BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260605T154541Z
LOCATION:Plenary Room (Bldg. 6 - 001)
DTSTART;TZID=Europe/Stockholm:20260629T194500
DTEND;TZID=Europe/Stockholm:20260629T194600
UID:submissions.pasc-conference.org_PASC26_sess124_pos107@linklings.com
SUMMARY:P24 - A Machine Learning Framework for CFD Applications
DESCRIPTION:Masumeh Gholamisheeri, Harry Durnberger, Tim Powell, and Jony 
 Castagna (STFC)\n\nIn the present study, an automated framework is prepare
 d that contains two modules, Computational Fluid Dynamics (CFD) simulation
 s and surrogate modelling. CFD simulations are performed to model and make
  thermal assessment of battery air cooling in different air stream conditi
 ons (i.e. stream velocity and initial temperature) and various battery cel
 l generated heat. OpenFoam open-source code is used for the simulations. T
 he surrogate modelling is used with a primary aim to train a predictive mo
 del that approximates the outcome of the CFD simulation based on previousl
 y provided CFD data. Due to limited number of CFD results and having the r
 esults as a smooth function of the input data, surrogate model is built ba
 sed on Gaussian Process Regression (GPR). Quantities of Interest (QoI) wer
 e inlet velocity, initial temperature and heat source for battery heat gen
 eration. This method can also be useful for exploring large parameter spac
 es, performing sensitivity analyses, or enabling faster design iterations,
  where running many full CFD simulations would be too costly or time-consu
 ming. It is noteworthy that machine learning is applied to the averaged da
 ta and not the instantaneous fluctuations. Hence, the predictions are made
  for the trend and not the seasonality of the result.\n\nSession Chair: Mi
 roslava Nedyalkova (University of Fribourg)\n\n
END:VEVENT
END:VCALENDAR