Imperial College London
Portrait Picture

Professor Mehdi Vahdati

Faculty of Engineering, Department of Mechanical Engineering

Principal Research Fellow
 
 
 
//

Contact

 

+44 (0)20 7594 7073m.vahdati

 
 
//

Location

 

606City and Guilds BuildingSouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{He:2022:10.1016/j.ijheatfluidflow.2022.109038,
author = {He, X and Tan, J and Rigas, G and Vahdati, M},
doi = {10.1016/j.ijheatfluidflow.2022.109038},
journal = {International Journal of Heat and Fluid Flow},
pages = {1--16},
title = {On the explainability of machine-learning-assisted turbulence modeling for transonic flows},
url = {http://dx.doi.org/10.1016/j.ijheatfluidflow.2022.109038},
volume = {97},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Machine learning (ML) is a rising and promising tool for Reynolds-Averaged Navier–Stokes (RANS) turbulence model developments, but its application to industrial flows is hindered by the lack of explainability of the ML model. In this paper, two types of methods to improve the explainability are presented, namely the intrinsic methods that reduce the model complexity and the post-hoc methods that explain the correlation between the model inputs and outputs. The investigated ML-assisted turbulence model framework aims to improve the prediction accuracy of the Spalart–Allmaras (SA) turbulence model in transonic bump flows. A random forest model is trained to construct a mapping between the input flow features and the output eddy viscosity difference. Results show that the intrinsic methods, including the hyperparameter study and the input feature selection, can reduce the model complexity at a limited cost of accuracy. The post-hoc Shapley additive explanations (SHAP) method not only provides a ranked list of input flow features based on their global significance, but also unveils the local causal link between the input flow features and the output eddy viscosity difference. Based on the SHAP analysis, the ML model is found to discover: (1) the well-known scaling between eddy viscosity and its source term, which was originally found from dimensional analysis; (2) the well-known rotation and shear effects on the eddy viscosity source term, which was explicitly written in the Reynolds stress transport equations; and (3) the pressure normal stress and normal shear stress effect on the eddy viscosity source term, which has not attracted much attention in previous research. The methods and the knowledge obtained from this work provide useful guidance for data-driven turbulence model developers, and they are transferable to future ML turbulence model developments.
AU  - He,X
AU  - Tan,J
AU  - Rigas,G
AU  - Vahdati,M
DO  - 10.1016/j.ijheatfluidflow.2022.109038
EP  - 16
PY  - 2022///
SN  - 0142-727X
SP  - 1
TI  - On the explainability of machine-learning-assisted turbulence modeling for transonic flows
T2  - International Journal of Heat and Fluid Flow
UR  - http://dx.doi.org/10.1016/j.ijheatfluidflow.2022.109038
UR  - http://hdl.handle.net/10044/1/103448
VL  - 97
ER  -
Download