Physics-guided Bayesian neural networks for zonal corrections and uncertainty quantification in separated flows

TL;DR

This paper introduces a physics-guided Bayesian neural network framework for improved correction and uncertainty quantification in RANS models of complex separated flows, enhancing reliability and generalization across different geometries.

Contribution

The novel framework combines physics-guided invariant inputs, targeted flow zone training, and a classifier for selective corrections, advancing turbulence modeling with uncertainty quantification.

Findings

Accurately predicts correction terms for Reynolds stress anisotropy.

Effectively addresses dominant modeling errors in separated flows.

Provides probabilistic uncertainty estimates for RANS predictions.

Abstract

Data-driven techniques have improved the accuracy of Reynolds-averaged Navier-Stokes (RANS) models in fluid dynamics. However, modeling separated flows remains challenging due to their complex physics and sensitivity to local conditions. Existing approaches often struggle with generalization beyond training cases and lack robust uncertainty quantification frameworks, limiting their utility in complex flow regimes. We propose a Bayesian neural network (BNN)-based framework specifically designed for two-dimensional separated flows. By focusing on flow zones near separated regions, we ensure targeted training and enhance predictive reliability. The BNN framework incorporates physics-guided, invariant inputs to maintain consistency with turbulence physics. Correction terms predicted by the BNN are selectively applied to specific regions of the flow domain using a novel classifier, improving accuracy. A key feature of this approach is propagating BNN-derived corrections to flow solutions, enabling uncertainty quantification in unseen test cases. This probabilistic characterization of modeling errors offers insights into the reliability of RANS predictions across geometries with similar topologies. Preliminary results demonstrate that this method accurately predicts correction terms for Reynolds stress anisotropy and turbulent kinetic energy production in separated flow regions, effectively addressing dominant modeling errors and advancing turbulence modeling through uncertainty quantification.