Shape optimization in laminar flow with a label-guided variational autoencoder
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Dec 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 1; 2023: 2.
5 papers.
- 2023Constrained Bayesian Optimization for Automatic Underwater Vehicle Hull Designcited by 9
- 2023Sample-Efficient and Surrogate-Based Design Optimization of Underwater Vehicle Hullscited by 4
- 2021A machine learning approach for fighting the curse of dimensionality in global optimizationcited by 1
- 2021Analyzing High-Resolution Clouds and Convection using Multi-Channel VAEscited by 1
- 2022Heat Conduction Plate Layout Optimization using Physics-driven Convolutional Neural Networkscited by 0
- 2023Sample-Efficient and Surrogate-Based Design Optimization of Underwater Vehicle Hulls24 Apr 2023
- 2023Constrained Bayesian Optimization for Automatic Underwater Vehicle Hull Design28 Feb 2023
- 2022Heat Conduction Plate Layout Optimization using Physics-driven Convolutional Neural Networks21 Jan 2022
- 2021Analyzing High-Resolution Clouds and Convection using Multi-Channel VAEs1 Dec 2021
- 2021A machine learning approach for fighting the curse of dimensionality in global optimization28 Oct 2021