A Passive Detection Orbit Determination Method Based on Deep Neural Network

A deep neural network and passive detection technology, applied in the field of optical camera relative orbit determination and navigation, to achieve the effects of reducing load, accelerating convergence, and improving observability

Active Publication Date: 2022-04-08
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method yields observability by superimposing independent biases on top of linearized motion dynamics, but due to the bias position vector length limitation, this method is only suitable for the proximate rendezvous phase

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 Passive Detection Orbit Determination Method Based on Deep Neural Network
  • A Passive Detection Orbit Determination Method Based on Deep Neural Network
  • A Passive Detection Orbit Determination Method Based on Deep Neural Network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some, not all, embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0035] The invention discloses a method based on a deep neural network for space non-cooperative target only relative orbit determination based on angle measurement, aiming at the fact that there are three groups of angle observations that are not enough to determine the relative orbit determination based on the linearized relative motion model The relative distance between the satellite and the target satellite, so that the relative motion state cannot be dete...

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 passive detection orbit determination method based on a deep neural network, comprising the following steps: Step 1, defining a spacecraft training data generator, and obtaining training data of a deep neural network through the data generator; Step 2, Preprocess the training data generated in step 1 to obtain standardized data; step 3, define the deep neural network, determine the appropriate parameters, and train the deep neural network offline through the standardized data to obtain the nonlinearity of only angle measurement relative to orbit determination Relative motion model; step 4, deploying the nonlinear relative motion model on the sensing satellite, and inputting the relative measurement angle into the model to realize online determination of the relative orbit of the target satellite. In the present invention, three sets of relative line-of-sight measurement angles are set for one-to-one mapping of model input, so as to realize the determination of the relative orbit of the non-cooperative target in the passive detection on the orbit.

Description

technical field [0001] The invention relates to the technical field of optical camera relative orbit determination and navigation, in particular to a passive detection orbit determination method based on a deep neural network. Background technique [0002] With the increasing frequency of space activities, the number of space non-cooperative targets such as invalid satellites and space debris is increasing rapidly. The near-Earth space environment is becoming more and more deteriorating, and the safety problems of spacecraft in orbit are becoming more and more prominent. Therefore, it is of great significance to enhance space situational awareness and conduct on-orbit autonomous service research such as maintenance and de-orbit cleaning for space non-cooperative targets such as invalid satellites. The key prerequisite for autonomous on-orbit service and enhanced space situational awareness is to realize The target is relatively orbited independently. [0003] At present, s...

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 & AuthorityPatents(China)
IPC IPC(8): G06F30/27G06N3/04G06N3/08G01C21/20G01C21/24G06F119/14
CPCG06F30/27G06N3/04G06N3/08G01C21/20G01C21/24G06F2119/14
Inventor龚柏春马钰权李爽廖文和
OwnerNANJING UNIV OF AERONAUTICS & ASTRONAUTICS