Combined input training and radial basis function neural networks based nonlinear principal components analysis model applied for process monitoring

Messaoud Bouakkaz, Mohamed-Faouzi Harkat

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

Abstract

In this paper a novel Nonlinear Principal Component Analysis (NLPCA) is proposed. Generally, a NLPCA model is performed by using two sub-models, mapping and demapping. The proposed NLPCA model consists of two cascade three-layer neural networks for mapping and demapping, respectively. The mapping model is identified by using a Radial Basis Function (RBF) neural networks and the demapping is performed by using an Input Training neural networks (IT-Net). The nonlinear principal components, which represents the desired output of the first network, are obtained by the IT-NET. The proposed approach is illustrated by a simulation example and then applied for fault detection and isolation of the TECP process.

Original languageEnglish
Title of host publicationIJCCI 2012 - Proceedings of the 4th International Joint Conference on Computational Intelligence
Pages483-492
Number of pages10
Publication statusPublished - 1 Dec 2012
Externally publishedYes
Event4th International Joint Conference on Computational Intelligence, IJCCI 2012 - Barcelona, Spain
Duration: 5 Oct 20127 Oct 2012

Other

Other4th International Joint Conference on Computational Intelligence, IJCCI 2012
CountrySpain
CityBarcelona
Period5/10/127/10/12

Fingerprint

Process monitoring
Principal component analysis
Neural networks
Fault detection

Keywords

  • Fault Detection and Isolation
  • IT-net
  • Nonlinear PCA
  • Process Monitoring
  • RBF-neural Network

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Bouakkaz, M., & Harkat, M-F. (2012). Combined input training and radial basis function neural networks based nonlinear principal components analysis model applied for process monitoring. In IJCCI 2012 - Proceedings of the 4th International Joint Conference on Computational Intelligence (pp. 483-492)

Combined input training and radial basis function neural networks based nonlinear principal components analysis model applied for process monitoring. / Bouakkaz, Messaoud; Harkat, Mohamed-Faouzi.

IJCCI 2012 - Proceedings of the 4th International Joint Conference on Computational Intelligence. 2012. p. 483-492.

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

Bouakkaz, M & Harkat, M-F 2012, Combined input training and radial basis function neural networks based nonlinear principal components analysis model applied for process monitoring. in IJCCI 2012 - Proceedings of the 4th International Joint Conference on Computational Intelligence. pp. 483-492, 4th International Joint Conference on Computational Intelligence, IJCCI 2012, Barcelona, Spain, 5/10/12.
Bouakkaz M, Harkat M-F. Combined input training and radial basis function neural networks based nonlinear principal components analysis model applied for process monitoring. In IJCCI 2012 - Proceedings of the 4th International Joint Conference on Computational Intelligence. 2012. p. 483-492
Bouakkaz, Messaoud ; Harkat, Mohamed-Faouzi. / Combined input training and radial basis function neural networks based nonlinear principal components analysis model applied for process monitoring. IJCCI 2012 - Proceedings of the 4th International Joint Conference on Computational Intelligence. 2012. pp. 483-492
@inproceedings{ac5d83dd4ff04a9ba6c0348823a47807,
title = "Combined input training and radial basis function neural networks based nonlinear principal components analysis model applied for process monitoring",
abstract = "In this paper a novel Nonlinear Principal Component Analysis (NLPCA) is proposed. Generally, a NLPCA model is performed by using two sub-models, mapping and demapping. The proposed NLPCA model consists of two cascade three-layer neural networks for mapping and demapping, respectively. The mapping model is identified by using a Radial Basis Function (RBF) neural networks and the demapping is performed by using an Input Training neural networks (IT-Net). The nonlinear principal components, which represents the desired output of the first network, are obtained by the IT-NET. The proposed approach is illustrated by a simulation example and then applied for fault detection and isolation of the TECP process.",
keywords = "Fault Detection and Isolation, IT-net, Nonlinear PCA, Process Monitoring, RBF-neural Network",
author = "Messaoud Bouakkaz and Mohamed-Faouzi Harkat",
year = "2012",
month = "12",
day = "1",
language = "English",
isbn = "9789898565334",
pages = "483--492",
booktitle = "IJCCI 2012 - Proceedings of the 4th International Joint Conference on Computational Intelligence",

}

TY - GEN

T1 - Combined input training and radial basis function neural networks based nonlinear principal components analysis model applied for process monitoring

AU - Bouakkaz, Messaoud

AU - Harkat, Mohamed-Faouzi

PY - 2012/12/1

Y1 - 2012/12/1

N2 - In this paper a novel Nonlinear Principal Component Analysis (NLPCA) is proposed. Generally, a NLPCA model is performed by using two sub-models, mapping and demapping. The proposed NLPCA model consists of two cascade three-layer neural networks for mapping and demapping, respectively. The mapping model is identified by using a Radial Basis Function (RBF) neural networks and the demapping is performed by using an Input Training neural networks (IT-Net). The nonlinear principal components, which represents the desired output of the first network, are obtained by the IT-NET. The proposed approach is illustrated by a simulation example and then applied for fault detection and isolation of the TECP process.

AB - In this paper a novel Nonlinear Principal Component Analysis (NLPCA) is proposed. Generally, a NLPCA model is performed by using two sub-models, mapping and demapping. The proposed NLPCA model consists of two cascade three-layer neural networks for mapping and demapping, respectively. The mapping model is identified by using a Radial Basis Function (RBF) neural networks and the demapping is performed by using an Input Training neural networks (IT-Net). The nonlinear principal components, which represents the desired output of the first network, are obtained by the IT-NET. The proposed approach is illustrated by a simulation example and then applied for fault detection and isolation of the TECP process.

KW - Fault Detection and Isolation

KW - IT-net

KW - Nonlinear PCA

KW - Process Monitoring

KW - RBF-neural Network

UR - http://www.scopus.com/inward/record.url?scp=84886900801&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84886900801&partnerID=8YFLogxK

M3 - Conference contribution

SN - 9789898565334

SP - 483

EP - 492

BT - IJCCI 2012 - Proceedings of the 4th International Joint Conference on Computational Intelligence

ER -