ICML 2018

Our ICML paper about our approach to Aerodynamic shape optimisation.

This new contribution using the Geometric Deep Learning methods, improves upon previously used Kriging-based surrogate models for CFD optimization.

The full paper can be downloaded here.

Online Pressure and Drag prediction with GCNN.

Optimization Results

Optimization of a foil with control points.
Optimization of a Foil in 3D.
Shape Optimisation using Geodesic Convolutional Networks.Finding the most aerodynamic shape around a sphere.

Finding the most aerodynamic shape around a sphere.

Pin It on Pinterest