Volume 5, Number 3, July 2020 , pages 291-304 DOI: https://doi.org/10.12989/acd.2020.5.3.291 |
||
Predicting the 2-dimensional airfoil by using machine learning methods |
||
K. Thinakaran, R. Rajasekar, K. Santhi and M. Nalini
|
||
Abstract | ||
In this paper, we develop models to design the airfoil using Multilayer Feed-forward Artificial Neural Network (MFANN) and Support Vector Regression model (SVR). The aerodynamic coefficients corresponding to series of airfoil are stored in a database along with the airfoil coordinates. A neural network is created with aerodynamic coefficient as input to produce the airfoil coordinates as output. The performance of the models have been evaluated. The results show that the SVR model yields the lowest prediction error. | ||
Key Words | ||
support vector regression model; neural networks; airfoil design; inverse design; backpropagation | ||
Address | ||
K. Thinakaran: Computer Science Engeneering., Saveetha School of Engineering, SIMATS, Chennai 600 077 TN, India R. Rajasekar: Aeronautical Engineering, MVJ Engineering College, Bangalore, India K. Santhi: Sreenivasa Institute of Technology and Management Studies, Chittoor, India M. Nalini: Computer Science Engeneering., Saveetha School of Engineering, SIMATS, Chennai 600 077 TN, India | ||