Researchers at Uppsala University have developed an artificial intelligence model that provides a more accurate picture of battery aging, a breakthrough that could extend the lifespan and safety of electric vehicle (EV) batteries.
Battery degradation is often the first factor limiting an EV’s useful life, creating resource inefficiencies that slow the electrification of transport. To address this, the automotive industry has been developing AI-based software to improve battery management and control systems.
The Uppsala team said their model increases the robustness of battery health predictions by up to 70%. The findings were published in the journal Energy & Environmental Science.
“Being able to learn more about the life and aging of batteries will benefit future control systems in electric vehicles. It also shows how important it is to understand what happens inside the batteries,” said Professor Daniel Brandell, who led the study and heads the Ångström Advanced Battery Center at Uppsala University. “If we stop looking at them as black boxes that are simply expected to provide power, and instead acquire a detailed picture of the processes, we can manage them so that they stay in good condition longer.”
The study, carried out with Aalborg University in Denmark, drew on several years of battery testing. Researchers built a database from very short charging segments, combining it with a detailed model of the chemical processes taking place inside batteries.
“Altogether, this gives us a very precise picture of the various chemical reactions that result in the battery generating power, but also of how it ages during use,” said Wendi Guo, who conducted the study.
The researchers said their method could also help predict safety risks, as many battery failures stem from design flaws or side reactions that can be identified through charge-discharge data.
“The fact that we only use short charging segments is probably an added advantage,” Brandell added. “Battery data from electric vehicles is sensitive, both for the industry and from an anonymization point of view for users. This research shows how far you can get without needing complete datasets.”
Resource:
- Wendi Guo et al, Uncovering the impact of battery design parameters on health and lifetime using short charging segments, Energy & Environmental Science (2025). DOI: 10.1039/D5EE03268G
