Communications of the ACM
Machine Learning Method From Stanford, with Toyota Researchers, Could Supercharge Battery Development for Electric Vehicles
Stanford University researchers, working with colleages at the Massachusetts Institute of Technology and the Toyota Research Institute, have developed a machine learning technique that reduces testing times for electric vehicle batteries by 98%.
Credit: Charged Electric Vehicles Magazine.
Stanford University researchers collaborated with the Massachusetts Institute of Technology and the Toyota Research Institute on a machine learning technique that reduces battery testing times by 98%—a step toward longer-lasting, faster-charging batteries for electric vehicles.
The algorithm predicts batteries' response to different charging approaches based on its first 100 charging cycles, and can determine the best charging protocols to use in real time.
This method accelerates the battery testing process from nearly two years to 16 days.
Stanford's Stefano Ermon said, "The bigger hope is to help the process of scientific discovery itself. We're asking: can we design these methods to come up with hypotheses automatically?"
From Stanford News
View Full Article
Abstracts Copyright © 2020 SmithBucklin, Washington, DC, USA
No entries found