Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Unsupervised clustering anomaly detection method

An unsupervised clustering and anomaly detection technology, applied in digital data information retrieval, special data processing applications, instruments, etc., can solve problems such as difficulty in acquiring knowledge and difficulty in building models

Active Publication Date: 2020-09-01
CHINA XIAN SATELLITE CONTROL CENT
View PDF4 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present disclosure provides a method for unsupervised clustering anomaly detection, which can solve too much dependence on the prior knowledge of the spacecraft system. In practical applications, the model Difficult to build, difficult to acquire knowledge, etc. issues

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
  • Unsupervised clustering anomaly detection method
  • Unsupervised clustering anomaly detection method
  • Unsupervised clustering anomaly detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0089] Time scale alignment and equally spaced sample sequence generation;

[0090] Establish the Kth target telemetry data sequence with equal time intervals for the Kth telemetry data of the n original telemetry data, and obtain the Kth target telemetry data sequence through time scale alignment for the Kth target telemetry data sequence;

[0091] Assuming that there are n spacecraft telemetry parameters in total, record the original time series data of the kth telemetry parameter as {(t,s k (t)), t ∈ [t s ,t e ]}, where t represents time, s k (t) represents the data value of the kth telemetry parameter corresponding to time t, t s Indicates the start time, t e Indicates the end time.

[0092] In one embodiment, such as image 3 As shown, time scale alignment and equal interval sample sequence generation include the following step 101: given n spacecraft telemetry parameters, and sample sequence start time ts and end time t e , for a given time interval t d , satisfy...

Embodiment 2

[0103] 1. Modeling sample preparation;

[0104] In one embodiment, such as Figure 4 As shown, the Kth target telemetry data is standardized to obtain the data vector X of the target telemetry data. After time-scale alignment of each component of the data vector X of the Kth target telemetry data, the Single-Linkage clustering method Modeling to obtain a clustering model set S; modeling sample preparation includes the following steps:

[0105] 201: m sample data X with n telemetry parameters i ∈R n ,i=1,2,...,m,

[0106] where sample X i =(x i1 ,x i2 ,...,x in ),

[0107] Calculate the mean of each telemetry parameter sample data separately and standard deviation

[0108] 202: Use the Z-score method according to the formula Normalize the parameters, where x' ij is the standardized variable value, x ij is the actual variable value.

[0109] 203: Output the standardized data set D={X' i ,i=1,…,m}, where X i '=(x' i1 ,x′ i2 ,…,x′ in ).

[0110] 204: Use ra...

Embodiment 3

[0123] Calculate the detection threshold threshold;

[0124] In one embodiment such as Figure 6 Shown; Obtain the detection threshold threshold value step of the Kth target telemetry data as follows;

[0125] 401: Take a subset D of the data set D 2 .

[0126] 402: Calculate D 2 Each data vector in The distance from the clustering model set S Get the distance set {d i ,i=1,2,3,…,n}, n is the data set D 2 The number of data vectors in .

[0127] 403: Calculate distance set {d i ,i=1,2,3,…,n} average value and standard deviation

[0128] 404: Take the threshold value β=μ+3σ.

[0129] In dataset D 2 , calculate the detection threshold β=0.55 for data anomaly detection according to step 4.

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 provides an unsupervised clustering anomaly detection method, relates to a spacecraft anomaly detection method, and can solve the problems that an accurate physical analysis model of spacecraft operation at present depends too much on priori knowledge of a spacecraft system, a model is difficult to establish in practical application, knowledge is difficult to obtain and the like. According to the specific technical scheme, a large amount of accumulated spacecraft normal state data are utilized, time scale alignment and equal-interval sampling are conducted on sample data, the sample data are generated, and a spacecraft normal state data model is established through unsupervised clustering analysis based on the thought of inductive learning. The minimum distance of the sampledata is calculated by utilizing a clustering result, a minimum distance set of the sample data is counted and analyzed, and a threshold value of telemetry data anomaly detection is established by utilizing Gaussian distribution. On the above basis, abnormal data detection is realized by judging the deviation degree between the real-time observation data of the spacecraft and the normal state datamodel. The method is used for processing and analyzing spacecraft telemetry data.

Description

technical field [0001] The disclosure relates to the field of radio tracking measurement data processing and application, and is suitable for processing and analyzing spacecraft telemetry data, and in particular relates to a method for unsupervised clustering anomaly detection Background technique [0002] Due to the long-term operation of satellites in orbit in complex and harsh space environments, affected by various uncertain factors, their performance and functions may change, which will also be reflected in telemetry parameters. abnormal, the corresponding telemetry parameters will also change. Therefore, it is necessary to analyze the changing law of telemetry data of in-orbit satellites, study the abnormal detection methods of in-orbit satellites, find out the abnormal signs of in-orbit satellites early, take measures in advance to avoid possible major failures, reduce the risk of satellite in-orbit operation, and improve the quality of satellites in orbit. The safet...

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
IPC IPC(8): G06K9/62G06F16/2458
CPCG06F16/2474G06F18/23
Inventor 袁线李卫平高宇郭小红程富强付枫周轩张雷王超蔡立锋张峻华林海晨
Owner CHINA XIAN SATELLITE CONTROL CENT
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com