Use of Convolutional Neural Network for multi-fidelity CFD problems

In recent years, there has been a growing interest in applying deep learning techniques to Computational Fluid Dynamics (CFD), particularly for accelerating simulations and enhancing data resolution. This work explores the use of Convolutional Neural Networks (CNNs) to reconstruct high-resolution CFD fields from low-resolution inputs. A U-Net architecture was selected due to its proven ability to capture both global context and fine-scale features. The study focuses on two CFD problems: a bump-in-a-duct configuration and a hydrogen combustion chamber. These cases were chosen to encompass both non-reactive and reactive flow regimes and to test the generalization capability of the model under different physical conditions. The network was trained to predict high-resolution pressure, axial velocity, and heat of reaction fields from their corresponding low-resolution versions, thus performing a super-resolution task. The datasets were generated using two solvers: a custom Fortran-based code solving the non-dimensional Euler equations, and the commercial CFD software Ansys Fluent for more complex reactive flow simulations. The training process involved careful hyperparameter optimization, early stopping strategies, and loss function selection to prevent overfitting and maximize prediction quality. Quantitative assessments demonstrated prediction errors on the order of a few percent, while qualitative analyses confirmed the ability of the models to accurately reconstruct the flow structures, even in complex reacting flows. The final phase of the project focused on identifying potential future developments of the proposed framework. The individual contribution to this thesis project includes the generation of the datasets, the design and full implementation of the U-Net architecture within a complete Python framework featuring a structured-to-unstructured (and vice versa) grid interpolator, the definition of training strategies, the extension to a multi-network architecture, and the systematic evaluation of the model performance. The work highlights the promising role of deep learning techniques, particularly CNN-based surrogate models, in enhancing CFD simulation capabilities and accelerating future engineering workflows by enabling fast and accurate predictions across different fidelity levels.