RANS turbulence model development using CFD-driven machine learning

DOI10.1016/J.JCP.2020.109413zbMATH Open1436.76011arXiv1902.09075OpenAlexW3013108861MaRDI QIDQ777616FDOQ777616

Jack Weatheritt, Yaomin Zhao, Vittorio Michelassi, Harshal D. Akolekar, Richard D. Sandberg

Publication date: 7 July 2020

Published in: Journal of Computational Physics (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/1902.09075

Recommendations

• Machine learning for RANS turbulence modeling of variable property flows
• Machine Learning in CFD
• A perspective on machine learning methods in turbulence modeling
• The use of the Reynolds force vector in a physics informed machine learning approach for predictive turbulence modeling
• High Reynolds number airfoil turbulence modeling method based on machine learning technique
• Nonlinear reduced-order modeling for three-dimensional turbulent flow by large-scale machine learning
• Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
• On the Generalizability of Machine-Learning-Assisted Anisotropy Mappings for Predictive Turbulence Modelling
• Machine-aided turbulence theory
• Physics-guided deep learning for generating turbulent inflow conditions

zbMATH Keywords

machine learningturbulence modellingwake mixing

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Statistical turbulence modeling (76F55)

Cites Work

• Title not available (Why is that?)
• Bayesian estimates of parameter variability in the \(k-\varepsilon\) turbulence model
• The return to isotropy of homogeneous turbulence
• A paradigm for data-driven predictive modeling using field inversion and machine learning
• Presentation of anisotropy properties of turbulence, invariants versus eigenvalue approaches
• A more general effective-viscosity hypothesis
• Turbulence Modeling in the Age of Data
• A methodology to evaluate statistical errors in DNS data of plane channel flows
• A novel evolutionary algorithm applied to algebraic modifications of the RANS stress-strain relationship
• A framework to develop data-driven turbulence models for flows with organised unsteadiness
• Reynolds averaged turbulence modelling using deep neural networks with embedded invariance
• Title not available (Why is that?)

Cited In (22)

• A probabilistic, data-driven closure model for RANS simulations with aleatoric, model uncertainty
• The use of the Reynolds force vector in a physics informed machine learning approach for predictive turbulence modeling
• Data-driven approach for modeling Reynolds stress tensor with invariance preservation
• Revisiting tensor basis neural network for Reynolds stress modeling: application to plane channel and square duct flows
• High Reynolds number airfoil turbulence modeling method based on machine learning technique
• Learning about structural errors in models of complex dynamical systems
• Integration of neural networks with numerical solution of PDEs for closure models development
• On the improvement of the extrapolation capability of an iterative machine-learning based RANS framework
• \(S\)-frame discrepancy correction models for data-informed Reynolds stress closure
• CFD-driven symbolic identification of algebraic Reynolds-stress models
• Multi-objective CFD-driven development of coupled turbulence closure models
• Determining \textit{a priori} a RANS model's applicable range via global epistemic uncertainty quantification
• Conditioning and accurate solutions of Reynolds average Navier–Stokes equations with data-driven turbulence closures
• A turbulent eddy-viscosity surrogate modeling framework for Reynolds-averaged Navier-Stokes simulations
• Machine learning for RANS turbulence modeling of variable property flows
• Feature importance in neural networks as a means of interpretation for data-driven turbulence models
• A wall model for separated flows: embedded learning to improve \textit{a posteriori} performance
• Data-driven RANS closures for three-dimensional flows around bluff bodies
• Ensemble Kalman method for learning turbulence models from indirect observation data
• Ensemble Gradient for Learning Turbulence Models from Indirect Observations
• Three-dimensional realizations of flood flow in large-scale rivers using the neural fuzzy-based machine-learning algorithms
• A highly accurate strategy for data-driven turbulence modeling

This page was built for publication: RANS turbulence model development using CFD-driven machine learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q777616)