Open AccessThe use of neural network technologies to optimize the shape of an object during mass transfer of air
Author(s) -
Н. Н. Чернов,
Andrey Kovalev,
Alexander Palii,
A. V. Sayenko,
Maevskiy Andrey
Publication year - 2020
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/862/3/032028
Subject(s) - drag , separator (oil production) , aerodynamics , artificial neural network , computer science , duct (anatomy) , mechanics , artificial intelligence , physics , medicine , pathology , thermodynamics
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.