CZ/SK verze

EXCITING: AI to Revolutionize Rail Operations in Germany

EXCITING: AI to Revolutionize Rail Operations in Germany
photo: Deutsche Bahn, RAILTARGET Archive/AI to Revolutionize Rail Operations in Germany
22 / 06 / 2023

Deutsche Bahn is expanding the use of AI for train schedules. With the help of a tool developed in-house, rail operations throughout Germany are to become more punctual. The programme supports the dispatchers in efficiently managing traffic and avoiding delays.

The tool is already in use on the S-Bahn in Stuttgart, the Rhine-Main network, and Munich. Last year, 58,000 minutes of delay could be avoided there. In the second half of this year, the AI will be introduced on the S-Bahn in Berlin. DB expects this to result in around 90,000 avoided delay minutes across Germany by 2023. Next year, the tool will also be used in the Hamburg S-Bahn network. It means that all five metropolitan S-Bahns in Germany will be able to work with AI support in the future.

In addition, the tool is currently being tested on the line between Elmshorn and Sylt. In this section, the AI is operating outside a closed S-Bahn system for the first time and has to deal with mixed traffic, i.e. freight, local and long-distance trains. If these tests are successful, the system will be used in the next step on the heavily used line between Mannheim and Basel.

Dr Daniela Gerd Tom Markotten, DB Board Member for Digitalisation and Technology: "With artificial intelligence, we create more punctuality and reliability for our customers. At the same time, the AI tool makes our dispatchers' work easier and grows with their tasks. In this way, we are working our way step by step towards the nationwide real-time timetable."

The application area of AI is thus gradually expanding. The general rule is, the higher the complexity, the greater the effect that can be achieved with AI. The long-term goal is a real-time timetable that will become the digital control centre of German rail traffic like a kind of brain. With the help of AI, all delays caused by disruptions, road works or other incidents could then flow directly into the control of traffic. Internal processes will thus be accelerated and made more efficient by the enormous computing power of AI.

The functioning of the AI tool is based on a digital twin of the respective network. With this digital image, the system can simulate rail operations about 100 times in real-time and run through different variants of the traffic situation. The dispatchers then receive suggestions for measures to optimise operations and can intervene at an early stage before a bottleneck occurs. As a result, trains rarely have to reduce their speed or wait if another train is blocking a section of track. Therefore, AI ensures more punctuality and creates more capacity on the railways through better use of the existing infrastructure.

Source: Deutsche Bahn