Neural network compound learning control method for hypersonic vehicle re-entry stage

A hypersonic and neural network technology, applied in the direction of adaptive control, general control system, control/regulation system, etc., can solve problems such as poor precision, improve control precision, reduce conservatism, improve learning accuracy and rapidity Effect

Active Publication Date: 2019-10-18
NORTHWESTERN POLYTECHNICAL UNIV +1
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In order to overcome the deficiencies of the poor accuracy of existing hypersonic vehicle re-entry section attitude control methods, the present invention provides a hypersonic vehicle re-entry section neural network composite learning control method

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Neural network compound learning control method for hypersonic vehicle re-entry stage
  • Neural network compound learning control method for hypersonic vehicle re-entry stage
  • Neural network compound learning control method for hypersonic vehicle re-entry stage

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0027] refer to figure 1 . The specific steps of the hypersonic vehicle re-entry section neural network compound learning control method of the present invention are as follows:

[0028] (a) Establish the dynamic model of hypersonic vehicle re-entry section:

[0029]

[0030]

[0031] The dynamic model contains state variables X = [v, ω] T and control input U=M c , where v=[α β σ] T is the attitude angle vector, α, β, σ represent the angle of attack, sideslip angle and tilt angle respectively; ω=[p q r] T is the attitude angular rate vector, p, q, r represent the rolling, pitching and yaw angular rates respectively; M c =[M x m y m z ] T Indicates the control torque of the system;

[0032] (b) Define X=[x 1 x 2 ] T , x 1 =v,x 2 =ω. Then the attitude control model can be expressed as:

[0033]

[0034] where g 1 (x 1 )=R(·), f 2 (x 2 )=-I -1 ΩIω,g 2 (x 2 ) = I -1 .

[0035] (c) Define the attitude angle tracking error e 1 =x 1 -y d ;...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The present invention discloses a hypersonic flight vehicle reentry stage neural network composite learning control method used for solving the technical problem that a conventional hypersonic flight vehicle reentry stage attitude control method is poor in precision. The method of the technical scheme is characterized by firstly describing the hypersonic flight vehicle reentry stage dynamics into a control-oriented attitude model, then utilizing a neural network to learn an uncertainty function of a system to design a controller, and finally adopting the online data to construct a prediction modeling error, and utilizing a tracking error and the prediction error to form a composite error to update the weights of the neural network, thereby improving the learning performance of the neural network during the enclosed loop control process and the tracking performance. By utilizing the neural network to learn, the adaptive capability of the system can be improved, thereby improving the control precision. By utilizing the online data to construct the prediction error to evaluate the learning performance of the neural network, and combining the tracking error of the system to update the weights and the vectors of the neural network compositely, the learning accuracy of the neural network during the enclosed loop control process and the system tracking precision are improved.

Description

technical field [0001] The invention relates to a hypersonic aircraft re-entry attitude control method, in particular to a hypersonic aircraft re-entry neural network compound learning control method. Background technique [0002] Due to its high-speed flight capability, hypersonic vehicles make it possible to achieve "global reach and global operations" in emergency situations, so they have attracted widespread attention at home and abroad; NASA's X-43A test flight successfully confirmed the feasibility of this technology. During the reentry process of a hypersonic vehicle, the angle of attack and roll angle vary widely, and the system has a strong nonlinearity; at the same time, the aerodynamic coefficient and the control efficiency of the thrust reverser are all heavily dependent on the flight attitude, which makes the parameters and There is a serious nonlinear coupling between the states. The characteristics of the re-entry stage of hypersonic vehicles bring great chal...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Patents(China)
IPC IPC(8): G05B13/04
Inventor 许斌寿莹鑫
Owner NORTHWESTERN POLYTECHNICAL UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap