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:20220812T074334Z
LOCATION:Osaka Room
DTSTART;TZID=Europe/Stockholm:20220628T150000
DTEND;TZID=Europe/Stockholm:20220628T153000
UID:submissions.pasc-conference.org_PASC22_sess176_pap109@linklings.com
SUMMARY:Flow Field Prediction on Large Variable Sized 2D Point Clouds with
  Graph Convolution
DESCRIPTION:Paper\n\nFlow Field Prediction on Large Variable Sized 2D Poin
 t Clouds with Graph Convolution\n\nStrönisch, Meyer, Lehmann\n\nComputatio
 nal Fluid Dynamics (CFD) solvers are an important tool to predict the beha
 viour of fluid flows in many industrial sectors. Thereby, accelerating the
  solution process without compromisingon geometric accuracy is a major goa
 l in the development of numerical flow solvers and design optimization fra
 meworks. For tackling the issue of complex geometries, this paper utilizes
  a graph-based machine learning approach for solving the regression proble
 m of stationary fluid flow field prediction. Concretely, a graph convoluti
 onal network (GCN) architecture is applied and successfully predicts flow 
 fields around geometrical different objects. As the GCN model operates on 
 the numerical mesh directly, the exact geometry of the object as well as a
 ll other properties of the mesh are preserved. It turned out that a GCN is
  able to predict fluid flow fields of two-dimensional bluff-bodies and NAC
 A airfoils, even considering predictions based on extrapolation. Furthermo
 re, this approach is able to handle different sizes of point clouds up to 
 50k points. Finally, using the predicted flow field as an initial flow dis
 tribution for a CFD simulation, showed a decreased solver runtime in some 
 cases.\n\nDomain: Engineering, Physics
END:VEVENT
END:VCALENDAR