McLaren's Fluid Dynamics

[Wizzo]

 
Advances in the usage of computational fluid dynamics are enabling one F1 racing team to improve the design of its cars.

The Vodafone McLaren Mercedes team has expanded its computational fluid dynamics (CFD) capacity – opening up the way to improving and enhancing the design of its Formula 1 cars.
 
"One of the key parameters in differentiating a Formula 1 car is its aerodynamics," says McLaren Racing’s managing director Jonathan Neale. "To optimise the aerodynamics, we do a lot of design work and track testing, but computational fluid dynamics (CFD) in particular has been an area of major advance for us in recent years."

As part of that process, McLaren has purchased an additional two Altix supercomputers from its CFD partner, high-tech computing firm SGI, while also introducing SGI’s InfiniteStorage Data Migration Facility (DMF), which helps to manage CFD data.

CFD simulates airflows over a Formula 1 car to help develop its shape, primarily to create downforce. This helps to provide enhanced grip, particularly during cornering, according to SGI. It can also minimise drag and increase understanding of the car’s behaviour in yaw – crosswind and cornering – with the front wheels turned, and roll.
 
“When we first engaged with McLaren [in 2005], their use of CFD was very much in its infancy,” says SGI’s northern Europe pre-sales manager Keith Vickers. “They were using quite small model sizes. And also the number of car models they could do per week was limited to one car.”

McLaren can now model more than 25 cars per week, with sizes moving towards a billion cells. This allows McLaren to carry out detailed studies of various aspects of the car and spend less time in wind tunnel tests, according to Vickers. He says the SGI supercomputers also provide a simpler computing environment for the engineers. “The engineers focus on the CSD and don’t have to worry about being a computer expert.”

McLaren Racing’s CFD head Dr Mark Taylor stresses that the expansion of the SGI platform over the last few years has meant the quality of components sent to the tunnel is much higher. "We have a much better knowledge of the impact a component will have on the performance of the car before we wind tunnel test it, with the result that more components coming from CFD end up being used on the car,” he says.

However, large model sizes lead to large data files and in January 2007 McLaren introduced SGI DMF. This, states SGI, ensures data from an entire year’s car programme is available without clogging up its ‘scratch storage’ facility – a high-performance temporary data file store that helps keep up with the output from the super-computer.

“DMF has been a huge benefit, enabling us to look at results from throughout the year – which is very effective, in terms of how our programme works,” continues Taylor.

Vickers adds: “SGI storage technology allows [McLaren’s engineers] to share very large files, without passing them between machines.” As well as reducing storage space, this also saves copying time at each stage, which allows the team to process more cars.

As Vickers concludes: “Engineers are expensive people and, if they are just sitting there twiddling their thumbs, waiting for something to finish, or data moving around, then it’s likely they’re not being productive. The key thing [is maximising] productivity – and engineers are always happier when they are engineering, rather than just hanging around.”