qualifying numbers of the track, which shows the geometrical condition of a given rail section. More than one million measured data with the car (FMK-004) were processed than analysed and defined by configuring and programming a new regression method. The aim was the perfection of an analytic examination, which describes the differences between models of the track deterioration process, through characterized the correspondences more precisely and better to use in practice. Seven models were built and tested for prediction of the track qualifying numbers. One conventional non-linear regression model based on Vaszary’s model using VBA, four new model using basic predictable equations, one new model using linear regression in VBA and one new model using an artificial neural network in MATLAB. When compare the predictions of models, the result shows that exist some basic models with more accurate predictions than a complex model.

Keywords


rail geometric deterioration, track dimensioning factor, measuring and qualifying numbers, curve fitting, linear and non-linear regression, artificial neural network, visual basic, matlab

Full Text:

PDF

References


Fischer Sz. Comparison of railway track transition curves, Pollack Periodica, Vol. 4, No. 3, 2009, pp. 99−110.

Horvát F. The railway geometry progress from the beginning to nowadays (in Hungarian) Indóház, Vasúti Magazin, Vol. 9, No. 4, 2013, pp. 2−7.

Fischer Sz., Horvát F. Superstructure Stabilization of Ballast Bedded Railway Tracks with Geogrids, Hungarian Journal of Industrial Chemistry, Vol. 39, No. 1, 2011, pp. 101−106.

Šestáková J., Mečár M. Evaluation of track design and track geometry of the track with unconventional structure of railway superstructure, Procedia Engineering, Vol. 111, 2015, pp. 709–716.

Lestoille N., Soize C., Funfschilling C. Stochastic prediction of high-speed train dynamics to long-term evolution of track irregularities, Mechanics Research Communications, Vol. 75, 2016, pp. 29–39.

Vinkó Á. Monitoring and condition assessment of tramway track using in-service vehicle, Pollack Periodica, Vo. 11, No. 3, 2016, pp. 73–82.

Papp H., Liegner N. Investigation of internal forces in the rail due to the interaction of CWR tracks and steel railway bridges with ballasted track superstructure, Pollack Periodica, Vol. 11, No. 2, 2016, pp. 65–74.

Cárdenas-Galloa I., Sarmientoa C. A., Moralesa G. A., Bolivara M. A., Akhavan-Tabatabaeia R. An ensemble classifier to predict track geometry degradation, Reliability Engineering & System Safety, Vol. 161, 2017, pp. 53–60.

Andradea A. R., Teixeirab P. F. Statistical modeling of railway track geometry degradation using Hierarchical Bayesian models, Reliability Engineering & System Safety, Vol. 142, 2015, pp. 169–183.

Lestoille N., Soize C., Funfschilling C. Stochastic prediction of high-speed train dynamics to long-term evolution of track irregularities, Mechanics Research Communications, Vol. 75, 2016, pp. 29–39.

Lee J. S., Choi I. Y., Kim S. H., Moon D. S. Kinematic modeling of a track geometry using an unscented Kalman filter, Measurement, Vol. 94, 2016, pp. 707–716.

Vaszary P. The theory of the track degradation, in I. Mezei and F. Horváth (Eds.) Railway construction and maintenance, Part II., Magyar Államvasutak Ltd. Budapest, 1999.

Veit P. Rail steel grades in track, Europien Railway Preview, Vol. 19, No. 4, 2013, pp. 32−36.

Veit P. The sustainability of railways (in Hungarian), Sinek Világa, No. 2, 2015, pp. 2−7.

Fischer Sz. Investigation of inner shear resistance of geogrids built under granular protection layers and railway ballast, Nauka ta Progres Transportu, Vol. 59, No. 5, 2015, pp. 97−106.

Fischer Sz., Szatmári T. Investigation of the geogrid-granular soil combination layer with laboratory multi-level shear box test, 6th European Geosynthetics Congress, Eurogeo6, Ljubljana, Slovenia, 25-28 September 2016, pp. 439−448.

Esveld C. Modern railway track, Second Edition, MRT-Productions, Zaltbommel, Netherlands, 2001.

Fischer Sz. Traction Energy Consumption of Electric Locomotives and Electric Multiple Units at Speed Restrictions, Acta Technica Jaurinensis, Vol. 8, No. 3, 2015, pp. 240−256.

Y. Shafahi, P Masoudi, R Hakhamaneshi Track Degradation Prediction Models, Using Markov Chain, Artificial Neural and Neuro-Fuzzy Network

https://www.researchgate.net/publication/268011897_Track_Degradation_Prediction_Models_Using_Markov_Chain_Artificial_Neural_and_Neuro-Fuzzy_Network


Refbacks

  • There are currently no refbacks.


Copyright (c) 2017 INTERSECTII / INTERSECTIONS

Indexed

Google Scholar