Degradation patterns of lithium ion batteries from impedance spectroscopy using machine learning

Lennard-Jones Centre discussion group seminar by Dr Yunwei Zhang from Sun Yat-sen University.
Forecasting the state of health and remaining useful life of Li-ion batteries is an unsolved challenge that limits technologies such as consumer electronics and electric vehicles. This talk introduces recent work on how to use AI techniques to improve battery health and safety. It builds an accurate battery forecasting system by combining electrochemical impedance spectroscopy (EIS)-a real-time, non-invasive and information-rich measurement that is hitherto underused in battery diagnosis-with Gaussian process machine learning. Over 20,000 EIS spectra of commercial Li-ion batteries are used to train the model, the largest data of this kind. The model takes the entire spectrum as input, without further feature engineering, and automatically determines which spectral features predict degradation from irrelevant noise. The model accurately predicts the remaining useful life and can be interpreted to give hints about the physical mechanism of degradation. The results demonstrate the value of EIS signals in battery management systems.
The seminar was held on 30th May 2022.
🖥️ Check out our websites: linktr.ee/cumaterials

[@DineshKumar-wv1uq]

Thanks a lot. Much informative!

[@energyeve2152]

Thanks for sharing

[@tunahanakan8018]

Danke

[@hidhrmadjido156]

Voll gut danke

[@AayushiKar]

Where can i find the code of this project

[@morthim]

'70% battery life is end of life'
end of life for a thing is when it breaks.

[@Nxck2440]

the voltage drops off very rapidly after falling to ~70% so it is a useful metric for end of life