Chalmers Researchers Innovate AI-Driven Charging to Extend EV Battery Life

Recent research from Chalmers University of Technology in Gothenburg has unveiled an AI-based charging strategy that could extend the lifespan of electric vehicle (EV) batteries by 23%, particularly during frequent fast charging. While EV batteries typically degrade faster under fast charging due to increased risk of lithium plating and cell wear, the new software update smartly adjusts the charging current based on the battery's chemistry and health conditions, significantly reducing harmful chemical reactions without substantially increasing charging time. The approach uses reinforcement learning to optimize charging actions, a method praised by Professor Changfu Zou and former Chalmers researcher Meng Yuan, now at Victoria University in New Zealand. Yuan noted, "We show that it is possible to charge almost as quickly as today, but with significantly less long-term degradation of the battery." This AI method is also designed for easy integration with existing battery management systems via software updates and can be calibrated for various battery types using transfer learning. Next steps involve physical testing of the technology to confirm its benefits, with the goal of advancing the electrification of transportation by enhancing battery durability and performance.