Skip to content

Opening book details…

About this document

DeepCFD: CNN for Steady Flow Solutions by Mrinal Manoj is a document available to read on EtoBox.

This document proposes DeepCFD, a convolutional neural network model that can efficiently approximate solutions to the Navier-Stokes equations for steady laminar flows. DeepCFD is trained on ground truth data generated by a computational fluid dynamics (CFD) solver. It can provide solutions for both velocity and pressure fields that are up to 3 orders of magnitude faster than standard CFD, with low error rates. The model aims to accelerate engineering design processes that rely on CFD simulations by allowin

Author
Mrinal Manoj
Language
EN