Aircraft aerodynamic parameter identification method based on recurrent neural network

Abstract

The invention discloses an aircraft aerodynamic parameter identification method based on a recurrent neural network. The method comprises the following steps: 1) performing a simulated flight test by using a training-level simulator in combination with flight simulation software to obtain flight data; 2) taking the six-degree-of-freedom dynamic equation set of the aircraft rigid body as a state equation of the system, and calculating to obtain corresponding aerodynamic force and aerodynamic torque according to data obtained by the test; 3) taking flight data such as an attack angle and a sideslip angle as input, taking the aerodynamic parameters calculated in the step 2 as reference data, and training by utilizing a recurrent neural network combined with a real-time recurrent learning algorithm to obtain an aerodynamic parameter identification model; 4, selecting and loading flight data which do not participate in model training into the aerodynamic parameter identification model of the recurrent neural network obtained in the third step for parameter identification, and corresponding aerodynamic force and aerodynamic moment. The parameter identification model established through the method has good applicability, accurate modeling can be completed for aerodynamic force, and application and popularization can be achieved.

Description

technical field [0001] The invention relates to the field of aircraft aerodynamic parameter identification, in particular to a method for identifying aircraft aerodynamic parameters based on a cyclic neural network. Background technique [0002] Aircraft is an extremely complex system, and with the development of aircraft research, obtaining its accurate aerodynamic characteristics is an important premise and basis for establishing its aircraft model and designing an aircraft control system with excellent performance. There are three ways to obtain the aerodynamic characteristics of aircraft: theoretical calculation, wind tunnel test and aircraft test. In the process of developing an aircraft, the use of theoretical calculations can greatly reduce the design cycle and R&D costs. However, theoretical calculations are limited by imperfect theoretical research and computing power of computers, and cannot completely replace the other two methods. Compared with the flight test, ...

AI Technical Summary

Problems solved by technology

In the process of developing an aircraft, the use of theoretical calculations can greatly reduce the design cycle and R&D costs. However, theoretical calculations are limited by imperfect theoretical research and computing power of computers, and cannot completely replace the other two methods.

Compared with the flight test, the wind tunnel test is less expensive and more flexible, but the Reynolds number of the wind tunnel test is low, and there are wall interference and support interference, which has certain limitations

Images