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:20230831T095745Z
LOCATION:Davos
DTSTART;TZID=Europe/Stockholm:20230626T112000
DTEND;TZID=Europe/Stockholm:20230626T115000
UID:submissions.pasc-conference.org_PASC23_sess104_pos163@linklings.com
SUMMARY:P09 - Analyzing Physics-Informed Neural Networks for Solving Class
 ical Flow Problems
DESCRIPTION:Poster\n\nRishabh Puri (Forschungszentrum Jülich); Mario Rüttg
 ers (Forschungszentrum Jülich, RWTH Aachen University); and Rakesh Sarma a
 nd Andreas Lintermann (Forschungszentrum Jülich)\n\nThe application of Neu
 ral Networks (NNs) has been extensively investigated for fluid dynamic pro
 blems. A specific form of NNs are Physics-Informed Neural Networks (PINNs)
 , which incorporate physics-based embeddings to account for physical laws.
  In this work, the performance of PINNs is compared to that of DNNs with r
 espect to accuracy. Therefore, results obtained from PINNs and DNNs are co
 mpared to analytical solutions of four classical flow problems - Poiseuill
 e flow, potential flow around cylinder and Rankine oval, and Blasius bound
 ary layer flow. The findings show that the PINNs provide more accurate rep
 resentations of the flow fields than their DNN counterpart for potential f
 low around a cylinder and Blasius boundary layer flow. The investigations 
 show that in some flow problems, inclusion of information on problem physi
 cs, governing equations, and boundary conditions in the loss function of a
 n NN can improve prediction accuracy of NNs. Since PINNs are computational
 ly expensive compared to DNNs, it is also investigated if the accuracy ach
 ieved with PINNs over DNNs is significantly high to justify the additional
  computation costs that are associated with their training.\n\nSession Cha
 ir: Elaine M. Raybourn (Sandia National Laboratories)
END:VEVENT
END:VCALENDAR