Machine learning slashes battery fast charging scheme development time

March 20, 2020 //By Nick Flaherty
From left, Stanford Professor William Chueh, Toyota Research Institute scientist Muratahan Aykol, Stanford PhD student Aditya Grover, Stanford PhD alumnus Peter Attia, Stanford Professor Stefano Ermon and TRI scientist Patrick Herring. (Image credit: Farrin Abbott)
Machine learning has cut the time taken to develop a fast charging scheme for electric vehicle batteries from two years to 16 days.

Researchers from Stanford University, MIT and the Toyota Research Institute in the US have used machine learning to cut the fast charging time for electric vehicle and energy storage batteries dramatically.

The group initially tested their method on battery charge speed, and said it can be applied to numerous other parts of the battery development pipeline and even to non-energy technologies.

“In battery testing, you have to try a massive number of things, because the performance you get will vary drastically,” said Stefano Ermon, an assistant professor of computer science. “With AI, we’re able to quickly identify the most promising approaches and cut out a lot of unnecessary experiments.”

The researchers wrote a machine learning framework that, based on only a few charging cycles, predicted how batteries would respond to different charging approaches. The software also decided in real time what fast charging approaches to focus on or ignore. By reducing both the length and number of trials, the researchers cut the testing process from almost two years to 16 days.

“We figured out how to greatly accelerate the testing process for extreme fast charging,” said Peter Attia, who co-led the study while he was a graduate student. “What’s really exciting, though, is the method. We can apply this approach to many other problems that, right now, are holding back battery development for months or years.”

Fast charging optimization uses many trial-and-error tests, something that is inefficient for humans, but the perfect problem for a machine. “Machine learning is trial-and-error, but in a smarter way,” said Aditya Grover, a graduate student in computer science who also co-led the study. “Computers are far better than us at figuring out when to explore – try new and different approaches – and when to exploit, or zero in, on the most promising ones.”


Vous êtes certain ?

Si vous désactivez les cookies, vous ne pouvez plus naviguer sur le site.

Vous allez être rediriger vers Google.