How BMW uses AI to make vehicle assembly more efficient

Artificial intelligence is making an enormous effect on the auto industry.

Revenue from sales of autonomous vehicles is anticipated to top $70 billion by 2033, in line with Future Market Insights. But self-driving cars powered by AI usually are not the one change — AI technology is already being infused into vehicle production. 

As a part of that industry-wide trend, the BMW Group is now shifting gears to rely more heavily on AI to create a leaner and more efficient manufacturing process. 

Inside BMW’S plant Spartanburg in South Carolina.

CNBC

Over the past few years, BMW has upgraded its Spartanburg, South Carolina, plant to incorporate latest AI capabilities. The factory spans greater than 8 million square feet and produces about 60% of all BMWs sold within the U.S. That works out to greater than 1,500 vehicles produced each day.

Within the body shop, robots weld between 300 and 400 metal studs onto the frame of each SUV. That is about half 1,000,000 studs every day applied by machines and now managed by AI. 

The assembly line inside BMW’s plant Spartanburg.

CNBC

Further down the road, AI technology checks to make sure every stud is precisely placed, in line with BMW Group Manager Curtis Tingle. If a stud is misplaced, the system tells the robots to correct it. No human intervention is required.

“It’s a totally closed loop,” Tingle told CNBC. “[AI] removes the human pondering, the human manual intervention, directly out of the equation.”

Tingle said the brand new technology has dramatically improved efficiency. “We’re achieving five times of what we thought was even possible before, with what the AI is achieving now.”

A BMW employee on the AI Stud Correction Station.

CNBC

In response to Tingle, the AI stud correction laser has already saved the corporate greater than $1 million a yr. The brand new tech, he said, has allowed BMW to remove six staff from the road and redeploy them to other jobs on the factory.

BMW told CNBC the AI technology is patent pending and was developed contained in the Spartanburg plant.

On the factory floor, BMW Group’s IT Project Lead Camille Roberts explains latest AI software helps speed up the automaker’s existing inspection process.

As SUVs move down the road, 26 different cameras throughout the ground snap photos. That is when, in line with Roberts, “the AI kicks in, identifying issues and flagging them for a human to repair,” thus stopping an imperfect vehicle from getting shipped out.

BMW’S AIQX camera inspecting vehicles.

cnbc

Roberts told CNBC that before the brand new AI upgrade, human staff couldn’t check every vehicle to the extent they will now, adding, “it’s not likely humanly possible to examine each automobile. … The production numbers just would not meet the worldwide demand.” 

Oliver Bilstein, BMW Group’s vice chairman of logistics and production control, said there’s still room to run for BMW’s AI technology.

Staff on the plant wear what Bilstein calls factory scanner devices that take measurements and high-resolution images of each centimeter of the factory.

Those images are used to construct a 3D “digital twin” of the plant, allowing BMW to immediately make adjustments and understand how it’s going to affect production before it implements a change in the true world, Bilstein said. BMW factory planners world wide can access those detailed plans online. 

With the assistance of recent AI software, the scanning process now takes days as an alternative of months, Bilstein said.

Eventually, such a AI technology will have the ability to learn, by itself, discover and recommend latest ways to make the BMW Group’s automated assembly line much more efficient, he said.