BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//talks.cam.ac.uk//v3//EN
BEGIN:VTIMEZONE
TZID:Europe/London
BEGIN:DAYLIGHT
TZOFFSETFROM:+0000
TZOFFSETTO:+0100
TZNAME:BST
DTSTART:19700329T010000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0100
TZOFFSETTO:+0000
TZNAME:GMT
DTSTART:19701025T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
CATEGORIES:Machine learning in Physics\, Chemistry and Materi
 als discussion group (MLDG)
SUMMARY:Identifying degradation patterns of Li-ion batteri
 es from impedance spectroscopy using machine learn
 ing - Yunwei Zhang 	
DTSTART;TZID=Europe/London:20200120T170000
DTEND;TZID=Europe/London:20200120T173000
UID:TALK137578AThttp://talks.cam.ac.uk
URL:http://talks.cam.ac.uk/talk/index/137578
DESCRIPTION:Forecasting the state of health and remaining usef
 ul life of Li-ion batteries is yet an unsolved cha
 llenge that limits technologies such as consumer e
 lectronics and electric vehicles. We build an accu
 rate battery forecasting system by combining elect
 rochemical impedance spectroscopy – a real-time\, 
 non-invasive and information-rich measurement that
  is hitherto underused in battery diagnosis – with
  Gaussian process machine learning. We collected o
 ver 20\,000 EIS spectra of commercial Li-ion batte
 ries at different states of health (SoH)\, states 
 of charge (SoC) and temperatures – the largest dat
 aset to our knowledge of its kind. Our Gaussian pr
 ocess model takes the entire spectrum as input\, w
 ithout manual feature engineering\, and automatica
 lly determines which spectral features predict deg
 radation. Our model significantly outperforms the 
 state of the art\, accurately predicting remaining
  useful life (RUL) even when the past operating co
 nditions of the battery are unknown to the user. T
 he model can be interpreted to shed light on the p
 hysical mechanisms of battery degradation. Our res
 ults are uniquely able to design the next-generati
 on intelligent battery management systems which wo
 uld enable a considerably safer operation of Li-io
 n batteries.
LOCATION:Mott Seminar (531) room\, top floor of the Mott Bu
 ilding\, in the Cavendish Laboratory\, West Cambri
 dge.
CONTACT:Bingqing Cheng 
END:VEVENT
END:VCALENDAR