Using Parametric PINNs for Predicting Internal and External Turbulent Flows

TL;DR

This paper explores the use of parametric physics-informed neural networks (PINNs) to efficiently predict turbulent flows in both internal and external scenarios, building on previous work focused on flow over a cylinder.

Contribution

It extends the RANS-PINN framework to more complex internal and external turbulent flow problems and introduces a novel sampling method for improved training convergence.

Findings

PINNs can accurately predict turbulent flow variables in diverse scenarios.

The proposed sampling approach enhances training stability and convergence.

The framework demonstrates potential for real-time flow prediction applications.

Abstract

Computational fluid dynamics (CFD) solvers employing two-equation eddy viscosity models are the industry standard for simulating turbulent flows using the Reynolds-averaged Navier-Stokes (RANS) formulation. While these methods are computationally less expensive than direct numerical simulations, they can still incur significant computational costs to achieve the desired accuracy. In this context, physics-informed neural networks (PINNs) offer a promising approach for developing parametric surrogate models that leverage both existing, but limited CFD solutions and the governing differential equations to predict simulation outcomes in a computationally efficient, differentiable, and near real-time manner. In this work, we build upon the previously proposed RANS-PINN framework, which only focused on predicting flow over a cylinder. To investigate the efficacy of RANS-PINN as a viable approach to building parametric surrogate models, we investigate its accuracy in predicting relevant turbulent flow variables for both internal and external flows. To ensure training convergence with a more complex loss function, we adopt a novel sampling approach that exploits the domain geometry to ensure a proper balance among the contributions from various regions within the solution domain. The effectiveness of this framework is then demonstrated for two scenarios that represent a broad class of internal and external flow problems.