Photo credit (banner): Alex Profit

Pioneering predictive maintenance at SNCF

Innovative predictive maintenance solutions are delivering enhanced reliability and on-time performance for passengers—and revolutionizing our day-to-day work. Get the inside story from Cyril Verdun, head of the Rolling Stock Engineering Cluster West in Saint-Pierre-des-Corps, near Tours.

Published on | Updated on

“Predictive maintenance has reduced breakdowns by nearly two-thirds.”

What is predictive maintenance?

Do you visit the doctor just to find out whether your knee hurts? Of course not. Our knees have a web of built-in sensors that constantly send out signals. When the brain receives them, it acts like an algorithm, interpreting the messages and telling us when the pain becomes chronic or unbearable.

And tells us it’s time to see the doctor?

Exactly. That’s predictive maintenance: we receive data from our trains, interpret it with our own algorithms and put it to work. Today we can assess the condition of our trains remotely and in real time, which means that we can eliminate routine preventive maintenance tasks. The fact is that 90% of maintenance involves checking something—a level, a reading, how the equipment is performing. Now that we already have access to that data, we can skip all the checking and focus on the remaining 10%.

But what’s predictive about it?

In my opinion, “predictive maintenance” is a misnomer. I prefer to call it “analytic maintenance.” Instead of carrying out preventive maintenance based on averages—a bit like the 20,000-km servicing on a car—we can eliminate periodic inspections. Not only can we predict and anticipate failures, we can tailor our maintenance schedule to the condition of the rolling stock. To go back to the medical metaphor: your knee isn’t exactly the same as your co-worker’s knee or your neighbour’s. No two trains are identical either, so we adapt our periodic checks accordingly.

What parts of the train do you check?

We analyse data from the doors, the mobile steps, the air conditioning and heating systems, the toilets, the compressors (which supply air to the brakes), the pantographs1, the batteries and the brakes. On the ground, that means that we no longer have technicians performing annual check-ups on heating and air conditioning. Similarly, we track the water level in the toilets so we can optimize filling. And we know which groups of components are working and what kinds of problems to expect: a leak, a clogged filter, a breakdown in an air-conditioning compressor, and so on.

How do you collect and analyse all the data?

On older trainsets, we install sensors connected to the Internet of Things2 (IoT). That’s what we call remote diagnostics. Output from the sensors is limited to select data of our choosing. Once we’ve analysed that, we know when to expect a breakdown.

What about new trains?

On more recent models—like the Francilien and Regio 2N3—there’s no need to install sensors. These trains are natively designed with a network and 3G or 4G SIM cards that transmit thousands of data points. We have access to some 8,000 variables for each train, and 2,000 of them are transmitted to us remotely in real time. If a user on one of these trains opens a door, the door receives a command, opens and tells the network: “I opened in X seconds and consumed this much electricity.” We simply capture this dialogue between the command, the door and the network. The same is true for the air conditioning, the heating, the compressors, and so on.

So there are two levels of predictive maintenance?

Absolutely. At the highest level, which is extremely advanced, we receive innumerable data points covering all of the train’s variables. At the second level, we use remote diagnostics to collect targeted data, which is often binary. Obviously, this type of maintenance is less precise, because native networks can transmit about 1,000 times more data than the sensors we install for remote diagnostics. Right now, 280 SNCF trainsets are equipped with the most recent technology, and 1,900 are set up for remote diagnostics. We’re the only ones in the world doing predictive maintenance on this scale.

Which lines are the most technologically advanced?

We’ve developed these tools over the past six years, and so far we’ve focused primarily on commuter service in the Paris region. Today, Transilien lines H, K, J, L and P, served by Francilien trainsets, have cutting-edge predictive maintenance technology. That’s also true for line R and RER line D, which operate around 60 Regio 2N trains. And we’ll have 100% predictive maintenance on the RER NG train, manufactured by Alstom and Bombardier. It’s set for rollout on line E in 2021 as part of the Eole project.

More recently, our TER regional trains have made the leap to predictive maintenance. Since early 2019 we’ve been trialling remote diagnostics on TER Régiolis trainsets in Normandy, Regio 2N trainsets in Centre-Val de Loire and TER 2N NG trainsets in the Grand Est region.

How does this benefit your passengers?

I’m tempted to tell them, ‘Relax. We’re “spying” on your train.’ If anything goes wrong, we know about it in real time, and we build in a lot of redundancy. For example, if the air conditioning breaks down in one trainset, the other coaches can compensate. With Francilien and Regio 2N trainsets, we can look ahead and know with 95% certainty whether a failure will happen in a week, in two days or in three. Over the past two years, we’ve cut breakdowns by more than half in trainsets with remote diagnostics, and by nearly two-thirds on lines with predictive maintenance.

And that improves on-time performance? 

Unquestionably. Here’s a case in point: we have 100 Francilien trainsets at Paris Nord station, and in the past nine of them were always offline for maintenance. Today that number has dropped to six. That’s a significant difference, because we can use available assets to make the network more robust—by adding an extra train at rush hour, for example.

20 %

reduction in train maintenance costs

Predictive maintenance has also revolutionized the day-to-day work of rolling stock employees, hasn’t it?

Digital technology is changing the workplace for all of us, from front-line operations staff to the heads of our specialized maintenance centres. Technicians are transitioning from a world where trains didn’t talk at all to trainsets that are literally in dialogue with them—like a veterinarian who changes careers and becomes a general practitioner for humans. Now our patients can tell us what their symptoms are, so we can make a much more accurate diagnosis.

How does that work on the ground?

In the past, we scheduled maintenance around deadlines and a specific calendar. We’d bring rolling stock in for repairs without realizing that we needed certain tools, or that we needed to move the trainset to a special track where we had access to its roof. Predictive maintenance is completely different: it’s scheduled solely around the variables of each train. Routine servicing is a thing of the past, and technicians don’t have to fly blind any more. When they carry out maintenance, they know exactly what and where the problem is, they know the history of the affected part, and thanks to data signatures, they know how much time the repair will take. Bottom line: we’ve cut maintenance costs by 20% and reduced shunting and maintenance centre visits by 30%.

That know-how has to be an advantage for SNCF as the market opens to competition.

I’m convinced of it. Tomorrow’s maintenance market will belong to the provider that is best able to know what’s happening with the train in real time. Our know-how is so good that we’re even better at predictive maintenance and remote diagnostics than the train and equipment manufacturers that design our rolling stock. We didn’t reach this level of excellence by accident. We were convinced that data analysis would pay dividends, so my teams and I got in very early. By the spring of 2013, we had hired a data scientist, and we’re exploring our data more and more every day. We’re looking for new practices and new ways to make everyday life better for our passengers and our employees.

Découvrez en vidéo le télédiagnostic et la maintenance prédictive chez SNCF

How remote diagnostics work

Diagram detailing the remote diagnostics chain. Step 1: Train communicates independently with IOT as it passes over instruments in the ground Step 2: Data is transmitted to data storage servers. Step 3: Scientists and rail experts analyse the data Step 4: Once the data has been analysed, it is retrieved for use by CMMS software.

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

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

3 Built by Bombardier, a Canadian train manufacturer.