Imperial College London
Portrait Picture

Prof Francesco Montomoli

Faculty of Engineering, Department of Aeronautics

Professor in Computational Aerodynamics
 
 
 
//

Contact

 

+44 (0)20 7594 5151f.montomoli Website

 
 
//

Location

 

215City and Guilds BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@inproceedings{Marioni:2022:10.1115/GT2022-82531,
author = {Marioni, YF and Cassinelli, A and Adami, P and Sherwin, S and Diaz, RV and Montomoli, F},
doi = {10.1115/GT2022-82531},
title = {DEVELOPMENT OF MACHINE-LEARNT TURBULENCE CLOSURES FOR WAKE MIXING PREDICTIONS IN LOW-PRESSURE TURBINES},
url = {http://dx.doi.org/10.1115/GT2022-82531},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - In this work, a DNS – Machine Learning (ML) framework is developed for low-pressure turbine (LPT) profiles to inform turbulence closures in Reynolds-Averaged Navier–Stokes (RANS) calculations. This is done by training the coefficients of Explicit Algebraic Reynolds Stress Models (EARSM) with shallow artificial neural networks (ANN) as a function of input flow features. DNS data are generated with the incompressible Navier–Stokes solver in Nektar++ and validated against experiments. All calculations include moving bars upstream of the profile to capture the effect of incoming wakes. The resulting formulations are then implemented in the Rolls-Royce solver HYDRA and tested a posteriori. The aim is to improve mixing predictions in LPT wakes, compared to the baseline model, Wilcox’s k− ω SST, in terms of velocity profiles, turbulent kinetic energy (TKE) production and mixing losses. LPT calculations are run at Reynolds numbers spanning from ≈ 80k to ≈ 300k, to cover the range of aircraft engine applications. Models for the low and high Reynolds datasets are trained separately and a method is developed to merge the two together. The resulting model is tested on an intermediate Reynolds case. This process is followed for two computational domains: one starting downstream of the profile trailing edge and one including the last portion of the profile. Finally, the developed closures are tested on the entire profile, to confirm the validity of the improvements when the additional effect of transition is included in the simulation. This work explains the methodology used to develop ML-driven closures and shows how it is possible to combine models trained on different datasets.
AU  - Marioni,YF
AU  - Cassinelli,A
AU  - Adami,P
AU  - Sherwin,S
AU  - Diaz,RV
AU  - Montomoli,F
DO  - 10.1115/GT2022-82531
PY  - 2022///
TI  - DEVELOPMENT OF MACHINE-LEARNT TURBULENCE CLOSURES FOR WAKE MIXING PREDICTIONS IN LOW-PRESSURE TURBINES
UR  - http://dx.doi.org/10.1115/GT2022-82531
ER  -
Download