"Machine learning complements and augments physical understanding. The interpretable signals identified by our machine learning model are a starting point for future theoretical and experimental studies."Yunwei Zhang, University of Cambridge
Researchers in the UK have designed a machine-learning method that can predict battery health with 10 times greater accuracy than the current industry standard, potentially aiding in the development of safer and more reliable batteries for electric vehicles and consumer electronics.
The researchers, from the universities of Cambridge and Newcastle, have designed a new way to monitor batteries by sending electrical pulses into them and measuring the response. The measurements are then processed by a machine-learning algorithm to predict the battery's health and useful lifespan. As the researchers report in a paper in Nature Communications, their method is non-invasive and is a simple add-on to any existing battery system.
Predicting the state of health and the remaining useful lifespan of lithium-ion batteries is one of the big problems limiting widespread adoption of electric vehicles; it's also a familiar annoyance to mobile phone users. Over time, battery performance degrades via a complex network of subtle chemical processes. Individually, each of these processes doesn't have much of an effect on battery performance, but collectively they can severely shorten a battery's performance and lifespan.
Existing methods for predicting battery health are based on tracking the current and voltage during battery charging and discharging, but this can miss important features that indicate battery health. Tracking the many processes that are happening within the battery requires new ways of probing batteries in action, as well as new algorithms that can detect subtle signals as batteries are charged and discharged.
"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 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 designed a way to monitor a battery by sending electrical pulses into it and measuring its response. A machine-learning model is then used to discover specific features in the electrical response that are tell-tale signs of battery aging. The researchers performed over 20,000 experimental measurements to train the model, the largest dataset of its kind. Importantly, the model learns how to distinguish important signals from irrelevant noise.
The researchers also showed that the machine-learning model can be interpreted to give hints about the physical mechanisms of degradation. It can determine which electrical signals are most correlated with aging, which in turn allows the researchers to design specific experiments to probe why and how batteries degrade.
"Machine learning complements and augments physical understanding," said co-first author Yunwei Zhang, 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 researchers are now using their machine-learning platform to understand degradation in different battery chemistries. They are also developing optimal battery charging protocols, powered by machine learning, to allow fast charging and minimize degradation.
This story is adapted from material from the University of Cambridge, with editorial changes made by Materials Today. The views expressed in this article do not necessarily represent those of Elsevier. Link to original source.