Improved data-based fault detection strategy and application to distillation columns

Muddu Madakyaru, Fouzi Harrou, Ying Sun

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Chemical and petrochemical processes require continuous monitoring to detect abnormal events and to sustain normal operations. Furthermore, process monitoring enhances productivity, efficiency, and safety in process industries. Here, we propose an innovative statistical approach that exploits the advantages of multiscale partial least squares (MSPLS) models and generalized likelihood ratio (GLR) tests for fault detection in processes. Specifically, we combine an MSPLS algorithm with wavelet analysis to create our modeling framework. Then, we use GLR hypothesis testing based on the uncorrelated residuals obtained from the MSPLS model to improve fault detection. We use simulated distillation column data to evaluate the MSPLS-based GLR chart. Results show that our MSPLS-based GLR method is more powerful than the PLS-based Q and GLR method and MSPLS-based Q method, especially in early detection of small faults with abrupt or incipient behavior.

Original languageEnglish
Pages (from-to)22-34
Number of pages13
JournalProcess Safety and Environmental Protection
Volume107
DOIs
Publication statusPublished - 2017

Fingerprint

Distillation columns
distillation
Fault detection
Wavelet analysis
Process monitoring
Petrochemicals
Productivity
hypothesis testing
wavelet analysis
monitoring
Monitoring
Testing
safety
Industry
productivity
industry
modeling
method
detection

All Science Journal Classification (ASJC) codes

  • Environmental Engineering
  • Environmental Chemistry
  • Chemical Engineering(all)
  • Safety, Risk, Reliability and Quality

Cite this

@article{8e7aa11ee89f499ea0e7208c6babb169,
title = "Improved data-based fault detection strategy and application to distillation columns",
abstract = "Chemical and petrochemical processes require continuous monitoring to detect abnormal events and to sustain normal operations. Furthermore, process monitoring enhances productivity, efficiency, and safety in process industries. Here, we propose an innovative statistical approach that exploits the advantages of multiscale partial least squares (MSPLS) models and generalized likelihood ratio (GLR) tests for fault detection in processes. Specifically, we combine an MSPLS algorithm with wavelet analysis to create our modeling framework. Then, we use GLR hypothesis testing based on the uncorrelated residuals obtained from the MSPLS model to improve fault detection. We use simulated distillation column data to evaluate the MSPLS-based GLR chart. Results show that our MSPLS-based GLR method is more powerful than the PLS-based Q and GLR method and MSPLS-based Q method, especially in early detection of small faults with abrupt or incipient behavior.",
author = "Muddu Madakyaru and Fouzi Harrou and Ying Sun",
year = "2017",
doi = "10.1016/j.psep.2017.01.017",
language = "English",
volume = "107",
pages = "22--34",
journal = "Process Safety and Environmental Protection",
issn = "0957-5820",
publisher = "Institution of Chemical Engineers",

}

Improved data-based fault detection strategy and application to distillation columns. / Madakyaru, Muddu; Harrou, Fouzi; Sun, Ying.

In: Process Safety and Environmental Protection, Vol. 107, 2017, p. 22-34.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Improved data-based fault detection strategy and application to distillation columns

AU - Madakyaru, Muddu

AU - Harrou, Fouzi

AU - Sun, Ying

PY - 2017

Y1 - 2017

N2 - Chemical and petrochemical processes require continuous monitoring to detect abnormal events and to sustain normal operations. Furthermore, process monitoring enhances productivity, efficiency, and safety in process industries. Here, we propose an innovative statistical approach that exploits the advantages of multiscale partial least squares (MSPLS) models and generalized likelihood ratio (GLR) tests for fault detection in processes. Specifically, we combine an MSPLS algorithm with wavelet analysis to create our modeling framework. Then, we use GLR hypothesis testing based on the uncorrelated residuals obtained from the MSPLS model to improve fault detection. We use simulated distillation column data to evaluate the MSPLS-based GLR chart. Results show that our MSPLS-based GLR method is more powerful than the PLS-based Q and GLR method and MSPLS-based Q method, especially in early detection of small faults with abrupt or incipient behavior.

AB - Chemical and petrochemical processes require continuous monitoring to detect abnormal events and to sustain normal operations. Furthermore, process monitoring enhances productivity, efficiency, and safety in process industries. Here, we propose an innovative statistical approach that exploits the advantages of multiscale partial least squares (MSPLS) models and generalized likelihood ratio (GLR) tests for fault detection in processes. Specifically, we combine an MSPLS algorithm with wavelet analysis to create our modeling framework. Then, we use GLR hypothesis testing based on the uncorrelated residuals obtained from the MSPLS model to improve fault detection. We use simulated distillation column data to evaluate the MSPLS-based GLR chart. Results show that our MSPLS-based GLR method is more powerful than the PLS-based Q and GLR method and MSPLS-based Q method, especially in early detection of small faults with abrupt or incipient behavior.

UR - http://www.scopus.com/inward/record.url?scp=85011977009&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85011977009&partnerID=8YFLogxK

U2 - 10.1016/j.psep.2017.01.017

DO - 10.1016/j.psep.2017.01.017

M3 - Article

AN - SCOPUS:85011977009

VL - 107

SP - 22

EP - 34

JO - Process Safety and Environmental Protection

JF - Process Safety and Environmental Protection

SN - 0957-5820

ER -