Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A Control Method of Three-axis Inertially Stabilized Platform Based on Model Reference Adaptive Neural Network

A technology of neural network and stable platform, applied in adaptive control, general control system, control/regulation system, etc.

Active Publication Date: 2019-10-18
北京宇鹰科技有限公司
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The technical problem solved by the present invention is: the control accuracy of the three-axis inertial stable platform is affected by the nonlinearity of the system model and multi-source interference, the nonlinearity of the model is solved by real-time estimation of the feedback control parameters through the adaptive neural network, and the expansion observer is constructed to improve the system Excellent anti-interference ability, realize high-precision control of three-axis inertial stable platform in complex environment

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 Control Method of Three-axis Inertially Stabilized Platform Based on Model Reference Adaptive Neural Network
  • A Control Method of Three-axis Inertially Stabilized Platform Based on Model Reference Adaptive Neural Network
  • A Control Method of Three-axis Inertially Stabilized Platform Based on Model Reference Adaptive Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0061] Such as figure 1 Shown, the concrete realization of the present invention is as follows

[0062] (1) Build a model-based reference adaptive neural network

[0063] Based on the Newton-Euler equation, the dynamic equation of the three-axis inertial stabilized platform is expressed as

[0064]

[0065] Among them, x=[θ j ω j ] T , H=0 3×3 , F=(f jk ),j,k=1,2,3,

[0066] u=[u 1 u 2 u 3 ] T , g=[g 1 g 2 g 3 ] T , d=[d 1 d 2 d 3 ] T ,

[0067] Among them, when j=1, it represents the roll frame, when j=2, the pitch frame, and when j=3, it represents the azimuth frame, is the state variable of the system, n=6 is the dimension of the state variable, θ j is the corresponding j-frame angle, ω j is the corresponding j-frame angular velocity, is the coefficient matrix of the state variables, The coefficient matrix input for the framework, m=3 is the dimension of the system input, u j is the corresponding j frame voltage input, g is the ...

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 provides a model reference self-adaptive neural network-based three-axis inertial stabilization platform control method and relates to the disturbance rejection design based on the control parameter online estimation of an adaptive neural network and an expansion state observer. According to the method, firstly, according to a three-axis inertial stabilization platform dynamics model, constructing an adaptive neural network for the online estimation of adaptive neural network aiming at the time-variant characteristics of feedback control parameters caused by the uncertain model parameters of the three-axis inertia stabilization platform, so as to enable the control precision of the three-axis inertial stabilization platform to approach an expected model control precision; secondly, aiming at the estimation error of the adaptive neural network and the influence of a disturbance compensation controlled variable constructed on the three-axis inertial stabilization platform on the control precision, constructing the expansion state observer to estimate and inhibit the disturbance. In this way, the high-precision control of the three-axis inertial stabilization platform in a complex environment is realized. The method has the advantages of being good in real-time performance, high in dynamic parameter response, high in multi-source interference adaptability and the like. The method can be used for the high-precision control of the three-axis inertial stabilization platform in the complex multi-source interference environment.

Description

technical field [0001] The invention relates to a control method of a three-axis inertial stable platform based on a model reference self-adaptive neural network, which is suitable for the field of high-precision control of aeronautical surveying and mapping stable platforms. Background technique [0002] The three-axis inertial stabilization platform is fixed to the flight carrier through the base, supports and stabilizes the remote sensing imaging load, isolates the influence of multi-source interference on the boresight of the remote sensing imaging load, and improves the ground pointing accuracy of the remote sensing load, which has broad application prospects. [0003] There are various types of disturbances in the working process of the three-axis inertial stabilized platform, not only unpredictable random wind disturbances and angular motion disturbances caused by the vibration of the aircraft body, but also unbalanced moments caused by the misalignment of the center o...

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 李志毅
Owner 北京宇鹰科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com