Play Video

A.I. speeds up battery testing for electric vehicles

A new machine learning-based method cuts the time it takes to test batteries for electric vehicles by 98%. "With AI, we're able to quickly identify the most promising approaches and cut out a lot of unnecessary experiments." (Credit: Getty Images)

Researchers have used artificial intelligence to slash battery testing times—a key barrier to longer-lasting, faster-charging batteries for electric vehicles.

Battery performance can make or break the electric vehicle experience, including driving range, charging time, and the lifetime of the car. Now, AI has made the dream of recharging an EV in the time it takes to stop at a gas station a more likely reality, researchers report. It could also help improve other aspects of battery technology.

For decades, evaluation times have caused a major bottleneck in advances in electric vehicle. At every stage of the battery development process, researchers must test new technologies for months or even years to determine how long they will last.

But now, researchers have developed a machine learning-based method that cuts these testing times by 98%. Although the group tested their method on battery charge speed, they say it can apply to it 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,” says Stefano Ermon, an assistant professor of computer science at Stanford University who led the project with William Chueh, associate professor of materials science and engineering. “With AI, we’re able to quickly identify the most promising approaches and cut out a lot of unnecessary experiments.”

Trial and error battery testing

The goal of the study in Nature was finding the best method for charging an EV battery in 10 minutes that maximizes the battery’s overall lifetime. The researchers wrote a program 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 charging approaches to focus on or ignore.

Reducing both the length and number of trials, allowed the researchers to cut the testing process from almost two years to 16 days.

“Machine learning is trial-and-error, but in a smarter way.”

“We figured out how to greatly accelerate the testing process for extreme fast charging,” says Peter Attia, who co-led the study while 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.”

Designing ultra-fast-charging batteries is a major challenge, mainly because it is difficult to make them last. The intensity of the faster charge puts greater strain on the battery, which often causes it to fail early. To prevent this damage to the battery pack, a component that accounts for a large chunk of an electric car‘s total cost, battery engineers must test an exhaustive series of charging methods to find the ones that work best.

The new research sought to optimize this process. At the outset, the team saw that fast-charging optimization amounted to 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,” says 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.”

Machines vs. humans

The team used this power to their advantage in two key ways. First, they used it to reduce the time per cycling experiment. In a previous study, the researchers found that instead of charging and recharging every battery until it failed—the usual way of testing a battery’s lifetime—they could predict how long a battery would last after only its first 100 charging cycles. That’s because the machine learning system, after researchers trained it on a few batteries cycled to failure, could find patterns in the early data that presaged how long a battery would last.

Second, machine learning reduced the number of methods they had to test. Instead of testing every possible charging method equally, or relying on intuition, the computer learned from its experiences to quickly find the best protocols to test.

By testing fewer methods for fewer cycles, the researchers quickly found an optimal ultra-fast-charging protocol for their battery. In addition to dramatically speeding up the testing process, the computer’s solution proved better—and much more unusual—than what a battery scientist would likely have devised, Ermon says.

“It gave us this surprisingly simple charging protocol—something we didn’t expect,” Ermon says. “That’s the difference between a human and a machine: The machine is not biased by human intuition, which is powerful but sometimes misleading.”

More than electric vehicles

The researchers say their approach could accelerate nearly every piece of the battery development pipeline: from designing the chemistry of a battery to determining its size and shape, to finding better systems for manufacturing and storage.

This would have broad implications not only for electric vehicles but for other types of energy storage, a key requirement for making the switch to wind and solar power on a global scale.

“This is a new way of doing battery development,” says coauthor Patrick Herring, a scientist at the Toyota Research Institute. “Having data that you can share among a large number of people in academia and industry, and that is automatically analyzed, enables much faster innovation.”

The researchers will make the study’s machine learning and data collection system available for future battery scientists to freely use, Herring says. Using the system to optimize other parts of the process with machine learning, battery development—and the arrival of newer, better technologies—could accelerate by an order of magnitude or more, he says.

The potential of the study’s method extends even beyond the world of batteries, Ermon says. Other big data testing problems, such as drug development and optimizing the performance of X-rays and lasers, could also benefit from machine learning optimization. And ultimately, he says, it could even help to optimize one of the most fundamental processes of all.

“The bigger hope is to help the process of scientific discovery itself,” Ermon says. “We’re asking: Can we design these methods to come up with hypotheses automatically? Can they help us extract knowledge that humans could not? As we get better and better algorithms, we hope the whole scientific discovery process may drastically speed up.”

Additional coauthors are from MIT, Stanford, and the Toyota Research Institute. Stanford, the Toyota Research Institute, the National Science Foundation, the US Department of Energy, and Microsoft supported the work.

Source: Matthew Vollrath for Stanford University