TY - JOUR

T1 - Discovery of Algebraic Reynolds-Stress Models Using Sparse Symbolic Regression

AU - Schmelzer, Martin

AU - Dwight, Richard P.

AU - Cinnella, Paola

PY - 2019

Y1 - 2019

N2 - A novel deterministic symbolic regression method SpaRTA (Sparse Regression of Turbulent Stress Anisotropy) is introduced to infer algebraic stress models for the closure of RANS equations directly from high-fidelity LES or DNS data. The models are written as tensor polynomials and are built from a library of candidate functions. The machine-learning method is based on elastic net regularisation which promotes sparsity of the inferred models. By being data-driven the method relaxes assumptions commonly made in the process of model development. Model-discovery and cross-validation is performed for three cases of separating flows, i.e. periodic hills (Re=10595), converging-diverging channel (Re=12600) and curved backward-facing step (Re=13700). The predictions of the discovered models are significantly improved over the k-ω SST also for a true prediction of the flow over periodic hills at Re=37000. This study shows a systematic assessment of SpaRTA for rapid machine-learning of robust corrections for standard RANS turbulence models.

AB - A novel deterministic symbolic regression method SpaRTA (Sparse Regression of Turbulent Stress Anisotropy) is introduced to infer algebraic stress models for the closure of RANS equations directly from high-fidelity LES or DNS data. The models are written as tensor polynomials and are built from a library of candidate functions. The machine-learning method is based on elastic net regularisation which promotes sparsity of the inferred models. By being data-driven the method relaxes assumptions commonly made in the process of model development. Model-discovery and cross-validation is performed for three cases of separating flows, i.e. periodic hills (Re=10595), converging-diverging channel (Re=12600) and curved backward-facing step (Re=13700). The predictions of the discovered models are significantly improved over the k-ω SST also for a true prediction of the flow over periodic hills at Re=37000. This study shows a systematic assessment of SpaRTA for rapid machine-learning of robust corrections for standard RANS turbulence models.

KW - Data-driven

KW - Explicit Algebraic Reynolds-stress models

KW - Machine learning

KW - Sparse symbolic regression

KW - Turbulence modelling

UR - http://www.scopus.com/inward/record.url?scp=85076879692&partnerID=8YFLogxK

U2 - 10.1007/s10494-019-00089-x

DO - 10.1007/s10494-019-00089-x

M3 - Article

AN - SCOPUS:85076879692

JO - Flow, Turbulence and Combustion

JF - Flow, Turbulence and Combustion

SN - 1386-6184

ER -