Unlock instant, AI-driven research and patent intelligence for your innovation.

A backstepping neural network control method for airship 3D track tracking

A neural network control and track tracking technology, which is applied in three-dimensional position/channel control, adaptive control, general control system, etc. The stability of the closed-loop control system is difficult to guarantee, so as to achieve the effect of ensuring stability, improving control accuracy and system performance

Active Publication Date: 2017-09-26
NAT UNIV OF DEFENSE TECH
View PDF8 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the above track control methods have not effectively solved the following two types of problems: one is that the dynamic model of the airship is uncertain, there are modeling errors and unmodeled dynamics; the other is that the airship track control system is a complex multivariable nonlinear system, It is difficult to guarantee the stability of the closed-loop control system within the flight envelope

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
  • A backstepping neural network control method for airship 3D track tracking
  • A backstepping neural network control method for airship 3D track tracking
  • A backstepping neural network control method for airship 3D track tracking

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0145] The present invention "a backstepping neural network control method for three-dimensional track tracking of an airship", its specific steps are as follows:

[0146] Step 1: Given command track

[0147] The given command track is:

[0148] n d =[x d ,y d ,z d ,θ d ,ψ d ,φ d ] T =[(3t)m,(0.93t)m,10m,0rad,0.3rad,0rad] T , x d 、y d ,z d , θ d 、ψ d and φ d They are command x coordinate, command y coordinate, command z coordinate, command pitch angle, command yaw angle and command roll angle;

[0149] Step 2: Calculation of track control error amount

[0150] Calculate the amount of track control error between the commanded track and the actual track:

[0151] e=η d -η=[x d -x,y d -y,z d -z,θ d -θ,ψ d -ψ,φ d -φ] T ,

[0152] where, η=[x,y,z,θ,ψ,φ] T is the actual track, x, y, z, θ, ψ, φ are the x coordinate, y coordinate, z coordinate, pitch angle, yaw angle and roll angle of the actual track respectively, which are continuously changing values.

...

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 invention relates to a backstepping neural network control method for airship three-dimensional track tracking. Aiming at the track tracking control problem of the airship, the present invention establishes the nonlinear dynamic model of the airship; with this as the controlled object, the nonlinear dynamic model is decomposed into two subsystems, and the backstepping method is used to design the Lyapunov model for each subsystem. function and the intermediate virtual control quantity, by determining the appropriate virtual feedback, the previous state of the system can be asymptotically stable, and it has been "reverse deduced" to the entire system, so as to achieve the asymptotic stability of the entire system; for the uncertain airship dynamics model problem, a neural network approximator is used to accurately estimate the unknown airship dynamics model to improve control accuracy and system performance. The closed-loop system controlled by this method can track any given parameterized instruction track with high precision, and has good stability, adaptability, robustness and dynamic performance, which provides an effective solution for the engineering realization of airship track control .

Description

technical field [0001] The invention relates to a flight control method in the aerospace field, which provides a backstepping neural network control method for airship track tracking, and belongs to the technical field of automatic control. Background technique [0002] An airship refers to an aircraft that relies on a gas that is lighter than air (such as helium, hydrogen, etc.) to provide static buoyancy, and relies on an automatic flight control system to achieve fixed-point residence and low-speed maneuvering. With the advantages of high cost ratio and fixed-point residence, it is widely used in reconnaissance and surveillance, earth observation, environmental monitoring, emergency relief, scientific detection and other fields. It has important application value and broad application prospects, and has become a research hotspot in the aviation field. [0003] Track tracking means that the airship starts from a given initial state and tracks the command track under a give...

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): G05D1/10G05B13/04
Inventor 杨跃能闫野朱正龙刘二江徐博婷
Owner NAT UNIV OF DEFENSE TECH