How Neural Concept’s aerodynamic AI is shaping Formula 1

WhatsApp Group Join Now
Telegram Group Join Now
Instagram Group Join Now

Image credit: Williams Racing

It’s a long way from pedal bikes to Formula 1. But that’s exactly the quantum leap that AI-based startup Neural Concept and its co-founder and CEO Pierre Baci have made in just six years.

In 2018, the company’s new software helped create the world’s most aerodynamic bicycle. Today, four out of 10 Formula 1 teams use this evolution of the technology.

Along the way, Baqué’s company struck deals with aerospace suppliers like Airbus and Safran, raising a $9.1 million Series A in 2022. Now with 50 employees, Switzerland-based Neural Concept is working toward a Series B round while its software supports historic F1. Teams like Williams Racing find their way back to the premier form of motorsport.

However, while Formula 1 cars rely on 1,000-horsepower hybrid V6 engines, the first practical application of Bacchi’s technology was human-powered.

Pedal power

In 2018, Baqué was studying at the Computer Vision Laboratory of the École Polytechnique Fédérale de Lausanne, working on applying machine learning techniques to three-dimensional problems.

“I was approached by the guy who was leading the team, designing the sixth or seventh generation of the bike, and their goal was to break the world speed record,” Baki said. The guy was Guillaume DeFrance, and the team was IUT Annecy of the University Savoie Mont Blanc. The cycling team has already gone through half a dozen iterations of the bike design.

“Two days later, I came back to him with a figure that almost looked like the current world record holder,” said Baki. Impressed, the team asked for more iterations. The result was, per Baqué, “the most aerodynamic bike in the world at the time”.

That’s a strong statement, but it’s backed up by a number of world records achieved in 2019. We’re not talking aerofoil-shaped downtubes or dimpled rims to reduce drag. The bike is fully shrouded, with the rider sweating in a composite cocoon, completely protected from the wind.

The underlying technology is a product called Neural Concept Shape, or NCS. It is a machine learning based system that makes aerodynamic suggestions and recommendations. It fits into the broader field of computational fluid dynamics (CFD), where highly trained engineers use advanced software suites to run three-dimensional aerodynamic simulations.

CFD is much faster than carving physical models and throwing them into wind tunnels. Yet, it is highly system-based and relies heavily on humans making good decisions.

At its core, NCS helps engineers avoid potential aerodynamic pitfalls while pushing them in directions they might not have considered. In “co-pilot mode”, an engineer can upload an existing 3D shape, providing a starting point for example.

NCS will then suggest improvements or modifications to its neural network, choosing possible paths in a 3D game to choose your own adventure. The human engineer then selects the most promising proposals and runs them through further testing and refinement, retracing their path to aerodynamic glory.

Not just “cheating the wind”

NCS is useful not only for racing but also in the automotive and aerospace industries. “The path to widespread adoption in these types of companies is slow,” Bucky said of working in the somewhat conservative aerospace industry. “So we started working more with the automotive industry, where the needs are a little more pressing, and they will change quickly.”

Neural Concept has secured contracts with several global suppliers, including Bosch and Mahle. Aerodynamics is increasingly key in the automotive world, with manufacturers increasingly looking for more aerodynamic cars that provide the most possible range from a given size battery pack.

But it’s not all about cheating the air. NCS is also used to develop things like battery cooling plates that, if made more efficient, can keep the battery at its optimal temperature without wasting too much energy in the process. “Mass gains can be made, which means more range,” Bucky said.

While the ultimate proving ground for these technologies is always the road, the ultimate testbed is Formula 1. A global motorsports phenomenon since the 1950s, F1 is currently experiencing an unprecedented wave of popularity.

The power of Netflix

The Netflix series “Formula 1: Drive to Survive” brings the excitement of F1 to a new audience. While the series focuses on inter-team politics and drama, success on the track has a lot to do with aerodynamics. That’s where neural concepts come in.

Baqué started watching Formula 1 before Netflix caught Red Hastings’ eye. “I always watched, from the time of David Coulthard and Michael Schumacher.”

Today, his company’s software-engineered parts drive the pinnacle of global motorsport. “It’s a great, great feeling of accomplishment,” Bucky said. “When I started the company, I was looking at it as a landmark. Not just Formula 1, but just to have parts that were designed with the software on the road. And, yes, when Even so, it’s a great, great feeling.

Formula 1 is also a highly secretive sport. Of the four teams that Neural Concepts works with, only one was willing to identify itself as a client, and even that was pretty tight-lipped about the whole process.

Williams Racing is one of Formula 1’s most storied teams. Founded in 1977 by racing legend Frank Williams, his team was so dominant in the 1990s that it won five constructors’ world championships, including three in a row from 1992 to 1994.

But like most sports, success is cyclical for Formula 1 teams, and right now, Williams is in a rebuilding phase. The team finished last in the 2022 season, finishing just seventh last year.

NCS is one of the tools that helps Williams gain its competitive edge. “We use this technology in a variety of ways, some of which improve our simulations, and other methods we’re working on will help deliver better results in CFD for the first time,” Williams-head said. of Aerodynamic Technology Harry Roberts said.

Again, CFD simulations are time-consuming and expensive, a situation compounded by Formula 1 regulations that limit the team’s ability to test. Physical time in the wind tunnel is very limited, while each team also has a limited budget for the computing time they can use to develop their cars.

Any tool that can help a team get its aerodynamic design into shape quickly is a potential advantage, and NCS is very fast indeed. Baqué estimated that a full CFD simulation that would normally take an hour would take at least 20 seconds via NCS.

And, because NCS isn’t running actual physics-based calculations but rather AI-powered guesses based on its aerodynamic learning network, it’s largely exempt from F1’s strict restrictions. “Anything we can do that allows us to gain more knowledge and therefore more efficiency from every CFD and wind tunnel run gives us a competitive advantage,” said Roberts.

But teams still have to pay for it. Baqué said the cost of NCS varies depending on the size of the team and the type of access, but generally, it is in the range of €100,000 to €1 million per year. Considering F1 teams also operate under a $135 million annual cost cap, that’s quite a commitment.

Williams Roberts was unwilling to point to any specific parts or lap time improvements thanks to the NCS software, but said it has affected his car’s performance: “The technology is part of our toolset. It’s used to develop the car aerodynamically. So, we can’t directly attribute the lap times to it, but we know it helps our correlation and the speed we do. can investigate new aerodynamic conditions.”

Beyond aerodynamics

The endless march of AI will not stop there. There is talk of artificial agents on the pit wall calling the shots for race strategy and even car setup.

“This is an exciting time as the AI/ML industry continues to grow rapidly,” said Roberts. “However, it’s also a real challenge facing everyone involved in technology today. What new tools do we spend time discovering, developing and adopting?

It’s not the kind of plot that will captivate your average “Drive to Survive” viewer, but for many F1 fans, the back-to-back races are the ultimate source of drama.

As for the Neural Concept, the company is pushing deeper into the non-motorsport side of the automotive industry, developing more efficient electric motors, improving cabin heating and cooling, and even getting involved in crash testing. is working

Baki said the company’s software can help engineers improve a car’s crashworthiness by removing unnecessary weight. But, for now, the company can only perform crash simulations on individual components, not entire cars. “This is one of the few applications where we’re pushing performance limits,” he said.

Another request for maybe The EU’s growing AI supercomputing platforms?

WhatsApp Group Join Now
Telegram Group Join Now
Instagram Group Join Now

Leave a Comment