Here, we investigate a method for the inverse design of airfoil sections using artificial neural networks (ANNs). The aerodynamic force coefficients corresponding to series of airfoil are stored in a database along with the airfoil coordinates. A feedforward neural network is created with aerodynamic coefficient as input to produce the airfoil coordinates as output. In this paper, we explore different strategies for training this neural network. From our test, the most promising backpropagation strategy is to initially use steepest descent algorithm and then continue with linear and nonlinear constraint in the algorithm. Results indicate that our combined approach optimally trains artificial neural network and may accurately predict airfoil profile.
Design of Airfoil Using Backpropagation Training with Combined Approach
Lect.Notes Mechanical Engineering
Innovative Design, Analysis and Development Practices in Aerospace and Automotive Engineering ; Chapter : 36 ; 295-306
2014-05-03
12 pages
Article/Chapter (Book)
Electronic Resource
English
Optical backpropagation training method and its applications
British Library Conference Proceedings | 2020
|Efficient Training of Neural Networks using Optical Backpropagation with Momentum Factor
British Library Online Contents | 2008
|