AI Tech Used to Improve Lithium Battery Health and Safety

A new way to monitor lithium battery by sending electrical pulses into it and measuring the response has been designed by researchers from Cambridge and Newcastle Universities. The measurements are then processed by AI tech to predict the lithium battery's health and useful lifespan. Their method is non-invasive and is a simple add-on to any existing battery system.

AI sometimes called machine intelligence, is intelligence demonstrated by machines, in contrast to the natural intelligence displayed by humans and animals. Leading AI textbooks define the field as the study of "intelligent agents": any device that perceives its environment and takes actions that maximize its chance of successfully achieving its goals.

Predicting the health status and remaining service life of lithium-ion batteries is a major problem that limiting the widespread use of electric vehicles. Over time, battery performance will decline through a series of sophisticated fine chemical processes. Individually, these processes do not have much impact on battery performance, but together, they will severely shorten the performance and life of the battery.

"Safety and reliability are the most important design criteria as we develop batteries that can pack a lot of energy in a small space," said Dr. Alpha Lee from Cambridge's Cavendish Laboratory, who co-led the research. "By improving the software that monitors charging and discharging, and using data-driven software to control the charging process, I believe we can power a big improvement in battery performance."

The researchers devised an AI tech to monitor the battery by sending electrical pulses to the battery and measuring its response. A machine learning model is then used to identify specific features of the electrical response, which are signals of lithium battery aging. The researchers conducted more than 20,000 experimental measurements to train the model. Importantly, the model learns how to distinguish important signals from irrelevant noise. Their method is non-invasive and is a simple additional system.

The researchers also found that AI tech models can be interpreted to give hints about the physical mechanism of degradation. The model can tell which electrical signals are most relevant to aging, which allows them to design specific experiments to explore the causes and methods of lithium battery degradation.

"Machine learning complements and augments physical understanding," said Dr. Yunwei Zhang, one of the first authors, also from the Cavendish Laboratory. "The interpretable signals identified by our machine learning model are a starting point for future theoretical and experimental studies." The results are reported in the journal Nature Communications.

• < Prev
• Next >