Prediction of track geometry degradation using artificial neural network: a case study

Abstract

The aim of this study has been to predict the track geometry degradation rate using artificial neural network. Tack geometry measurements, asset information, and maintenance history for five line sections from the Swedish railway network were collected, processed, and prepared to develop the ANN model. The information of track was taken into account and different features of track sections were considered as model input variables. In addition, Garson method was applied to explore the relative importance of the variables affecting geometry degradation rate. By analysing the performance of the model, we found out that the ANN has an acceptable capability in explaining the variability of degradation rates in different locations of the track. In addition, it is found that the maintenance history, the degradation level after tamping, and the frequency of trains passing along the track have the strongest contributions among the considered set of features in prediction of degradation rate.