Machine learning for adjoint vector in aerodynamic shape optimization

Mengfei Xu, Shufang Song, Xuxiang Sun, Wengang Chen, Weiwei Zhang

科研成果: 期刊稿件文章同行评审

10 引用 (Scopus)

摘要

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: [Figure not available: see fulltext.].

源语言英语
页(从-至)1416-1432
页数17
期刊Acta Mechanica Sinica/Lixue Xuebao
37
9
DOI
出版状态已出版 - 9月 2021

指纹

探究 'Machine learning for adjoint vector in aerodynamic shape optimization' 的科研主题。它们共同构成独一无二的指纹。

引用此