BEGIN:VCALENDAR
METHOD:PUBLISH
PRODID:www-matsim-tf-fau-de//Events//EN
VERSION:2.0
BEGIN:VEVENT
SUMMARY:System Identification of physical chemical model of Li-ion cel
 l using deep learing - Sandhra Ganesh
UID:b8717ed5-6cfc-456b-8644-fc17625cb907
DESCRIPTION:Sandhra Ganesh Clean Energy Processes\, FAU 05. August 202
 5\, 11:00 WW8\, Fürth Lithium-ion batteries (LIBs) are essential comp
 onents of electromobility\, where safe\, long-lasting\, and fast-charg
 ing performance is crucial. However\, during fast charging and extende
 d use\, internal degradation phenomena such as lithium plating and los
 s of active material which lead to a decline in capacity and increased
  safety risks. Accurate state estimation for battery management relies
  on high-fidelity physical chemical models with well-calibrated parame
 ters. As the battery ages\, deviations between nominal and true parame
 ter values increase\, necessitating continuous model adaptation throug
 h parameter identification. This thesis presents a deep learning-based
  framework for identifying internal electrochemical parameters of a de
 tailed battery model\, using only external measurements specifically\,
  terminal voltage and current time series data. These quantities are c
 ommonly available from vehicle sensor systems and can serve as non-inv
 asive inputs for tracking internal cell behaviour in real life. A glob
 al sensitivity analysis was performed using synthetic data generated f
 rom a Doyle-Fuller-Newman (DFN) model to determine which parameters si
 gnificantly influence the terminal voltage and are theoretically ident
 ifiable. Based on this analysis and R-square fit of the deep learning 
 model\, a subset of sensitive parameters was selected for training a T
 ransformer-based deep learning model. The model learns the complex\, n
 onlinear mapping from a very short time-series data (300 s) of voltage
  and current time series data. The results show that deep learning pro
 vides a viable and flexible method for dynamic parameter identificatio
 n using only these external measurements. This approach enables improv
 ed model adaptability and accurate state estimation over the battery&#
 8217\;s lifecycle\, paving the way for more robust and data-driven bat
 tery management systems.
DTSTART:20250805T090000Z
DTEND:20250805T100000Z
LOCATION:WW8\, Room 2.018-2\, Dr.-Mack-Str. 77\, Fürth
DTSTAMP:20260503T141433Z
END:VEVENT
END:VCALENDAR