Skip Ribbon Commands
Skip to main content

Project title

Developing an intelligence ensemble system for predicting and preventing train delays (COF-INP-02)

  • Project number:

  • Topic:

  • Status:


Project Summary

This feasibility study investigated how to use artificial intelligence and machine learning technologies to develop an Artificial Intelligence Enhanced Decision Support System (AIEDSS) able to predict, prevent and discover patterns of train delays.

Project Abstract

Project Briefs are hosted on
Rail network performance in the UK has been declining in recent years, despite the commitment of more resources and effort. This has resulted in an understandable increase in customer dissatisfaction and costs. Data shows that while the initial delays of trains has maintained relatively stable,  knock-on delays (also called reactionary delays) have become a main factor for the decline in performance. This is because once an initial delay has occurred many other trains that run through the same route or connected routes and stations can be affected. This knock-on effect may cascade throughout the entire rail network, making the planned timetable invalid. As a result, the required resources such as trains, tracks, drivers and crews “may be unavailable in the right place at the right time”. The whole situation can quickly escalate to become too complicated to be managed efficiently and effectively by rail service staff with the current systems.

With recent advances in artificial intelligence and machine learning, along with the vast amount of rail network data collected, it is possible to use this data to discover useful knowledge about train delays and to consequently improve network performance.

Project Reports

Project Reports are hosted on SPARK

This document is hosted on SPARK


You are now being redirected to SPARK, RSSB's knowledge sharing hub, to access the requested information.

Your RSSB user name and password can be used to access SPARK.