Anomaly detection method of satellite telemetry data based on dtw

A satellite telemetry data and anomaly detection technology, which is applied in the field of satellite telemetry data anomaly detection, can solve the problems of missing abnormal detection of satellite components, inaccurate time series measurement results, and inaccurate abnormal detection results, etc., to achieve the effect of solving abnormal missing detection

Active Publication Date: 2017-09-29
HARBIN INST OF TECH
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the problem that the abnormal parameters of the existing detection method do not exceed the alarm threshold, which causes the abnormal missed detection of satellite components, and the problem that there is a large deviation in the segmentation of satellite telemetry data with periodic characteristics with a fixed number of points There is a slight deviation from the time series, which makes the measurement results inaccurate and leads to inaccurate anomaly detection results.

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
  • Anomaly detection method of satellite telemetry data based on dtw
  • Anomaly detection method of satellite telemetry data based on dtw
  • Anomaly detection method of satellite telemetry data based on dtw

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0037] Specific implementation mode one: combine figure 1 Illustrate this embodiment, the method for abnormal detection of satellite telemetry data based on DTW, comprises the following steps:

[0038] Step 1: Segment with the point of the argument mutation point as the mark, and obtain the time series with category labels, including the normal time series X={x 1 ,x 2 ,...,x n}, the corresponding category label L={l 1 , l 2 ,...,l n}; where n is the number of time series containing category labels, l=1, 2, ..., c; c is the number of categories;

[0039] Step 2: Calculate the average DTW distance within each category in the time series containing category labels in is calculated as follows:

[0040]

[0041] in, Indicates the mean value of the intra-class distance of the l-th class, m l Indicates the number of members of class l, Indicates all members of class l, DTW(x li ,x lj ) means to calculate x li with x lj DTW distance between, i=1,2,...,m l -1,j=i+...

specific Embodiment approach 2

[0049] Specific implementation mode two: the specific implementation steps of step one described in this implementation mode are as follows:

[0050] Step 1.1: Segment the historical satellite telemetry data under the normal operating state of the satellite with the point of change in argument angle as the mark, and obtain the normal time series X={x 1 ,x 2 ,...,x n}; Argument is one of the test parameters in satellite telemetry data, and its changing law is increasing from 0 to 360. When it reaches 360, it becomes 0 and starts to increase again. The point from 360 to 0 is the argument Sudden point: Segmentation is carried out with the mark of the sudden change point of the argument angle, that is: record the corresponding time of the sudden change point of the argument angle, and extract other test parameters according to the time corresponding to the sudden change point of the argument angle, the extraction method is two adjacent sudden change points of the argument angle ...

specific Embodiment approach 3

[0053] Specific implementation mode three: the specific implementation steps of step five described in this embodiment mode are as follows:

[0054] Step 5.1: Determine the K time series containing category labels that are closest to the DTW of the time series x' to be detected, that is, when D={d 1 , d 2 ,...,d n}, take the K smallest values, and determine the time series containing the category labels corresponding to the K smallest values; the corresponding category labels are

[0055] Step 5.2: Statistical category labels The category with the highest frequency in , that is, the quasi-category is l'.

[0056] Other steps and parameters are the same as in the second embodiment.

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

A DTW-based satellite telemetry data anomaly detection method relates to the field of satellite telemetry data anomaly detection. In order to solve the problem that the abnormal parameter of the existing detection method does not exceed the alarm threshold, the problem of missing abnormal detection of satellite components, the problem of large deviation in the segmentation of satellite telemetry data with a fixed number of points and the time sequence There is a problem that the measurement results are not accurate enough due to the small offset, which leads to the inaccurate anomaly detection results. In the present invention, the satellite telemetry data is segmented using the argument point as a mark, and then the mean value of the DTW distance in each category in the time series containing the category label is calculated, and the time series x' to be detected abnormally is obtained; and x is calculated The DTW distance between ' and the time series X containing category labels, determine the minimum DTW distance dmin between x' and the quasi-category l', and determine whether x' is an abnormal sequence according to the size relationship between dmin and The invention is applicable to abnormal detection of satellite telemetry data.

Description

technical field [0001] The invention relates to the field of abnormal detection of satellite telemetry data. Background technique [0002] With the development of science and technology, more and more technologies depend on the realization of satellites, so the normal work of satellites is related to many industries and fields; during the operation of satellites in orbit, by monitoring satellite telemetry data, timely discovery of telemetry data Abnormalities play a decisive role in judging that various faults may occur in satellites; [0003] Threshold method is a common method used by the satellite measurement and control center to monitor the abnormality of satellite telemetry data. The main principle is to set the alarm threshold according to the nature and functional requirements of each telemetry data. When the telemetry data value exceeds the alarm threshold, it is judged that the parameters are abnormal, which belongs to abnormal point detection, but some satellite ...

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): G06K9/62G06F17/50
Inventor 彭宇刘大同陈静庞景月彭喜元
Owner HARBIN INST OF TECH
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