Cordel’s approach to revolutionise the management of ‘Track Geometry’ and ‘Vehicle Response’ monitoring, by exploiting AI and ML techniques

Track Geometry measurement regimes used today are typically delivered by dedicated measurement trains and ‘attended’ systems. Its purpose is to measure track irregularities and drive remedial works to maintain acceptable ride quality and to prevent vehicle derailment risk. It could be argued that the approach is no different to the adopted methods of last century.

Alternative approaches of simpler, cheaper solutions where outputs of vehicle response and correlation to track irregularities have been trialled and studied but have not been adopted. This data, in the opinion of many track engineers, doesn’t give enough correlation or information of what the risk is, what work needs to be done to prevent, and by when.

This paper highlights the problems and limitations with the current processes, providing recommendations that Cordel believes are necessary to enhance and streamline the end-to-end management of the track/vehicle system interaction. It fully challenges the status quo, enabling a significant step change in predictive asset management. It discusses introducing a holistic asset management change such as the introduction of an ‘asset performance’ biassed maintenance approach.

With successful introduction of ‘full system’ monitoring capabilities, from track irregularity through to car body response, accurately aligned with state-of-the-art data management and AI/ML algorithms, a fully risk managed, predictive asset management regime can be introduced. This will provide efficiencies across the entire industry specifically for stretched maintenance teams with reduced asset access windows

Transform your infrastructure inspections

Book a demo to see first-hand how Cordel can provide your business with deeper insights.

Enter the form below and we’ll be in touch.

Please enter your details to access the case study PDF