Over the past few years, neural networks have arisen great interest in the computational fluid dynamics community, especially when used as surrogate models, either for flow reconstruction, turbulence modeling, or for the prediction of aerodynamic coefficients. This thesis considers using convolutional neural networks, a special category of neural networks designed for images, as surrogate models for steady flow prediction around 2D obstacles. The surrogate models are calibrated in the framework of data fitting, with the data set prepared by high-fidelity solvers to Navier-Stokes equations and projected onto cartesian grids. Once calibrated, the models show high accuracy in terms of velocity and pressure prediction, even around obstacles not...
International audienceThe ubiquity of fluids in the physical world explains the need to accurately s...
In recent years, the development of deep learning is noticeably influencing the progress of computat...
Aircraft design requires a multitude of aerodynamic data and providing this solely based on high-qua...
Over the past few years, neural networks have arisen great interest in the computational fluid dynam...
Computational Fluid Dynamics (CFD) simulations are a numerical tool to model and analyze the behavio...
In the recent years, the domain of fast flow field prediction has been vastly dominated by pixel-bas...
A convolution neural network (CNN)-based approach for the construction of reduced order surrogate mo...
project "Centre of research and experimental development of reliable energy production" TE01020068 o...
Determining the behavior of fluids is of interest in many fields. In this work, we focus on incompr...
In this study, we propose an encoder–decoder convolutional neural network-based approach for estimat...
This work proposes a novel multi-output neural network for the prediction of the lift coefficient of...
The spread of machine learning (ML) techniques in combination with the availability of high-quality ...
In a myriad of engineering situations, we often hope to establish a model which can acquire load con...
Machine learning is a popular tool that is being applied to many domains, from computer vision to na...
This research is supported by the projects GA21-31457S ”Fast flow-field prediction using deep neura...
International audienceThe ubiquity of fluids in the physical world explains the need to accurately s...
In recent years, the development of deep learning is noticeably influencing the progress of computat...
Aircraft design requires a multitude of aerodynamic data and providing this solely based on high-qua...
Over the past few years, neural networks have arisen great interest in the computational fluid dynam...
Computational Fluid Dynamics (CFD) simulations are a numerical tool to model and analyze the behavio...
In the recent years, the domain of fast flow field prediction has been vastly dominated by pixel-bas...
A convolution neural network (CNN)-based approach for the construction of reduced order surrogate mo...
project "Centre of research and experimental development of reliable energy production" TE01020068 o...
Determining the behavior of fluids is of interest in many fields. In this work, we focus on incompr...
In this study, we propose an encoder–decoder convolutional neural network-based approach for estimat...
This work proposes a novel multi-output neural network for the prediction of the lift coefficient of...
The spread of machine learning (ML) techniques in combination with the availability of high-quality ...
In a myriad of engineering situations, we often hope to establish a model which can acquire load con...
Machine learning is a popular tool that is being applied to many domains, from computer vision to na...
This research is supported by the projects GA21-31457S ”Fast flow-field prediction using deep neura...
International audienceThe ubiquity of fluids in the physical world explains the need to accurately s...
In recent years, the development of deep learning is noticeably influencing the progress of computat...
Aircraft design requires a multitude of aerodynamic data and providing this solely based on high-qua...