Improved anomaly detection using multi-scale PLS and generalized likelihood ratio test

Muddu Madakyaru, Fouzi Harrou, Ying Sun

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

4 Citations (Scopus)

Abstract

Process monitoring has a central role in the process industry to enhance productivity, efficiency, and safety, and to avoid expensive maintenance. In this paper, a statistical approach that exploit the advantages of multiscale PLS models (MSPLS) and those of a generalized likelihood ratio (GLR) test to better detect anomalies is proposed. Specifically, to consider the multivariate and multi-scale nature of process dynamics, a MSPLS algorithm combining PLS and wavelet analysis is used as modeling framework. Then, GLR hypothesis testing is applied using the uncorrelated residuals obtained from MSPLS model to improve the anomaly detection abilities of these latent variable based fault detection methods even further. Applications to a simulated distillation column data are used to evaluate the proposed MSPLS-GLR algorithm.

Original languageEnglish
Title of host publication2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781509042401
DOIs
Publication statusPublished - 09-02-2017
Event2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016 - Athens, Greece
Duration: 06-12-201609-12-2016

Conference

Conference2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016
CountryGreece
CityAthens
Period06-12-1609-12-16

Fingerprint

Generalized Likelihood Ratio Test
Anomaly Detection
Likelihood Ratio
Process Industry
Distillation
Model
Process Monitoring
Wavelet analysis
Wavelet Analysis
Process monitoring
Distillation columns
Dynamic Process
Latent Variables
Fault Detection
Hypothesis Testing
Fault detection
Productivity
Anomaly
Maintenance
Safety

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Information Systems and Management
  • Control and Optimization
  • Artificial Intelligence

Cite this

Madakyaru, M., Harrou, F., & Sun, Y. (2017). Improved anomaly detection using multi-scale PLS and generalized likelihood ratio test. In 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016 [7849880] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SSCI.2016.7849880
Madakyaru, Muddu ; Harrou, Fouzi ; Sun, Ying. / Improved anomaly detection using multi-scale PLS and generalized likelihood ratio test. 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016. Institute of Electrical and Electronics Engineers Inc., 2017.
@inproceedings{c624808d14ed4b26a9b87da4555cf3e4,
title = "Improved anomaly detection using multi-scale PLS and generalized likelihood ratio test",
abstract = "Process monitoring has a central role in the process industry to enhance productivity, efficiency, and safety, and to avoid expensive maintenance. In this paper, a statistical approach that exploit the advantages of multiscale PLS models (MSPLS) and those of a generalized likelihood ratio (GLR) test to better detect anomalies is proposed. Specifically, to consider the multivariate and multi-scale nature of process dynamics, a MSPLS algorithm combining PLS and wavelet analysis is used as modeling framework. Then, GLR hypothesis testing is applied using the uncorrelated residuals obtained from MSPLS model to improve the anomaly detection abilities of these latent variable based fault detection methods even further. Applications to a simulated distillation column data are used to evaluate the proposed MSPLS-GLR algorithm.",
author = "Muddu Madakyaru and Fouzi Harrou and Ying Sun",
year = "2017",
month = "2",
day = "9",
doi = "10.1109/SSCI.2016.7849880",
language = "English",
booktitle = "2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Madakyaru, M, Harrou, F & Sun, Y 2017, Improved anomaly detection using multi-scale PLS and generalized likelihood ratio test. in 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016., 7849880, Institute of Electrical and Electronics Engineers Inc., 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016, Athens, Greece, 06-12-16. https://doi.org/10.1109/SSCI.2016.7849880

Improved anomaly detection using multi-scale PLS and generalized likelihood ratio test. / Madakyaru, Muddu; Harrou, Fouzi; Sun, Ying.

2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016. Institute of Electrical and Electronics Engineers Inc., 2017. 7849880.

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

TY - GEN

T1 - Improved anomaly detection using multi-scale PLS and generalized likelihood ratio test

AU - Madakyaru, Muddu

AU - Harrou, Fouzi

AU - Sun, Ying

PY - 2017/2/9

Y1 - 2017/2/9

N2 - Process monitoring has a central role in the process industry to enhance productivity, efficiency, and safety, and to avoid expensive maintenance. In this paper, a statistical approach that exploit the advantages of multiscale PLS models (MSPLS) and those of a generalized likelihood ratio (GLR) test to better detect anomalies is proposed. Specifically, to consider the multivariate and multi-scale nature of process dynamics, a MSPLS algorithm combining PLS and wavelet analysis is used as modeling framework. Then, GLR hypothesis testing is applied using the uncorrelated residuals obtained from MSPLS model to improve the anomaly detection abilities of these latent variable based fault detection methods even further. Applications to a simulated distillation column data are used to evaluate the proposed MSPLS-GLR algorithm.

AB - Process monitoring has a central role in the process industry to enhance productivity, efficiency, and safety, and to avoid expensive maintenance. In this paper, a statistical approach that exploit the advantages of multiscale PLS models (MSPLS) and those of a generalized likelihood ratio (GLR) test to better detect anomalies is proposed. Specifically, to consider the multivariate and multi-scale nature of process dynamics, a MSPLS algorithm combining PLS and wavelet analysis is used as modeling framework. Then, GLR hypothesis testing is applied using the uncorrelated residuals obtained from MSPLS model to improve the anomaly detection abilities of these latent variable based fault detection methods even further. Applications to a simulated distillation column data are used to evaluate the proposed MSPLS-GLR algorithm.

UR - http://www.scopus.com/inward/record.url?scp=85016086660&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016086660&partnerID=8YFLogxK

U2 - 10.1109/SSCI.2016.7849880

DO - 10.1109/SSCI.2016.7849880

M3 - Conference contribution

BT - 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Madakyaru M, Harrou F, Sun Y. Improved anomaly detection using multi-scale PLS and generalized likelihood ratio test. In 2016 IEEE Symposium Series on Computational Intelligence, SSCI 2016. Institute of Electrical and Electronics Engineers Inc. 2017. 7849880 https://doi.org/10.1109/SSCI.2016.7849880