VR Group electric train in snow

IoT and predictive maintenance keep trains rolling

Finnish railway VR Group uses SAS® Analytics to provide punctual travel service and improve customer satisfaction

When it comes to transportation, nothing frustrates passengers more than delays – especially unexpected ones. That’s why railway companies take every advantage possible to maximize their operations and keep customers happy.

VR Group’s vision is to become the leading travel company in Finland. In my opinion, we could not make this happen without predictive analytics.
VR Group Kimmo Soini

Kimmo Soini
Senior Vice President for Maintenance

The key is using the data that you have – or the data that you can easily get – to find new ways to deliver better service. VR Group, the state-owned railway in Finland, turned to analytics and the Internet of Things (IoT) to keep its fleet of 1,500 trains on the rails and provide a better, safer experience for its customers.

In constant operation in all kinds of weather, trains endure harsh conditions. So it’s no surprise that a large portion of VR Group’s operational costs go toward maintenance. To reduce costs and maximize uptime, VR Group wanted to move from a traditional maintenance approach that focused on replacing parts as needed.

“Although we are the only service for passenger railway traffic in Finland, we are certainly competing with other means of transportation,” says Kimmo Soini, Senior Vice President for Maintenance at VR Group. “We also want to ensure our competitiveness when it comes to maintenance, because maintenance costs are included in ticket prices.”

In recent years, VR Group began fitting sensors on various systems and subsystems to monitor symptoms of wear and other failures. But the sensors themselves only collect the raw data. The real benefit comes in analyzing that data, often in real time, to allow engineers to take faster, more appropriate responses. To add this level of intelligence to their operations, VR Group turned to SAS Analytics.

VR Group smiling employee

Going from reactive to predictive maintenance

Traditionally, VR Group approached maintenance in two ways. Major systems, like wheels and bogies, were covered by scheduled maintenance. Often, parts were replaced when they still had a lot of life left. The other method was to fix things, like doors, when they broke down. These were hard to forecast and could lead to missed routes and unhappy customers.

VR Group developed a predictive maintenance program that focuses on monitoring the condition of parts at all times. In this program, mathematical models predict when parts are likely to fail so that they can be replaced before they cause unplanned downtime. By looking at sensor data, SAS Analytics gives VR Group a real-time overview of its fleet. The railway company’s goal is to change its maintenance approach, so eventually everything will be based on real-time monitoring.

VR Group electric train at station

“If a door on a train starts to open and close slower than usual, it is likely to break down within a certain time frame, and we must do something before that happens,” says Soini. “Analytics allows us to develop our repair operations around predictive maintenance.”

By looking at new and historical data, SAS Analytics helps VR Group plan the maximum interval between certain maintenance events, like turning wheels (on a lathe) or replacing the wheel-and-axle sets on the trains. Each train has more than 30,000 of these sets. If VR Group can optimize the dates of turning, it can keep trains on the rails longer. “In fact, we might be able to reduce the amount of maintenance work by one third,” says Soini.

SAS Analytics also helps VR Group identify the root causes of failures, which can increase savings and improve the reliability of the trains. Additionally, effective insight into IoT enables the railway company to minimize stock levels of spare parts and materials, keeping only what it needs on hand.

VR Group electric train in background

Turning sensor data into action

“The amount of sensor data has grown extensively, and the controlling of the data has become more targeted. Sensor data, analytics – and the automation of the two – are the technological advances we need in order to take the next step,” says Soini. “I believe that all maintenance will sooner or later be transformed by the Internet of Things, in all industries.

“VR Group’s vision is to become the leading travel company in Finland. In my opinion, we could not make this happen without predictive analytics.”

Photos courtesy of VR Group.



  • Improve the quality and efficiency of fleet maintenance.
  • Produce cost-efficient travel services that meet customers’ expectations.
  • Operate trains in a punctual and safe manner.



  • Smoother rail service as trains are more apt to run on time.
  • The ability to predict when parts need replacing before they break.
  • Improved reliability of its fleet of trains.
  • Minimized stock levels of spare parts.
  • Passengers have a better experience and benefit from more competitive pricing.
The results illustrated in this article are specific to the particular situations, business models, data input, and computing environments described herein. Each SAS customer’s experience is unique based on business and technical variables and all statements must be considered non-typical. Actual savings, results, and performance characteristics will vary depending on individual customer configurations and conditions. SAS does not guarantee or represent that every customer will achieve similar results. The only warranties for SAS products and services are those that are set forth in the express warranty statements in the written agreement for such products and services. Nothing herein should be construed as constituting an additional warranty. Customers have shared their successes with SAS as part of an agreed-upon contractual exchange or project success summarization following a successful implementation of SAS software. Brand and product names are trademarks of their respective companies.

Back to Top