Aeromat

Applying state-of-the-art evolutionary optimization and surrogate modeling techniques to the automated design of aerodynamic structures and vehicles.

Project description

A sustainable energy future requires that we both do more with less, and that we fully exploit the renewable energy sources we have available. In this project we explore a common thread between these two approaches, developing tools to better explore and understand aerodynamic design. On the one hand our tools can be used to improve the performance of aerodynamic vehicles, and on the other improving our ability to harvest energy from wind. We develop automated methods for the design of complete aerodynamic structures, using machine-learning techniques to guide iterative experimentation with novel designs.

We focus on:

  1. Optimization of entire structures, rather than iterative improvement on existing designs
  2. Human-machine collaborative design exploration, to discover innovative design concepts
  3. Inclusion of structural mechanics and fluid structure interaction into the optimization, design, and modeling process
  4. Modeling techniques to support these goals, using data-driven approaches to approximate computationally intensive techniques and simulations

In particular we face challenges when creating tools which address these issues in tandem, such as:

  • modeling the performance of designs produced with non-traditional parameterizations
  • broad exploration of possible designs in computationally demanding contexts
  • optimization and modeling of aerodynamic and structural properties simultaneously

 

Project manager at H-BRS

Prof. Dr Dirk Reith

Computational Science and Engineering
Managing Director of the TREE Institute
Hochschule Bonn-Rhein-Sieg
Email: 
dirk.reith [at] h-brs.de

Co-operating professors

Research associates

Publications

Hochschule Bonn-Rhein-Sieg
Nine of the hundreds of near-optimal designs which vary in volume and curvature, produced in a single run of the surrogate-assisted illumination (SAIL) algorithm.

Aerodynamic Design Exploration through Surrogate-Assisted
Illumination

(Best Student Paper -- Multidisciplinary Design Optimization)
Gaier, Adam, Alexander Asteroth, and Jean-Baptiste Mouret. AIAA Aviation and Aeronautics Forum 2017 

Hochschule Bonn-Rhein-Sieg
An overview of the airfoil design space. Produced through the surrogate-assisted illumination algorithm (SAIL).

Data-Efficient Exploration, Optimization, and Modeling of Diverse Designs through Surrogate-Assisted
Illumination

(Best Paper -- Complex Systems)
Gaier, Adam, Alexander Asteroth, and Jean-Baptiste Mouret. Genetic and Evolutionary Computation Conference 2017

Hochschule Bonn-Rhein-Sieg
Predicting performance based on features rather than parameters.

Hierarchical Surrogate Modeling for Illumination Algorithms
Alexander Hagg. Genetic and Evolutionary Computation Conference 2017

Project publications

Automatisiertes Entwickeln aerodynamischer Strukturen und Fahrzeuge mithilfe evolutionärer Optimierung und Surrogatmodellierung (DE/BMBF/03FH012PX5)

2020 | 2019 | 2018 | 2017

2020

Alexander Hagg, Mike Preuss, Simon Wessing, Alexander Asteroth, Thomas Bäck: An Analysis of Phenotypic Diversity in Multi-Solution Optimization.
URL BibTeX | RIS

Alexander Asteroth, Alexander Hagg, Jakob Meng, Andreas Priesnitz, Lea Prochnau, Dirk Reith: AErOmAt Abschlussbericht.
PDF Download doi:10.18418/opus-4850 urn:nbn:de:hbz:1044-opus-48506 BibTeX | RIS

Adam Gaier, Alexander Asteroth, Jean-Baptiste Mouret: Automating Representation Discovery with MAP-Elites.
arXiv BibTeX | RIS

2019

Alexander Hagg, Martin Zaefferer, Jörg Stork, Adam Gaier: Prediction of neural network performance by phenotypic modeling.
doi:10.1145/3319619.3326815 arXiv BibTeX | RIS

Alexander Hagg, Alexander Asteroth, Thomas Bäck: Modeling User Selection in Quality Diversity.
doi:10.1145/3321707.3321823 arXiv BibTeX | RIS

2018

Alexander Hagg, Alexander Asteroth, Thomas Bäck: Prototype Discovery Using Quality-Diversity.
doi:10.1007/978-3-319-99253-2_40 arXiv BibTeX | RIS

Adam Gaier, Alexander Asteroth, Jean-Baptiste Mouret: Data-Efficient Design Exploration through Surrogate-Assisted Illumination.
doi:10.1162/evco_a_00231 arXiv BibTeX | RIS

Adam Gaier, Alexander Asteroth, Jean-Baptiste Mouret: Data-efficient Neuroevolution with Kernel-Based Surrogate Models.
doi:10.1145/3205455.3205510 arXiv BibTeX | RIS

2017

Adam Gaier, Alexander Asteroth, Jean-Baptiste Mouret: Data-Efficient Exploration, Optimization, and Modeling of Diverse Designs through Surrogate-Assisted Illumination.
doi:10.1145/3071178.3071282 arXiv URL BibTeX | RIS

Adam Gaier, Alexander Asteroth, Jean-Baptiste Mouret: Aerodynamic Design Exploration through Surrogate-Assisted Illumination.
doi:10.2514/6.2017-3330 URL BibTeX | RIS

Alexander Hagg: Hierarchical Surrogate Modeling for Illumination Algorithms.
doi:10.1145/3067695.3082495 arXiv BibTeX | RIS

Alexander Hagg, Maximilian Mensing, Alexander Asteroth: Evolving Parsimonious Networks by Mixing Activation Functions.
doi:10.1145/3071178.3071275 arXiv BibTeX | RIS

Adam Gaier, Alexander Asteroth, Jean-Baptiste Mouret: Feature Space Modeling Through Surrogate Illumination.
arXiv BibTeX | RIS

Sponsors

Co-operation partners