A Physics Informed Machine Learning Approach for Reconstructing Reynolds Stress Modeling Discrepancies Based on DNS Data

Abstract

Turbulence modeling is a critical component in numerical simulations of industrial flows based on Reynolds-averaged Navier-Stokes (RANS) equations. However, after decades of efforts in the turbulence modeling community, universally applicable RANS models with predictive capabilities are still lacking. Recently, data-driven methods have been proposed as a promising alternative to the traditional approaches of turbulence model development. In this work we propose a data-driven, physics-informed machine learning approach for predicting discrepancies in RANS modeled Reynolds stresses. The discrepancies are formulated as functions of the mean flow features. By using a modern machine learning technique based on random forests, the discrepancy functions are first trained with benchmark flow data and then used to predict Reynolds stresses discrepancies in new flows. The method is used to predict the Reynolds stresses in the flow over periodic hills by using two training flow scenarios of increasing difficulties: (1) the flow in the same periodic hills geometry yet at a lower Reynolds number, and (2) the flow in a different hill geometry with a similar recirculation zone. Excellent predictive performances were observed in both scenarios, demonstrating the merits of the proposed method. Improvement of RANS modeled Reynolds stresses enabled by the proposed method is an important step towards predictive turbulence modeling, where the ultimate goal is to predict the quantities of interest (e.g., velocity field, drag, lift) more accurately by solving RANS equations with the Reynolds stresses obtained therefrom.

arXiv comment36 pages, 1 figures

References in corpus (3)

• Quantifying and Reducing Model-Form Uncertainties in Reynolds-Averaged Navier-Stokes Simulations: A Data-Driven, Physics-Based Bayesian Approach
• A Bayesian Calibration-Prediction Method for Reducing Model-Form Uncertainties with Application in RANS Simulations
• Data-Driven CFD Modeling of Turbulent Flows Through Complex Structures

Cited by in corpus (110)

• Machine Learning for Fluid Mechanics
• Theory-guided Data Science: A New Paradigm for Scientific Discovery from Data
• Turbulence Modeling in the Age of Data
• NSFnets (Navier-Stokes Flow nets): Physics-informed neural networks for the incompressible Navier-Stokes equations
• Surrogate Modeling for Fluid Flows Based on Physics-Constrained Deep Learning Without Simulation Data
• PhyGeoNet: Physics-Informed Geometry-Adaptive Convolutional Neural Networks for Solving Parameterized Steady-State PDEs on Irregular Domain
• Enhancing Computational Fluid Dynamics with Machine Learning
• A Comprehensive Physics-Informed Machine Learning Framework for Predictive Turbulence Modeling
• Physics-Informed Machine Learning Approach for Augmenting Turbulence Models: A Comprehensive Framework
• A Physics-Informed Machine Learning Approach for Solving Heat Transfer Equation in Advanced Manufacturing and Engineering Applications
• Machine Learning in Aerodynamic Shape Optimization
• Using machine learning to parameterize moist convection: potential for modeling of climate, climate change and extreme events
• RANS Turbulence Model Development using CFD-Driven Machine Learning
• Sub-grid modelling for two-dimensional turbulence using neural networks
• Unsupervised deep learning for super-resolution reconstruction of turbulence
• Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence
• A Physics-Guided Neural Network Framework for Elastic Plates: Comparison of Governing Equations-Based and Energy-Based Approaches
• Uncertainty Quantification in Machine Learning for Engineering Design and Health Prognostics: A Tutorial
• Data-assisted reduced-order modeling of extreme events in complex dynamical systems
• Seeing Permeability From Images: Fast Prediction with Convolutional Neural Networks
• Super-resolution and denoising of fluid flow using physics-informed convolutional neural networks without high-resolution labels
• A neural network approach for the blind deconvolution of turbulent flows
• RANS Equations with Explicit Data-Driven Reynolds Stress Closure Can Be Ill-Conditioned
• Enforcing Statistical Constraints in Generative Adversarial Networks for Modeling Chaotic Dynamical Systems
• Construction of Reduced Order Models for Fluid Flows Using Deep Feedforward Neural Networks
• A Perspective on Machine Learning Methods in Turbulence Modelling
• Physics-guided deep learning framework for predictive modeling of the Reynolds stress anisotropy
• Physics-informed Neural Networks for Solving Nonlinear Diffusivity and Biot's equations
• Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning
• Assessment of unsteady flow predictions using hybrid deep learning based reduced order models
• High-fidelity reconstruction of turbulent flow from spatially limited data using enhanced super-resolution generative adversarial network
• Ensemble Kalman method for learning turbulence models from indirect observation data
• Classification of Machine Learning Frameworks for Data-Driven Thermal Fluid Models
• Feature selection and processing of turbulence modeling based on an artificial neural network
• Uniformly Accurate Machine Learning Based Hydrodynamic Models for Kinetic Equations
• A transformer-based synthetic-inflow generator for spatially-developing turbulent boundary layers
• Deconvolutional artificial neural network models for large eddy simulation of turbulence
• Sub-grid scale model classification and blending through deep learning
• Explore missing flow dynamics by physics-informed deep learning: the parameterised governing systems
• Physically-Constrained Data-Driven, Filtered Reduced Order Modeling of Fluid Flows
• A Priori Assessment of Prediction Confidence for Data-Driven Turbulence Modeling
• Learning physics-constrained subgrid-scale closures in the small-data regime for stable and accurate LES
• Three-dimensional deep learning-based reduced order model for unsteady flow dynamics with variable Reynolds number
• Neural Network Models for the Anisotropic Reynolds Stress Tensor in Turbulent Channel Flow
• Turbulence closure modeling with data-driven techniques: physical compatibility and consistency considerations
• Learning nonlocal constitutive models with neural networks
• A priori analysis on deep learning of subgrid-scale parameterizations for Kraichnan turbulence
• An Iterative Machine-Learning Framework for RANS Turbulence Modeling
• Data-driven turbulence modeling in separated flows considering physical mechanism analysis
• Assessments of epistemic uncertainty using Gaussian stochastic weight averaging for fluid-flow regression
• Non-intrusive model reduction of large-scale, nonlinear dynamical systems using deep learning
• 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
• Fluid Simulation on Neural Flow Maps
• Reinforcement-learning-based actuator selection method for active flow control
• Deep learning of the spanwise-averaged Navier-Stokes equations
• An iterative data-driven turbulence modeling framework based on Reynolds stress representation
• Invariant Data-Driven Subgrid Stress Modeling in the Strain-Rate Eigenframe for Large Eddy Simulation
• Reconstruction of three-dimensional turbulent flow structures using surface measurements for free-surface flows based on a convolutional neural network
• Machine learning based non-Newtonian fluid model with molecular fidelity
• Analysis on numerical stability and convergence of RANS turbulence models from the perspective of coupling modes
• Adaptive physics-informed neural operator for coarse-grained non-equilibrium flows
• A data-driven approach for the closure of RANS models by the divergence of the Reynolds Stress Tensor
• Combining direct and indirect sparse data for learning generalizable turbulence models
• A Bi-fidelity Ensemble Kalman Method for PDE-Constrained Inverse Problems
• Towards learning Lattice Boltzmann collision operators
• A variational data assimilation approach for sparse velocity reference data in coarse RANS simulations through a corrective forcing term
• Opening the Black Box: Towards inherently interpretable energy data imputation models using building physics insight
• Physics-informed machine learning improves detection of head impacts
• A physics-informed reinforcement learning approach for the interfacial area transport in two-phase flow
• Variational assimilation of sparse time-averaged data for efficient adjoint-based optimization of unsteady RANS simulations
• 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
• Temporally sparse data assimilation for the small-scale reconstruction of turbulence
• Neural Dynamical Operator: Continuous Spatial-Temporal Model with Gradient-Based and Derivative-Free Optimization Methods
• Robust deep learning for emulating turbulent viscosities
• CEBoosting: Online Sparse Identification of Dynamical Systems with Regime Switching by Causation Entropy Boosting
• CGNSDE: Conditional Gaussian Neural Stochastic Differential Equation for Modeling Complex Systems and Data Assimilation
• Probabilistic learning inference of boundary value problem with uncertainties based on Kullback-Leibler divergence under implicit constraints
• An equivariant neural operator for developing nonlocal tensorial constitutive models
• CGKN: A Deep Learning Framework for Modeling Complex Dynamical Systems and Efficient Data Assimilation
• Quantification of Reynolds-averaged-Navier-Stokes model form uncertainty in transitional boundary layer and airfoil flows
• Modeling Partially Observed Nonlinear Dynamical Systems and Efficient Data Assimilation via Discrete-Time Conditional Gaussian Koopman Network
• Review of Physics-based and Data-driven Multiscale Simulation Methods for Computational Fluid Dynamics and Nuclear Thermal Hydraulics
• Robust physics discovery via supervised and unsupervised pattern recognition using the Euler characteristic
• Particle clustering in turbulence: Prediction of spatial and statistical properties with deep learning
• Frame-independent vector-cloud neural network for nonlocal constitutive modeling on arbitrary grids
• Particles to Partial Differential Equations Parsimoniously
• Large Language Model Driven Development of Turbulence Models
• Artificial neural network approach for turbulence models: A local framework
• Stochastic Inference of Plate Bending from Heterogeneous Data: Physics-informed Gaussian Processes via Kirchhoff-Love Theory
• Reduced order modeling of dynamical systems using artificial neural networks applied to water circulation
• Quantum Iterative Methods for Solving Differential Equations with Application to Computational Fluid Dynamics
• Spectral adjoint-based assimilation of sparse data in unsteady simulations of turbulent flows
• Active Learning of Model Discrepancy with Bayesian Experimental Design
• Machine-learning-based simulation of turbulent flows over periodic hills using a hybrid U-Net and Fourier neural operator framework
• Interpretable data-driven turbulence modeling for separated flows using symbolic regression with unit constraints
• Bayesian Experimental Design for Model Discrepancy Calibration: A Rivalry between Kullback--Leibler Divergence and Wasserstein Distance
• Bayesian Experimental Design for Model Discrepancy Calibration: An Auto-Differentiable Ensemble Kalman Inversion Approach
• Determining a priori a RANS model's applicable range via global epistemic uncertainty quantification
• Progressive Mixture-of-Experts with autoencoder routing for continual RANS turbulence modelling
• Turbulence Closure in RANS and Flow Inference around a Cylinder using PINNs and Sparse Experimental Data
• Finding Closure Terms Directly from Coarse Data for 2D Turbulent Flow
• Data-Driven RANS Closures Using a Relative Importance Term Analysis Based Classifier for 2D and 3D Separated Flows
• Data-driven detached-eddy simulations based on explicit algebraic stress expressions for turbulent flows
• Physics-informed Dyna-Style Model-Based Deep Reinforcement Learning for Dynamic Control
• Realizability-Constrained Machine Learning for Turbulence Closures in Wake Flows