Best Scientific Paper Award from the American Institute of Aeronautics and Astronautics 2024 Multidisciplinary Design Optimization
Available online :
As part of an international collaboration between EPFL, the Hong Kong University of Science and Technologyg and ISAE-SUPAERO, six researchers have been awarded the AIAA Best Scientific Paper Award for their paper “DeepGeo: Deep Geometric Mapping for Automated and Effective Parameterization in Aerodynamic Shape Optimization”.
The DeepGeo model proposes an innovative, fully automated, neural network-based approach to generating the mesh required for complex non-parametric geometries.
This AI model, coupled with a numerical simulation code, considerably reduces the trial-and-error phases involved in optimizing an object’s physical performance. It opens up new prospects for aerodynamic design research and for the development of sustainable aeronautics solutions.
The authors:
- Zhen Wei, EPFL
- Aobo Yang, The Hong Kong University of Science and Technology
- Jichao Li, Institute of High Performance Computing, A*STAR
- Michaël Bauerheim, ISAE-SUPAERO
- Rhea P. Liem, The Hong Kong University of Science and Technology
- Pascal Fua, EPFL
To read the article: https://infoscience.epfl.ch/entities/publication/b3fd399e-a66f-433d-b066-c44d454ec9bd
Michaël Bauerheim, associate professor at DAEP
Michaël Bauerheim is an associate professor at ISAE-SUPAERO, the University of Sherbrooke (Canada) and an AI consultant.
His research at DAEP focuses on aeroacoustics and high-performance learning for aeronautical flow physics. In this field, he is exploring the potential of AI techniques (deep and/or reinforcement learning) to solve fluid mechanics problems for which conventional methods fail, or have shown their limitations.
He is also working on fluid-structure interactions, bio-inspired aerodynamics and Lattice-Boltzmann methods in various projects.
More information on his work: https://pagespro.isae-supaero.fr/michael-bauerheim/