Researchers in the UK have designed a machine learning method that can predict battery health with 10 times the accuracy of industry standard approaches and made the code freely available.
The researchers from Cambridge and Newcastle Universities, working on a Faraday Institute project, used a new way of monitoring batteries by sending electrical pulses into them and measuring the response. The measurements are then processed by a machine learning algorithm to predict battery health and useful lifespan. Their method is non-invasive and is a simple add-on to any existing battery system. The results are reported in the journal Nature Communications.
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. Battery performance degrades as a result of 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 shorten a battery’s performance and lifespan signficantly.
Current methods for predicting battery health are based on tracking the current and voltage during battery charging and discharging. This misses 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 they 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 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.”
Next: Battery health AI code on Github
The researchers designed a way to monitor batteries by sending electrical pulses into it and measuring its response. A machine learning model was used to discover specific features in the electrical response to detect 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. Team has released the code on GitHub.
The key is that the model can estimate the capacity and health of batteries cycled at three constant temperatures, at any point of its life, from a single impedance measurement.
The researchers also showed that the machine learning model can be interpreted to give hints about the physical mechanism of degradation. The model can inform which electrical signals are most correlated with aging, which in turn allows them to design specific experiments to probe why and how batteries degrade.
“Machine learning complements and augments physical understanding,” said co-first author Dr 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 the platform to understand degradation in different battery chemistries. They are also using the platform to develop optimal battery charging protocols.
The technical storage or access is strictly necessary for the legitimate purpose of enabling the use of a specific service explicitly requested by the subscriber or user, or for the sole purpose of carrying out the transmission of a communication over an electronic communications network.
The technical storage or access is necessary for the legitimate purpose of storing preferences that are not requested by the subscriber or user.
The technical storage or access that is used exclusively for statistical purposes.The technical storage or access that is used exclusively for anonymous statistical purposes. Without a subpoena, voluntary compliance on the part of your Internet Service Provider, or additional records from a third party, information stored or retrieved for this purpose alone cannot usually be used to identify you.
The technical storage or access is required to create user profiles to send advertising, or to track the user on a website or across several websites for similar marketing purposes.