Gerhard Kress is surrounded by trains — both real and virtual. In front of him, on a monitor, is a schematic drawing of a vehicle. A whiteboard looms behind him in the open-plan office of the MindSphere Application Center for Rail that he heads. The whiteboard is dotted with red and blue formulas and equations that describe what happens during train operations. If Kress looks out the window, he can see the saw-tooth roofs of the Allach industrial site on the outskirts of Munich where Siemens builds locomotives. This is also where the locomotives can be serviced and maintained — at the Rail Service Center located just three rail car lengths away. The vehicle workshop is unusual because of what goes into it — not just the two rail tracks, but two worlds: the virtual and the real.
From Big Data to Smart Data
Heading for Data-Driven Rail Systems
Whether in Atlanta, Munich, Moscow, London, Perth or Hong Kong, Siemens' MindSphere Application Center for Rail use the complex streams of mobility-related data for predictive maintenance, and thus for optimized train operation. The experts at the centers accomplish this using Railigent, a new platform that enables them to intelligently use rail system data and generate added value from these systems.
The Digital Transformation of Rail Technology
The digital transformation has long since caught up with rail transport. Whereas maintenance traditionally consisted of checking rail vehicles at operating centers on a regular basis, resolving obvious problems, and maintaining machines, digital technology has opened the door to a new level of service. Remotely or locally collected sensor data, error messages, and log files provide MindSphere Application Center for Rail employees with an unprecedented level of detail regarding rail vehicles and their infrastructure.
Five more centers (in Atlanta, Moscow, London, Perth, Hong Kong) have been put into operation since 2014, when the one in Allach was opened. The data streams from locomotives, high-speed trains, and regional trains from more than 15 countries converge at these three centers. To turn this big data into smart data, the centers’ programmers, database experts, and implementation managers have developed a data-driven service offering in the rail sector that is unrivalled in terms of real-time train monitoring, forecasting of wear and failure of components, and analysis of complex vehicle problems.
The resulting Railigent platform can depict the entire information path — from the sensors on the tracks to the report on the user's smartphone — and also recommend specific actions. The advantages for the rail system operators and maintenance teams are obvious because the system results in greater availability, a longer service life, and substantially increased efficiency when it comes to maintenance and the operation of all of the train and infrastructure components. “Before a rail vehicle rolls into our Service Center, we already know what needs to be done,” says Kress. This enables up to 100 percent availability of the trains.
100 Trainsets, up to 200 Billion Data Points
Indeed, digital technologies provide experts with much more than just information on standard variables such as speed, braking behavior, and mileage. They also provide information regarding, for instance, the behavior of compressors, the weight of connected rail cars, and the status of automatic control processes. What’s more, the state of the rails and gradients as well as weather conditions during operation are registered along with the operating frequency of trains in a rail network. “For the future of the Mobility business, vehicles alone are not the decisive factor,” says Kress. “For customers, it is about vehicles’ lifetime costs and their efficient use. Success can be achieved only with the help of bundled data from the vehicles, the infrastructure, and the operations.”
All of this results in a veritable mountain of data. A fleet of 100 trainsets produces about 100 to 200 billion data points every year. And that’s just the beginning. As they analyze this data, Kress and his team are looking for meaningful patterns. The resulting knowledge can, for instance, enable them to optimize maintenance processes. A brake failure that involves error messages, for example, can be normal if the locomotive simultaneously hooks up to a rail car. This kind of knowledge makes it possible to distinguish between important and unimportant factors and recognize causal chains. Thanks to this approach, Kress and his team are now able to use forecasting models with a high level of reliability. With gearbox bearings, for example, which are subject to a high level of wear and tear at high speeds, the MindSphere Application Center for Rail can predict problems at least three days in advance. This increases the availability of the trains and saves money.
The German railway company Deutsche Bahn is also interested in such possibilities. In October 2016, Deutsche Bahn joined forces with Siemens to launch a pilot system for the predictive maintenance and servicing of Velaro D (ICE 3) high-speed trains. Moreover, the company’s freight transport division DB Cargo recently announced that it would use the solution from Siemens to further digitalize its vehicle fleet. It aims to equip all of its 2,000 vehicles with diagnostic technology by 2020.
High Speed and Reliability
Just how well this works can already be seen from the high-speed rail route that the Spanish national rail operator (Renfe) runs between Madrid and Barcelona. Here, Renfe competes with an air route. The train takes two and a half hours compared to a flight time of an hour and twenty minutes. Renfe, however, guarantees train passengers that they will receive a complete refund of their fare if the train is delayed by 15 minutes or more. To guarantee this high level of reliability, Renfe teamed up with Siemens to establish a joint venture that uses advanced data analysis for trains. The result has been that only one noteworthy delay, related to technical problems, has occurred over the course of around 2,300 trips. Whereas only 20 percent of travelers took the train when the route started operation more than ten years ago, this proportion has now risen to over 60 percent.
A Digital Analysis of All Train-related Information
The MindSphere Application Center for Rail team has a further advantage — It can draw upon datasets not only from different rail fleets but also from rail fleets operating under different conditions — whether in Germany, Spain, or Russia. All of this adds up to an information toolbox that can translate into enhanced rail vehicle reliability. This can be an advantage for smaller operators as well, because companies that operate routes for only a few years using only a few of their own or leased vehicles can benefit from reduced technical risks if they work together with service providers such as Siemens. “Forecasts of breakdowns and wear, error diagnostics, and well-planned maintenance cycles are just the beginning,” says Kress. “In the future it is conceivable that we at the Rail Service Center will be able to download a vehicle’s complete database via a cable, as is now possible with airplanes, in order to review the data for anomalies.”