Privacy policy

Our website uses cookies to enhance your online experience by; measuring audience engagement, analyzing how our webpage is used, improving website functionality, and delivering relevant, personalized marketing content.
Your privacy is important to us. Thus, you have full control over your cookie preferences and can manage which ones to enable. You can find more information about cookies in our Cookie Policy, about the types of cookies we use on Atos Cookie Table, and information on how to withdraw your consent in our Privacy Policy.

Our website uses cookies to enhance your online experience by; measuring audience engagement, analyzing how our webpage is used, improving website functionality, and delivering relevant, personalized marketing content. Your privacy is important to us. Thus, you have full control over your cookie preferences and can manage which ones to enable. You can find more information about cookies in our Cookie Policy, about the types of cookies we use on Atos Cookie Table, and information on how to withdraw your consent in our Privacy Policy.

Skip to main content

Data and analytics transport Talgo to the future of train operations

Streaming 30k signals per second at 350km per hour


At a glance

Talgo works with Eviden to revolutionize rail transport with real-time data and predictive maintenance that enhance efficiency and reliability.


Outcomes

  • 15% improved fleet reliability
  • 5% improved availability
  • 10% improved maintainability
  • 99% fleet availability
  • 200 hours of maintenance inspection time projected to be saved per train per year

Developing the TSMART platform has changed the conventional maintenance paradigm from systematic preventive maintenance to a new, dynamic maintenance management model based on predictive and condition-based maintenance using AI.

Jose Antonio Marcos
Head of Intelligent Maintenance Systems Engineering and New Projects, Sponsor of Talgo-TSMART

Client Challenge

Monitoring high-speed trains: why and how

High-speed train manufacturer Talgo has been innovating for more than 80 years. It was founded in 1942 and started breaking with tradition from the start. Its first trains were designed with extra features to improve passenger comfort, train safety and speed; an approach that still guides the company’s R&D.

When the technologies for predictive and condition-based maintenance cycled from initial hype to practical usability, the manufacturer embarked on its Talgo SMART Maintenance (TSMART) journey.

In 2020, Talgo began collaborating with, Atos company, Eviden to design and build a state-of-the-art fleet monitoring system that could accomplish four goals:

  • Ingest telemetry information from Talgo trains in real time and address communication failures.
  • Process a large volume of signal information and handling around 5GB of data per train per day.
  • Display processed information in a user-friendly format to maintenance engineers in less than one second.
  • Achieve architectural flexibility and scalability to incorporate modern train series without additional development efforts.

Solution

Developing TSMART: Talgo Fleet Monitoring System

The fleet monitoring system

Currently, the system manages streaming and analysis of more than 30,000 signals per second per train from 100 trains around the world:

  • Arabia
  • Egypt
  • Kazakhstan
  • Spain
  • United States
  • Uzbekistan
  • Russia

The data is ingested in real time and presented to users in friendly visualizations, maintaining end-to-end latency of around one second from signal arrival to display.

Business Benefits

TSMART Enhancements optimize train operations

Talgo and Atos have added several enhancements since launching TSMART:

  • Predictive maintenance: In 2022, Talgo decided to enhance TSMART with advanced condition-based maintenance to monitor the health status of main train systems and predict equipment lifespan.
  • AI delivered by MLOps: The predictive maintenance is not only based on AI models and rules. It was also delivered from an MLOps architecture for agile and flexible implementation.
    During implementation, the project team reinforced TSMART’s reliability by increasing automatic inspection frequency and early failure detection.
  • Data and analytics: The data and analytics platform behind TSMART was developed using Google Cloud capabilities for data storage, real-time data processing, advanced geo analytics and machine learning.
  • Visualizations: Eviden built Engineer cockpit visualization screens to provide maintenance engineers real-time and historical operational dashboards. To investigate the cause of an event or alarm, the engineers use a flexible and personalized interface to easily navigate between screens. They can select any component, geolocation, alarm, event or signal sent by the train to see its value in real time.
  • Expanded data analysis and system management: Eviden expanded the solution’s capabilities by implementing several modules in TSMART, including Event analysis, Gauge monitoring, Range analysis, Train data graphing, Train version configuration monitoring, Notification management and Functional administration.

Talgo and Atos are currently optimizing the user experience with customization capabilities as well as maintaining the TSMART platform. Eviden has also created a new module that analyzes gauge system change summaries, providing the user with richer event and variable indicators.

Streamlined maintenance processes
Today, Talgo has the foresight and tools to plan any necessary interventions before a train arrives at the maintenance base. Getting ahead of maintenance reduces breakdowns and saves the manufacturer time and money.

The sum of these efficiencies gives the maintenance engineering department more time to develop new maintenance workshops as the fleets increase.

Overall, TSMART represents a significant advancement in train fleet monitoring and maintenance; leveraging real-time data, predictive analytics and advanced visualization to enhance operational efficiency, reliability and cost savings.

How continuous monitoring of key train safety systems has improved Talgo’s operational safety:

5% improvement in fleet availability

  • Fewer failures on the tracks and reduced train stoppages are achieved through 24/7 monitoring and support from help desk teams.
  • 10% improvement in fleet maintainability
    Systematic preventive inspections are obsolete now that continuous remote monitoring enables condition-based maintenance.
  • 15% improvement in fleet reliability
    Continuous monitoring opens the door to preventive maintenance that keeps trains from failing.
  • Fewer corrective maintenance repairs
    Predictive maintenance of systems prevents breakdowns, reducing the need for reactive repairs.
  • Increased maintenance intervals
    Continuous monitoring allows for extending maintenance intervals based on actual system conditions.

 

Going there: packaged to resell as a service
Long an aspiration of smart manufacturing, the ability to create value-adding services from products is now Talgo’s reality. TSMART can be enhanced with product packaging/branding to be offered as a service to third parties.

Talgo can easily extend the TSMART system to new train series or offer it to customers as a service. Its customizable interfaces include options for company branding and user personalization as well as new train configurations.