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

Low-orbit satellite precision orbit determination strategy supported by machine learning

A machine learning and precise orbit determination technology, applied in machine learning, artificial satellites, instruments, etc., can solve the problems of high conditions and long periods of observation.

Active Publication Date: 2021-03-30
CHINA XIAN SATELLITE CONTROL CENT
View PDF2 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although the reliability of the precise orbit determination strategy supported by expert experience is relatively high, the period for forming effective experience is relatively long, and observations need to meet relatively high conditions

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
  • Low-orbit satellite precision orbit determination strategy supported by machine learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0059] A set of common simplified policy combinations is used as the policy space and labeled separately:

[0060] (11) Simultaneous estimation of atmospheric drag and light pressure,

[0061] (10) Estimates of atmospheric drag only,

[0062] (00) Atmospheric resistance and light pressure are not estimated.

[0063] Considering the characteristics of the machine learning design samples and the available actual samples, a number of civil and commercial low-orbit satellites with orbital heights ranging from 400km to 1000km were selected as training samples, and the S-band signals of the sample satellites were continuously observed for several months. (up to one year). The data of 0.5, 1.0, 1.5, 2.0, 3.0, 4.0, and 5.0 days are selected for precise orbit determination every month, and no orbital maneuvers are guaranteed during this period. The data set has a total of 709 pieces of data, including 358 pieces with the label 00, 289 pieces with the label 10, and 62 pieces with 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 discloses a low-orbit satellite precision orbit determination strategy supported by machine learning. The low-orbit satellite precision orbit determination strategy is specifically implemented according to the following steps: defining an orbit determination strategy set as a strategy space of the low-orbit satellite precision orbit determination strategy supported by machine learning; selecting four types of characteristics of observation, satellite, orbit and space environment as characteristics of a machine learning training sample; defining an orbit determination quality function as a label used for machine learning; taking the features of the orbit determination strategy set and the machine learning training sample as input, learning the features by using a label and adopting an automatic supervised learning algorithm to obtain a machine learning model of an orbit determination strategy; and obtaining an intelligent precise orbit determination strategy according to the machine learning model of the orbit determination strategy. According to the low-orbit satellite precision orbit determination strategy supported by machine learning, the precision orbit determination strategy drawing accuracy under complex observation conditions can be improved, and the use efficiency of a current kinetic model and observation data is improved to the maximum extent.

Description

technical field [0001] The invention belongs to the intersection field of aerospace measurement and control and artificial intelligence technology, and specifically relates to a low-orbit satellite precision orbit determination strategy supported by machine learning. Background technique [0002] Modern precision satellite orbit determination is a system engineering that includes various technologies such as tracking measurement, data processing, optimal estimation, and orbit dynamics forecasting. Position speed, acceleration, etc. At present, satellite precise orbit determination mainly improves the accuracy of orbit determination by improving various dynamic models and improving observation accuracy. However, the limitations of different models and the engineering constraints in the measurement greatly increase the complexity of the precise orbit determination process. Therefore, the process of precise satellite orbit determination requires experts with a lot of experien...

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): G06N20/00G01C21/24B64G1/10
CPCG06N20/00G01C21/24B64G1/10
Inventor 呼延宗泊李恒年马鹏斌姜春生朱俊王奥
Owner CHINA XIAN SATELLITE CONTROL CENT
Features
  • R&D
  • Intellectual Property
  • Life Sciences
  • Materials
  • Tech Scout
Why Patsnap Eureka
  • Unparalleled Data Quality
  • Higher Quality Content
  • 60% Fewer Hallucinations
Social media
Patsnap Eureka Blog
Learn More