RANS Turbulence Model Development using CFD-Driven Machine Learning

Abstract

This paper presents a novel CFD-driven machine learning framework to develop Reynolds-averaged Navier-Stokes (RANS) models. The CFD-driven training is an extension of the gene expression programming method (Weatheritt and Sandberg, 2016), but crucially the fitness of candidate models is now evaluated by running RANS calculations in an integrated way, rather than using an algebraic function. Unlike other data-driven methods that fit the Reynolds stresses of trained models to high-fidelity data, the cost function for the CFD-driven training can be defined based on any flow feature from the CFD results. This extends the applicability of the method especially when the training data is limited. Furthermore, the resulting model, which is the one providing the most accurate CFD results at the end of the training, inherently shows good performance in RANS calculations. To demonstrate the potential of this new method, the CFD-driven machine learning approach is applied to model development for wake mixing in turbomachines. A new model is trained based on a high-pressure turbine case and then tested for three additional cases, all representative of modern turbine nozzles. Despite the geometric configurations and operating conditions being different among the cases, the predicted wake mixing profiles are significantly improved in all of these a posteriori tests. Moreover, the model equation is explicitly given and available for analysis, thus it could be deduced that the enhanced wake prediction is predominantly due to the extra diffusion introduced by the CFD-driven model.

Accepted by Journal of Computational Physics

Cited by in corpus (39)

• Perspectives on Machine Learning-augmented Reynolds-averaged and Large Eddy Simulation Models of Turbulence
• Discovery of Algebraic Reynolds-Stress Models Using Sparse Symbolic Regression
• Physics-guided deep learning framework for predictive modeling of the Reynolds stress anisotropy
• Ensemble Kalman method for learning turbulence models from indirect observation data
• Formulating turbulence closures using sparse regression with embedded form invariance
• Multi-Objective CFD-Driven Development of Coupled Turbulence Closure Models
• Generative Modeling of 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
• Data augmented turbulence modeling for three-dimensional separation flows
• Interpreting neural network models of residual scalar flux
• Discovering explicit Reynolds-averaged turbulence closures for turbulent separated flows through deep learning-based symbolic regression with non-linear corrections
• Machine-learning accelerated turbulence modelling of transient flashing jets
• Calibrating hypersonic turbulence flow models with the HIFiRE-1 experiment using data-driven machine-learned models
• Space-dependent Aggregation of Stochastic Data-driven Turbulence Models
• A wall model for separated flows: embedded learning to improve a posteriori performance
• Data-driven algebraic models of the turbulent Prandtl number for buoyancy-affected flow near a vertical surface
• Revisiting Tensor Basis Neural Networks for Reynolds stress modeling: application to plane channel and square duct flows
• Physics-integrated machine learning: embedding a neural network in the Navier-Stokes equations. Part I
• Progressive augmentation of Reynolds stress tensor models for secondary flow prediction by computational fluid dynamics driven surrogate optimisation
• Physics-integrated machine learning: embedding a neural network in the Navier-Stokes equations. Part II
• Robust deep learning for emulating turbulent viscosities
• Physics Informed Neural Networks for Modeling of 3D Flow-Thermal Problems with Sparse Domain Data
• End-to-end differentiable learning of turbulence models from indirect observations
• Optimal mesh generation for a non-iterative grid-converged solution of flow through a blade passage using deep reinforcement learning
• Data-driven approach for modeling Reynolds stress tensor with invariance preservation
• Review of Physics-based and Data-driven Multiscale Simulation Methods for Computational Fluid Dynamics and Nuclear Thermal Hydraulics
• Review and Examination of Input Feature Preparation Methods and Machine Learning Models for Turbulence Modeling
• Progressive Mixture-of-Experts with autoencoder routing for continual RANS turbulence modelling
• Determining a priori a RANS model's applicable range via global epistemic uncertainty quantification
• A turbulent eddy-viscosity surrogate modeling framework for Reynolds-Averaged Navier-Stokes simulations
• Symbolic identification of tensor equations in multidimensional physical fields
• Turbulence closure modeling with data-driven techniques: Investigation of generalizable deep neural networks
• Three-dimensional realizations of flood flow in large-scale rivers using the neural fuzzy-based machine-learning algorithm
• Realizability-Constrained Machine Learning for Turbulence Closures in Wake Flows
• Prediction of three-dimensional flood-flow past bridge piers in a large-scale meandering river using convolutional neural networks
• Data-driven Augmentation of a Turbulence Model in Three dimensional Separated Flows
• Ensemble gradient for learning turbulence models from indirect observations