Particle filter-based prognostic approach for railway track geometry

Abstract

Track degradation of ballasted railway track systems has to be measured on a regular basis, and these tracks must be maintained by tamping. Tamping aims to restore the geometry to its original shape to ensure an efficient, comfortable and safe transportation system. To minimize the disturbance introduced by tamping, this action has to be planned in advance. Track degradation forecasts derived from regression methods are used to predict when the standard deviation of a specific track section will exceed a predefined maintenance or safety limit. This paper proposes a particle filter-based prognostic approach for railway track degradation; this approach is demonstrated by examining different railway switches. The standard deviation of the longitudinal track degradation is studied, and forecasts of the maintenance limit intersection are derived. The particle filter-based prognostic results are compared with the standard regression method results for four railway switches, and the particle filter method shows similar or better result for the four cases. For longer prediction times, the error of the proposed method is equal to or smaller than that of the regression method. The main advantage of the particle filter-based prognostic approach is its ability to generate a probabilistic result based on input parameters with uncertainties. The distributions of the input parameters propagate through the filter, and the remaining useful life is presented using a particle distribution.