EMAIL    ;


Predictive High-Speed Network Maintenance pilot strives to provide functionality that predicts the failure of mainline railway assets with sufficient foresight that preventative maintenance can be scheduled and performed. Improving the maintenance of rail assets consistently and predictably improves the safety case and other sub goals of the project such as cost efficiency and minimising disruption.

The typically applied maintenance schedule is periodic preventive maintenance based on rules established a long time ago. So far, the basis of maintenance strategy has been to maintain continuous intensive monitoring of the elements and track geometry, even though when no repair tasks are needed. The next step for the rail maintenance strategy is to be based on predictions of the evolution of infrastructure.

Understanding the history of an asset could also lend itself to predicting the asset’s future behaviour. By using big data techniques to process the various sources of disparate data will allow the data scientist to perform analysis and visualise correlations.

Essential for efficient maintenance of the railway infrastructure is the availability of up-to-date, accurate, and reliable asset information which only becomes available by measuring key parameters and monitoring the condition and behaviour of critical assets as tracks and point-machines.

Unlike conventional “static” maintenance models in use today, the new proposed model shall be dynamically updated. The updates will be based on:

  • information provided by traditional inspections (but with the aim of reducing them to a minimum);
  • indirect information provided by traffic control systems (e.g. from the number of train passing on a given switch in a certain time it is possible to infer the switch stress);
  • information provided by vehicles for track analysis and inspection;
  • information related to weather (and possibly other environmental) conditions;
  • information from capacity and/or infrastructure managers about utilization, traffic and route planning, possessions etc.;
  • information from asset managers about maintenance and renewal plans and realization;

Furthermore, organizing and planning maintenance activities in the most efficient and safe way requires up to date information about traffic and capacity planning which implies close cooperation with infrastructure managers and train operating companies. In fact the mentioned information will be used in forecast models that will allow to establish more accurately the maintenance intervals and will also help to determine the consequences of any failure.

Finally, some of them will contribute to the analyses of possible step changes in component degradation that will be performed considering for example changes in traffic patterns, rolling stock, line speeds, weather conditions, and so on.

The demonstrator will showcase:

  • Availability and accessibility of reliable and up to date information of infrastructure for operational purposes as capacity assignment, traffic planning, maintenance planning and preparation.
  • Implementation of predictive models of decaying infrastructure valid for life cycle management and intelligent maintenance planning.

According to the expected results, this pilot will significantly upgrade the maintenance strategy of the rail profile and point machine, not only decreasing economic and environmental costs of maintenance, but avoiding realizing preventive maintenance (which is the current way of work)  when it is not necessary by setting predictive maintenance.


The project will focus on three use cases, the first two are focused on the status of two main elements of the railway infrastructure, track profiles and point machines, and the third one is related to traffic optimization.

The objectives of the pilot are:

  • Objective 1: Prediction of track profiles degradation:

Different sources from track profile degradation variables are used in order to collect the most important information that affects the track structure. These variables come from the analysis that the different maintenance companies perform, highlighting dynamic inspection, geometric inspection and maintenance task. Two different severity thresholds will be obtained from this analysis.

  • Objective 2: Prediction of the degradation of point machines:

Different sources from point machine degradation variables are used in order to collect the most important information that affects the point-machines structure. These variables come from the analysis that the different maintenance companies perform, highlighting movements time, maintenance task and characteristic data.

  • Objective 3: Optimization of railway operation in the Rail Traffic Management System.

By using the predictions obtained in objectives 1 and 2, new data will be available to modify and optimize the railway traffic.


Expected results:

  • Objective 1: Prediction of track profiles degradation: The result of this use case will be a prediction about the degradation of the Track Profile installed at High-Speed Lines. Data will be analysed, including an assessment of the railway infrastructure, operational, environmental and maintenance information. The possibility of exceeding the two thresholds previously defined will determine the new maintenance strategy, which will allow to compare the costs between current maintenance activities and predictive maintenance activities.
  • Objective 2: Prediction of the degradation of point machines: The result of this use case will be a prediction about the wear of point machines and a comparative about cost between current maintenance activities and the cost of the maintenance activities designed using the pilot results.
  • Objective 3: Optimization of railway operation in the Rail Traffic Management System: The result is the automatic generation of operational restrictions to improve the use of infrastructure taking into account its wear and state.


The main KPI of the pilot are:

  • RI-OE-6: Reduction of average train lateral (upwards) acceleration of car body.
    • Most important value measured by the dynamic and geometric auscultation system that affects the security (and consequently the maintenance tasks and strategy) in rail infrastructure.
  • RI-AM-1: Reduction in number of interventions.
    • Comparation between the number of interventions that would take place applying the traditional maintenance strategy and the predictive maintenance one.
  • RI-AM-14: Distance covered by the machinery to reach the working area.
    • Comparation between the distance covered by maintenance machinery to reach a working area using preventive or predictive maintenance.