Railways to deploy artificial intelligence to predict signalling failures

Indian Railways, track

With an aim to eliminate the possibility of signals failing, Indian Railways has started remote condition monitoring of the signalling system, which would allow it to predict failures through the use of artificial intelligence (AI), according to a report by The Economic Times.

Currently, Railways is using a manual maintenance system and use the find-and-fix method to resolve issues.

"Now, we are introducing remote condition monitoring using non-intrusive sensors for continuous online monitoring of signals, track circuits, axle counters and their sub-systems of interlocking, power supply systems including the voltage and current levels, relays, timers," a senior railway official involved with the project told the newspaper.

The new system collects inputs at pre-determined intervals and sends the information to the central system, thus leading to problems being detected on a real-time basis.

According to an official, the system will allow prediction of signalling asset failures, automated self-correction and informed decisions on intervention strategies, thereby helping to avoid mishaps.

According to the report, Indian Railways decided to test the system on two sections of Western Railway and South Western Railway on the Ahmedabad-Vadodara and Bengaluru-Mysuru sections. The system will then be extended further depending on the feedback received.

The system is currently operational in UK.