European race fans are famously sniffy about stock car racing, but there’s something about an ostensibly low-tech, normally-aspirated pushrod V8—with a capacity of 358 cubic inches ( 5.8 liters ) and a 670-hp output—charging round an oval that reaches the parts other race series do n’t. or have probably given up.
Not that the Nascar grid does n’t make every effort to gain technological advantage. There are many pit stops in the Nascar Cup Series, between five and twelve, depending on the circuit and what’s happening on-track, and Lenovo is working with one of the line ‘ biggest names, Richard Childress Racing, to help with them. In specific, the firm is using AI to get real-time insight into fuel.
Gas mileage is undoubtedly a crucial component of any Nascar competition, and it is almost an art in itself, in addition to being a resource of drama and jeopardy. ( NB: Refueling has been banned in F1 since 2010 for cost and safety reasons. ) It’s up to the teams ‘ managers to constantly monitor the amount that enters during a pit stop and the rate at which it’s consumed because the cars themselves are n’t fitted with fuel measurements in the cockpit.
Energy usage depends on a number of factors, including the size and construction of the monitor and the speeds the cars are moving at. There are a number of” cautions” during a race, at which time the cars will typically use half as much fuel.
In Nascar, the owners also “draft”, a technique that enables them to maintain acceleration in the bottle without using full throttle. Less energy consumed results in fewer pit stops, and when they do crater, they eat less. On average, a Nascar Cup series car—not the most energy efficient device—will use 100 gallons ( 380 liters ) of fuel in a race.
Light Is Often Faster
It’s not an exact science, but the aim of Lenovo’s AI group is to make it while close to one as possible. The team may estimate more accurately the amount of energy delivered if RCR may track how long the gas cans were connected to its cars, it figured.
That was the brief. In order to determine when a car has entered the box and start a real-time videofeed, Novo developed a system that used in-car transponders and a camera mounted above RCR’s pitbox.
According to Sachin Wani, a Lenovo AI data scientist,” an AI engine looks at each frame and determines whether the fuel can is plugged or unplugged.” ” We’re working at 30 frames per second, so the information is accurate to within about 0.03 seconds. The fuel man was aware of this prior to the incident that he had to pump in about seven seconds worth of fuel without using any tools to assist because of safety concerns.
” So, basically it came down to mental calculations, which meant that seven seconds could become eight or nine. Or worse still, five or six. That obviously messes up the strategy, and creates a situation where they’ve short-fueled and need to make another pit stop”, says Wani.
It’s a numbers game, with Lenovo’s pit-stop AI now doing lots of the heavy lifting. During a pit stop, approximately 11 gallons of premium race juice will flow into the tank when the car is plugged into a can. The fuel man can switch to a second fuel can when the tire change goes from left to right. A Nascar fuel cell holds 20 gallons ( 76 liters ). A liter of fuel, depending on its exact composition, weighs approximately 0.75 kilograms. It’s obvious how even an extra second of refueling can negatively impact the car’s weight and competitiveness. Motorsport racing is all about fine margins. Lighter is always faster.
Nascar Numbers Game
” The AI provides the teams with more confidence in the numbers”, RCR’s technical director, Eric Kominek, says. The teams can calculate fuel mileage to within 100 feet using telemetry data and precise fuel additions. The AI fuel flow numbers are very helpful, whether the teams are attempting to ensure they do n’t have to wait on fuel during the next stop or find their best finishing position for a stage or race end.
Sachin Wani claims Lenovo tested its Nascar AI helper on a personal dataset before improving it to the highest level of accuracy. ” We looked at all sorts of different weather conditions, night races, and so on. When the driver enters the pitbox, he might overstep his mark. So there were lots of scenarios to consider. We spent most of 2023 training the AI model for the 2024 season”, says Wani.
And the work did n’t stop there. Wai claims that his team is constantly working on improving the AI model and looking into other time-sensitive issues. To further optimize fuel flow, it includes determining the precise angle at which the fuel can is attached. Additionally, they intend to mount GoPros on the tire crew to check whether the single lug nuts on the wheels have been sufficiently tightened during a pit stop.
” None of us here were big Nascar fans before this project”, admits David Ellison, Lenovo’s chief data scientist,” so we’ve learned a lot, and really respect how the teams operate as a result”.
