A satellite sensor fault detection and positioning method based on self-encoding observer

A fault detection and observer technology, applied in the direction of instruments, measuring devices, integrated navigators, etc., can solve the problems of insufficient fault location accuracy of sensors, and achieve the enhancement of autonomous working ability, reliability, reliability and autonomy. Effect

Active Publication Date: 2022-08-05
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Purpose of the invention: Aiming at the problem of insufficient fault location accuracy of sensors in satellite attitude control systems in the prior art, the present invention provides a satellite attitude sensor fault location method based on an autoencoder observer, which provides fast and accurate fault-tolerant control of satellite attitude. fault location

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 satellite sensor fault detection and positioning method based on self-encoding observer
  • A satellite sensor fault detection and positioning method based on self-encoding observer
  • A satellite sensor fault detection and positioning method based on self-encoding observer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0074] The method of the present invention performs fault detection and positioning on the satellite attitude sensor based on the self-encoding observer. The training stage and the application stage, such as figure 1 The specific steps are as follows:

[0075] (1) Design multiple self-encoding observers according to the attitude sensor equipped with the satellite, and use the sensor-free data to train the self-encoding observer, so that the encoder can compress the sensor signal, and the self-encoding observer can The sensor signal is inversely calculated from the data compressed by the encoder.

[0076] (2) Input the sensor signal into the self-encoding observer, and compare the input and output of the self-encoding observer to obtain the residual.

[0077] (3) After generating the residual, extract the feature information of the residual. The residual feature information in the book includes the mean value, mean square error and Shannon information entropy of the residual. ...

Embodiment 2

[0138] Configure the attitude sensor as Figure 5 The specific implementation steps of the satellite attitude sensor fault location method based on the self-encoding observer according to the present invention are as follows:

[0139] (1) According to the type and number of measurement signals of the attitude sensor configured by the satellite, the measurement signal types include vector type, attitude type and angular velocity type, and the number of designed self-encoding observers is 7:

[0140] Table 1 Autoencoder Observer Design

[0141]

[0142] And according to the input signal requirements of these seven self-encoding observers, the output signals of the satellite attitude sensor when there are no faults are collected, and the self-encoding observers are trained.

[0143]where Γ 1 The tracking effect of the autoencoder observer on the sensor signal is as follows Image 6 As shown, because the orbital position changes slowly, the last 6-dimensional data representi...

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 satellite sensor fault detection and positioning method based on an auto-encoding observer. The method performs fault detection and positioning on a satellite attitude sensor based on the self-encoding observer, including an observer design based on the self-encoding observer and a support vector machine. The system builds a self-encoding observer according to the satellite attitude measurement method, compares the input and output of the observer to generate residuals, uses a support vector machine to detect faults according to the mean, mean square error and information entropy of the residuals, and combines multiple self-encoding observations The detection result of the sensor is used to locate the faulty sensor. The invention can perform fault detection and fault location in combination with signals of a plurality of satellite attitude sensors, thereby improving the reliability and ground monitoring capability of the satellite attitude control system.

Description

technical field [0001] The invention belongs to fault diagnosis technology of satellite attitude sensor, in particular to a fault location method of satellite attitude sensor based on self-encoding observer. Background technique [0002] With the continuous development of technology in the aerospace field, the complexity of aerospace tasks has continued to increase, and the density of spacecraft system functions has also continued to increase. As a system with complex structure and functions, the development of spacecraft is time-consuming and costly. The spacecraft attitude control subsystem is one of the most important subsystems of the spacecraft. In order to ensure the reliability of the spacecraft, multiple attitude sensors are often configured for redundancy, but it also increases the complexity of the design of the fault diagnosis method, so that the fault diagnosis method can be used. Transplantability decreased. Therefore, it is urgent to propose a method that can ...

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): G01C25/00G01C21/24
CPCG01C25/00G01C21/24
Inventor 程月华叶正宇姜斌陆宁云何漫丽薛琪
Owner NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products