Improved Statistical Method Based Exponentially Weighted GLRT Chart and Its Application to Fault Detection

Raoudha Baklouti, Majdi Mansouri, Ahmed Ben Hamida, Hazem Nounou, Mohamed Nounou

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

Abstract

This paper deals with fault detection (FD) of chemical processes. Our previous study [1] has proved the effectiveness of multiscale principal component analysis (MSPCA)-based Moving Window (MW)-Generalized Likelihood Ratio Test (GLRT) to detect faults by maximizing the detection probability for a particular false alarm rate with different values of windows. However, the conventional PCA method is not suitable in nonlinear processes. In fact, this lack affects the monitoring system. To address this problem, we propose, first, to use multistage kernel PCA (MSKPCA) technique to extract the deterministic features and compute the principal components (PCs) in the original space. Second, integrate exponentially weighted moving average (EWMA), that has shown better abilities to reduce the false alarm rates and enhance the (FD) performances. Therefore, this work focuses on extending MSKPCA, and developing a MSKPCA-based EWMA-GLRT technique in order to improve the (FD) performance. The performances of the MSKPCA-based EWMA- GLRT are illustrated using Tennessee Eastman benchmark process.

Original languageEnglish
Title of host publication2018 European Control Conference, ECC 2018
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages703-708
Number of pages6
ISBN (Electronic)9783952426982
DOIs
Publication statusPublished - 27 Nov 2018
Event16th European Control Conference, ECC 2018 - Limassol, Cyprus
Duration: 12 Jun 201815 Jun 2018

Other

Other16th European Control Conference, ECC 2018
CountryCyprus
CityLimassol
Period12/6/1815/6/18

Fingerprint

Kernel PCA
Generalized Likelihood Ratio Test
Fault Detection
Fault detection
Chart
Exponentially Weighted Moving Average
Statistical method
Statistical methods
False Alarm Rate
Principal component analysis
Detection Probability
Multiscale Analysis
Chemical Processes
Nonlinear Process
Principal Components
Monitoring System
Principal Component Analysis
Fault
Monitoring
Integrate

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Control and Optimization

Cite this

Baklouti, R., Mansouri, M., Hamida, A. B., Nounou, H., & Nounou, M. (2018). Improved Statistical Method Based Exponentially Weighted GLRT Chart and Its Application to Fault Detection In 2018 European Control Conference, ECC 2018 (pp. 703-708). [8550495] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.23919/ECC.2018.8550495

Improved Statistical Method Based Exponentially Weighted GLRT Chart and Its Application to Fault Detection . / Baklouti, Raoudha; Mansouri, Majdi; Hamida, Ahmed Ben; Nounou, Hazem; Nounou, Mohamed.

2018 European Control Conference, ECC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. p. 703-708 8550495.

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

Baklouti, R, Mansouri, M, Hamida, AB, Nounou, H & Nounou, M 2018, Improved Statistical Method Based Exponentially Weighted GLRT Chart and Its Application to Fault Detection in 2018 European Control Conference, ECC 2018., 8550495, Institute of Electrical and Electronics Engineers Inc., pp. 703-708, 16th European Control Conference, ECC 2018, Limassol, Cyprus, 12/6/18. https://doi.org/10.23919/ECC.2018.8550495
Baklouti R, Mansouri M, Hamida AB, Nounou H, Nounou M. Improved Statistical Method Based Exponentially Weighted GLRT Chart and Its Application to Fault Detection In 2018 European Control Conference, ECC 2018. Institute of Electrical and Electronics Engineers Inc. 2018. p. 703-708. 8550495 https://doi.org/10.23919/ECC.2018.8550495
Baklouti, Raoudha ; Mansouri, Majdi ; Hamida, Ahmed Ben ; Nounou, Hazem ; Nounou, Mohamed. / Improved Statistical Method Based Exponentially Weighted GLRT Chart and Its Application to Fault Detection 2018 European Control Conference, ECC 2018. Institute of Electrical and Electronics Engineers Inc., 2018. pp. 703-708
@inproceedings{e923b8b0fc8b4ef09ddda955579b702c,
title = "Improved Statistical Method Based Exponentially Weighted GLRT Chart and Its Application to Fault Detection∗",
abstract = "This paper deals with fault detection (FD) of chemical processes. Our previous study [1] has proved the effectiveness of multiscale principal component analysis (MSPCA)-based Moving Window (MW)-Generalized Likelihood Ratio Test (GLRT) to detect faults by maximizing the detection probability for a particular false alarm rate with different values of windows. However, the conventional PCA method is not suitable in nonlinear processes. In fact, this lack affects the monitoring system. To address this problem, we propose, first, to use multistage kernel PCA (MSKPCA) technique to extract the deterministic features and compute the principal components (PCs) in the original space. Second, integrate exponentially weighted moving average (EWMA), that has shown better abilities to reduce the false alarm rates and enhance the (FD) performances. Therefore, this work focuses on extending MSKPCA, and developing a MSKPCA-based EWMA-GLRT technique in order to improve the (FD) performance. The performances of the MSKPCA-based EWMA- GLRT are illustrated using Tennessee Eastman benchmark process.",
author = "Raoudha Baklouti and Majdi Mansouri and Hamida, {Ahmed Ben} and Hazem Nounou and Mohamed Nounou",
year = "2018",
month = "11",
day = "27",
doi = "10.23919/ECC.2018.8550495",
language = "English",
pages = "703--708",
booktitle = "2018 European Control Conference, ECC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Improved Statistical Method Based Exponentially Weighted GLRT Chart and Its Application to Fault Detection∗

AU - Baklouti, Raoudha

AU - Mansouri, Majdi

AU - Hamida, Ahmed Ben

AU - Nounou, Hazem

AU - Nounou, Mohamed

PY - 2018/11/27

Y1 - 2018/11/27

N2 - This paper deals with fault detection (FD) of chemical processes. Our previous study [1] has proved the effectiveness of multiscale principal component analysis (MSPCA)-based Moving Window (MW)-Generalized Likelihood Ratio Test (GLRT) to detect faults by maximizing the detection probability for a particular false alarm rate with different values of windows. However, the conventional PCA method is not suitable in nonlinear processes. In fact, this lack affects the monitoring system. To address this problem, we propose, first, to use multistage kernel PCA (MSKPCA) technique to extract the deterministic features and compute the principal components (PCs) in the original space. Second, integrate exponentially weighted moving average (EWMA), that has shown better abilities to reduce the false alarm rates and enhance the (FD) performances. Therefore, this work focuses on extending MSKPCA, and developing a MSKPCA-based EWMA-GLRT technique in order to improve the (FD) performance. The performances of the MSKPCA-based EWMA- GLRT are illustrated using Tennessee Eastman benchmark process.

AB - This paper deals with fault detection (FD) of chemical processes. Our previous study [1] has proved the effectiveness of multiscale principal component analysis (MSPCA)-based Moving Window (MW)-Generalized Likelihood Ratio Test (GLRT) to detect faults by maximizing the detection probability for a particular false alarm rate with different values of windows. However, the conventional PCA method is not suitable in nonlinear processes. In fact, this lack affects the monitoring system. To address this problem, we propose, first, to use multistage kernel PCA (MSKPCA) technique to extract the deterministic features and compute the principal components (PCs) in the original space. Second, integrate exponentially weighted moving average (EWMA), that has shown better abilities to reduce the false alarm rates and enhance the (FD) performances. Therefore, this work focuses on extending MSKPCA, and developing a MSKPCA-based EWMA-GLRT technique in order to improve the (FD) performance. The performances of the MSKPCA-based EWMA- GLRT are illustrated using Tennessee Eastman benchmark process.

UR - http://www.scopus.com/inward/record.url?scp=85059823977&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85059823977&partnerID=8YFLogxK

U2 - 10.23919/ECC.2018.8550495

DO - 10.23919/ECC.2018.8550495

M3 - Conference contribution

AN - SCOPUS:85059823977

SP - 703

EP - 708

BT - 2018 European Control Conference, ECC 2018

PB - Institute of Electrical and Electronics Engineers Inc.

ER -