Multiple sensor fault detection and isolation of an air quality monitoring network using RBF-NLPCA model

Mohamed-Faouzi Harkat, G. Mourot, J. Ragot

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

4 Citations (Scopus)

Abstract

This paper presents a data-driven method based on nonlinear principal component analysis to detect and isolate multiple sensor faults. The RBF-NLPCA model is obtained by combining a principal curve algorithm and two three layer radial basis function (RBF) networks. The reconstruction approach for multiple sensors is proposed in the non linear case and successfully applied for multiple sensor fault detection and isolation of an air quality monitoring network. The proposed approach reduces considerably the number of reconstruction combinations and allows to determine replacement values for the faulty sensors.

Original languageEnglish
Title of host publicationSAFEPROCESS'09 - 7th IFAC International Symposium on Fault Detection, Supervision and Safety of Technical Systems, Proceedings
Pages828-833
Number of pages6
DOIs
Publication statusPublished - 1 Dec 2009
Externally publishedYes
Event7th IFAC International Symposium on Fault Detection, Supervision and Safety of Technical Systems, SAFEPROCESS'09 - Barcelona, Spain
Duration: 30 Jun 20093 Jul 2009

Other

Other7th IFAC International Symposium on Fault Detection, Supervision and Safety of Technical Systems, SAFEPROCESS'09
CountrySpain
CityBarcelona
Period30/6/093/7/09

Fingerprint

Radial basis function networks
Fault detection
Air quality
Monitoring
Sensors
Principal component analysis

ASJC Scopus subject areas

  • Control and Systems Engineering

Cite this

Harkat, M-F., Mourot, G., & Ragot, J. (2009). Multiple sensor fault detection and isolation of an air quality monitoring network using RBF-NLPCA model. In SAFEPROCESS'09 - 7th IFAC International Symposium on Fault Detection, Supervision and Safety of Technical Systems, Proceedings (pp. 828-833) https://doi.org/10.3182/20090630-4-ES-2003.0305

Multiple sensor fault detection and isolation of an air quality monitoring network using RBF-NLPCA model. / Harkat, Mohamed-Faouzi; Mourot, G.; Ragot, J.

SAFEPROCESS'09 - 7th IFAC International Symposium on Fault Detection, Supervision and Safety of Technical Systems, Proceedings. 2009. p. 828-833.

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

Harkat, M-F, Mourot, G & Ragot, J 2009, Multiple sensor fault detection and isolation of an air quality monitoring network using RBF-NLPCA model. in SAFEPROCESS'09 - 7th IFAC International Symposium on Fault Detection, Supervision and Safety of Technical Systems, Proceedings. pp. 828-833, 7th IFAC International Symposium on Fault Detection, Supervision and Safety of Technical Systems, SAFEPROCESS'09, Barcelona, Spain, 30/6/09. https://doi.org/10.3182/20090630-4-ES-2003.0305
Harkat M-F, Mourot G, Ragot J. Multiple sensor fault detection and isolation of an air quality monitoring network using RBF-NLPCA model. In SAFEPROCESS'09 - 7th IFAC International Symposium on Fault Detection, Supervision and Safety of Technical Systems, Proceedings. 2009. p. 828-833 https://doi.org/10.3182/20090630-4-ES-2003.0305
Harkat, Mohamed-Faouzi ; Mourot, G. ; Ragot, J. / Multiple sensor fault detection and isolation of an air quality monitoring network using RBF-NLPCA model. SAFEPROCESS'09 - 7th IFAC International Symposium on Fault Detection, Supervision and Safety of Technical Systems, Proceedings. 2009. pp. 828-833
@inproceedings{1a22bbdab4b84e8d8f05dcf43bf23bd6,
title = "Multiple sensor fault detection and isolation of an air quality monitoring network using RBF-NLPCA model",
abstract = "This paper presents a data-driven method based on nonlinear principal component analysis to detect and isolate multiple sensor faults. The RBF-NLPCA model is obtained by combining a principal curve algorithm and two three layer radial basis function (RBF) networks. The reconstruction approach for multiple sensors is proposed in the non linear case and successfully applied for multiple sensor fault detection and isolation of an air quality monitoring network. The proposed approach reduces considerably the number of reconstruction combinations and allows to determine replacement values for the faulty sensors.",
author = "Mohamed-Faouzi Harkat and G. Mourot and J. Ragot",
year = "2009",
month = "12",
day = "1",
doi = "10.3182/20090630-4-ES-2003.0305",
language = "English",
isbn = "9783902661463",
pages = "828--833",
booktitle = "SAFEPROCESS'09 - 7th IFAC International Symposium on Fault Detection, Supervision and Safety of Technical Systems, Proceedings",

}

TY - GEN

T1 - Multiple sensor fault detection and isolation of an air quality monitoring network using RBF-NLPCA model

AU - Harkat, Mohamed-Faouzi

AU - Mourot, G.

AU - Ragot, J.

PY - 2009/12/1

Y1 - 2009/12/1

N2 - This paper presents a data-driven method based on nonlinear principal component analysis to detect and isolate multiple sensor faults. The RBF-NLPCA model is obtained by combining a principal curve algorithm and two three layer radial basis function (RBF) networks. The reconstruction approach for multiple sensors is proposed in the non linear case and successfully applied for multiple sensor fault detection and isolation of an air quality monitoring network. The proposed approach reduces considerably the number of reconstruction combinations and allows to determine replacement values for the faulty sensors.

AB - This paper presents a data-driven method based on nonlinear principal component analysis to detect and isolate multiple sensor faults. The RBF-NLPCA model is obtained by combining a principal curve algorithm and two three layer radial basis function (RBF) networks. The reconstruction approach for multiple sensors is proposed in the non linear case and successfully applied for multiple sensor fault detection and isolation of an air quality monitoring network. The proposed approach reduces considerably the number of reconstruction combinations and allows to determine replacement values for the faulty sensors.

UR - http://www.scopus.com/inward/record.url?scp=79960912499&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79960912499&partnerID=8YFLogxK

U2 - 10.3182/20090630-4-ES-2003.0305

DO - 10.3182/20090630-4-ES-2003.0305

M3 - Conference contribution

AN - SCOPUS:79960912499

SN - 9783902661463

SP - 828

EP - 833

BT - SAFEPROCESS'09 - 7th IFAC International Symposium on Fault Detection, Supervision and Safety of Technical Systems, Proceedings

ER -