Researchers from the University of the West of England (UWE Bristol), engineering solutions company Costain and startup Enable My Team (EMT) have devised a system capable of predicting parts, equipment and device failures at train stations.

Using thousands of sensors and 3D modeling connected to big data, the team can predict train track issues or signal equipment failures, for instance, before they emerge and result in delays.

The system also allows engineers to access augmented reality (AR) through smartphones or head-mounted displays (HMDs) to spot component or structure faults, enabling them to make repairs with real-time, onscreen instructions.

To test the technology, researchers will install a network of internet of things (IoT) sensors in London Bridge Station. The sensors will amass data concerning the tracks as well as station facilities including barriers, lighting and ventilation systems ahead of transferring that data to software called i-Ramp (IoT-enabled platform for rail assets monitoring and predictive maintenance).

Using artificial intelligence (AI) techniques, the system analyzes that data, making predictions about fault occurrences, while also highlighting stress points or component failures using a 3D virtual model of the tracks and station.

Professor Lukumon Oyedele, assistant vice-chancellor, Digital Innovation and Enterprise, who is the lead investigator on the project at UWE Bristol, said: "Every day in the UK, production is adversely affected by the hundreds of hours lost through train delays, often caused by faulty signal boxes or broken tracks.

The system will enable companies to fix a problem before it even becomes one, and at a time when commuting is not disrupted, all thanks to the IoT sensors in the station and on the track."

The IoT sensors can disseminate a host of data including structure pressure or strain, humidity, temperature or vibration. This data, according to the team, will allow train station operators to oversee multiple components of a train system at once.

Sandeep Jain, who is founder and CEO at EMT, said: "i-RAMP could bring reliability to the 1.7 billion annual passenger journeys on the UK railway, increasing productivity across the country. With machine learning and big data processing we can predict problematic vegetation, damaged structures and faulty signals, allowing repairs to be implemented before issues arise."

The testing will conclude in 2020 and the system is set for trial with select customers for up to nine months. Upon the completion of the trials, the system will roll out in 2021.