Real-time fault diagnosis of satellite attitude control system based on sliding-window wavelet and DRNN

Zhaohui Cen, Jiao Long Wei, Rui Jiang, Xiong Liu

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

This paper proposes an online fault detecting and isolating (FDI) scheme of satellite attitude control system (SACS) based on Wavelet and Dynamic Recurrent Neural Network (DRNN) which is capable of processing time-varying signals in real time. First, a novel improved wavelet method is proposed to detect faults; then, a DRNN is designed for fault isolating (FI) and the relevant fault decision module as well. The DRNN is trained by corresponding target FDI result of fault data set sampled from actuator and sensor outputs. Unlike many previous wavelet-based fault detecting methods developed in the literature, our proposed FDI scheme is only based on measurement signals which can avoid modeling, also wavelet method is improved and suitable for online signal processing .Real-time simulation is performed and the results demonstrate the validity and superiority of our method.

Original languageEnglish
Title of host publication2010 Chinese Control and Decision Conference, CCDC 2010
Pages1218-1222
Number of pages5
DOIs
Publication statusPublished - 13 Aug 2010
Externally publishedYes
Event2010 Chinese Control and Decision Conference, CCDC 2010 - Xuzhou, China
Duration: 26 May 201028 May 2010

Other

Other2010 Chinese Control and Decision Conference, CCDC 2010
CountryChina
CityXuzhou
Period26/5/1028/5/10

Fingerprint

Recurrent neural networks
Attitude control
Failure analysis
Satellites
Control systems
Signal processing
Actuators
Sensors
Processing
Sliding window
Fault
Wavelets
Fault diagnosis

Keywords

  • DRNN
  • Real-time fault diagnosis
  • SACS
  • Wavelet

ASJC Scopus subject areas

  • Decision Sciences (miscellaneous)
  • Control and Systems Engineering
  • Electrical and Electronic Engineering

Cite this

Cen, Z., Wei, J. L., Jiang, R., & Liu, X. (2010). Real-time fault diagnosis of satellite attitude control system based on sliding-window wavelet and DRNN. In 2010 Chinese Control and Decision Conference, CCDC 2010 (pp. 1218-1222). [5498162] https://doi.org/10.1109/CCDC.2010.5498162

Real-time fault diagnosis of satellite attitude control system based on sliding-window wavelet and DRNN. / Cen, Zhaohui; Wei, Jiao Long; Jiang, Rui; Liu, Xiong.

2010 Chinese Control and Decision Conference, CCDC 2010. 2010. p. 1218-1222 5498162.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Cen, Z, Wei, JL, Jiang, R & Liu, X 2010, Real-time fault diagnosis of satellite attitude control system based on sliding-window wavelet and DRNN. in 2010 Chinese Control and Decision Conference, CCDC 2010., 5498162, pp. 1218-1222, 2010 Chinese Control and Decision Conference, CCDC 2010, Xuzhou, China, 26/5/10. https://doi.org/10.1109/CCDC.2010.5498162
Cen Z, Wei JL, Jiang R, Liu X. Real-time fault diagnosis of satellite attitude control system based on sliding-window wavelet and DRNN. In 2010 Chinese Control and Decision Conference, CCDC 2010. 2010. p. 1218-1222. 5498162 https://doi.org/10.1109/CCDC.2010.5498162
Cen, Zhaohui ; Wei, Jiao Long ; Jiang, Rui ; Liu, Xiong. / Real-time fault diagnosis of satellite attitude control system based on sliding-window wavelet and DRNN. 2010 Chinese Control and Decision Conference, CCDC 2010. 2010. pp. 1218-1222
@inproceedings{626599a62a8c48c58fdb7e631f5bf3dd,
title = "Real-time fault diagnosis of satellite attitude control system based on sliding-window wavelet and DRNN",
abstract = "This paper proposes an online fault detecting and isolating (FDI) scheme of satellite attitude control system (SACS) based on Wavelet and Dynamic Recurrent Neural Network (DRNN) which is capable of processing time-varying signals in real time. First, a novel improved wavelet method is proposed to detect faults; then, a DRNN is designed for fault isolating (FI) and the relevant fault decision module as well. The DRNN is trained by corresponding target FDI result of fault data set sampled from actuator and sensor outputs. Unlike many previous wavelet-based fault detecting methods developed in the literature, our proposed FDI scheme is only based on measurement signals which can avoid modeling, also wavelet method is improved and suitable for online signal processing .Real-time simulation is performed and the results demonstrate the validity and superiority of our method.",
keywords = "DRNN, Real-time fault diagnosis, SACS, Wavelet",
author = "Zhaohui Cen and Wei, {Jiao Long} and Rui Jiang and Xiong Liu",
year = "2010",
month = "8",
day = "13",
doi = "10.1109/CCDC.2010.5498162",
language = "English",
isbn = "9781424451821",
pages = "1218--1222",
booktitle = "2010 Chinese Control and Decision Conference, CCDC 2010",

}

TY - GEN

T1 - Real-time fault diagnosis of satellite attitude control system based on sliding-window wavelet and DRNN

AU - Cen, Zhaohui

AU - Wei, Jiao Long

AU - Jiang, Rui

AU - Liu, Xiong

PY - 2010/8/13

Y1 - 2010/8/13

N2 - This paper proposes an online fault detecting and isolating (FDI) scheme of satellite attitude control system (SACS) based on Wavelet and Dynamic Recurrent Neural Network (DRNN) which is capable of processing time-varying signals in real time. First, a novel improved wavelet method is proposed to detect faults; then, a DRNN is designed for fault isolating (FI) and the relevant fault decision module as well. The DRNN is trained by corresponding target FDI result of fault data set sampled from actuator and sensor outputs. Unlike many previous wavelet-based fault detecting methods developed in the literature, our proposed FDI scheme is only based on measurement signals which can avoid modeling, also wavelet method is improved and suitable for online signal processing .Real-time simulation is performed and the results demonstrate the validity and superiority of our method.

AB - This paper proposes an online fault detecting and isolating (FDI) scheme of satellite attitude control system (SACS) based on Wavelet and Dynamic Recurrent Neural Network (DRNN) which is capable of processing time-varying signals in real time. First, a novel improved wavelet method is proposed to detect faults; then, a DRNN is designed for fault isolating (FI) and the relevant fault decision module as well. The DRNN is trained by corresponding target FDI result of fault data set sampled from actuator and sensor outputs. Unlike many previous wavelet-based fault detecting methods developed in the literature, our proposed FDI scheme is only based on measurement signals which can avoid modeling, also wavelet method is improved and suitable for online signal processing .Real-time simulation is performed and the results demonstrate the validity and superiority of our method.

KW - DRNN

KW - Real-time fault diagnosis

KW - SACS

KW - Wavelet

UR - http://www.scopus.com/inward/record.url?scp=77955345976&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77955345976&partnerID=8YFLogxK

U2 - 10.1109/CCDC.2010.5498162

DO - 10.1109/CCDC.2010.5498162

M3 - Conference contribution

SN - 9781424451821

SP - 1218

EP - 1222

BT - 2010 Chinese Control and Decision Conference, CCDC 2010

ER -