Method for controlling neural network of hypersonic aerocraft on basis of prediction model

Abstract

The invention discloses a method for controlling a neural network of a hypersonic aerocraft on the basis of a prediction model, and belongs to the field of control for aerocrafts. The method is used for solving the technical problem of difficulty in engineering implementation of discrete adaptive control for an existing hypersonic aerocraft. The method includes obtaining a strict feedback form of a height subsystem by means of reasonable assumption, and creating a discrete form of an original system by an Eulerian method; building the four-step prediction model of the original system by means of continuous forward prediction; and adopting a lumped nominal design and error feedback for a controller and estimating and compensating lumped uncertain portions by the neural network. The four-step prediction model contains only one equation and provides the relation among height output at future moments, a current system state and control input. The method has the advantages that features of computer control are combined with the method, the discrete prediction model is built, virtual control variables are not required to be designed, only the neural network is required, and the method is suitable for engineering application.

Description

technical field [0001] The invention relates to a hypersonic aircraft control method, in particular to a predictive model-based hypersonic aircraft neural network control method, which belongs to the field of aircraft control. Background technique [0002] Due to its outstanding flight capability, hypersonic aircraft makes global real-time strike possible, so it has attracted widespread attention at home and abroad; NASA X-43A test flight successfully confirmed the feasibility of this technology; affected by its own complex dynamic characteristics and the airframe With the integrated design of the engine, the coupling between the elastic body, propulsion system and structural dynamics of the hypersonic vehicle is stronger, and the nonlinearity of the model is also higher; sensitive. [0003] The control of hypersonic vehicles is mostly concentrated in the continuous domain; with the development of computer technology, the control system of hypersonic vehicles in the future ...

AI Technical Summary

Problems solved by technology

[0004] "Adaptive Discrete-time Controller Design with Neural Network for Hypersonic Flight Vehicle via Back-stepping" (Xu Bin, Sun Fuchun, Yang Chengguang, Gao Daoxiang, Ren Jianxin, "International Journal of Control", Volume 84, Issue 9, 2011 ) transforms the altitude subsystem into a fourth-order model, and controls the altitude, track angle, and pitch angle by designing virtual control variables (track angle, pitch angle, and pitch angular velocity), and finally uses the rudder angle to control the pitch Angular velocity; this method uses a neural network to estimate the virtual control amount at the required future time, and requires four steps to achieve height control, the design process is complicated, and it is not conducive to engineering implementation

Images