Non-domain knowledge satellite sub-system exception detection method

A technology of anomaly detection and domain knowledge, applied in the interdisciplinary field of aerospace science and computer science, to achieve the effect of solving high noise

Active Publication Date: 2017-05-10
NANJING UNIV OF AERONAUTICS & ASTRONAUTICS
View PDF2 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is to invent an anomaly detection method for satellite telemetry data based on satellite telemetry data. Based on this method, the occurrence time of satellite anomalies can be detected, thereby solving problems such as satellite health monitoring, and realizing timely discovery of satellite suspicious behaviors and avoidance, providing new technical support for the control and management of satellite in-orbit operation

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
  • Non-domain knowledge satellite sub-system exception detection method
  • Non-domain knowledge satellite sub-system exception detection method
  • Non-domain knowledge satellite sub-system exception detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0014] The present invention will be further described below in conjunction with the accompanying drawings and related algorithms.

[0015] The overall process of the present invention is as figure 1 shown.

[0016] The present invention designs an anomaly detection method without domain knowledge for satellite telemetry data, removes noise data in the data and extracts normalized data in combination with wavelet analysis and data preprocessing methods. Use the shared nearest neighbor algorithm to construct the relevant data set space, determine the search range of each data record, reduce the search space, and improve operating efficiency. For the constructed related data set space, combined with the attribute selection method based on angle deviation to screen the characteristic attributes, for the related data set space that has been screened for the characteristic attributes, use the normalized Mahalanobis distance to calculate the abnormal value, and combine the statisti...

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 non-domain knowledge satellite sub-system exception detection method. The method includes, to a high-dimensional data space constructed by satellite telemetry data, constructing a related data set space by a shared neighbor algorithm with distance replaced by angle; screening attributes associated with exception by an angular offset attribute selection algorithm; and finally, calculating exception valve by normalized mahalanobis distance, calculating to obtain the exception threshold according to knowledge of statistics, and classifying the data set. The non-domain knowledge satellite sub-system exception detection method to the complicated satellite subsystem telemetry data has the advantages of higher detection accuracy and better effect according to repeated tests.

Description

technical field [0001] The invention relates to a satellite subsystem anomaly detection method without domain knowledge. The method utilizes a shared nearest neighbor algorithm to construct a related data set space, adopts an attribute selection method based on an angle deviation to screen characteristic attributes, and utilizes a normalized Mahalanobis distance to calculate anomalies value and carry out abnormal classification, the invention belongs to the intersection field of aerospace science and computer science. Background technique [0002] Satellite is a multi-functional system developed by integrating remote sensing, communication, computer science and other multi-disciplinary technologies. It is the primary way for human beings to explore the mysteries of the universe. Due to various factors such as solar radiation and large temperature changes in outer space, various abnormalities or failures will occur during the satellite’s in-orbit operation. Timely detection a...

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): G06F19/00
CPCG16Z99/00
Inventor 皮德常康旭
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap