The Development of an Integrated Computing Platform for Measuring, Predicting and Analyzing Profile-specific Fixity of Railway Tracks

The current measures for the railway track fixity in the UK’s railway system remain at a relatively low level of granularity. This paper presents a pilot study of the development of an integrated computing framework for improving the measurement, prediction, and analysis of profile-specific fixity of railway tracks in the context of the UK rail network. The framework is aimed to produce a data integration and mining tool, which can determine track fixity parameters for any given section of track. In this fundamental phase of the study, we propose to measure the track movement based on LiDAR point cloud data and describe the track fixity by a set of parameters, which are associated with the direction of track movement relative to the plane of rail and the rate of the movement within a certain period. We seek to integrate a data mining algorithm into the framework to predict the values of those parameters, given a very large amount of heterogeneous data in the area. From the pilot study, a prototype framework, which allows the rapid implementation of data workflows with the functionality, has been created. We demonstrate the feasibility of the prototype by training a random forest model on the real data from an 80-km section of the East Coast Main Line south of Edinburgh in Scotland. Curvature, cant, and maximum speed of trains proved to be the key factors that impact on, and hence are critical for predicting and analyzing, profile-specific track fixity.