Photo credit (banner): Christophe Recoura / SNCF

How predictive maintenance makes your rail journey better

SNCF is a global leader in predictive maintenance, using sensors and the 4G network to “spy” on your train. With over 1,000 trains already equipped, we can fix breakdowns before they happen—and get you there on time.

Published on | Updated on

3-minute read

In 2019 SNCF Group Chairman and CEO Jean-Pierre Farandou1 said, “Soon we’ll have predictive maintenance: thanks to data from sensors, we’ll be able to take trains offline just before a door stops working. Downtime will be shorter and much more efficient, and it will cost much less.” Today, thanks to over 8 years of hard work, predictive maintenance is a reality. We’re installing sensors on hundreds of Transilien, TER, INTERCITÉS and TGV trains and collecting data to anticipate breakdowns as early as possible. For you, that means ever more reliable trains and better on-time performance.

SNCF is a global leader in predictive maintenance for rail. We can analyse more than 8,000 variables per train—including 2,000 in real time—from over 1,000 trains at the same time. 

Get the inside story from Cyril Verdun, Director of Maintenance Engineering in our Rolling Stock Division.

Learn more about predictive maintenance

SNCF has been deploying predictive maintenance solutions on trains for nearly 6 years now. What progress have you made?

Right now we’re moving forward with 2 different groups of trains. The first group has no built-in predictive maintenance equipment, so we install IoT devices2—connected sensors that transmit the data we need. That’s called remote diagnostics. The second group of trainsets already have a built-in data network, and we simply install SNCF 4G SIM cards. This innovative solution lets us carry out predictive maintenance, and we can expand it to new parts of the train. Examples of this group include the Regio 2N, Régiolis and Francilien.

Concretely, what difference does it make when you expand predictive maintenance to new parts of a train?

With remote diagnostics and predictive maintenance, we can eliminate half—even two-thirds—of breakdowns. That’s huge. Put simply, it makes day-to-day transport better. Consider the pantograph3. With predictive maintenance, we can check the pressure it exerts on the catenary without climbing up onto the train’s roof, and that means we don’t have to take the train out of service. Batteries are another good example. Thanks to some new settings, we now know exactly what condition they’re in and exactly when to change them, so we don’t need to carry out preventive battery maintenance every X number of years. Bottom line: we can keep more trains in circulation and be kinder to the environment at the same time.

8,000 variables from a train can be analysed in real time

 

Which trains are fitted with these innovative solutions?

SNCF Voyageurs has already installed SIM cards or IoT sensors in over 1,000 Regio 2N, Régiolis and Francilien trains in the Paris region and elsewhere in France.

In short, TER is a new front in your rollout of remote diagnostics and predictive maintenance. Why now?

Regional transport organizing authorities have realized that predictive maintenance is a game-changer that can improve on-time performance and reduce the number of TER breakdowns. With the domestic market set to open up to competition, our expertise in this area gives us an undeniable edge. What’s more, our TER 2N NGs and high-capacity AGC trains are now reaching mid-life. When they hit the 20-year mark, we do a complete overhaul, and that gives us the opportunity to suggest adding new IoT options and installing sensors on the components that are most likely to cause breakdowns, such as doors. Once installed, a sensor can tell us how often the door opens and closes, in how much time, so we can solve problems before they shut the train down. But we also use predictive maintenance on the tracks.

What are your goals in 2022?

We have two goals for this year. The first is to continue installing predictive maintenance solutions on the brakes and compressors of Francilien trains that run on the lines departing from Paris Saint-Lazare station. We also want to install them on all double-decker TGV trainsets before the new TGV M arrives. It will be a game-changer, with millions of accessible data points. That’s unprecedented.

Our second goal is to scale up our IT systems. Our algorithms—which we’ve developed in-house—and our processes are mature, but we need to strengthen the IT systems that have supported them for so many years.

With remote diagnostics and predictive maintenance, we can eliminate two-thirds of breakdowns.

Cyril Verdun, Director of Maintenance Engineering, Rolling Stock Division

How will you do that?

We’ve installed several fully equipped, modular maintenance benches on the tracks at our Châtillon TGV depot near Montparnasse station in Paris. They let us analyse the condition of mechanical parts on the outside of TGVs, such as the axles and the brake linings and discs.

How does that work?

We use automated test benches to round out our maintenance systems, particularly for mechanical components, where information from IoT2 devices is less conclusive. With the benches, we can automate regular preventive maintenance on components such as axles, wheels, and brake linings and discs. That lets us focus on what we need to do before a part breaks down or reaches its wear limit.

TGV and Transilien have invested in benches and are now rolling them out.

1 Excerpt from remarks by Jean-Pierre Farandou to the French National Assembly’s Sustainable Development and Regional Planning Commission, 2 October 2019.

2 The “Internet of Things” (IoT) is the network of physical objects that are connected to the Internet.

3 A hinged device mounted on an electric train to collect power through contact with the catenary.