Real-time prediction of switch faults
Improving passenger journeys by minimizing rail delays
PROJECT STORY
The challenge
Unforeseen switch faults cost train passengers time and entail high costs for rail network managers.
The solution
Arcadis and Asset Rail developed an advanced tool to predict switch faults using fault profiles. Preventive maintenance reduces the number of rail problems.
The impact
With properly functioning switches, there are far fewer delays on the tracks, which keeps passengers and transport operators happy.
40%
of all switch faults predicted
The challenge
Unforeseen rail switch faults are very inconvenient for everyone involved. For passengers, these faults are a major cause of delays. For rail operators, they entail a lot of extra costs — in an age when operators are increasingly adopting an operational excellence strategy that aims to do more with less money. But systematic cutbacks can lead to higher costs in the long run, so it is important that asset-intensive organizations review and optimize their conventional business processes on an ongoing basis.
The solution
For rail operators, repairing faulty switches can be an expensive undertaking, so Arcadis and Asset Rail developed an advanced tool to predict switch faults. By using the results to carry out condition-based maintenance of suspect switches and points, Asset Rail can prevent the faults that are a major cause of delays for train passengers.
-
READ MORE
Common switch faults can be predicted by measuring and analyzing electrical currents in the motor that controls the switch. The first step was to develop a model that is 'trained' with legacy data sourced from a selected number of switches over an eight-year period. The data was then analyzed in conjunction with the technical data, using various data analysis and machine learning techniques. Together with Asset Rail, Arcadis used these fault profiles to create a predictive model that continuously compares the current profile with previously collected data.
We are able to predict 40% of faults a few days before they occur.
The impact
On the ten switches on which the model has been tested, we are able to predict 40% of faults before they occurred. This allows preventive maintenance to be carried out on the equipment in good time. Properly functioning switches mean far fewer rail delays, which keeps passengers and transport operators happy.
