Predictive large-eddy-simulation wall modeling via physics-informed neural networks

Xiang Yang, S. Zafar, J. X. Wang, H. Xiao

    Research output: Contribution to journalArticle

    Abstract

    While data-based approaches were found to be useful for subgrid scale (SGS) modeling in Reynolds-averaged Navier-Stokes (RANS) simulations, there have not been many attempts at using machine learning techniques for wall modeling in large-eddy simulations (LESs). Large-eddy simulation differs from RANS simulation in many aspects. For one thing, LES is scale resolving. For another, LES is in and of itself a high-fidelity tool. Because data sets of higher fidelity are in general not frequently accessible or available, this poses additional challenges to data-based modeling in LES. Further, SGS modeling usually needs flow information at only large scales, in contrast with wall modeling, which needs to account for both near-wall small scales and large scales above the wall. In this work we discuss how the above-noted challenges may be addressed when taking a data-based approach for wall modeling. We also show the necessity of incorporating physical insights in model inputs, i.e., using inputs that are inspired by the vertically integrated thin-boundary-layer equations and the eddy population density scalings. We show that the inclusion of the above physics-based considerations would enhance extrapolation capabilities of a neural network to flow conditions that are not within the train data. Being cheap to evaluate and using only channel flow data at Reτ=1000, the trained networks are found to capture the law of the wall at arbitrary Reynolds numbers and outperform the conventional equilibrium model in a nonequilibrium flow.

    Original languageEnglish (US)
    Article number034602
    JournalPhysical Review Fluids
    Volume4
    Issue number3
    DOIs
    StatePublished - Mar 1 2019

    Fingerprint

    Large Eddy Simulation
    Large eddy simulation
    Physics
    Neural Networks
    Neural networks
    Modeling
    Navier-Stokes
    Fidelity
    Channel flow
    Extrapolation
    Channel Flow
    Equilibrium Model
    Thin Layer
    Information Flow
    Learning systems
    Boundary layers
    Reynolds number
    Thing
    Non-equilibrium
    Boundary Layer

    All Science Journal Classification (ASJC) codes

    • Computational Mechanics
    • Modeling and Simulation
    • Fluid Flow and Transfer Processes

    Cite this

    @article{1f8b4540a36946c98611197242d958e5,
    title = "Predictive large-eddy-simulation wall modeling via physics-informed neural networks",
    abstract = "While data-based approaches were found to be useful for subgrid scale (SGS) modeling in Reynolds-averaged Navier-Stokes (RANS) simulations, there have not been many attempts at using machine learning techniques for wall modeling in large-eddy simulations (LESs). Large-eddy simulation differs from RANS simulation in many aspects. For one thing, LES is scale resolving. For another, LES is in and of itself a high-fidelity tool. Because data sets of higher fidelity are in general not frequently accessible or available, this poses additional challenges to data-based modeling in LES. Further, SGS modeling usually needs flow information at only large scales, in contrast with wall modeling, which needs to account for both near-wall small scales and large scales above the wall. In this work we discuss how the above-noted challenges may be addressed when taking a data-based approach for wall modeling. We also show the necessity of incorporating physical insights in model inputs, i.e., using inputs that are inspired by the vertically integrated thin-boundary-layer equations and the eddy population density scalings. We show that the inclusion of the above physics-based considerations would enhance extrapolation capabilities of a neural network to flow conditions that are not within the train data. Being cheap to evaluate and using only channel flow data at Reτ=1000, the trained networks are found to capture the law of the wall at arbitrary Reynolds numbers and outperform the conventional equilibrium model in a nonequilibrium flow.",
    author = "Xiang Yang and S. Zafar and Wang, {J. X.} and H. Xiao",
    year = "2019",
    month = "3",
    day = "1",
    doi = "10.1103/PhysRevFluids.4.034602",
    language = "English (US)",
    volume = "4",
    journal = "Physical Review Fluids",
    issn = "2469-990X",
    publisher = "American Physical Society",
    number = "3",

    }

    Predictive large-eddy-simulation wall modeling via physics-informed neural networks. / Yang, Xiang; Zafar, S.; Wang, J. X.; Xiao, H.

    In: Physical Review Fluids, Vol. 4, No. 3, 034602, 01.03.2019.

    Research output: Contribution to journalArticle

    TY - JOUR

    T1 - Predictive large-eddy-simulation wall modeling via physics-informed neural networks

    AU - Yang, Xiang

    AU - Zafar, S.

    AU - Wang, J. X.

    AU - Xiao, H.

    PY - 2019/3/1

    Y1 - 2019/3/1

    N2 - While data-based approaches were found to be useful for subgrid scale (SGS) modeling in Reynolds-averaged Navier-Stokes (RANS) simulations, there have not been many attempts at using machine learning techniques for wall modeling in large-eddy simulations (LESs). Large-eddy simulation differs from RANS simulation in many aspects. For one thing, LES is scale resolving. For another, LES is in and of itself a high-fidelity tool. Because data sets of higher fidelity are in general not frequently accessible or available, this poses additional challenges to data-based modeling in LES. Further, SGS modeling usually needs flow information at only large scales, in contrast with wall modeling, which needs to account for both near-wall small scales and large scales above the wall. In this work we discuss how the above-noted challenges may be addressed when taking a data-based approach for wall modeling. We also show the necessity of incorporating physical insights in model inputs, i.e., using inputs that are inspired by the vertically integrated thin-boundary-layer equations and the eddy population density scalings. We show that the inclusion of the above physics-based considerations would enhance extrapolation capabilities of a neural network to flow conditions that are not within the train data. Being cheap to evaluate and using only channel flow data at Reτ=1000, the trained networks are found to capture the law of the wall at arbitrary Reynolds numbers and outperform the conventional equilibrium model in a nonequilibrium flow.

    AB - While data-based approaches were found to be useful for subgrid scale (SGS) modeling in Reynolds-averaged Navier-Stokes (RANS) simulations, there have not been many attempts at using machine learning techniques for wall modeling in large-eddy simulations (LESs). Large-eddy simulation differs from RANS simulation in many aspects. For one thing, LES is scale resolving. For another, LES is in and of itself a high-fidelity tool. Because data sets of higher fidelity are in general not frequently accessible or available, this poses additional challenges to data-based modeling in LES. Further, SGS modeling usually needs flow information at only large scales, in contrast with wall modeling, which needs to account for both near-wall small scales and large scales above the wall. In this work we discuss how the above-noted challenges may be addressed when taking a data-based approach for wall modeling. We also show the necessity of incorporating physical insights in model inputs, i.e., using inputs that are inspired by the vertically integrated thin-boundary-layer equations and the eddy population density scalings. We show that the inclusion of the above physics-based considerations would enhance extrapolation capabilities of a neural network to flow conditions that are not within the train data. Being cheap to evaluate and using only channel flow data at Reτ=1000, the trained networks are found to capture the law of the wall at arbitrary Reynolds numbers and outperform the conventional equilibrium model in a nonequilibrium flow.

    UR - http://www.scopus.com/inward/record.url?scp=85063998967&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85063998967&partnerID=8YFLogxK

    U2 - 10.1103/PhysRevFluids.4.034602

    DO - 10.1103/PhysRevFluids.4.034602

    M3 - Article

    AN - SCOPUS:85063998967

    VL - 4

    JO - Physical Review Fluids

    JF - Physical Review Fluids

    SN - 2469-990X

    IS - 3

    M1 - 034602

    ER -