Neural network identification of aircraft nonlinear aerodynamic characteristics

2017 Workshop on Materials and Engineering in Aeronautics

材料科学;航空航天工程

Egorchev, M.V.^1 ; Tiumentsev, Yu V.^1

Flight Dynamics and Control Department, Moscow Aviation Institute (National Research University), Volokolamskoe shosse, 4, R-Moscow

125993, Russia^1

关键词: Aerodynamic characteristics;    Aerodynamic forces;    Data characterizing;    Neural network identifications;    Neural network model;    Non-linear aerodynamics;    Operating condition;    Simulation example;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/312/1/012008/pdf
DOI  :  10.1088/1757-899X/312/1/012008

来源: IOP

【 摘 要 】

The simulation problem for the controlled aircraft motion is considered in the case of imperfect knowledge of the modeling object and its operating conditions. The work aims to develop a class of modular semi-empirical dynamic models that combine the capabilities of theoretical and neural network modeling. We consider the use of semi-empirical neural network models for solving the problem of identifying aerodynamic characteristics of an aircraft. We also discuss the formation problem for a representative set of data characterizing the behavior of a simulated dynamic system, which is one of the critical tasks in the synthesis of ANN-models. The effectiveness of the proposed approach is demonstrated using a simulation example of the aircraft angular motion and identifying the corresponding coefficients of aerodynamic forces and moments.