Research on prediction method of hydro-resistance of a seaplane based on BP network

As one of the important hydrodynamic indexes of seaplane, resistance performance is related to the practicality and economy of a seaplane. Due to the strong nonlinearity between resistance and test variables, it is difficult to predict the response relationship between them by conventional data fitt...

Full description

Saved in:
Bibliographic Details
Published in:Journal of physics. Conference series 2022-03, Vol.2228 (1), p.12018
Main Authors: Gao, Xianjiao, Liu, Tao, Zuo, Zibin, Wu, Bin
Format: Article
Language:English
Subjects:
Back propagation networks
Model testing
Performance indices
Physics
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:As one of the important hydrodynamic indexes of seaplane, resistance performance is related to the practicality and economy of a seaplane. Due to the strong nonlinearity between resistance and test variables, it is difficult to predict the response relationship between them by conventional data fitting method. This paper proposes to use BP neural network to construct the response relationship between model parameters and hydro-resistance, and so it can be used to the prediction of aircraft resistance under different conditions. The result shows that prediction error of this method is controlled within 4.4%, which meets the needs of engineering accuracy. This method can reduce the model test cost to some extent, and provide a new way for the prediction of hydro-resistance of seaplane.
ISSN:1742-6588
1742-6596
DOI:10.1088/1742-6596/2228/1/012018