Abstract
An efficient computational framework is presented and applied to the inverse aerodynamic shape design problem. The main building block is a novel neural network capable to accurately predict the pressure distribution on aerofoils and wings. The trained neural network is used to accelerate the evaluation of the objective function in an optimisation algorithm based on the gradient-free modified cuckoo search method. Two applications are presented in two and three dimensions for problems involving up to 50 geometric parameters.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Balla K, Sevilla R, Hassan O, Morgan K (2021) An application of neural networks to the prediction of aerodynamic coefficients of aerofoils and wings. Appl Math Model 96:456–479
Brezillon J, Abu-Zurayk M (2013) Aerodynamic inverse design framework using discrete adjoint method. New results in numerical and experimental fluid mechanics VIII. Springer, pp 489–496
Dulikravich GS (1997) Aerodynamic shape inverse design methods. In: Sobieczky H (eds) New design concepts for high speed air transport. International centre for mechanical sciences, vol 366. Springer, 1997
Haga M, Demuth H, Beale M, DeJesus O (2014) Neural network design, 2nd edn. Martin Hagan
Khurana M, Winarto H, Sinha A (2008) Application of swarm approach and artificial neural networks for airfoil shape optimization. In: 12th AIAA/ISSMO multidisciplinary analysis and optimization conference, vol 5954
Piegl L, Tiller W (1995) The NURBS book. Springer, Berlin, Heidelberg
Sevilla R, Fernández-Méndez S (2011) Numerical integration over 2D NURBS-shaped domains with applications to NURBS-enhanced FEM. Finite Elem Anal Des 47(10):1209–1220
Sørensen KA, Hassan O, Morgan K, Weatherill NP (2003) A multigrid accelerated hybrid unstructured mesh method for 3D compressible turbulent flow. Comput Mech 31(1–2):101–114
Suresh S, Omkar S, Mani V, Prakash TG (2003) Lift coefficient prediction at high angle of attack using recurrent neural network. Aerosp Sci Technol 7(8):595–602
Walton S, Hassan O, Morgan K, Brown M (2011) Modified cuckoo search: a new gradient free optimisation algorithm. Chaos, Solitons & Fractals 44(9):710–718
Yang XS (2010) Nature-inspired metaheuristic algorithms. Luniver Press
Yang XS, Deb S (2010) Engineering optimisation by cuckoo search. Int J Math Model Numer Optim 1(4):330–343
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Balla, K., Sevilla, R., Hassan, O., Morgan, K. (2022). Inverse Aerodynamic Design Using Neural Networks. In: Knoerzer, D., Periaux, J., Tuovinen, T. (eds) Advances in Computational Methods and Technologies in Aeronautics and Industry. Computational Methods in Applied Sciences, vol 57. Springer, Cham. https://doi.org/10.1007/978-3-031-12019-0_10
Download citation
DOI: https://doi.org/10.1007/978-3-031-12019-0_10
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-12018-3
Online ISBN: 978-3-031-12019-0
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)