New Energy World™
New Energy World™ embraces the whole energy industry as it connects and converges to address the decarbonisation challenge. It covers progress being made across the industry, from the dynamics under way to reduce emissions in oil and gas, through improvements to the efficiency of energy conversion and use, to cutting-edge initiatives in renewable and low-carbon technologies.
AI extends EV battery lifetime by nearly 23%
18/5/2026
News
Researchers at Chalmers University of Technology in Sweden say they have developed an AI-based charging method capable of extending electric vehicle (EV) battery lifetime by nearly 23%.
In a new study, the team reports a 22.9% increase in battery lifespan compared with standard charging approaches, without increasing charging time.
‘We demonstrate that it is possible to charge just as fast as today, but with substantially less long-term degradation,’ said Meng Yuan, a researcher at the Department of Electrical Engineering, Chalmers.
Battery lifetime was measured in equivalent full cycles (EFCs) – the number of complete charge and discharge cycles a battery can undergo before its capacity falls to 80% of its original level, typically considered the end of life for EV use.
Using the new method, the battery was able to sustain a higher number of full cycles than under conventional charging. At the same time, charging time remained virtually unchanged: 24.12 minutes on average, compared to 24.15 minutes for the standard method.
Fast charging is known to accelerate battery degradation because high currents can trigger side reactions inside the cell. One of the most significant is lithium plating, where metallic lithium builds up on the electrode, reducing capacity and, in some cases, affecting safety.
Conventional charging strategies use fixed voltage and current limits, regardless of the battery’s age or condition.
In the study, researchers instead used reinforcement learning, a form of machine learning in which an algorithm learns by interacting with its environment. In this case, the system was trained to optimise charging in real time, balancing speed with long-term battery health.
‘This work shows that the true bottleneck of fast charging is not simply current limits, but the evolving electrochemical state inside the battery,’ commented Changfu Zou, Professor at the Department of Electrical Engineering. By integrating AI with physics-based understanding, we move closer to health-aware charging strategies that maximise both performance and lifetime.’
The resulting charging strategy dynamically adjusts to the battery’s condition, rather than applying a fixed profile.
According to the researchers, the approach could potentially be implemented through software updates to existing battery management systems, without requiring additional hardware.
The team said further work is needed to adapt the method to different battery chemistries and to validate the approach in real-world conditions.
