Prediction of railway track geometry deterioration using artificial neural networks: a case study for Turkish state railways

The main goal of this paper is to model track geometry deterioration using a comprehensive field investigation gathered over a period of 2 years on approximately 180 km of railway line. Artificial neural networks (ANNs) were adapted for this research. The railway line was divided into analytical segments (ASs). For each AS, the following data were collected: track structure, traffic characteristics, track layout, environmental factors, track geometry, and maintenance and renewal data. ANN models were developed for the main track geometry parameters and produced significant relationships between the variables. In addition, sensitivity analyses were performed to compute the importance of each predictor in determining the neural network. The obtained results proved that ANN may be an alternative method for predicting track geometry deterioration.

[1]  Jeen-Shing Wang,et al.  A digital circuit design of hyperbolic tangent sigmoid function for neural networks , 2008, 2008 IEEE International Symposium on Circuits and Systems.

[2]  Gail M. Brion,et al.  A neural network approach to identifying non-point sources of microbial contamination , 1999 .

[3]  Simon Iwnicki,et al.  TRACK SETTLEMENT PREDICTION USING COMPUTER SIMULATION TOOLS , 1999 .

[4]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .

[5]  Javad Sadeghi,et al.  Development of track condition assessment model based on visual inspection , 2011 .

[6]  Ernest T. Selig,et al.  PERMANENT STRAIN BEHAVIOR OF RAILROAD BALLAST , 1981 .

[7]  Mats Berg,et al.  Assessing track geometry quality based on wavelength spectra and track–vehicle dynamic interaction , 2008 .

[8]  Javad Sadeghi,et al.  Development of improved railway track degradation models , 2010 .

[9]  Krishna B. Misra,et al.  Handbook of Performability Engineering , 2008 .

[10]  Iqbal M. Mujtaba,et al.  Composite Materials Technology: Neural Network Applications , 2009 .

[11]  H Lichtberger.  TRACK MAINTENANCE STRATEGIES FOR BALLASTED TRACK - A SELECTION , 2001 .

[12]  Ernest T. Selig,et al.  Track Geotechnology and Substructure Management , 1995 .

[13]  E. Berggren,et al.  A new approach to the analysis and presentation of vertical track geometry quality and rail roughness , 2008 .

[14]  Hakan Guler,et al.  Modelling railway track geometry deterioration , 2011 .

[15]  M. Shenton.  Ballast deformation and track deterioration , 1985 .

[16]  Roger M. Goodall,et al.  Monitoring lateral track irregularity from in-service railway vehicles , 2007 .

[17]  Tarek Hegazy,et al.  Potential applications of neural networks in construction , 1992 .

[18]  P. Fonseca Teixeira,et al.  Uncertainty in Rail-Track Geometry Degradation: Lisbon-Oporto Line Case Study , 2011 .

[19]  S Kay,et al.  DEVELOPMENTS TOWARDS INTEGRATED TRACK MANAGEMENT , 2002 .

[20]  Christos Pyrgidis.  Bogie behavior of high-speed trains in curves , 2001 .

[21]  Sato Yoshihiko,et al.  Japanese Studies on Deterioration of Ballasted Track , 1995 .

[22]  Tore Dahlberg,et al.  Some railroad settlement models—A critical review , 2001 .

[23]  Ana Belén Porto Pazos,et al.  Advancing Artificial Intelligence through Biological Process Applications , 2008 .