A Machine Learning Approach to Predict Near-optimal Meshes for Turbulent Compressible Flow Simulations

被引：0

作者：

Sanchez-Gamero, Sergi ^{[1
]}

Hassan, Oubay ^{[1
]}

Sevilla, Ruben ^{[1
]}

机构：

[1] Swansea Univ, Zienkiewicz Ctr Computat Engn, Fac Sci & Engn, Swansea, Wales

来源：

INTERNATIONAL JOURNAL OF COMPUTATIONAL FLUID DYNAMICS | 2024年 / 38卷 / 2-3期

基金：

英国工程与自然科学研究理事会;

关键词：

Mesh generation; spacing function; machine learning; artificial neural network; turbulent compressible viscous flow; SUPERCONVERGENT PATCH RECOVERY; NEURAL-NETWORKS; GENERATOR; TIME;

D O I：

10.1080/10618562.2024.2306941

中图分类号：

O3 [力学];

学科分类号：

08 ; 0801 ;

摘要：

This work presents a methodology to predict a near-optimal spacing function, which defines the element sizes, suitable to perform steady RANS turbulent viscous flow simulations. The strategy aims at utilising existing high fidelity simulations to compute a target spacing function and train an artificial neural network (ANN) to predict the spacing function for new simulations, either unseen operating conditions or unseen geometric configurations. Several challenges induced by the use of highly stretched elements are addressed. The final goal is to substantially reduce the time and human expertise that is nowadays required to produce suitable meshes for simulations. Numerical examples involving turbulent compressible flows in two dimensions are used to demonstrate the ability of the trained ANN to predict a suitable spacing function. The influence of the NN architecture and the size of the training dataset are discussed. Finally, the suitability of the predicted meshes to perform simulations is investigated.

引用

页码：221 / 245

页数：25

共 44 条

[1]

Abadi M., Barham P., Chen J., Chen Z., Davis A., Dean J., Devin M., (2016)

[2]

Alfonzetti S., A Finite Element Mesh Generator Based on An Adaptive Neural Network, IEEE Transactions on Magnetics, 34, 5, pp. 3363-3366, (1998)

[3]

Alfonzetti S., A Neural Network Generator for Tetrahedral Meshes, IEEE Transactions on Magnetics, 39, 3, pp. 1650-1653, (2003)

[4]

Alfonzetti S., Coco S., Cavalieri S., Malgeri M., Automatic Mesh Generation by the Let-it-grow Neural Network, IEEE Transactions on Magnetics, 32, 3, pp. 1349-1352, (1996)

[5]

Balla K., Sevilla R., Hassan O., Morgan K., (2022)

[6]

Bohn J., Feischl M., Recurrent Neural Networks As Optimal Mesh Refinement Strategies, Computers & Mathematics with Applications, 97, pp. 61-76, (2021)

[7]

Chang-Hoi A., Sang-Soo L., Hyuek-Jae L., Soo-Young L., A Self-organizing Neural Network Approach for Automatic Mesh Generation, IEEE Transactions on Magnetics, 27, 5, pp. 4201-4204, (1991)

[8]

Chedid R., Najjar N., Automatic Finite-element Mesh Generation Using Artificial Neural Networks-Part I: Prediction of Mesh Density, IEEE Transactions on Magnetics, 32, 5, pp. 5173-5178, (1996)

[9]

Cheng J., Druzdzel M.J., (2000)

[10]

Cook P.H., McDonald M.A., Firmin M.C.P., Aerofoil RAE2822. Pressure Distributions, and Boundary Layer and Wake Measurements. Experimental Data Base for Computer Program Assessment, AGARD Report AR, 138, (1979)

← 1 2 3 4 5 →