“Battery lifetime and aging dynamics vary significantly with chemistry, operating conditions, cycling demands, electrode design, and operational history, which makes optimal handling, design, and maintenance difficult,” researcher Kandler Smith said in the summary. He leads the lab’s electrochemical modeling and data science research.
“It’s especially difficult to understand the physical degradation mechanisms of a battery during use without opening it up. We need reliable methods to check in on batteries’ internal state in a nondestructive way,” Smith added.
The lab’s approach replaces the common physics-based model with what’s called a physics-informed neural network, or PINN. It also uses artificial intelligence. It’s geared to quantify degradation and provide better solutions to manage battery aging during cycling, per the release.