A fault detection index using principal component analysis and mahalanobis distance

I. Jaffel, O. Taouali, Mohamed-Faouzi Harkat, H. Messaoud

Research output: Contribution to journalConference article

4 Citations (Scopus)

Abstract

This paper proposes a novel index to detect a sensor fault based on Principal Component Analysis (PCA) method. The main idea behind this index is to evaluate similarity between Principal Components PCs that represent a normal behavior of a system and a new PCs that represent current function. This index is evaluated on a Chemical Reactor (CSTR) and the results are satisfactory.

Original languageEnglish
Pages (from-to)1397-1401
Number of pages5
JournalIFAC-PapersOnLine
Volume28
Issue number21
DOIs
Publication statusPublished - 1 Sep 2015
Externally publishedYes

Fingerprint

Chemical reactors
Fault detection
Principal component analysis
Sensors

Keywords

  • Fault detection
  • PCA

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

A fault detection index using principal component analysis and mahalanobis distance. / Jaffel, I.; Taouali, O.; Harkat, Mohamed-Faouzi; Messaoud, H.

In: IFAC-PapersOnLine, Vol. 28, No. 21, 01.09.2015, p. 1397-1401.

Research output: Contribution to journalConference article

Jaffel, I. ; Taouali, O. ; Harkat, Mohamed-Faouzi ; Messaoud, H. / A fault detection index using principal component analysis and mahalanobis distance. In: IFAC-PapersOnLine. 2015 ; Vol. 28, No. 21. pp. 1397-1401.
@article{84df9941374d42a8999e5f181db058cb,
title = "A fault detection index using principal component analysis and mahalanobis distance",
abstract = "This paper proposes a novel index to detect a sensor fault based on Principal Component Analysis (PCA) method. The main idea behind this index is to evaluate similarity between Principal Components PCs that represent a normal behavior of a system and a new PCs that represent current function. This index is evaluated on a Chemical Reactor (CSTR) and the results are satisfactory.",
keywords = "Fault detection, PCA",
author = "I. Jaffel and O. Taouali and Mohamed-Faouzi Harkat and H. Messaoud",
year = "2015",
month = "9",
day = "1",
doi = "10.1016/j.ifacol.2015.09.720",
language = "English",
volume = "28",
pages = "1397--1401",
journal = "IFAC-PapersOnLine",
issn = "2405-8963",
publisher = "IFAC Secretariat",
number = "21",

}

TY - JOUR

T1 - A fault detection index using principal component analysis and mahalanobis distance

AU - Jaffel, I.

AU - Taouali, O.

AU - Harkat, Mohamed-Faouzi

AU - Messaoud, H.

PY - 2015/9/1

Y1 - 2015/9/1

N2 - This paper proposes a novel index to detect a sensor fault based on Principal Component Analysis (PCA) method. The main idea behind this index is to evaluate similarity between Principal Components PCs that represent a normal behavior of a system and a new PCs that represent current function. This index is evaluated on a Chemical Reactor (CSTR) and the results are satisfactory.

AB - This paper proposes a novel index to detect a sensor fault based on Principal Component Analysis (PCA) method. The main idea behind this index is to evaluate similarity between Principal Components PCs that represent a normal behavior of a system and a new PCs that represent current function. This index is evaluated on a Chemical Reactor (CSTR) and the results are satisfactory.

KW - Fault detection

KW - PCA

UR - http://www.scopus.com/inward/record.url?scp=84992513219&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84992513219&partnerID=8YFLogxK

U2 - 10.1016/j.ifacol.2015.09.720

DO - 10.1016/j.ifacol.2015.09.720

M3 - Conference article

AN - SCOPUS:84992513219

VL - 28

SP - 1397

EP - 1401

JO - IFAC-PapersOnLine

JF - IFAC-PapersOnLine

SN - 2405-8963

IS - 21

ER -