A hybrid stochastic approach for offline train trajectory reconstruction

Abstract

The next generation of railway systems will require more and more accurate information for the planning of rail operation. These are essential for the introduction of automatic processes of an optimized traffic planning, the optimal use of infrastructure capacity and energy, and, overall, the introduction of data-driven approaches into rail operation. Train trajectories collection constitutes a primary source of information for offline procedures such as timetable generation, driving behaviour analysis and models’ calibration. Unfortunately, current train trajectory data are often affected by measurement errors, missing data and, in many cases, incongruence between dependent variables. To overcome this problem, a trajectory reconstruction problem must be solved, before using trajectories for any further purpose. In the present paper, a new hybrid stochastic trajectory reconstruction is proposed. On-board monitoring data on train position and velocity (kinematics) are combined with data on power used for traction and feasible acceleration values (dynamics). A fusion of those two types of information is performed by considering the stochastic characteristics of the data, via smoothing techniques. A promising potential use is seen especially in those cases where information on continuous train positions is not available or unreliable (e.g. tunnels, canyons, etc.).