Copyright: ThalesSource : Thales


AI x Time-Series Analysis

This challenge is over, applications are closed

Challenge Overview

Description du challenge

Countries, cities and transport operators rely on Thales’ ground transportation solutions to adapt to rapid urbanisation and meet new mobility demands – locally, between cities and across national frontiers.

Regarding the Rail systems, one of the solution provided by Thales offers a Big Data, cloud hosted platform for visualising and analysing railway asset time-series data.The intelligence built in to the product allows operators to identify and respond to failures before they cause major disruption to the rail network.

We collect large quantities of sensor data from various railway assets (points machines, communication logs, axle counters, track circuits, etc.) in real-time. We provide a tool for visualising and analysing this time-series data.

Copyright: 945_7039.NEF
Copyright: 945_7039.NEF
Copyright: Thales
Copyright: Thales


In this challenge, we are looking for:

  • Machine Learning state-of-the-art techniques for analysing time-series data, finding anomalous behaviour and classifying events, in order to improve the recommendations made to the operators
  • Improve the intelligence provided by this service through the integration of algorithms (techniques such as Recurrent Neural Networks should be particularly applicable here) that provide classifications/predictions on time-series data. For example, we have a complex time-series measuring the current in track circuits, which is variant to environmental and seasonal conditions
  • Algorithms that are able to identify anomalies independently of these factors would be hugely advantageous

Projects you could be working on

This challenge is global in scope and does not focus on a specific project.