Data Analytics Takes the F1 2019 Chequered Flag

When Mercedes-AMG Petronas Motorsport hoists the constructor’s cup for 2019, it will be a nod to the rising influence of data analytics.

F1 is not shy about data analytics. Since the early days when sports cars were constructed with experimental designs, data took on a significant role.

But much of the early day F1 racing was about the driver, the machine (often the engine), and the track. Everyone took the backseat as they saw how their creation and the driver navigated the straights and curves of the racetrack.

Today, data analytics is right there in the driver’s cockpit. It has helped to extend the race all the way to the factory, where the analyses help engineers finetune car design.

Data analytics fuels up today's F1 wins.

Analytics Makes F1 a Teamsport

Data analytics plays a huge part in creating the right conversation between engineers, race strategists, and drivers.

A large part of this is driven by regulations. The Federation Internationale de l'Automobile (FIA) has been imposing different rules to ensure driver safety and a fair playing field for all teams.

The hope is to ensure that teams do not win races by sheer money and having the fastest engines. Instead, it helps the race remain a sport (and not a mere technological race), allowing skilled drivers and well-managed race teams to win. For example, the engine power was reduced from 710 to 560 kW (950 to 750 bhp) by shifting from the 3.0L V10s to 2.4L V8s. The FIA also limited all engines to 19,000 rpm to control reliability and handling at top speeds.

Such rules saw engineers working with drivers to create new engine designs that can work within the FIA constraints optimally. A large part of this is due to data analytics.

Another FIA rule is using the same setup during qualifying and races. So if the track conditions change (e.g., change of weather), there is no reset button to press.

The Mercedes-AMG Petronas Motorsport team optimizes the setup performance before the qualifying session, using data gathered from the simulator and historical data from the previous race or circuit from years past.

"A lot of the work is just checking that what’s provided is building up to the event and that it isn’t going to mislead us in any way,” said Andrew Shovlin, trackside engineering director, Mercedes-AMG Petronas Motorsport in a case study. “We’re constantly refining that because models are getting more complicated."

The team uses TIBCO Spotfire and TIBCO Data Science software to analyze previous races and previous circuits. The team then applies predictive algorithms to understand what changes were made in earlier races to help them learn and predict what to do at future events.

The TIBCO software also helps the team to crunch the data from a large magnitude of simulations to extract the optimal car setup. It will also unearth performance trends that can help the team react to what it sees during a race weekend.

This means the team no longer has to wait on an analysis report. Instead, new data is added to current information to improve the analyses. Essentially, TIBCO is helping the F1 team to go into every race with their eyes open. It also reduces the pressure on drivers to rely solely on their past experiences, which can be seen by the number of new young drivers reaching F1 and even podium stages.

"There are so many parameters you can change on the car to deal with wet, dry, hot, or cold conditions. A lot of that comes from experience. Still, when you can run millions of simulations, and use a tool like Spotfire software to distill the results into a subgroup, you can conceptualize and understand what's really going on," said Shovlin.

Singapore F1 is one of the few races where engine performance alone will not win.

Data Optimization at Over 300 km per hour

Today, cars are fitted on average with 150 sensors, transmitting around 2GB of data in one lap and 3TB throughout the race. Engineers rely on SAP HANA to process the data around 14,000 times faster than before.

As tires wear and the track conditions change, teams can tune suspension, aerodynamics, and power unit settings to affect performance. Potential lap times, tire degradation, and tire life grip and wear are also part of race strategy.

"We need to make sure that we get the perfect combination of each one of these different identities, and that's really what we leverage TIBCO for, and where we really see the performance benefits," said Michael Sansoni, senior performance and simulation engineer at Mercedes-AMG Petronas Motorsport in the case study.

But there is one problem: the sheer volume of data that needs to be processed. The second is overcoming the cadence of data. As the sport continues to change, teams that don't evolve quickly won't be successful. So, for Mercedes-AMG Petronas Motorsport, one of the keys to its continued success has been continuously innovating and changing alongside F1.

"We need to be able to react with all the new data we receive, the new aerodynamic platforms we receive from aerodynamics, the optimum performance from the suspension, and power units," said Sansoni. "We need to be able to combine these as soon as we have the latest data to ensure that out of those billion combinations, we can choose the fastest setup."

Centrifugal force and data download speeds are occurring in unison.

Strategic Decisions at Light Speeds

The season began well for the Mercedes-AMG Petronas Motorsport team. However, midway through the season in Belgium, the Ferrari team came back strong with their engine performance at straight-line speeds.

Ferrari then started to win — consecutively. This saw the Mercedes team double down on their analytics and using the insights to make prescient strategic design decisions.

After three races, it worked.

“All the teams have good people, all working really hard. But, it’s about how you get those people to work together, how you get those people to collaborate on data, collaborate on the processes that get you that last bit of performance,” said Mike Elliott, technology director, Mercedes-AMG Petronas Motorsport.

Data is not to replace drivers; but it gives a welcome boost!

Beyond F1

Analytics is undoubtedly shaping F1 sports. No other competition uses so much data at such high speeds. For example, drivers now wear biometric gloves so rescue teams can monitor the oxygen levels and pulse rate of drivers.

The use of analytics is also growing beyond the race pits, garages, and cockpits. Instead of watching the cars whizzing by and following the cars on the screens, today's audience has access to heat maps, tire wear data, and computer predictions on the likelihood of being taken over — all powered by data analytics. And it is already influencing other industries, like manufacturingenergy, and healthcare.

But TIBCO is not done yet. It sees the next battle in pulling data together. The company has already added a third element to its Connected Intelligence strategy called Unify. It considers data fabric and information management critical for decision-makers to pull together the various data stores and make sense of it all in real-time.

The next F1 competition will become an information race, and TIBCO is helping Mercedes-AMG Petronas Motorsport to prepare for it.

Data analytics keeps drivers poised for the win.