Enhanced monitoring using PCA-based GLR fault detection and multiscale filtering

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

11 Citations (Scopus)

Abstract

One of the most popular multivariate statistical methods used for data-based process monitoring is Principal Component Analysis (PCA). In the absence of a process model, PCA has been successfully used as a data-based FD technique for highly correlated process variables. Some of the PCA detection indices include the T2 or Q statistics, which have their advantages and disadvantages. When a process model is available, however, the generalized likelihood ratio (GLR) test, which is a statistical hypothesis testing method, has shown good fault detection abili ties. In this work, a PCA-based GLR fault detection algorithm is developed to exploit the advantages of the GLR test in the absence of a process model. In fact, PCA is used to provide a modeling framework for the develop fault detection algorithm. The PCA-based GLR fault detection algorithm provides optimal properties by maximizing the detection probability of faults for a given false alarm rate. However, the presence of measurement noise and modeling errors increase the rate of false alarms. Therefore, to further improve the quality of fault detection, multiscale filtering is utilized to filter the residuals obtained from the PCA model, which helps suppress the effect on errors, and thus decrease the false alarm rate. The proposed fault detection methodology is demonstrated through its application to monitor the ozone level in the Upper Normandy region, France, and it is shown to effectively reduce the rate of false alarms whilst retaining the capability of detecting process faults.

Original languageEnglish
Title of host publicationProceedings of the 2013 IEEE Symposium on Computational Intelligence in Control and Automation, CICA 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
Pages1-8
Number of pages8
DOIs
Publication statusPublished - 2013
Event2013 3rd IEEE Symposium on Computational Intelligence in Control and Automation, CICA 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 - Singapore, Singapore
Duration: 16 Apr 201319 Apr 2013

Other

Other2013 3rd IEEE Symposium on Computational Intelligence in Control and Automation, CICA 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013
CountrySingapore
CitySingapore
Period16/4/1319/4/13

Fingerprint

Fault detection
Principal component analysis
Monitoring
Process monitoring
Ozone
Statistical methods
Statistics
Testing

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Science Applications

Cite this

Harrou, F., Nounou, M., & Nounou, H. (2013). Enhanced monitoring using PCA-based GLR fault detection and multiscale filtering. In Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Control and Automation, CICA 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013 (pp. 1-8). [6611656] https://doi.org/10.1109/CICA.2013.6611656

Enhanced monitoring using PCA-based GLR fault detection and multiscale filtering. / Harrou, Fouzi; Nounou, Mohamed; Nounou, Hazem.

Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Control and Automation, CICA 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 1-8 6611656.

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

Harrou, F, Nounou, M & Nounou, H 2013, Enhanced monitoring using PCA-based GLR fault detection and multiscale filtering. in Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Control and Automation, CICA 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013., 6611656, pp. 1-8, 2013 3rd IEEE Symposium on Computational Intelligence in Control and Automation, CICA 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013, Singapore, Singapore, 16/4/13. https://doi.org/10.1109/CICA.2013.6611656
Harrou F, Nounou M, Nounou H. Enhanced monitoring using PCA-based GLR fault detection and multiscale filtering. In Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Control and Automation, CICA 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. p. 1-8. 6611656 https://doi.org/10.1109/CICA.2013.6611656
Harrou, Fouzi ; Nounou, Mohamed ; Nounou, Hazem. / Enhanced monitoring using PCA-based GLR fault detection and multiscale filtering. Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Control and Automation, CICA 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013. 2013. pp. 1-8
@inproceedings{03954a088fc24ff88bc9a95caf8c625a,
title = "Enhanced monitoring using PCA-based GLR fault detection and multiscale filtering",
abstract = "One of the most popular multivariate statistical methods used for data-based process monitoring is Principal Component Analysis (PCA). In the absence of a process model, PCA has been successfully used as a data-based FD technique for highly correlated process variables. Some of the PCA detection indices include the T2 or Q statistics, which have their advantages and disadvantages. When a process model is available, however, the generalized likelihood ratio (GLR) test, which is a statistical hypothesis testing method, has shown good fault detection abili ties. In this work, a PCA-based GLR fault detection algorithm is developed to exploit the advantages of the GLR test in the absence of a process model. In fact, PCA is used to provide a modeling framework for the develop fault detection algorithm. The PCA-based GLR fault detection algorithm provides optimal properties by maximizing the detection probability of faults for a given false alarm rate. However, the presence of measurement noise and modeling errors increase the rate of false alarms. Therefore, to further improve the quality of fault detection, multiscale filtering is utilized to filter the residuals obtained from the PCA model, which helps suppress the effect on errors, and thus decrease the false alarm rate. The proposed fault detection methodology is demonstrated through its application to monitor the ozone level in the Upper Normandy region, France, and it is shown to effectively reduce the rate of false alarms whilst retaining the capability of detecting process faults.",
author = "Fouzi Harrou and Mohamed Nounou and Hazem Nounou",
year = "2013",
doi = "10.1109/CICA.2013.6611656",
language = "English",
isbn = "9781467358934",
pages = "1--8",
booktitle = "Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Control and Automation, CICA 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013",

}

TY - GEN

T1 - Enhanced monitoring using PCA-based GLR fault detection and multiscale filtering

AU - Harrou, Fouzi

AU - Nounou, Mohamed

AU - Nounou, Hazem

PY - 2013

Y1 - 2013

N2 - One of the most popular multivariate statistical methods used for data-based process monitoring is Principal Component Analysis (PCA). In the absence of a process model, PCA has been successfully used as a data-based FD technique for highly correlated process variables. Some of the PCA detection indices include the T2 or Q statistics, which have their advantages and disadvantages. When a process model is available, however, the generalized likelihood ratio (GLR) test, which is a statistical hypothesis testing method, has shown good fault detection abili ties. In this work, a PCA-based GLR fault detection algorithm is developed to exploit the advantages of the GLR test in the absence of a process model. In fact, PCA is used to provide a modeling framework for the develop fault detection algorithm. The PCA-based GLR fault detection algorithm provides optimal properties by maximizing the detection probability of faults for a given false alarm rate. However, the presence of measurement noise and modeling errors increase the rate of false alarms. Therefore, to further improve the quality of fault detection, multiscale filtering is utilized to filter the residuals obtained from the PCA model, which helps suppress the effect on errors, and thus decrease the false alarm rate. The proposed fault detection methodology is demonstrated through its application to monitor the ozone level in the Upper Normandy region, France, and it is shown to effectively reduce the rate of false alarms whilst retaining the capability of detecting process faults.

AB - One of the most popular multivariate statistical methods used for data-based process monitoring is Principal Component Analysis (PCA). In the absence of a process model, PCA has been successfully used as a data-based FD technique for highly correlated process variables. Some of the PCA detection indices include the T2 or Q statistics, which have their advantages and disadvantages. When a process model is available, however, the generalized likelihood ratio (GLR) test, which is a statistical hypothesis testing method, has shown good fault detection abili ties. In this work, a PCA-based GLR fault detection algorithm is developed to exploit the advantages of the GLR test in the absence of a process model. In fact, PCA is used to provide a modeling framework for the develop fault detection algorithm. The PCA-based GLR fault detection algorithm provides optimal properties by maximizing the detection probability of faults for a given false alarm rate. However, the presence of measurement noise and modeling errors increase the rate of false alarms. Therefore, to further improve the quality of fault detection, multiscale filtering is utilized to filter the residuals obtained from the PCA model, which helps suppress the effect on errors, and thus decrease the false alarm rate. The proposed fault detection methodology is demonstrated through its application to monitor the ozone level in the Upper Normandy region, France, and it is shown to effectively reduce the rate of false alarms whilst retaining the capability of detecting process faults.

UR - http://www.scopus.com/inward/record.url?scp=84885992978&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885992978&partnerID=8YFLogxK

U2 - 10.1109/CICA.2013.6611656

DO - 10.1109/CICA.2013.6611656

M3 - Conference contribution

SN - 9781467358934

SP - 1

EP - 8

BT - Proceedings of the 2013 IEEE Symposium on Computational Intelligence in Control and Automation, CICA 2013 - 2013 IEEE Symposium Series on Computational Intelligence, SSCI 2013

ER -