HomeNewsHow Neural Concept's aerodynamic AI is shaping Formula 1

How Neural Concept's aerodynamic AI is shaping Formula 1

It's long Away from the pedal bike to Formula 1. But that is strictly the quantum leap that the AI-based startup Neural Concept and its co-founder and CEO Pierre Baqué have achieved in only six years.

In 2018, the corporate's fledgling software helped create the world's most aerodynamic bike. Today, 4 out of ten Formula 1 teams use an additional development of the identical technology.

Over time, Baqué's company secured contracts with aerospace suppliers resembling Airbus and Safran. raise $9.1 million in Series A in 2022. Now employing 50 people, Switzerland-based Neural Concept is working on a Series B round, while its software helps historic F1 teams like Williams Racing find their way back to the highest of the world's premier type of motorsport.

However, while Formula 1 cars depend on 1,000 horsepower hybrid V6 engines, Baqué's first practical application of the technology was through human power.

Pedal power

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

“I used to be put in contact with this man who was leading this team and designing the sixth or seventh generation of bicycles, and their goal was to interrupt a world bicycle speed record,” Baqué said. That guy was Guillaume DeFrance and the team was IUT Annecy from Université Savoie Mont Blanc. The cycling team had already passed through half a dozen iterations of motorcycle designs.

“I got here back to him two days later with a form that looked almost like that of the present world record holder,” Baqué said. Impressed, the team asked for further iterations. The result, based on Baqué, was “currently essentially the most aerodynamic bicycle on the planet.”

That's a powerful statement, but one which is backed up by several world records from 2019. We're not talking about wing-shaped downtubes or knobby rims to cut back air resistance. This bike is fully enclosed and the cyclist sweats in a composite cocoon, completely protected against the wind.

The core technology is a product called Neural Concept Shape or NCS. It is a machine learning-based system that makes aerodynamic suggestions and suggestions. It suits into the broad field of Computational Fluid Dynamics (CFD), where highly expert engineers use advanced software packages to perform three-dimensional aerodynamic simulations.

CFD is way faster than creating physical models and throwing them into wind tunnels. Yet it is usually hugely systems intensive and relies largely on people making good decisions.

At its core, NCS helps engineers avoid potential aerodynamic pitfalls while pushing them in directions they won’t have considered. In “Co-Pilot Mode,” an engineer can upload an existing 3D shape, providing a start line, for instance.

NCS will then enter its neural network to suggest improvements or modifications and possible paths in a 3D game to decide on your personal adventure. The human engineer then selects essentially the most promising proposals and puts them through further testing and refinement to attain aerodynamic glory.

Not just “cheating the wind”

NCS shouldn’t be only useful in racing, but additionally within the automotive and aerospace industries. “The path to widespread acceptance in such corporations is slow,” BaquĂ© said of working within the more conservative aerospace industry. “So we began working more closely with the automotive industry, where the needs are somewhat more urgent and may change quickly.”

Neural Concept secured contracts with several global suppliers, including Bosch and Mahle. Aerodynamics is becoming increasingly essential within the automotive world as manufacturers search for increasingly aerodynamic vehicles that supply the best possible range from a given size battery pack.

But it's not nearly cheating the wind. NCS can be utilized in the event of battery cooling plates, which, when made more efficient, can keep the battery at its optimal temperature without consuming an excessive amount of energy. “Enormous gains could be made,” said Baqué, meaning even greater reach.

While the last word testing ground for these technologies is all the time the road, the last word laboratory is Formula 1. A worldwide motorsport phenomenon since 1950, Formula 1 is currently experiencing an unprecedented wave of recognition.

The power of Netflix

The Netflix series “Formula 1: Drive to Survive” has brought the thrill of Formula 1 to an entire recent audience. While this series focuses on the politics and drama between teams, success on the track has way more to do with aerodynamics. This is where Neural Concepts comes into play.

Baqué began watching Formula 1 before Netflix was even a twinkle in Reed Hastings' eyes. “I’ve all the time watched, because the days of David Coulthard and Michael Schumacher.”

Today, parts developed using his company's software run on this premier class of world motorsport. “It’s an excellent sense of accomplishment,” said Baqué. “When I founded the corporate, I felt it was a milestone. Not just in Formula 1, but simply to have parts designed with the software on the road. And yeah, each time that happens, it’s an excellent, great feeling.”

Formula 1 can be a particularly mysterious sport. Of the 4 teams Neural Concept works with, just one was willing to be named as a customer, and even that team remained pretty tight-lipped about your complete process.

Williams Racing is probably the most traditional teams in Formula 1. Founded in 1977 by racing legend Frank Williams, the team was so dominant within the Nineteen Nineties that it won five constructors' world championships, including three in a row from 1992 to 1994.

But like most sports, success for Formula One teams is cyclical and Williams is currently in a period of rebuilding. The team finished last within the 2022 season and only rose to seventh place last 12 months.

NCS is certainly one of the tools helping Williams regain its competitive edge. “We are using this technology in a wide range of ways, a few of which is able to improve our simulation, and other methods we’re working on will help produce higher CFD results the primary time,” said Hari Roberts, head of aerodynamics technology at Williams.

Again, CFD simulations are time-consuming and expensive, which is exacerbated by Formula 1 regulations that limit a team's ability to check. Physical time within the wind tunnel may be very limited, and every team has a limited budget for computing time that they will use to develop their cars.

Any tool that may help a team get their aerodynamic designs into shape quickly is a possible advantage, and NCS may be very fast indeed. Baqué estimated that a full CFD simulation, which might normally take an hour, would take just 20 seconds through NCS.

And because NCS doesn’t perform actual physics-based calculations, but as an alternative makes AI-driven guesses based on its network of aerodynamic insights, it is essentially exempt from Formula 1's draconian restrictions. “Anything we are able to do to realize more knowledge and due to this fact more performance from every CFD and wind tunnel run gives us a competitive advantage,” said Roberts.

But the teams still must pay for it. Baqué said NCS costs vary depending on team size and form of access, but are typically between 100,000 and 1 million euros per 12 months. Considering F1 teams also operate under an annual cost cap of $135 million, that's a big commitment.

Williams' Roberts was unwilling to indicate specific parts or lap time improvements due to the NCS software, but said it had impacted his automobile's performance: “This technology is used as a part of our toolset for the aerodynamic development of the automobile.” Therefore “We can’t directly attribute the lap time to this, but we understand it improves our correlation and the speed at which we are able to investigate recent aerodynamic conditions.”

Beyond aerodynamics

The ceaseless march of AI won’t end here. There is talk of artificial agents on the pit wall determining the racing strategy and even the vehicle set-up.

“It’s an interesting time as the expansion within the AI/ML industry is exponential,” said Roberts. “However, it is usually an actual challenge facing anyone engaging with technology today. What recent tools are we dedicating to research, development and adoption?”

That's not the type of intrigue that can captivate the typical Drive to Survive viewer, but for a lot of F1 fans, the race behind the race is the last word source of drama.

As for Neural Concept, the corporate continues to push deeper into the non-motorsports side of the automotive industry, working on developing more efficient electric motors, optimizing cabin heating and cooling, and even participating in crash testing.

Baqué said the corporate's software may help engineers optimize a automobile's crashworthiness while saving unnecessary weight. However, the corporate can currently only perform crash simulations for individual components, not entire cars. “This is certainly one of the few applications where we now have reached the bounds of performance,” he said.

Maybe one other application for that The EU's emerging AI supercomputing platforms?

LEAVE A REPLY

Please enter your comment!
Please enter your name here

Must Read