Real time fault diagnosis of Infrared Earth Sensor using Elman neural network

Zhaohui Cen, Jiaolong Wei, Rui Jiang, Xiong Liu

Research output: Contribution to journalArticle

Abstract

An online fault detecting and isolating (FDI) method was proposed for fault diagnosis of Infrared Earth Sensor. The Elman neural network was employed due to its capability of processing time-varying signals in real time. For the sake of simplicity, two Elman neural networks were developed for fault detecting (FD) and fault isolating (FI) respectively. For FD, an FD Elman neural network and corresponding logic judgment were designed to identify normal and faulty states; the output of FD was the moment when a fault occurred. For FI, a novel gradient updating strategy was introduced in FI Elman neural network which does faulty pattern matching and conducts FI. Simulation results demonstrate that the FDI strategy is real time, convergent available for output coupling, general with time-varying signals. The proposed FDI can avoid modeling, so it is suitable for online FDI of satellite attitude control system (SACS).

Original languageEnglish
Pages (from-to)504-509
Number of pages6
JournalZhendong Ceshi Yu Zhenduan/Journal of Vibration, Measurement and Diagnosis
Volume30
Issue number5
Publication statusPublished - 1 Oct 2010
Externally publishedYes

Fingerprint

Failure analysis
Earth (planet)
Infrared radiation
Neural networks
sensors
Sensors
satellite attitude control
Pattern matching
output
Attitude control
logic
Satellites
moments
Control systems
gradients
Processing
simulation

Keywords

  • Elman neural network
  • Fault detecting
  • Fault isolating
  • Infrared earth sensor
  • Real time fault diagnosis

ASJC Scopus subject areas

  • Mechanical Engineering
  • Mechanics of Materials
  • Acoustics and Ultrasonics
  • Instrumentation

Cite this

Real time fault diagnosis of Infrared Earth Sensor using Elman neural network. / Cen, Zhaohui; Wei, Jiaolong; Jiang, Rui; Liu, Xiong.

In: Zhendong Ceshi Yu Zhenduan/Journal of Vibration, Measurement and Diagnosis, Vol. 30, No. 5, 01.10.2010, p. 504-509.

Research output: Contribution to journalArticle

@article{15f0af5f036346919c117841b9165d9e,
title = "Real time fault diagnosis of Infrared Earth Sensor using Elman neural network",
abstract = "An online fault detecting and isolating (FDI) method was proposed for fault diagnosis of Infrared Earth Sensor. The Elman neural network was employed due to its capability of processing time-varying signals in real time. For the sake of simplicity, two Elman neural networks were developed for fault detecting (FD) and fault isolating (FI) respectively. For FD, an FD Elman neural network and corresponding logic judgment were designed to identify normal and faulty states; the output of FD was the moment when a fault occurred. For FI, a novel gradient updating strategy was introduced in FI Elman neural network which does faulty pattern matching and conducts FI. Simulation results demonstrate that the FDI strategy is real time, convergent available for output coupling, general with time-varying signals. The proposed FDI can avoid modeling, so it is suitable for online FDI of satellite attitude control system (SACS).",
keywords = "Elman neural network, Fault detecting, Fault isolating, Infrared earth sensor, Real time fault diagnosis",
author = "Zhaohui Cen and Jiaolong Wei and Rui Jiang and Xiong Liu",
year = "2010",
month = "10",
day = "1",
language = "English",
volume = "30",
pages = "504--509",
journal = "Zhendong Ceshi Yu Zhenduan/Journal of Vibration, Measurement and Diagnosis",
issn = "1004-6801",
publisher = "Nanjing University of Aeronautics an Astronautics",
number = "5",

}

TY - JOUR

T1 - Real time fault diagnosis of Infrared Earth Sensor using Elman neural network

AU - Cen, Zhaohui

AU - Wei, Jiaolong

AU - Jiang, Rui

AU - Liu, Xiong

PY - 2010/10/1

Y1 - 2010/10/1

N2 - An online fault detecting and isolating (FDI) method was proposed for fault diagnosis of Infrared Earth Sensor. The Elman neural network was employed due to its capability of processing time-varying signals in real time. For the sake of simplicity, two Elman neural networks were developed for fault detecting (FD) and fault isolating (FI) respectively. For FD, an FD Elman neural network and corresponding logic judgment were designed to identify normal and faulty states; the output of FD was the moment when a fault occurred. For FI, a novel gradient updating strategy was introduced in FI Elman neural network which does faulty pattern matching and conducts FI. Simulation results demonstrate that the FDI strategy is real time, convergent available for output coupling, general with time-varying signals. The proposed FDI can avoid modeling, so it is suitable for online FDI of satellite attitude control system (SACS).

AB - An online fault detecting and isolating (FDI) method was proposed for fault diagnosis of Infrared Earth Sensor. The Elman neural network was employed due to its capability of processing time-varying signals in real time. For the sake of simplicity, two Elman neural networks were developed for fault detecting (FD) and fault isolating (FI) respectively. For FD, an FD Elman neural network and corresponding logic judgment were designed to identify normal and faulty states; the output of FD was the moment when a fault occurred. For FI, a novel gradient updating strategy was introduced in FI Elman neural network which does faulty pattern matching and conducts FI. Simulation results demonstrate that the FDI strategy is real time, convergent available for output coupling, general with time-varying signals. The proposed FDI can avoid modeling, so it is suitable for online FDI of satellite attitude control system (SACS).

KW - Elman neural network

KW - Fault detecting

KW - Fault isolating

KW - Infrared earth sensor

KW - Real time fault diagnosis

UR - http://www.scopus.com/inward/record.url?scp=78649720548&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=78649720548&partnerID=8YFLogxK

M3 - Article

AN - SCOPUS:78649720548

VL - 30

SP - 504

EP - 509

JO - Zhendong Ceshi Yu Zhenduan/Journal of Vibration, Measurement and Diagnosis

JF - Zhendong Ceshi Yu Zhenduan/Journal of Vibration, Measurement and Diagnosis

SN - 1004-6801

IS - 5

ER -