Fault detection of uncertain chemical processes using interval partial least squares-based generalized likelihood ratio test

Research output: Contribution to journalArticle

Abstract

Fault detection (FD) is essential for monitoring various chemical processes. Many chemical processes can be described by input-output models. Partial least squares (PLS) method is one of the most popular statistical approaches used for modeling and monitoring chemical processes. In many situations, measured process data can exhibit some level of uncertainty. In such cases, expressing the data in interval form can be useful. Therefore, this work addresses the problem of fault detection of uncertain chemical processes using interval input-output PLS-based generalized likelihood ratio test (GLRT). The proposed novel approach helps extend the applicability of GLRT to uncertain processes represented by interval-valued input-output data. In the developed approach, the modeling phase is performed using PLS and then the GLRT chart is applied to the interval residuals for fault detection. To evaluate the fault detection abilities of the proposed PLS-based interval valued GLRT approach, two examples are used: a simulated example and a distillation column example. The performance of the proposed technique is evaluated in terms of the missed detection and false alarms rates.

Original languageEnglish
Pages (from-to)265-284
Number of pages20
JournalInformation sciences
Volume490
DOIs
Publication statusPublished - 1 Jul 2019

Fingerprint

Generalized Likelihood Ratio Test
Chemical Processes
Partial Least Squares
Fault Detection
Fault detection
Interval
Output
Monitoring
Distillation columns
Distillation
False Alarm Rate
Least Square Method
Modeling
Chart
Partial least squares
Likelihood ratio test
Uncertainty
Evaluate

Keywords

  • Fault detection (FD)
  • Generalized likelihood ratio test (GLRT)
  • Interval-valued data
  • Partial least squares (PLS)
  • Process monitoring

ASJC Scopus subject areas

  • Software
  • Control and Systems Engineering
  • Theoretical Computer Science
  • Computer Science Applications
  • Information Systems and Management
  • Artificial Intelligence

Cite this

@article{14507d55a37d4da9a43add8b2aaa24ae,
title = "Fault detection of uncertain chemical processes using interval partial least squares-based generalized likelihood ratio test",
abstract = "Fault detection (FD) is essential for monitoring various chemical processes. Many chemical processes can be described by input-output models. Partial least squares (PLS) method is one of the most popular statistical approaches used for modeling and monitoring chemical processes. In many situations, measured process data can exhibit some level of uncertainty. In such cases, expressing the data in interval form can be useful. Therefore, this work addresses the problem of fault detection of uncertain chemical processes using interval input-output PLS-based generalized likelihood ratio test (GLRT). The proposed novel approach helps extend the applicability of GLRT to uncertain processes represented by interval-valued input-output data. In the developed approach, the modeling phase is performed using PLS and then the GLRT chart is applied to the interval residuals for fault detection. To evaluate the fault detection abilities of the proposed PLS-based interval valued GLRT approach, two examples are used: a simulated example and a distillation column example. The performance of the proposed technique is evaluated in terms of the missed detection and false alarms rates.",
keywords = "Fault detection (FD), Generalized likelihood ratio test (GLRT), Interval-valued data, Partial least squares (PLS), Process monitoring",
author = "Harkat M.-F. and Majdi Mansouri and Mohamed Nounou and Hazem Nounou",
year = "2019",
month = "7",
day = "1",
doi = "10.1016/j.ins.2019.03.068",
language = "English",
volume = "490",
pages = "265--284",
journal = "Information Sciences",
issn = "0020-0255",
publisher = "Elsevier Inc.",

}

TY - JOUR

T1 - Fault detection of uncertain chemical processes using interval partial least squares-based generalized likelihood ratio test

AU - M.-F., Harkat

AU - Mansouri, Majdi

AU - Nounou, Mohamed

AU - Nounou, Hazem

PY - 2019/7/1

Y1 - 2019/7/1

N2 - Fault detection (FD) is essential for monitoring various chemical processes. Many chemical processes can be described by input-output models. Partial least squares (PLS) method is one of the most popular statistical approaches used for modeling and monitoring chemical processes. In many situations, measured process data can exhibit some level of uncertainty. In such cases, expressing the data in interval form can be useful. Therefore, this work addresses the problem of fault detection of uncertain chemical processes using interval input-output PLS-based generalized likelihood ratio test (GLRT). The proposed novel approach helps extend the applicability of GLRT to uncertain processes represented by interval-valued input-output data. In the developed approach, the modeling phase is performed using PLS and then the GLRT chart is applied to the interval residuals for fault detection. To evaluate the fault detection abilities of the proposed PLS-based interval valued GLRT approach, two examples are used: a simulated example and a distillation column example. The performance of the proposed technique is evaluated in terms of the missed detection and false alarms rates.

AB - Fault detection (FD) is essential for monitoring various chemical processes. Many chemical processes can be described by input-output models. Partial least squares (PLS) method is one of the most popular statistical approaches used for modeling and monitoring chemical processes. In many situations, measured process data can exhibit some level of uncertainty. In such cases, expressing the data in interval form can be useful. Therefore, this work addresses the problem of fault detection of uncertain chemical processes using interval input-output PLS-based generalized likelihood ratio test (GLRT). The proposed novel approach helps extend the applicability of GLRT to uncertain processes represented by interval-valued input-output data. In the developed approach, the modeling phase is performed using PLS and then the GLRT chart is applied to the interval residuals for fault detection. To evaluate the fault detection abilities of the proposed PLS-based interval valued GLRT approach, two examples are used: a simulated example and a distillation column example. The performance of the proposed technique is evaluated in terms of the missed detection and false alarms rates.

KW - Fault detection (FD)

KW - Generalized likelihood ratio test (GLRT)

KW - Interval-valued data

KW - Partial least squares (PLS)

KW - Process monitoring

UR - http://www.scopus.com/inward/record.url?scp=85063616735&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063616735&partnerID=8YFLogxK

U2 - 10.1016/j.ins.2019.03.068

DO - 10.1016/j.ins.2019.03.068

M3 - Article

VL - 490

SP - 265

EP - 284

JO - Information Sciences

JF - Information Sciences

SN - 0020-0255

ER -