Scientists at Stanford University are harnessing machine learning (ML) to design better batteries. In addition to using ML to speed up scientific analysis by looking for patterns in data, the researchers combined it with knowledge gained from experiments and equations guided by physics to discover and explain a process that shortens the lifetimes of fast-charging lithium-ion batteries.
“It was the first time this approach, known as scientific machine learning, has been applied to battery cycling,” said Professor Will Chueh, who led the study. He said the results overturn long-held assumptions about how lithium-ion batteries charge and discharge, and give researchers a new set of rules for engineering longer-lasting batteries.
The research, reported in Nature Materials, is the latest result from a collaboration between Stanford, SLAC, MIT and Toyota. The goal is to bring together foundational research and industry know-how to develop a long-lasting EV battery that can be charged in 10 minutes.
The new study builds on two previous efforts in which the group used more conventional forms of ML to accelerate both battery testing and the process of winnowing down many possible charging methods to find the ones that work best. While these studies allowed researchers to make much faster progress—reducing the time needed to determine battery lifetimes by 98%, for instance—they didn’t reveal the underlying physics or chemistry that made some batteries last longer than others, as the latest study did.
Combining all three approaches could potentially slash the time needed to bring a new battery technology from the lab bench to the consumer by as much as two thirds, Chueh said.
“In this case, we are teaching the machine how to learn the physics of a new type of failure mechanism that could help us design better and safer fast-charging batteries,” Chueh said.
Source: Stanford University
Image: Jacqueline Orrell/SLAC National Accelerator Laboratory