In-service railway track condition monitoring by analysis of axle-box accelerations for small- to medium-sized infrastructure operators

摘要

About 50% of the lifecycle costs of railway tracks are caused by maintenance actions, which are currently typically conducted within corrective maintenance schemes. The accelerating digitalisation and development of low-cost sensors provide the opportunity, especially for small infrastructure operators, to introduce cost-effective track condition monitoring on a daily basis, utilising embedded sensors on their in-service vehicles. This will allow the challenging step forward from reactive corrections to proactive preventative maintenance actions to significantly reduce maintenance costs. The authors present the overall framework and initial results of a prototype implementation of the complete system for quasi-continuous condition monitoring of short-wavelength (a few centimetres to a few metres) defects of railway tracks, such as rail corrugation, from the embedded sensor to the visualised data analysis result. Georeferenced triaxial axle-box accelerations are gathered in the frequency range from 0.8 Hz to 8000 Hz using a prototype measurement system on a shunter locomotive operating on the railway network of Braunschweig inland harbour in Germany (with a total track length of about 15 km). The implementation of the prototype in an operational environment provides data covering four months of shunting operation to develop and evaluate data analysis algorithms. The acceleration sensor data is combined with further relevant data, such as the digital map of the railway infrastructure and other operational data, to be prepared for data analysis by the authors' prototype implementation of a land-side data management system. Results of the land-side data analysis chain are presented, including the track-selective georeferencing by multi-sensor fusion, the extraction of relevant features from the axle-box acceleration data for pattern recognition and further intelligent data analysis to provide spatiotemporal information about track conditions. The results obtained are finally visualised for the infrastructure operator by the data management web front-end.