Rumo grain train

BRAZIL: Operator and logistics company Rumo has introduced an enhanced broken rail detection system, integrating artificial intelligence to improve the accuracy of detection and reduce the number of false alarms.

Rumo began its broken rail detection project in 2018, installing devices at various locations across its 1 676 mm gauge freight network to monitor track condition. These transmitted information about potential anomalies to a network monitoring centre which then passed the relevant data to train drivers in real time, helping to reduce the risk of derailments.

Introduction of the AI functionality on a trial basis started in August and September this year, leading to a 6∙25% increase in detection accuracy, according to Rumo’s Railway Technology Manager Rodrigo de Souza. During the two-month period Rumo would expect to have identified 96 broken rails, but the use of AI enabled the detection of 102 fractures.

The AI-assisted equipment also identified 14 false alarms that would have otherwise required maintenance inspection teams to be sent out to the track sites. ‘Integration of the system reduced the notifications that caused the train to stop or the need for speed restrictions’, Souza explained. ‘With this new model, we increased the efficiency of the operation and reduced the rate of cases of this type by 50%.’

Following completion of the initial test programme, Rumo began a process of updating 60% of its broken rail detectors across the network with AI functionality. It has now moved into a phase described as ‘assisted operation’.