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

A Satellite Fault Diagnosis Method Based on Adaboost Algorithm

A satellite fault and diagnosis method technology, applied in computing, computer parts, special data processing applications, etc., can solve problems such as weak fault state diagnosis ability, achieve the effect of increasing attention, enhancing performance, and improving classification accuracy

Active Publication Date: 2017-03-29
HARBIN INST OF TECH
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0026] The purpose of the invention is to propose a satellite fault diagnosis method based on the AdaBoost algorithm, to solve the problem that the fault diagnosis method of the existing naive Bayesian system is weak to the fault state diagnosis ability of the number

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 Fault Diagnosis Method Based on Adaboost Algorithm
  • A Satellite Fault Diagnosis Method Based on Adaboost Algorithm
  • A Satellite Fault Diagnosis Method Based on Adaboost Algorithm

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach 1

[0059] Embodiment 1: The method for diagnosing satellite faults based on the AdaBoost algorithm described in this embodiment includes the following steps: Step 1: Data initialization: Counting the information provided by the satellite, constructing each fault type and each different type The corresponding matrix of the occurrence times of event features is used to establish a fault diagnosis model;

[0060] The data relationship between the state of the satellite and the feature of the event is shown in Equation (1),

[0061] C 1 C 2 ... C j ... C K

[0062]

[0063] In the formula, E l ——The characteristics of the l-th type of event, l=1,2,...N';

[0064] K——Total number of satellite states;

[0065] C j ——The jth state of the satellite, j=1,2,...K;

[0066] e lj - the number of times the l-th event feature appears in the j-th state;

[0067] At this time, each sample of the training set is given the same weight for training the weak classifier;

[0068] Ste...

specific Embodiment approach 2

[0085] Embodiment 2: The difference between this embodiment and Embodiment 1 is that the specific process of assigning the same weight to each sample in the training set described in step 1 is as follows:

[0086] Assign the same weight w to all samples in the training set (i) , as in formula (3),

[0087]

[0088] where N is the number of state samples in the training set;

[0089] w (i) ——The weight of the i-th state sample, i=1,2...,N. Other steps are the same as in the first embodiment.

specific Embodiment approach 3

[0090] Embodiment 3: The difference between this embodiment and Embodiment 1 or 2 is that: the specific process of updating the weights of the training set described in step 3 is: in order to measure the classification accuracy of the weighted training set by the weak classifier, Calculate the parameter β, such as formula (4), and then use the parameter β to adjust the weight, such as formula (5),

[0091]

[0092]

[0093] In the formula, w′ (i) ——The adjusted weight of the ith state sample, w (i) is the weight of the i-th state sample;

[0094] After the adjusted weights of all state samples in the training set are calculated, all the weights are normalized so that the sum of the weights of the samples in the entire training set is 1, and the weight of the i-th state sample is at this time.

[0095] The normalized weights are given to the training set, that is, the weights of each sample are multiplied by the event characteristics of each state sample, as shown in ...

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 fault diagnosing method based on an AdaBoost algorithm and belongs to the technical field of satellite fault diagnosis. The satellite fault diagnosing method based on the AdaBoost algorithm is aimed to solve the problem that the fault diagnosing method of an existing Naive Bayes system is weak to diagnose a little of fault states. The satellite fault diagnosing method based on the AdaBoost algorithm reasonably uses the integrated AdaBoost algorithm for the existing Naive Bayes fault diagnosing system and includes that changing the weight of a sample after each training, to be specific, changing the value of an event type characteristic of a misclassified sample, and improving the concern extent of the fault diagnosing system for the characteristic; building a new correspondence matrix between the state and the event characteristic, training a classifier again, and integrating the trained classifier into a new fault diagnosing classifier. The satellite fault diagnosing method based on the AdaBoost algorithm is suitable for the satellite fault diagnosing field.

Description

technical field [0001] The invention relates to a satellite fault diagnosis method, mainly relates to a satellite fault diagnosis method based on an AdaBoost algorithm, and belongs to the technical field of satellite fault diagnosis. Background technique [0002] With the continuous progress of space technology, human's technical activities in space are increasing day by day. In recent years, the number of satellites in orbit in my country has increased significantly, and they are widely used in meteorological monitoring, image acquisition and military reconnaissance. However, the expansion of satellite functions has made it increasingly complex, and the rate of on-orbit accidents has increased significantly. Therefore, in the face of the huge and complex satellite system with huge investment, its reliability and safety are particularly important. Judging the working status and failure symptoms of the satellite, or performing rapid fault isolation and positioning under the...

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): G06F19/00G06K9/62
Inventor 彭宇刘大同贺思捷庞景月彭喜元
Owner HARBIN INST OF TECH
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