Skip to main navigation Skip to search Skip to main content

Online Intelligent Identification Method of Spacecraft Mass Characteristics

  • Harbin Institute of Technology
  • Aerospace System Engineering Shanghai
  • Shanghai Aerospace Control Technology Institute

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

Abstract

This paper investigates an online intelligent identification method for spacecraft mass characteristics. Firstly, the basic recursive least square method is given based on the modeling of the air-bearing tested system. To improve the identification speed and accuracy, an intelligent identification method using deep neural networks (DNNs) is introduced, where the training data for DNNs is derived from the designed identification scheme based on the grey wolf algorithm. Then, a reasonable stack mechanism with a small-sample data update is proposed to meet the needs of online identification. Simulation results show the online identification method can achieve high-precision and fast identification with a rotational inertia error of less than 0.33% and a center of mass offset error of less than 1.9%.

Original languageEnglish
Title of host publication2023 42nd Chinese Control Conference, CCC 2023
PublisherIEEE Computer Society
Pages1391-1396
Number of pages6
ISBN (Electronic)9789887581543
DOIs
StatePublished - 2023
Event42nd Chinese Control Conference, CCC 2023 - Tianjin, China
Duration: 24 Jul 202326 Jul 2023

Publication series

NameChinese Control Conference, CCC
Volume2023-July
ISSN (Print)1934-1768
ISSN (Electronic)2161-2927

Conference

Conference42nd Chinese Control Conference, CCC 2023
Country/TerritoryChina
CityTianjin
Period24/07/2326/07/23

Keywords

  • Air bearing testbed
  • Data stack
  • Deep neural networks
  • Grey wolf algorithm
  • Mass characteristics
  • Online identification

Fingerprint

Dive into the research topics of 'Online Intelligent Identification Method of Spacecraft Mass Characteristics'. Together they form a unique fingerprint.

Cite this