Machine learning for adjoint vector in aerodynamic shape optimization

Adjoint method is widely used in aerodynamic design because only once solution of flow field is required for it to obtain the gradients of all design variables. However, the computational cost of adjoint vector is approximately equal to that of flow computation. In order to accelerate the solution o...

Full description

Saved in:
Bibliographic Details
Published in:Acta mechanica Sinica 2021-09, Vol.37 (9), p.1416-1432
Main Authors: Xu, Mengfei, Song, Shufang, Sun, Xuxiang, Chen, Wengang, Zhang, Weiwei
Format: Article
Language:English
Subjects:
Artificial neural networks
Classical and Continuum Physics
Computational efficiency
Computational Intelligence
Computing costs
Drag reduction
Engineering
Engineering Fluid Dynamics
Local flow
Machine learning
Optimization
Research Paper
Shape optimization
Theoretical and Applied Mechanics
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Adjoint method is widely used in aerodynamic design because only once solution of flow field is required for it to obtain the gradients of all design variables. However, the computational cost of adjoint vector is approximately equal to that of flow computation. In order to accelerate the solution of adjoint vector and improve the efficiency of adjoint-based optimization, machine learning for adjoint vector modeling is presented. Deep neural network (DNN) is employed to construct the mapping between the adjoint vector and the local flow variables. DNN can efficiently predict adjoint vector and its generalization is examined by a transonic drag reduction of NACA0012 airfoil. The results indicate that with negligible computational cost of the adjoint vector, the proposed DNN-based adjoint method can achieve the same optimization results as the traditional adjoint method. Graphical abstract
ISSN:0567-7718
1614-3116
DOI:10.1007/s10409-021-01119-6