Neural network-augmented eddy viscosity closures for turbulent premixed jet flames

Abstract

Extending gradient-type turbulence closures to turbulent premixed flames is challenging due to the significant influence of combustion heat release. We incorporate a deep neural network (DNN) into Reynolds-averaged Navier--Stokes (RANS) models for the turbulent viscosity and thermal conductivity as nonlinear functions of the local flow state and thermochemical gradients. Our models are optimized over the RANS partial differential equations (PDEs) using an adjoint-based data assimilation procedure. Because we directly target the RANS solution, as opposed to the unclosed terms, successfully trained models are guaranteed to improve the in-sample accuracy of the DNN-augmented RANS predictions. We demonstrate the learned closures for in- and out-of-sample $\text{a posteriori}$ RANS predictions of compressible, premixed, turbulent jet flames with turbulent Damköhler numbers spanning the gradient- and counter-gradient transport regimes. The DNN-augmented RANS predictions have one to two orders of magnitude lower spatiotemporal mean-squared error than those using a baseline $k$--$\epsilon$ model, even for Damköhler numbers far from those used for training. This demonstrates the accuracy, stability, and generalizability of the PDE-constrained modeling approach for turbulent jet flames over this relatively wide Damköhler number range.

References in corpus (8)

• Machine Learning for Fluid Mechanics
• Turbulence Modeling in the Age of Data
• Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence
• Training convolutional neural networks to estimate turbulent sub-grid scale reaction rates
• A neural network approach for the blind deconvolution of turbulent flows
• RANS Equations with Explicit Data-Driven Reynolds Stress Closure Can Be Ill-Conditioned
• Deep Learning Closure Models for Large-Eddy Simulation of Flows around Bluff Bodies
• Influence of adversarial training on super-resolution turbulence reconstruction

Cited by in corpus (1)

• Physics-Based Machine Learning Closures and Wall Models for Hypersonic Transition-Continuum Boundary Layer Predictions