Sensor fault detection, isolation and reconstruction using nonlinear principal component analysis

Mohamed-Faouzi Harkat, Salah Djelel, Noureddine Doghmane, Mohamed Benouaret

Research output: Contribution to journalArticle

34 Citations (Scopus)

Abstract

State reconstruction approach is very useful for sensor fault isolation, reconstruction of faulty measurement and the determination of the number of components retained in the principal components analysis (PCA) model. An extension of this approach based on a Nonlinear PCA (NLPCA) model is described in this paper. The NLPCA model is obtained using five layer neural network. A simulation example is given to show the performances of the proposed approach.

Original languageEnglish
Pages (from-to)149-155
Number of pages7
JournalInternational Journal of Automation and Computing
Volume4
Issue number2
DOIs
Publication statusPublished - 1 Apr 2007
Externally publishedYes

Fingerprint

Fault Detection and Isolation
Nonlinear Analysis
Fault detection
Principal component analysis
Principal Component Analysis
Sensor
Sensors
Fault Isolation
Number of Components
Model
Neural Networks
Neural networks
Simulation

Keywords

  • Fault detection and isolation
  • Neural networks
  • Nonlinear PCA (NLPCA)
  • Reconstruction

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Modelling and Simulation
  • Computer Science Applications
  • Applied Mathematics

Cite this

Sensor fault detection, isolation and reconstruction using nonlinear principal component analysis. / Harkat, Mohamed-Faouzi; Djelel, Salah; Doghmane, Noureddine; Benouaret, Mohamed.

In: International Journal of Automation and Computing, Vol. 4, No. 2, 01.04.2007, p. 149-155.

Research output: Contribution to journalArticle

@article{23dc929a3f80440faff8ef6d42197e76,
title = "Sensor fault detection, isolation and reconstruction using nonlinear principal component analysis",
abstract = "State reconstruction approach is very useful for sensor fault isolation, reconstruction of faulty measurement and the determination of the number of components retained in the principal components analysis (PCA) model. An extension of this approach based on a Nonlinear PCA (NLPCA) model is described in this paper. The NLPCA model is obtained using five layer neural network. A simulation example is given to show the performances of the proposed approach.",
keywords = "Fault detection and isolation, Neural networks, Nonlinear PCA (NLPCA), Reconstruction",
author = "Mohamed-Faouzi Harkat and Salah Djelel and Noureddine Doghmane and Mohamed Benouaret",
year = "2007",
month = "4",
day = "1",
doi = "10.1007/s11633-007-0149-6",
language = "English",
volume = "4",
pages = "149--155",
journal = "International Journal of Automation and Computing",
issn = "1476-8186",
publisher = "Chinese Academy of Sciences",
number = "2",

}

TY - JOUR

T1 - Sensor fault detection, isolation and reconstruction using nonlinear principal component analysis

AU - Harkat, Mohamed-Faouzi

AU - Djelel, Salah

AU - Doghmane, Noureddine

AU - Benouaret, Mohamed

PY - 2007/4/1

Y1 - 2007/4/1

N2 - State reconstruction approach is very useful for sensor fault isolation, reconstruction of faulty measurement and the determination of the number of components retained in the principal components analysis (PCA) model. An extension of this approach based on a Nonlinear PCA (NLPCA) model is described in this paper. The NLPCA model is obtained using five layer neural network. A simulation example is given to show the performances of the proposed approach.

AB - State reconstruction approach is very useful for sensor fault isolation, reconstruction of faulty measurement and the determination of the number of components retained in the principal components analysis (PCA) model. An extension of this approach based on a Nonlinear PCA (NLPCA) model is described in this paper. The NLPCA model is obtained using five layer neural network. A simulation example is given to show the performances of the proposed approach.

KW - Fault detection and isolation

KW - Neural networks

KW - Nonlinear PCA (NLPCA)

KW - Reconstruction

UR - http://www.scopus.com/inward/record.url?scp=34547313739&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=34547313739&partnerID=8YFLogxK

U2 - 10.1007/s11633-007-0149-6

DO - 10.1007/s11633-007-0149-6

M3 - Article

VL - 4

SP - 149

EP - 155

JO - International Journal of Automation and Computing

JF - International Journal of Automation and Computing

SN - 1476-8186

IS - 2

ER -