Satellite Fault Detection and Diagnosis based on Data Compression and Improved Decision Tree

Yanyan Hao, Chen Zhang, Senchun Chai, Zhaoyang Li, Xiaopeng Liu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

6 Citations (Scopus)

Abstract

Human exploration of space is always ongoing, and satellites play a huge role in this process. Therefore, the stable operation of satellites is very important, and how to detect and diagnose satellite faults has become a key issue. This paper presents a method based on data compression and improved decision tree algorithm, which has improved in both the accuracy and efficiency of satellite fault diagnosis and detection. In the experiment, we used the actually collected communication satellite telemetry data as the original data set to verify the performance and efficiency of the method proposed in this article. The results show that our method can save computing resources and significantly improve model training efficiency; at the same time, it can also resist overfitting and improve detection accuracy. This method can provide an effective solution for satellite fault detection and diagnosis.

Original languageEnglish
Title of host publicationProceedings - 2020 Chinese Automation Congress, CAC 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1686-1691
Number of pages6
ISBN (Electronic)9781728176871
DOIs
Publication statusPublished - 6 Nov 2020
Externally publishedYes
Event2020 Chinese Automation Congress, CAC 2020 - Shanghai, China
Duration: 6 Nov 20208 Nov 2020

Publication series

NameProceedings - 2020 Chinese Automation Congress, CAC 2020

Conference

Conference2020 Chinese Automation Congress, CAC 2020
Country/TerritoryChina
CityShanghai
Period6/11/208/11/20

Keywords

  • data compression
  • decision tree
  • fault detection
  • fault diagnosis

Fingerprint

Dive into the research topics of 'Satellite Fault Detection and Diagnosis based on Data Compression and Improved Decision Tree'. Together they form a unique fingerprint.

Cite this