They’re the bane of every rail commuter’s life but train delays – from leaves on the line and the wrong kind of snow to major signal failures – could become a thing of the past within the next few years under a pioneering project involving tech experts from UWE Bristol.
The university is collaborating with engineering group Costain and London-based engineering tech start-up Enable My Team (EMT) on a system that predicts when part of a train track, signalling equipment or other devices at a station are likely to fail. 
The system, currently in development and about to be trialled at London Bridge station – one of the country’s busiest – will use thousands of Internet of Things (IoT) sensors and 3D-modelling to constantly tap into big data from railway operators on everything from the track and signalling to station facilities such as ventilation systems, barriers and lighting.
Deploying Artificial Intelligence (AI) techniques, the data will be analysed to predict when a fault is likely to occur by highlighting any stress points or component failures on a 3D virtual model of the station and tracks.
Engineers will then harness Augmented Reality (AR) technology via a smartphone or a head-mounted display (HMD) to locate the failing components or structure faults and access on-screen instructions in real-time to help them with repairs.
The London Bridge pilot will last until next April, after which it will be trialled with selected customers for up to nine months. Five other stations have been approached to serve as testing sites for the technology before the planned roll-out of the scheme in 2021.
UWE assistant vice-chancellor, digital innovation and enterprise, Prof Lukumon Oyedele, who is the university’s principal investigator on the project, 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 sensors will transmit a whole variety of data including vibration, strain or pressure on a structure, humidity or temperature. Using several such components will enable train companies and station managers to monitor many parts of a train network at the same time.
Meanwhile, the AR technology will offer engineers information about the location of faulty components and provide guidance on how to fix them. As well as guiding them to the exact place where the problem lies, it will also give them real-time instructions and warn of dangers when carrying out the repairs
Prof Oyedele added: “By wearing a headset or using their mobile phones, engineers can view instructions superimposed on the joint or electrical circuit that they are repairing or replacing. For instance, it might give information or warnings about the presence of high voltage in a section of a control panel, or how to disassemble an electric circuit in a signal box in a safe way.”
Enable My Team founder and CEO Sandeep Jain said the system could bring reliability to the 1.7bn 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,” he said.
