Spacecraft electrical signal classification method of reliability test based on random forest

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

Abstract

The spacecraft electrical signal characteristic data exist a large amount of data, high dimension features, computational complexity degree and low rate of identification problems. This paper proposes the feature extraction method based on wavelet de-noising and the classification method based on random forest (RF) algorithm. Considering the time complexity, the method of wavelet de-noising is used to compress the data and reduce the dimension and then applied to classification. The random forest algorithm has superior performance in dealing with the large amount of data. The experimental results show that compared with other algorithms, the proposed method shows excellent performance in accuracy, computational efficiency, stability in dealing with spacecraft electrical signal data.

Original languageEnglish
Title of host publicationMan–Machine–Environment System Engineering - Proceedings of the 17th International Conference on MMESE
EditorsShengzhao Long, Balbir S Dhillon
PublisherSpringer Verlag
Pages457-465
Number of pages9
ISBN (Print)9789811062315
DOIs
StatePublished - 2018
Event17th International Conference on Man–Machine–Environment System Engineering, MMESE 2017 - Jinggangshan, China
Duration: 21 Oct 201723 Oct 2017

Publication series

NameLecture Notes in Electrical Engineering
Volume456
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference17th International Conference on Man–Machine–Environment System Engineering, MMESE 2017
Country/TerritoryChina
CityJinggangshan
Period21/10/1723/10/17

Keywords

  • Electrical signal classification
  • RF
  • Spacecraft fault diagnosis

Fingerprint

Dive into the research topics of 'Spacecraft electrical signal classification method of reliability test based on random forest'. Together they form a unique fingerprint.

Cite this