Physics-Informed Machine Learning Approach for Augmenting Turbulence Models: A Comprehensive Framework

Abstract

Reynolds-averaged Navier-Stokes (RANS) equations are widely used in engineering turbulent flow simulations. However, RANS predictions may have large discrepancies due to the uncertainties in modeled Reynolds stresses. Recently, Wang et al. demonstrated that machine learning can be used to improve the RANS modeled Reynolds stresses by leveraging data from high fidelity simulations (Physics informed machine learning approach for reconstructing Reynolds stress modeling discrepancies based on DNS data. Physical Review Fluids. 2, 034603, 2017). However, solving for mean flows from the improved Reynolds stresses still poses significant challenges due to potential ill-conditioning of RANS equations with Reynolds stress closures. Enabling improved predictions of mean velocities are of profound practical importance, because often the velocity and its derived quantities (QoIs, e.g., drag, lift, surface friction), and not the Reynolds stress itself, are of ultimate interest in RANS simulations. To this end, we present a comprehensive framework for augmenting turbulence models with physics-informed machine learning, illustrating a complete workflow from identification of input features to final prediction of mean velocities. This work has two innovations. First, we demonstrate a systematic procedure to generate mean flow features based on the integrity basis for mean flow tensors. Second, we propose using machine learning to predict linear and nonlinear parts of the Reynolds stress tensor separately. Inspired by the finite polynomial representation of tensors in classical turbulence modeling, such a decomposition is instrumental in overcoming the ill-conditioning of RANS equations. Numerical tests demonstrated merits of the proposed framework.

This manuscript is for substitution purpose of a previous arXiv submission (arXiv:1701.07102). That previous arXiv submission is no longer under consideration for any journal publication and is only for archive purpose

References in corpus (1)

• A neural network approach for the blind deconvolution of turbulent flows

Cited by in corpus (101)

• Turbulence Modeling in the Age of Data
• Informed Machine Learning -- A Taxonomy and Survey of Integrating Knowledge into Learning Systems
• Enhancing Computational Fluid Dynamics with Machine Learning
• Enforcing Analytic Constraints in Neural-Networks Emulating Physical Systems
• Physics-informed Neural Networks (PINNs) for Wave Propagation and Full Waveform Inversions
• Sub-grid modelling for two-dimensional turbulence using neural networks
• Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence
• Discovery of Algebraic Reynolds-Stress Models Using Sparse Symbolic Regression
• Seeing Permeability From Images: Fast Prediction with Convolutional Neural Networks
• Improving aircraft performance using machine learning: a review
• A new prediction method of unsteady wake flow by the hybrid deep neural network
• RANS Equations with Explicit Data-Driven Reynolds Stress Closure Can Be Ill-Conditioned
• On the prediction of critical heat flux using a physics-informed machine learning-aided framework
• Scientific multi-agent reinforcement learning for wall-models of turbulent flows
• Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systems
• Physics-informed neural network simulation of multiphase poroelasticity using stress-split sequential training
• Probabilistic neural networks for fluid flow surrogate modeling and data recovery
• Physics-guided deep learning framework for predictive modeling of the Reynolds stress anisotropy
• Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning
• A physics-informed operator regression framework for extracting data-driven continuum models
• Ensemble Kalman method for learning turbulence models from indirect observation data
• Experimental velocity data estimation for imperfect particle images using machine learning
• Feature selection and processing of turbulence modeling based on an artificial neural network
• Deconvolutional artificial neural network models for large eddy simulation of turbulence
• Physics-informed neural network solution of thermo-hydro-mechanical (THM) processes in porous media
• A curated dataset for data-driven turbulence modelling
• Inverse modeling of nonisothermal multiphase poromechanics using physics-informed neural networks
• Prediction of Reynolds Stresses in High-Mach-Number Turbulent Boundary Layers using Physics-Informed Machine Learning
• Multi-Objective CFD-Driven Development of Coupled Turbulence Closure Models
• Learning physics-constrained subgrid-scale closures in the small-data regime for stable and accurate LES
• Neural Network Models for the Anisotropic Reynolds Stress Tensor in Turbulent Channel Flow
• Physics-inspired architecture for neural network modeling of forces and torques in particle-laden flows
• Learning nonlocal constitutive models with neural networks
• Physics-Informed Echo State Networks
• A priori analysis on deep learning of subgrid-scale parameterizations for Kraichnan turbulence
• An Iterative Machine-Learning Framework for RANS Turbulence Modeling
• CFD-driven Symbolic Identification of Algebraic Reynolds-Stress Models
• Data-driven turbulence modeling in separated flows considering physical mechanism analysis
• Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
• Data-assisted combustion simulations with dynamic submodel assignment using random forests
• OpenFOAMGPT: a RAG-Augmented LLM Agent for OpenFOAM-Based Computational Fluid Dynamics
• Deep Structured Neural Networks for Turbulence Closure Modelling
• Probabilistic learning on manifolds constrained by nonlinear partial differential equations for small datasets
• Data augmented turbulence modeling for three-dimensional separation flows
• Extracting Interpretable Physical Parameters from Spatiotemporal Systems using Unsupervised Learning
• Neural modal ordinary differential equations: Integrating physics-based modeling with neural ordinary differential equations for modeling high-dimensional monitored structures
• An iterative data-driven turbulence modeling framework based on Reynolds stress representation
• Frozen propagation of Reynolds force vector from high-fidelity data into Reynolds-averaged simulations of secondary flows
• Log-law recovery through reinforcement-learning wall model for large-eddy simulation
• A data-driven approach for the closure of RANS models by the divergence of the Reynolds Stress Tensor
• Discovering explicit Reynolds-averaged turbulence closures for turbulent separated flows through deep learning-based symbolic regression with non-linear corrections
• Physics-Informed Echo State Networks for Chaotic Systems Forecasting
• Frame invariant neural network closures for Kraichnan turbulence
• Opening the Black Box: Towards inherently interpretable energy data imputation models using building physics insight
• Physics-informed machine learning improves detection of head impacts
• Space-dependent Aggregation of Stochastic Data-driven Turbulence Models
• On the generalizability of machine-learning-assisted anisotropy mappings for predictive turbulence modelling
• Revisiting Tensor Basis Neural Networks for Reynolds stress modeling: application to plane channel and square duct flows
• A Divide-and-Conquer Machine Learning Approach for Modelling Turbulent Flows
• Progressive augmentation of Reynolds stress tensor models for secondary flow prediction by computational fluid dynamics driven surrogate optimisation
• Neural Dynamical Operator: Continuous Spatial-Temporal Model with Gradient-Based and Derivative-Free Optimization Methods
• Physics-Informed Machine Learning for Modeling Turbulence in Supernovae
• A Status Quo Investigation of Large Language Models towards Cost-Effective CFD Automation with OpenFOAMGPT: ChatGPT vs. Qwen vs. Deepseek
• CEBoosting: Online Sparse Identification of Dynamical Systems with Regime Switching by Causation Entropy Boosting
• Coherent Organizational States in Turbulent Pipe Flow at moderate Reynolds numbers
• Dimension Reduced Turbulent Flow Data From Deep Vector Quantizers
• CGNSDE: Conditional Gaussian Neural Stochastic Differential Equation for Modeling Complex Systems and Data Assimilation
• CGKN: A Deep Learning Framework for Modeling Complex Dynamical Systems and Efficient Data Assimilation
• Probabilistic learning inference of boundary value problem with uncertainties based on Kullback-Leibler divergence under implicit constraints
• turbo-RANS: Straightforward and Efficient Bayesian Optimization of Turbulence Model Coefficients
• An equivariant neural operator for developing nonlocal tensorial constitutive models
• Evaluation of physics constrained data-driven methods for turbulence model uncertainty quantification
• Quantification of Reynolds-averaged-Navier-Stokes model form uncertainty in transitional boundary layer and airfoil flows
• Data-driven approach for modeling Reynolds stress tensor with invariance preservation
• Modeling Partially Observed Nonlinear Dynamical Systems and Efficient Data Assimilation via Discrete-Time Conditional Gaussian Koopman Network
• Godunov Loss Functions for Modelling of Hyperbolic Conservation Laws
• Learning a Reduced Basis of Dynamical Systems using an Autoencoder
• Review of Physics-based and Data-driven Multiscale Simulation Methods for Computational Fluid Dynamics and Nuclear Thermal Hydraulics
• Certified machine learning: Rigorous a posteriori error bounds for PDE defined PINNs
• Discovering Artificial Viscosity Models for Discontinuous Galerkin Approximation of Conservation Laws using Physics-Informed Machine Learning
• Nonlinear input feature reduction for data-based physical modeling
• Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids
• Learning of discrete models of variational PDEs from data
• Artificial neural network approach for turbulence models: A local framework
• Convolutional Neural Network Models and Interpretability for the Anisotropic Reynolds Stress Tensor in Turbulent One-dimensional Flows
• Model order reduction with neural networks: Application to laminar and turbulent flows
• A TVD neural network closure and application to turbulent combustion
• Active Learning of Model Discrepancy with Bayesian Experimental Design
• Bayesian Experimental Design for Model Discrepancy Calibration: An Auto-Differentiable Ensemble Kalman Inversion Approach
• PICT -- A Differentiable, GPU-Accelerated Multi-Block PISO Solver for Simulation-Coupled Learning Tasks in Fluid Dynamics
• Determining a priori a RANS model's applicable range via global epistemic uncertainty quantification
• Bayesian Experimental Design for Model Discrepancy Calibration: A Rivalry between Kullback--Leibler Divergence and Wasserstein Distance
• Machine learning and serving of discrete field theories -- when artificial intelligence meets the discrete universe
• Interpretable data-driven turbulence modeling for separated flows using symbolic regression with unit constraints
• Embedding stochastic differential equations into neural networks via dual processes
• Bayesian Reasoning for Physics Informed Neural Networks
• Modeling compressed turbulent plasma with rapid viscosity variations
• Data-driven detached-eddy simulations based on explicit algebraic stress expressions for turbulent flows
• Turbulence closure modeling with data-driven techniques: Investigation of generalizable deep neural networks
• Similarity-Based Equational Inference in Physics
• Data-driven quantification of model-form uncertainty in Reynolds-averaged simulations of wind farms