Summary
Over the past decades, aviation has become an essential component of today’s globalized world: before the current pandemic of coronavirus disease 2019 (COVID-19), over 100,000 flights took off everyday worldwide, and a number of studies indicate that after the pandemic its relevance in the transportation mix will be similar to that before COVID-19. Aviation alone is responsible for 12% of the carbon dioxide emissions from the whole transportation sector, and for 3% of the total CO2 emissions in the world. Due to the major environmental and economical impacts associated to aviation, there is a pressing need for improving the aerodynamic performance of airplane wings to reduce fuel consumption and emissions. This implies reducing the force parallel to the incoming flow, i.e. the drag, and one of the strategies to achieve such a reduction is to perform flow control.
DEEPCONTROL aims at using high-fidelity simulations and deep reinforcement learning to develop a framework for real-time prediction and control of the flow around wing sections and three-dimensional wings based only on sparse measurements. We will first perform high-order spectral-element simulations of wing sections and three-dimensional wings at high Reynolds numbers. Using sparse measurements at the wall, we will reconstruct the velocity fluctuations above the wall within a region of interest. To this end, we will employ a generative adversarial network (GAN), together with a fully-convolutional network (FCN) and modal decomposition. Then, we will perform flow control based on deep reinforcement learning (DRL), which will enable discovering novel solutions in terms of flow actuation and design of winglet geometry. In order to assess the robustness of the framework for real-time applications, we will carry out detailed wind-tunnel experiments at KTH.
This framework will constitute a breakthrough in aviation sustainability, and will enable developing more efficient aeronautical solutions worldwide.
DEEPCONTROL aims at using high-fidelity simulations and deep reinforcement learning to develop a framework for real-time prediction and control of the flow around wing sections and three-dimensional wings based only on sparse measurements. We will first perform high-order spectral-element simulations of wing sections and three-dimensional wings at high Reynolds numbers. Using sparse measurements at the wall, we will reconstruct the velocity fluctuations above the wall within a region of interest. To this end, we will employ a generative adversarial network (GAN), together with a fully-convolutional network (FCN) and modal decomposition. Then, we will perform flow control based on deep reinforcement learning (DRL), which will enable discovering novel solutions in terms of flow actuation and design of winglet geometry. In order to assess the robustness of the framework for real-time applications, we will carry out detailed wind-tunnel experiments at KTH.
This framework will constitute a breakthrough in aviation sustainability, and will enable developing more efficient aeronautical solutions worldwide.
Unfold all
/
Fold all
More information & hyperlinks
| Web resources: | https://cordis.europa.eu/project/id/101043998 |
| Start date: | 01-04-2022 |
| End date: | 31-03-2027 |
| Total budget - Public funding: | 1 999 748,00 Euro - 1 999 748,00 Euro |
Cordis data
Original description
Over the past decades, aviation has become an essential component of today’s globalized world: before the current pandemic of coronavirus disease 2019 (COVID-19), over 100,000 flights took off everyday worldwide, and a number of studies indicate that after the pandemic its relevance in the transportation mix will be similar to that before COVID-19. Aviation alone is responsible for 12% of the carbon dioxide emissions from the whole transportation sector, and for 3% of the total CO2 emissions in the world. Due to the major environmental and economical impacts associated to aviation, there is a pressing need for improving the aerodynamic performance of airplane wings to reduce fuel consumption and emissions. This implies reducing the force parallel to the incoming flow, i.e. the drag, and one of the strategies to achieve such a reduction is to perform flow control.DEEPCONTROL aims at using high-fidelity simulations and deep reinforcement learning to develop a framework for real-time prediction and control of the flow around wing sections and three-dimensional wings based only on sparse measurements. We will first perform high-order spectral-element simulations of wing sections and three-dimensional wings at high Reynolds numbers. Using sparse measurements at the wall, we will reconstruct the velocity fluctuations above the wall within a region of interest. To this end, we will employ a generative adversarial network (GAN), together with a fully-convolutional network (FCN) and modal decomposition. Then, we will perform flow control based on deep reinforcement learning (DRL), which will enable discovering novel solutions in terms of flow actuation and design of winglet geometry. In order to assess the robustness of the framework for real-time applications, we will carry out detailed wind-tunnel experiments at KTH.
This framework will constitute a breakthrough in aviation sustainability, and will enable developing more efficient aeronautical solutions worldwide.
Status
SIGNEDCall topic
ERC-2021-COGUpdate Date
09-02-2023
Images
No images available.
Geographical location(s)
