Recent Papers

Computational Fluid Dynamics (CFD) faces challenges in accurately modeling turbulent flows using traditional turbulence models. This paper presents a novel approach to improve Large Eddy Simulation (LES) turbulence modeling in CFD through deep learning. By training a deep learning model on a large dataset of high-fidelity turbulence simulations, intricate turbulence characteristics can be captured. Extensive numerical experiments on benchmark test cases and practical engineering problems demonstrate the superior predictive capabilities of the deep learning-enhanced turbulence models. They accurately capture critical flow features such as vortex shedding and boundary layer transition. Moreover, the deep learning models offer computational efficiency gains, enabling real-time simulations and optimization studies. This research paper highlights the potential of deep learning techniques to advance turbulence modeling in CFD, leading to more accurate and efficient computational tools for analyzing and optimizing turbulent flows in engineering systems.

Copyright © 2023 Harsh Makwana. This is an open access article distributed under the Creative Commons Attribution License.