August 17, 2025

Turbulent injection assisted by diffusion models for scale-resolving simulations

Key Points

Synthetic samples produced by the diffusion model effectively replicate turbulence statistics, enhancing simulation accuracy.
The method preserves detailed fluctuations while demonstrating promising results for energy spectrum and turbulent kinetic energy levels.
A guided diffusion model trained on turbulence samples provides computational efficiency for large scale simulations across multiple flow problems.
Impacts highlighted include the ability to inject realistic turbulence without increasing development distance, streamlining simulation processes.

Abstract

The present research proposes a new memory-efficient method using diffusion models to inject turbulent inflow conditions into large eddy simulation and direct numerical simulation for various flow problems. A guided diffusion model was trained on decaying homogeneous isotropic turbulence samples, characterized by different turbulent kinetic energy levels and integral length scales. Samples generated by the diffusion model accurately reproduce turbulence statistics, such as the energy spectrum and the two-point autocorrelation functions, while preserving the ability to generate instantaneous three-dimensional velocity fields with detailed fluctuations. Physical representativeness is also evaluated by injecting the synthetic samples into a free domain (i.e., without any wall boundary) through an inlet boundary condition. The method demonstrates promising results regarding energy spectrum, spatial correlation, turbulent kinetic energy level, and integral length scales without increasing the development distance as compared to a library-based method.

اسأل الذكاء الاصطناعي

Bookmark