Survival analysis at multiple scales for the modeling of track geometry deterioration

Defects in track geometry have a notable impact on the safety of rail transportation. In order to make the optimal maintenance decisions to ensure the safety and efficiency of railroads, it is necessary to analyze the track geometry defects and develop reliable defect deterioration models. In general, standard deterioration models are typically developed for a segment of track. As a result, these coarse-scale deterioration models may fail to predict whether the isolated defects in a segment will exceed the safety limits after a given time period or not. In this paper, survival analysis is used to model the probability of exceeding the safety limits of the isolated defects. These fine-scale models are then used to calculate the probability of whether each segment of the track will require maintenance after a given time period. The model validation results show that the prediction quality of the coarse-scale segment-based models can be improved by exploiting information from the fine-scale defect-based deterioration models.

[1]  Qing He,et al.  Track geometry defect rectification based on track deterioration modelling and derailment risk assessment , 2015, J. Oper. Res. Soc..

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

[3]  Samer Madanat,et al.  Semiparametric Hazard Rate Models of Reinforced Concrete Bridge Deck Deterioration , 2001 .

[4]  Dan M. Frangopol,et al.  Deterioration and Maintenance Models for Insuring Safety of Civil Infrastructures at Lowest Life-Cycle Cost , 2003 .

[5]  R. B. Faiz,et al.  Information analysis of rail track for predictive maintenance , 2009 .

[6]  Mario Cleves,et al.  An Introduction To Survival Analysis Using Stata Third | , 2012 .

[7]  Uday Kumar,et al.  Comparative study of track geometry quality prediction models , 2013 .

[8]  Håkan Schunnesson,et al.  Optimisation of track geometry inspection interval , 2014 .

[9]  C. Martland.  Productivity Improvements in the U.S. Rail Freight Industry, 1980-2010 , 2012 .

[10]  Thomas Y. Hou,et al.  Multiscale Modeling and Computation of Incompressible Flow , 2002 .

[11]  G. Rodŕıguez,et al.  Parametric Survival Models , 2010 .

[12]  James G. Wiener,et al.  The Weibull Distribution: A New Method of Summarizing Survivorship Data , 1978 .

[13]  António Ramos Andrade,et al.  A Bayesian model to assess rail track geometry degradation through its life-cycle , 2012 .

[14]  R. Dekker,et al.  Predicting rail geometry deterioration by regression models , 2012 .

[15]  David G. Kleinbaum,et al.  Parametric Survival Models , 2012 .

[16]  Wayne Nelson,et al.  Applied life data analysis , 1983 .

[17]  Samer Madanat,et al.  Computation of Infrastructure Transition Probabilities using Stochastic Duration Models , 2002 .

[18]  G Riboulet,et al.  Maintenance optimization for a system with a gamma deterioration process and intervention delay: Application to track maintenance , 2009 .

[19]  Futian Wang,et al.  Markov-based model for the prediction of railway track irregularities , 2015 .

[20]  Mohd Rapik Saat,et al.  Analysis of Causes of Major Train Derailment and Their Effect on Accident Rates , 2012 .

[21]  Murray Aitkin,et al.  The Fitting of Exponential, Weibull and Extreme Value Distributions to Complex Censored Survival Data using GLIM , 1980 .