Research on Prediction Models of Track Geometric Irregularity

Abstract

Rail track geometric irregularities are the concrete embodiment of track structure deterioration, and give an expression to the comprehensive performance of track members. Quality Index (TQI) could reflect the change of track geometry state. It is a time series changed with time. In this paper, the Gray-Weibull model is developed to model over TQI and compared with conventional non- equidistant GM (1,1) model. Effectiveness of the prediction model is validated by the actual data of Ning-Hang Line K219.2~K219.4 unit section. The results show that the Gray-Weibull model is with higher prediction accuracy, which guides the maintenance of railway track.