Abstract: The paper deals with the possibility of using a neural network to find the aerodynamic characteristics of moving objects. An assessment of neural network application in the field of unmanned aircraft aerodynamics is provided, the advantages of using neural networks compared to traditional methods of calculating aerodynamic characteristics are indicated. A neural network model based on the linear regression algorithm was compiled and trained. With the help of this model, the drag coefficient of a car has been calculated. Simulation results are presented.

Keywords: neural network, machine learning, aerodynamic characteristics, linear regression, drag force

For citation: Kotsko P. A., Lemeshonok T. Yu., Sizova A. A. Application of neural networks for aerodynamic calculations. Aerospace Engineering and Technology. 2023. Vol. 1, no. 3, pp. 80–91. EDN ESYIXR