Turbulence Modeling with Nek5000/RS, SOD2D and Alya

Technical Report · Mon Sep 25 04:00:00 EDT 2023

DOI:https://doi.org/10.2172/2044145· OSTI ID:2044145

Kumar, Vishal ^[1]; Lehmkuhl, Oriol ^[2]; Tomboulides, Ananias ^[3]; Fischer, Paul ^[4]; Min, Misun ^[1]

---

1. Argonne National Laboratory (ANL), Argonne, IL (United States)
2. Barcelona Supercomputing Center (BSC) (Spain)
3. Aristotle University, Thessaloniki (Greece)
4. Argonne National Laboratory (ANL), Argonne, IL (United States); Univ. of Illinois at Urbana-Champaign, IL (United States)

We present Validation and Verification (V & V) study of two high-order spectral element method (SEM) based Computational Fluid Dyanimcs (CFD) codes that we will utilize for work on turbulence modeling: Nek5000 and SOD2D. While the former solves the incompressible form of Navier-Stokes equation, the latter works with compressible set of equations and uses an entropy-viscosity formulation to account for the discontinuities for high Mach number flows. We demonstrate the accuracy of these codes for two benchmark sub-sonic turbulent flows: periodic channel and pipe flow, by carrying out first and second order statistical analysis, grid convergence and turbulent structure analysis using wall-resolved large eddy simulations (WRLES). Later, we report on the implementation and testing of various wall-modeling strategies for large eddy simulation of turbulent flows in Nek5000. These include both classical log-law based and decision-tree based machine-learning models. Accuracy of these closure strategies are analyzed and necessary future work is outlined.

• Research Organization: Argonne National Laboratory (ANL), Argonne, IL (United States); Spanish Ministerio de Economia y Competitividad (MINECO)
• Sponsoring Organization: USDOE Office of Science (SC)
• DOE Contract Number: AC02-06CH11357
• OSTI ID: 2044145
• Report Number(s): ANL--23/59; 185415
• Country of Publication: United States
• Language: English

Related Subjects

97 MATHEMATICS AND COMPUTING
Large-eddy simulations
Machine Learning
Spectral Element Method
Turbulence modeling