Open AccessArtificial neural networks in panel method for solving aerodynamics problem
Author(s) -
D. Yu. Strelets,
A A Kataev,
A L Khrustalev
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1024/1/012115
Subject(s) - aerodynamics , artificial neural network , aerospace , computer science , software , wing , mathematical optimization , aerospace engineering , engineering , artificial intelligence , mathematics , programming language
The authors proposed an experimental panel method combined with an artificial neural network to solve the problems of aerodynamics with minimum computational power consumption and high accuracy. A software solution based on the proposed method has been created. A comparison with experiments and other existing solutions has been made. The proposed method is intended for solving aerodynamic problems in systems of multi-criteria optimization, as well as in related problems. For example, solutions to the problem of strength and aerodynamics in the associated wing of a civil aircraft. The proposed method and software solution based on it can open new horizons in aerospace industry optimization calculations.