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

Star pattern identification method by combining with neural network technology and triangle algorithm

A neural network and star map recognition technology, which is applied in the field of star map recognition and all-sky star map recognition, can solve the problems of large storage capacity and slow recognition speed of the classic triangle algorithm, so as to reduce the storage capacity of star catalogues, improve the recognition rate, enhance the The effect of anti-interference

Active Publication Date: 2018-04-20
SHANGHAI INST OF TECHNICAL PHYSICS - CHINESE ACAD OF SCI
View PDF4 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to propose a star map recognition method combining neural network technology and triangle algorithm, apply neural network technology to the star map recognition process, and solve the problems of large storage capacity and slow recognition speed of classic triangle algorithm

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
  • Star pattern identification method by combining with neural network technology and triangle algorithm
  • Star pattern identification method by combining with neural network technology and triangle algorithm
  • Star pattern identification method by combining with neural network technology and triangle algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The specific implementation of the present invention will be described in detail below based on the working principle of the simulation platform star sensor. The catalog preprocessing process is as follows: figure 2 As shown in , the Hipparcos catalog is selected as the basic star catalog, and the maximum magnitude is set to 6.5 magnitude. At this time, the star catalog contains 8874 stars. Remove the variable stars and binary stars in the star catalog, regard the stars whose angular distance between the two stars is less than 0.1 arcsecond as binary stars, remove the darker stars in the binary stars, and keep the brighter stars. At this time, there are 8674 stars in the star catalog.

[0024] like image 3 As shown in the figure, feature extraction is performed on the star at the center of the circle, and a 10-dimensional feature vector is constructed, and concentric circles are drawn with the star as the center, and the angular distance difference between adjacent c...

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 discloses a star pattern identification method by combining with a neural network technology and a triangle algorithm. During operation of a star sensor, under condition without prior attitude, all-sky star pattern identification is carried out by employing the method provided by the invention. For a screened star database, a characteristic vector is constructed according to the distribution characteristic of the adjacent star of each star, the nerve network technology is employed for constructing a classification network, all stars in a star catalogue are classified, and the triangle information each star and triangle information of the adjacent star are stored in a triangle database. During star pattern identification, the characteristic vector of the to-be-identified starcan be generated, a most similar type is output through the classification network, and the triangle algorithm is used in the triangle database corresponding to the most similar type to find the coupled triangle. After the validation succeeds, the identification attitude is output. The star pattern identification method has the advantages of small storage content, fast identification speed, high recognition rate, and strong anti-interference performance.

Description

technical field [0001] The invention belongs to the technical field of spacecraft attitude measurement, and relates to a star map recognition method combined with neural network technology and classical triangle algorithm, which is suitable for all-sky star map recognition by star sensors without prior attitude. Background technique [0002] The navigation technology of the aircraft is one of the key technologies for the aircraft to explore space, and the solution of the attitude of the aircraft is the basis of the navigation technology. The star sensor is one of the commonly used attitude determination instruments. The key technologies mainly include star point centroid positioning, star map recognition and attitude calculation. Among them, the star map recognition process determines the attitude accuracy and attitude output speed of the star sensor. Therefore, it is particularly important in the development process of the star sensor to apply the star map recognition metho...

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 Applications(China)
IPC IPC(8): G01C21/02G06N3/04G06N3/08
CPCG01C21/025G06N3/04G06N3/088
Inventor 席红霞刘烟曹珺曲海波宋崇金陈丽安俊洁
Owner SHANGHAI INST OF TECHNICAL PHYSICS - CHINESE ACAD OF SCI
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