Multiscale PLS-based GLRT for fault detection of chemical processes

Chiranjivi Botre, Majdi Mansouri, M. Nazmul Karim, Hazem Nounou, Mohamed Nounou

Research output: Contribution to journalArticle

23 Citations (Scopus)

Abstract

Fault detection is necessary to assure safe operations of plant and productivity at desired level. Most of the industrial process data are highly correlated, which causes an issue with analyzing huge process data. To address this issue, the Partial least squares (PLS) method has been used successfully in process monitoring. However, measured process data are usually contaminated with errors that mask the important features in the data and reduce the effectiveness of any fault detection method in which these data are used. Unfortunately chemical process data (as in the case of most practical data) usually possess multiscale characteristics, meaning that they contain features and noise that occur at varying contributions over time and frequency. Wavelet-based multiscale representation of data has been shown to be a powerful data analysis, modeling, and feature extraction tool due to its ability to provide efficient separation of deterministic and stochastic features. Hence, the objective of this paper is to extend our previous work (Botre et al., 2016) to deal with autocorrelated and noise in the dataset with multiscale representation and present a new fault detection method of chemical processes using Multiscale Partial Least Square (MSPLS)-based generalized likelihood ratio test (GLRT) technique. The efficiency and robustness of the proposed method are demonstrated through two illustrative examples, one using simulated continuous stirred tank reactor (CSTR) and the other using Tennessee Eastman process problem (TEP) data. The results demonstrate the effectiveness of developed MSPLS-based GLRT over the conventional PLS-based techniques for fault detection in CSTR and TEP processes.

Original languageEnglish
Pages (from-to)143-153
Number of pages11
JournalJournal of Loss Prevention in the Process Industries
Volume46
DOIs
Publication statusPublished - 1 Mar 2017

Fingerprint

Chemical Phenomena
Least-Squares Analysis
Fault detection
least squares
Noise
testing
Process monitoring
process monitoring
Masks
methodology
Feature extraction
Productivity
data analysis
Partial least squares
Likelihood ratio test

Keywords

  • Fault detection
  • Generalized likelihood ratio test
  • Multiscale partial least square
  • Tennessee Eastman process

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Food Science
  • Chemical Engineering(all)
  • Safety, Risk, Reliability and Quality
  • Energy Engineering and Power Technology
  • Management Science and Operations Research
  • Industrial and Manufacturing Engineering

Cite this

Multiscale PLS-based GLRT for fault detection of chemical processes. / Botre, Chiranjivi; Mansouri, Majdi; Karim, M. Nazmul; Nounou, Hazem; Nounou, Mohamed.

In: Journal of Loss Prevention in the Process Industries, Vol. 46, 01.03.2017, p. 143-153.

Research output: Contribution to journalArticle

@article{094e72a8d93e484b97933121bddfcf78,
title = "Multiscale PLS-based GLRT for fault detection of chemical processes",
abstract = "Fault detection is necessary to assure safe operations of plant and productivity at desired level. Most of the industrial process data are highly correlated, which causes an issue with analyzing huge process data. To address this issue, the Partial least squares (PLS) method has been used successfully in process monitoring. However, measured process data are usually contaminated with errors that mask the important features in the data and reduce the effectiveness of any fault detection method in which these data are used. Unfortunately chemical process data (as in the case of most practical data) usually possess multiscale characteristics, meaning that they contain features and noise that occur at varying contributions over time and frequency. Wavelet-based multiscale representation of data has been shown to be a powerful data analysis, modeling, and feature extraction tool due to its ability to provide efficient separation of deterministic and stochastic features. Hence, the objective of this paper is to extend our previous work (Botre et al., 2016) to deal with autocorrelated and noise in the dataset with multiscale representation and present a new fault detection method of chemical processes using Multiscale Partial Least Square (MSPLS)-based generalized likelihood ratio test (GLRT) technique. The efficiency and robustness of the proposed method are demonstrated through two illustrative examples, one using simulated continuous stirred tank reactor (CSTR) and the other using Tennessee Eastman process problem (TEP) data. The results demonstrate the effectiveness of developed MSPLS-based GLRT over the conventional PLS-based techniques for fault detection in CSTR and TEP processes.",
keywords = "Fault detection, Generalized likelihood ratio test, Multiscale partial least square, Tennessee Eastman process",
author = "Chiranjivi Botre and Majdi Mansouri and Karim, {M. Nazmul} and Hazem Nounou and Mohamed Nounou",
year = "2017",
month = "3",
day = "1",
doi = "10.1016/j.jlp.2017.01.008",
language = "English",
volume = "46",
pages = "143--153",
journal = "Journal of Loss Prevention in the Process Industries",
issn = "0950-4230",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Multiscale PLS-based GLRT for fault detection of chemical processes

AU - Botre, Chiranjivi

AU - Mansouri, Majdi

AU - Karim, M. Nazmul

AU - Nounou, Hazem

AU - Nounou, Mohamed

PY - 2017/3/1

Y1 - 2017/3/1

N2 - Fault detection is necessary to assure safe operations of plant and productivity at desired level. Most of the industrial process data are highly correlated, which causes an issue with analyzing huge process data. To address this issue, the Partial least squares (PLS) method has been used successfully in process monitoring. However, measured process data are usually contaminated with errors that mask the important features in the data and reduce the effectiveness of any fault detection method in which these data are used. Unfortunately chemical process data (as in the case of most practical data) usually possess multiscale characteristics, meaning that they contain features and noise that occur at varying contributions over time and frequency. Wavelet-based multiscale representation of data has been shown to be a powerful data analysis, modeling, and feature extraction tool due to its ability to provide efficient separation of deterministic and stochastic features. Hence, the objective of this paper is to extend our previous work (Botre et al., 2016) to deal with autocorrelated and noise in the dataset with multiscale representation and present a new fault detection method of chemical processes using Multiscale Partial Least Square (MSPLS)-based generalized likelihood ratio test (GLRT) technique. The efficiency and robustness of the proposed method are demonstrated through two illustrative examples, one using simulated continuous stirred tank reactor (CSTR) and the other using Tennessee Eastman process problem (TEP) data. The results demonstrate the effectiveness of developed MSPLS-based GLRT over the conventional PLS-based techniques for fault detection in CSTR and TEP processes.

AB - Fault detection is necessary to assure safe operations of plant and productivity at desired level. Most of the industrial process data are highly correlated, which causes an issue with analyzing huge process data. To address this issue, the Partial least squares (PLS) method has been used successfully in process monitoring. However, measured process data are usually contaminated with errors that mask the important features in the data and reduce the effectiveness of any fault detection method in which these data are used. Unfortunately chemical process data (as in the case of most practical data) usually possess multiscale characteristics, meaning that they contain features and noise that occur at varying contributions over time and frequency. Wavelet-based multiscale representation of data has been shown to be a powerful data analysis, modeling, and feature extraction tool due to its ability to provide efficient separation of deterministic and stochastic features. Hence, the objective of this paper is to extend our previous work (Botre et al., 2016) to deal with autocorrelated and noise in the dataset with multiscale representation and present a new fault detection method of chemical processes using Multiscale Partial Least Square (MSPLS)-based generalized likelihood ratio test (GLRT) technique. The efficiency and robustness of the proposed method are demonstrated through two illustrative examples, one using simulated continuous stirred tank reactor (CSTR) and the other using Tennessee Eastman process problem (TEP) data. The results demonstrate the effectiveness of developed MSPLS-based GLRT over the conventional PLS-based techniques for fault detection in CSTR and TEP processes.

KW - Fault detection

KW - Generalized likelihood ratio test

KW - Multiscale partial least square

KW - Tennessee Eastman process

UR - http://www.scopus.com/inward/record.url?scp=85012893132&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85012893132&partnerID=8YFLogxK

U2 - 10.1016/j.jlp.2017.01.008

DO - 10.1016/j.jlp.2017.01.008

M3 - Article

AN - SCOPUS:85012893132

VL - 46

SP - 143

EP - 153

JO - Journal of Loss Prevention in the Process Industries

JF - Journal of Loss Prevention in the Process Industries

SN - 0950-4230

ER -