Identification of Railway Vertical Track Alignment via the Unknown Input Observer

In this paper, a model-based approach for the identification of the railway vertical track alignment from simulation data is presented. The proposed methodology is based on the application of the unknown input observer algorithm. The model of a conventional train is used to simulate the acceleration levels that vehicle-mounted sensors (e.g., on the bogies and carbody) would measure during operation. Simulations are carried out at a constant speed on both straight and curved tracks, including different types of track geometry components (namely longitudinal level, alignment, and cross-level) to assess the algorithm capability to identify the input irregularity. The primary focus is on the identification of mean vertical track alignment, a critical irregularity component for safety issues. In the analysed cases, the comparison between the measured and reconstructed signal histories are quite satisfactory, with maximum errors in the order of 15% and 29% along straight and curved tracks. Comparing the frequency content of the signals, a significantly higher degree of accuracy is observed (with maximum errors of 5–10% depending on the track layout), which demonstrates that the proposed methodology is suitable for track irregularity identification and monitoring purposes using an instrumented vehicle.