Aerodynamic optimization of aircraft wings using machine learning

被引:3
作者
Hasan, M. [1 ]
Redonnet, S. [2 ]
Zhongmin, D. [1 ]
机构
[1] Beihang Univ, Sch Astronaut, Beijing, Peoples R China
[2] Hong Kong Univ Sci & Technol, Mech & Aerosp Engn Dept, Hong Kong, Peoples R China
关键词
Aircraft design; Aerodynamic optimization; Computational fluid dynamics; Machine learning; Common research model (CRM); MODEL;
D O I
10.1016/j.advengsoft.2024.103801
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
This study proposes a fast yet reliable optimization framework for the aerodynamic design of transonic aircraft wings. Combining Computational Fluid Dynamics (CFD) and Machine Learning (ML), the framework is successfully applied to the Common Research Model (CRM) benchmark aircraft proposed by NASA. The framework relies on a series of automated CFD simulations, from which no less than 160 planform variations of the CRM wing are assessed from an aerodynamic standpoint. This database is used to educate an ML surrogate model, for which two specific algorithms are explored, namely eXtreme Gradient Boosting (XGB) and Light Gradient Boosting Machine (LGBM). Once trained with 80% of this database and tested with the remaining 20%, the ML surrogates are employed to explore a larger design space, their optimum being then inferred using an optimization framework relying on a Multi-Objective Genetic Algorithm (MOGAO). Each ML-based optimal planform is then simulated through CFD to confirm its aerodynamic merits, which are then compared against those of a conventional, fully CFD-based optimization. The comparison is very favourable, the best ML-based optimal planform exhibiting similar performances as its CFD-optimized counterpart (e.g. a 14% higher lift-to-drag ratio) for only half of the CPU cost. Overall, this study demonstrates the potential of ML-based methods for optimizing aircraft wings, thereby paving the way to the adoption of more disruptive, data-driven aircraft design paradigms.
引用
收藏
页数:15
相关论文
共 50 条
[41]   Modelling aircraft noise map around an airport using machine learning [J].
Rafanambinantsoa, Valohery Clermont ;
Muraretu, Ionut Dorinel ;
Dimbisoa, William Germain ;
Mahatody, Thomas ;
Badica, Costin ;
Razafindrakoto, Raft .
2024 INTERNATIONAL CONFERENCE ON INNOVATIONS IN INTELLIGENT SYSTEMS AND APPLICATIONS, INISTA, 2024,
[42]   Multi-objective Aerodynamic Optimization for Telescopic Wings Considering Space Constraints [J].
Wu, Jiaxue ;
Chang, Min ;
Zheng, Zhongyuan ;
Bai, Junqiang .
2023 ASIA-PACIFIC INTERNATIONAL SYMPOSIUM ON AEROSPACE TECHNOLOGY, VOL II, APISAT 2023, 2024, 1051 :1830-1846
[43]   Parametric estimation scheme for aircraft fuel consumption using machine learning [J].
Mirza Anas Wahid ;
Syed Hashim Raza Bukhari ;
Muazzam Maqsood ;
Farhan Aadil ;
Muhammad Ismail Khan ;
Saeed Ehsan Awan .
Neural Computing and Applications, 2023, 35 :24925-24946
[44]   Parametric estimation scheme for aircraft fuel consumption using machine learning [J].
Wahid, Mirza Anas ;
Bukhari, Syed Hashim Raza ;
Maqsood, Muazzam ;
Aadil, Farhan ;
Khan, Muhammad Ismail ;
Awan, Saeed Ehsan .
NEURAL COMPUTING & APPLICATIONS, 2023, 35 (35) :24925-24946
[45]   Sitting posture detection and recognition of aircraft passengers using machine learning [J].
Cun, Wenzhe ;
Mo, Rong ;
Chu, Jianjie ;
Yu, Suihuai ;
Zhang, Huizhong ;
Fan, Hao ;
Chen, Yanhao ;
Wang, Mengcheng ;
Wang, Hui ;
Chen, Chen .
AI EDAM-ARTIFICIAL INTELLIGENCE FOR ENGINEERING DESIGN ANALYSIS AND MANUFACTURING, 2021, 35 (03) :284-294
[46]   Prediction of aircraft estimated time of arrival using machine learning methods [J].
Basturk, O. ;
Cetek, C. .
AERONAUTICAL JOURNAL, 2021, 125 (1289) :1245-1259
[47]   Evaluation of the aircraft fuel economy using advanced statistics and machine learning [J].
Baumann S. ;
Neidhardt T. ;
Klingauf U. .
CEAS Aeronautical Journal, 2021, 12 (03) :669-681
[48]   Using Big Data and Machine Learning to Improve Aircraft Reliability and Safety [J].
Salvador, Marcos ;
Yacout, Soumaya ;
AboElHassan, Ayman .
2022 68TH ANNUAL RELIABILITY AND MAINTAINABILITY SYMPOSIUM (RAMS 2022), 2022,
[49]   Inverse Aerodynamic Design of Gas Turbine Blades Using Probabilistic Machine Learning [J].
Ghosh, Sayan ;
Padmanabha, Govinda Anantha ;
Peng, Cheng ;
Andreoli, Valeria ;
Atkinson, Steven ;
Pandita, Piyush ;
Vandeputte, Thomas ;
Zabaras, Nicholas ;
Wang, Liping .
JOURNAL OF MECHANICAL DESIGN, 2022, 144 (02)
[50]   Comprehensive effects of aerodynamic performance and dynamic strength of aircraft wings after bird strike in numerical simulation [J].
Xing, Li ;
Zhang, Yongjie ;
Wang, Faliang ;
Fu, Rao ;
Sun, Zhonglei ;
Li, Yuanyuan .
MECHANICS OF ADVANCED MATERIALS AND STRUCTURES, 2024, 31 (26) :8564-8582