Improving aircraft performance using machine learning: A review

被引：71

作者：

Le Clainche, Soledad ^{[1
]}

Ferrer, Esteban ^{[1
,2
]}

Gibson, Sam ^{[3
]}

Cross, Elisabeth ^{[3
]}

Parente, Alessandro ^{[4
]}

Vinuesa, Ricardo ^{[5
]}

机构：

[1] Univ Politecn Madrid, ETSIAE UPM Sch Aeronaut, Plaza Cardenal Cisneros 3, Madrid 28040, Spain

[2] Univ Politecn Madrid, Ctr Computat Simulat, Campus Montegancedo, Madrid 28660, Spain

[3] Univ Sheffield, Dynam Res Grp, Sheffield, England

[4] Univ Libre Bruxelles, Brussels Fac Engn, Ave Franklin D Roosevelt 50, B-1050 Brussels, Belgium

[5] KTH Royal Inst Technol, FLOW, Engn Mech, Stockholm, Sweden

来源：

AEROSPACE SCIENCE AND TECHNOLOGY | 2023年 / 138卷

关键词：

PRINCIPAL COMPONENT ANALYSIS; PROPER ORTHOGONAL DECOMPOSITION; DYNAMIC ADAPTIVE CHEMISTRY; ARTIFICIAL NEURAL-NETWORKS; DIRECT NUMERICAL SIMULATIONS; TURBULENT-BOUNDARY-LAYERS; LARGE-EDDY SIMULATION; JET FLAMES; COMPUTATIONALLY-EFFICIENT; AERODYNAMIC COEFFICIENTS;

D O I：

10.1016/j.ast.2023.108354

中图分类号：

V [航空、航天];

学科分类号：

08 ; 0825 ;

摘要：

This review covers the new developments in machine learning (ML) that are impacting the multi-disciplinary area of aerospace engineering, including fundamental fluid dynamics (experimental and numerical), aerodynamics, acoustics, combustion and structural health monitoring. We review the state of the art, gathering the advantages and challenges of ML methods across different aerospace disciplines and provide our view on future opportunities. The basic concepts and the most relevant strategies for ML are presented together with the most relevant applications in aerospace engineering, revealing that ML is improving aircraft performance and that these techniques will have a large impact in the near future.(c) 2023 The Author(s). Published by Elsevier Masson SAS. This is an open access article under the CC BY license (http://creativecommons .org /licenses /by /4 .0/).

引用

页数：28

共 372 条

[1] A predictive hybrid reduced order model based on proper orthogonal decomposition combined with deep learning architectures [J].

Abadia-Heredia, R. ;

Lopez-Martin, M. ;

Carro, B. ;

Arribas, J., I ;

Perez, J. M. ;

Le Clainche, S. .

EXPERT SYSTEMS WITH APPLICATIONS, 2022, 187

[2] Aerodynamic technologies to improve aircraft performance [J].

Abbas, A. ;

de Vicente, J. ;

Valero, E. .

AEROSPACE SCIENCE AND TECHNOLOGY, 2013, 28 (01) :100-132

[3] Spanwise-coherent hydrodynamic waves around flat plates and airfoils [J].

Abreu, Leandra, I ;

Tanarro, Alvaro ;

Cavalieri, Andre V. G. ;

Schlatter, Philipp ;

Vinuesa, Ricardo ;

Hanifi, Ardeshir ;

Henningson, Dan S. .

JOURNAL OF FLUID MECHANICS, 2021, 927

[4] Information Dropout: Learning Optimal Representations Through Noisy Computation [J].

Achille, Alessandro ;

Soatto, Stefano .

IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2018, 40 (12) :2897-2905

[5]

Ajuria E., 2020, AIAA AVIATION FORUM, P1

[6] Predicting the propagation of acoustic waves using deep convolutional neural networks [J].

Alguacil, Antonio ;

Bauerheim, Michael ;

Jacob, Marc C. ;

Moreau, Stephane .

JOURNAL OF SOUND AND VIBRATION, 2021, 512

[7]

Alguacil Antonio, GENERIC DEEP LEARNIN

[8] A data-based hybrid model for complex fuel chemistry acceleration at high temperatures [J].

Alqahtani, Sultan ;

Echekki, Tarek .

COMBUSTION AND FLAME, 2021, 223 :142-152

[9]

[Anonymous], 2017, P IEEE C COMP VIS PA

[10]

[Anonymous], 2003, Computational models for turbulent reacting flows, DOI 10.1017/CBO9780511610103

← 1 2 3 4 5 6 7 8 9 10 →