Shape optimization in laminar flow with a label-guided variational autoencoder
This addresses computational design optimization in fluid dynamics, but it is incremental as it applies existing methods to a specific domain.
The paper tackled the problem of minimizing an object's drag coefficient in laminar flow by predicting drag directly from shape, using a Bayesian optimization approach with a variational autoencoder and Gaussian process regression, resulting in improved shapes in 2D cases.
Computational design optimization in fluid dynamics usually requires to solve non-linear partial differential equations numerically. In this work, we explore a Bayesian optimization approach to minimize an object's drag coefficient in laminar flow based on predicting drag directly from the object shape. Jointly training an architecture combining a variational autoencoder mapping shapes to latent representations and Gaussian process regression allows us to generate improved shapes in the two dimensional case we consider.