ELECTRONICS
RATP subway trains will feature TETRA radio communication systems
be so advanced that it will break current encryption algorithms. If the algorithms are broken on current devices, the whole switch needs to be replaced, which is very expensive when you consider there are thousands of these on the tracks. So, we developed a crypto-agile switch which has a replaceable SD card with a full encryption algorithm, meaning just the SD card would need replacing if the algorithms were broken in future.” Also announced at the show was
a new tender with long-standing partner RATP to equip the latter’s new MF19 metro trains and TW20 tramways with Eviden’s TETRA radio communication systems between the line’s Centralised Control Station (CCS) and the various rolling stocks. The solution will play a pivotal role in modernising RATP’s existing embedded radio systems, ensuring their long-term viability as they increasingly demand greater computing power for voice/data and safety/security services, while requiring minimal onboard space.
DATA-DRIVEN ANALYTICS Another key aspect of Eviden’s rail offering on display is its Computer Vision Platform (CVP), designed for real-time and post-event monitoring. Equipped with global technology patents and advanced AI, the CVP can be tailored to suit various use cases, verticals and specific customer needs. The end-to-end AI-powered video analytics solution delivers
precise object tracking, robust alarm triggering and tailored object classification to enable enhanced security, safety and operations. “We have approximately 50 use
cases which can be deployed straight off the shelf,” Todorovitsch says. “These range from detecting objects on the track to white line crossing, detecting abandoned luggage to counting people, and of course identifying suspicious behaviour.” The real-time monitoring and
metadata provided by the CVP provides valuable insights for a wide range of applications including traffic management, perimeter protection, operations management and intrusion detection.
DIGITAL TWINS Eviden’s digital twin platform also has a dedicated spot on the company’s Innotrans booth, which Todorovitsch says “brings huge value to customers.” The platform simulates real-
world systems to enable predictive maintenance by identifying potential issues before they occur. This helps the firm’s customers to reduce downtime and extend the lifespan of their assets. The booth showcased rail-specific use cases for digital twins, including a digital rail switch. “Railway switches are the most
expensive part on a track, with approximately 20% of train outages failing on the switches,” Todorovitsch explains. “It’s very important for rail operators to carry out predictive
The Eviden booth at Innotrans
maintenance on these switches so that they can reduce track outages and increase the part’s lifetime. Using sensors manufactured by one of our partners, we can build a digital twin of the switch to enable our customers to measure really technical details regarding vibration, such as detecting flat spots on the wheels. We then use AI to analyse the data from the digital twin which highlights where and when predictive maintenance needs to be carried out.” Continuing with Eviden’s AI
capabilities, Todorovitsch outlines another rail-specific case study made possible by the company’s unique “white box” approach to AI: “With a ‘black box’ approach to AI, such as ChatGPT, you don’t know where the data comes from. With a ‘white box’ approach, you get an explanation of what rules were taken to arrive at a given conclusion, which is vital for mission- and safety-critical applications. With this AI, we are detecting anomalies on concrete sleepers which can cause huge safety issues. Our trusted AI solution can automatically detect cracks and categorise them according to the rules of Deutsche Bahn, in this example, and then give recommendations for how to act accordingly, such as reducing the speed of trains by a certain amount.”
For more information visit:
www.eviden.com
www.engineerlive.com 41
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52
