BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Identifying degradation patterns of lithium ion batteries from imp
 edance spectroscopy using machine learning - Yunwei Zhang\, Sun Yat-sen Un
 iversity
DTSTART:20220530T133000Z
DTEND:20220530T140000Z
UID:TALK173192@talks.cam.ac.uk
CONTACT:Dr Christoph Schran
DESCRIPTION:Forecasting the state of health and remaining useful life of L
 i-ion batteries is an unsolved challenge that limits technologies such as 
 consumer electronics and electric vehicles. In this talk\, I will introduc
 e our recent work on how to use AI techniques to improve battery health an
 d safety. We built an accurate battery forecasting system by combining ele
 ctrochemical impedance spectroscopy (EIS)—a real-time\, non-invasive and
  information-rich measurement that is hitherto underused in battery diagno
 sis—with Gaussian process machine learning. Over 20\,000 EIS spectra of 
 commercial Li-ion batteries were collected to train the model\, the larges
 t data of this kind. The model takes the entire spectrum as input\, withou
 t further feature engineering\, and automatically determines which spectra
 l features predict degradation from irrelevant noise. Our model accurately
  predicts the remaining useful life and can be interpreted to give hints a
 bout the physical mechanism of degradation. Our results demonstrate the va
 lue of EIS signals in battery management systems.
LOCATION:https://zoom.us/j/92447982065?pwd=RkhaYkM5VTZPZ3pYSHptUXlRSkppQT0
 9
END:VEVENT
END:VCALENDAR