English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

We present a novel deep learning framework for flow field predictions inirregular domains when the solution is a function of the geometry of either thedomain or objects inside the domain. Grid vertices in a computational fluiddynamics (CFD) domain are viewed as point clouds and used as inputs to a neuralnetwork based on the PointNet architecture, which learns an end-to-end mappingbetween spatial positions and CFD quantities. Using our approach, (i) thenetwork inherits desirable features of unstructured meshes (e.g., fine andcoarse point spacing near the object surface and in the far field,respectively), which minimizes network training cost; (ii) object geometry isaccurately represented through vertices located on object boundaries, whichmaintains boundary smoothness and allows the network to detect small changesbetween geometries; and (iii) no data interpolation is utilized for creatingtraining data; thus accuracy of the CFD data is preserved. None of thesefeatures are achievable by extant methods based on projecting scattered CFDdata into Cartesian grids and then using regular convolutional neural networks.Incompressible laminar steady flow past a cylinder with various shapes for itscross section is considered. The mass and momentum of predicted fields areconserved. We test the generalizability of our network by predicting the flowaround multiple objects as well as an airfoil, even though only single objectsand no airfoils are observed during training. The network predicts the flowfields hundreds of times faster than our conventional CFD solver, whilemaintaining excellent to reasonable accuracy.

A Point-Cloud Deep Learning Framework for Prediction of Fluid Flow Fields on Irregular Geometries