Data-driven correlations for thermohydraulic roughness properties

TL;DR

This paper develops a data-driven model to predict thermohydraulic roughness properties in turbulent flows, introduces an empirical correlation for sand-grain roughness, and explores the relationship between roughness features and flow behavior.

Contribution

It presents a novel combination of machine learning and symbolic regression to predict and interpret roughness functions from high-fidelity simulation data.

Findings

The neural network model achieves low MSE in predicting roughness functions.

An empirical correlation for sand-grain roughness is derived with reasonable accuracy.

The study links roughness wavelengths to flow sheltering and windward effects.

Abstract

The influence of rough surfaces on fluid flow is characterized by the downward shift in the logarithmic layer of velocity and temperature profiles, namely the velocity roughness function $\Delta U^+$ and the corresponding temperature roughness function $\Delta \Theta^+$. Their computation relies on computational simulations, and hence a simple prediction without such simulation is envisioned. We present a framework, where a data-driven model is developed using the dataset of Yang et al. 2023 \cite{yang_2023} with $93$ high fidelity direct numerical simulations of a fully-developed turbulent channel flow at $Re_\tau \approx 800$ and $Pr = 0.71$. The model provides robust predictive capabilities (mean squared error $\text{MSE}_{k} = 0.09$ and $\text{MSE}_\theta = 0.096$), but lacks interpretability. Simplistic statistical roughness parameters provide a more understandable route, so the framework is extended with a symbolic regression approach to distill an empirical correlation from the data-driven model. The derived expression leads to a predictive correlation for the equivalent sand-grain roughness $k_\text{s} = k_\text{99} (ES_x ( - ES_x + Sk + 2.37) + 0.772)$ with reasonable predictive powers. The predictive capability of the temperature roughness function is subject to limitations due to the missing Prandtl-number variation in the dataset. Nevertheless, the interpretable correlation and the neural network as well as the original dataset can be used to explore the roughness functions. The functional form of the derived correlations, along with visual analysis of these surfaces, suggests a strong relationship with roughness wavelengths, further linking them to explanations based on sheltered and windward regions.