Scientists at Stanford University had an interesting thought. What if, they asked we could accurately predict which lithium battery lifespans would last longer? It would be nice to be able to distribute the best ones to phones and electric batteries. We would have problems with that because we are all supposed to be equal. However, if their method brought better batteries to market sooner that would be another thing.
How AI Shed a New Light on Lithium Battery Lifespans
The scientists invited Massachusetts Institute of Technology and Toyota Research Institute to join their efforts. Together, they found a way to apply artificial intelligence to comprehensive experimental data.
They loaded their AI machine with “a few hundred million data points of batteries charging and discharging.” This produced an algorithm able to predict how long each lithium battery would last, “based on voltage declines and other cycles”. Those predictions were within 9% of how many cycles each battery actually sustained.
The Research Team Have Placed Their Data in the Public Domain
Their system also sorted new batteries into short- and long-life lithium battery lifespans after the first five charge / discharge events. This information could fast track new battery designs, and get them to market faster. Accordingly the researchers have made their dataset – the biggest in the world – publicly available.
“For all of the time and money that gets spent on battery development, progress is still measured in decades.” So says study co-author Patrick Herring, a scientist at Toyota Research Institute. “In this work, we are reducing one of the most time-consuming steps – battery testing – by an order of magnitude.”
The research team has shifted its attention to charging batteries faster using the information they harvested. They hope to reduce this rate by “more than a factor of 10”.
Related
Phone Battery Lifespan & How to Extend It
Secret Life of Lithium-Rich Batteries Revealed
Preview Image: MIT prof Richard Braatz and William Chueh, assistant prof at Stanford
Video Share Link: https://youtu.be/ah3yJrPzZsw
