This article illustrates some outcomes of the EU project Assets4Rail, founded within the Shift2Rail Joint Undertaking. Nowadays, Track recording vehicles (TRV) are equipped with laser/optical systems with inertial units to monitor track geometry (TG). Dedicated trains and sophisticated measurement equipment are difficult, costly to acquire and maintain. So the time interval between two TRV recordings of the TG on the same line section cannot be too close (twice per month to twice per year). Recently, infrastructure managers have been more interested in using commercial trains to monitor track condition in a cost-effective manner. TRVs' expensive and constantly maintained optical systems make them unsuitable for commercial fleets. On-board sensor systems based on indirect measurements such as accelerations have been developed in various studies. While detecting the vertical irregularity is a straightforward method by doubling the recorded acceleration, it is yet an unsolved issue for lateral irregularities due to the complicated relative wheel-rail motion. The proposed system combines wheel-rail transversal relative position data with on-board lateral acceleration sensors to detect lateral alignment issues. It includes a functional prototype of an on-board computer vision sensor capable of monitoring Lateral displacement for TG measurements. This eliminates measurement errors due to wheelset transverse displacements relative to the track, which is essential for calculating lateral alignment. The sensor system prototype was tested in Italy at 100 km/h on the Aldebaran 2.0 TRV of RFI, the main Italian Infrastructure Manager. It was found that the estimated lateral displacement well corresponds to the lateral alignment acquired by the Aldebaran 2.0 commercial TG inspection equipment. Moreover, due to the lack of measurement of the acceleration on board the Aldebaran 2.0 TRV, a Simpack® simulation provide with axle box acceleration values, to evaluate the correlation between them, LDWR and track alignment issues.
Track geometry monitoring by an on-board computer-vision-based sensor system
2023-01-01
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
DDC: | 629 |
Railway track inspection method based on computer vision
Europäisches Patentamt | 2023
|Road intersection vehicle track extraction system based on computer vision
Europäisches Patentamt | 2022
|