The use of neural network technologies to optimize the shape of an object during mass transfer of air

In this article, the authors propose using a neural network to optimize the aerodynamic drag of a body in a gas flow. The use of such optimization methods using evolutionary algorithms makes it possible to obtain a mathematical model that describes the shape of the aerodynamic profile, which allows...

Full description

Saved in:
Bibliographic Details
Published in:IOP conference series. Materials Science and Engineering 2020-05, Vol.862 (3), p.32028
Main Authors: Chernov, N N, Kovalev, A V, Palii, A V, Sayenko, A V, Maevskiy, A M
Format: Article
Language:English
Subjects:
Aerodynamic drag
Air flow
Drag
Evolutionary algorithms
Gas flow
Mass transfer
Neural networks
Optimization
Rotating bodies
Separators
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this article, the authors propose using a neural network to optimize the aerodynamic drag of a body in a gas flow. The use of such optimization methods using evolutionary algorithms makes it possible to obtain a mathematical model that describes the shape of the aerodynamic profile, which allows the operator to easily change parameters. It is shown that the value of the drag force for a body of optimized shape is lower than the values for bodies of rotation and known profiles taken for comparison. As bodies, we can consider parts of engineering structures in the air flow, parts of vehicles, and bodies located in the air flow in the duct, in particular in the duct of the photo separator. The latter is important from the point of view of neural network photo separation of seeds and grain.
ISSN:1757-8981
1757-899X
DOI:10.1088/1757-899X/862/3/032028