Online reduced gaussian process regression based generalized likelihood ratio test for fault detection

R. Fezai, M. Mansouri, K. Abodayeh, H. Nounou, M. Nounou

Research output: Contribution to journalArticle

Abstract

In this paper we consider a new fault detection approach that merges the benefits of Gaussian process regression (GPR) with a generalized likelihood ratio test (GLRT). The GPR is one of the most well-known machine learning techniques. It is simpler and generally more robust than other methods. To deal with both high computational costs for large data sets and time-varying dynamics of industrial processes, we consider a reduced and online version of the GPR method. The online reduced GPR (ORGPR) aims to select a reduced set of kernel functions to build the GPR model and apply it for online fault detection based on GLRT chart. Compared with the conventional GPR technique, the proposed ORGPR method has the advantages of improving the computational efficiency by decreasing the dimension of the kernel matrix. The developed ORGPR-based GLRT (ORGPR-based GLRT) could improve the fault detection efficiency since it is able to track the time-varying characteristics of the processes. The fault detection performance of the developed ORGPR-based GLRT method is evaluated using a Tennessee Eastman process. The simulation results show that the proposed method outperforms the conventional GPR-based GLRT technique.

Original languageEnglish
Pages (from-to)30-40
Number of pages11
JournalJournal of Process Control
Volume85
DOIs
Publication statusPublished - Jan 2020

Fingerprint

Generalized Likelihood Ratio Test
Ground penetrating radar systems
Fault Detection
Gaussian Process
Fault detection
Regression
Computational efficiency
Time-varying
Learning systems
Kernel Function
Chart
Large Data Sets
Computational Efficiency
Process Model
Computational Cost
Regression Model
Machine Learning
Costs
kernel

Keywords

  • Fault detection (FD)
  • Gaussian process regression (GPR)
  • Generalized likelihood ratio test (GLRT)
  • Machine learning (ML)
  • Online reduced GPR
  • Tennessee eastman (TE) process

ASJC Scopus subject areas

  • Control and Systems Engineering
  • Modelling and Simulation
  • Computer Science Applications
  • Industrial and Manufacturing Engineering

Cite this

Online reduced gaussian process regression based generalized likelihood ratio test for fault detection. / Fezai, R.; Mansouri, M.; Abodayeh, K.; Nounou, H.; Nounou, M.

In: Journal of Process Control, Vol. 85, 01.2020, p. 30-40.

Research output: Contribution to journalArticle

@article{c88bca6b19d8429f88221c5d86ecf46f,
title = "Online reduced gaussian process regression based generalized likelihood ratio test for fault detection",
abstract = "In this paper we consider a new fault detection approach that merges the benefits of Gaussian process regression (GPR) with a generalized likelihood ratio test (GLRT). The GPR is one of the most well-known machine learning techniques. It is simpler and generally more robust than other methods. To deal with both high computational costs for large data sets and time-varying dynamics of industrial processes, we consider a reduced and online version of the GPR method. The online reduced GPR (ORGPR) aims to select a reduced set of kernel functions to build the GPR model and apply it for online fault detection based on GLRT chart. Compared with the conventional GPR technique, the proposed ORGPR method has the advantages of improving the computational efficiency by decreasing the dimension of the kernel matrix. The developed ORGPR-based GLRT (ORGPR-based GLRT) could improve the fault detection efficiency since it is able to track the time-varying characteristics of the processes. The fault detection performance of the developed ORGPR-based GLRT method is evaluated using a Tennessee Eastman process. The simulation results show that the proposed method outperforms the conventional GPR-based GLRT technique.",
keywords = "Fault detection (FD), Gaussian process regression (GPR), Generalized likelihood ratio test (GLRT), Machine learning (ML), Online reduced GPR, Tennessee eastman (TE) process",
author = "R. Fezai and M. Mansouri and K. Abodayeh and H. Nounou and M. Nounou",
year = "2020",
month = "1",
doi = "10.1016/j.jprocont.2019.11.002",
language = "English",
volume = "85",
pages = "30--40",
journal = "Journal of Process Control",
issn = "0959-1524",
publisher = "Elsevier Limited",

}

TY - JOUR

T1 - Online reduced gaussian process regression based generalized likelihood ratio test for fault detection

AU - Fezai, R.

AU - Mansouri, M.

AU - Abodayeh, K.

AU - Nounou, H.

AU - Nounou, M.

PY - 2020/1

Y1 - 2020/1

N2 - In this paper we consider a new fault detection approach that merges the benefits of Gaussian process regression (GPR) with a generalized likelihood ratio test (GLRT). The GPR is one of the most well-known machine learning techniques. It is simpler and generally more robust than other methods. To deal with both high computational costs for large data sets and time-varying dynamics of industrial processes, we consider a reduced and online version of the GPR method. The online reduced GPR (ORGPR) aims to select a reduced set of kernel functions to build the GPR model and apply it for online fault detection based on GLRT chart. Compared with the conventional GPR technique, the proposed ORGPR method has the advantages of improving the computational efficiency by decreasing the dimension of the kernel matrix. The developed ORGPR-based GLRT (ORGPR-based GLRT) could improve the fault detection efficiency since it is able to track the time-varying characteristics of the processes. The fault detection performance of the developed ORGPR-based GLRT method is evaluated using a Tennessee Eastman process. The simulation results show that the proposed method outperforms the conventional GPR-based GLRT technique.

AB - In this paper we consider a new fault detection approach that merges the benefits of Gaussian process regression (GPR) with a generalized likelihood ratio test (GLRT). The GPR is one of the most well-known machine learning techniques. It is simpler and generally more robust than other methods. To deal with both high computational costs for large data sets and time-varying dynamics of industrial processes, we consider a reduced and online version of the GPR method. The online reduced GPR (ORGPR) aims to select a reduced set of kernel functions to build the GPR model and apply it for online fault detection based on GLRT chart. Compared with the conventional GPR technique, the proposed ORGPR method has the advantages of improving the computational efficiency by decreasing the dimension of the kernel matrix. The developed ORGPR-based GLRT (ORGPR-based GLRT) could improve the fault detection efficiency since it is able to track the time-varying characteristics of the processes. The fault detection performance of the developed ORGPR-based GLRT method is evaluated using a Tennessee Eastman process. The simulation results show that the proposed method outperforms the conventional GPR-based GLRT technique.

KW - Fault detection (FD)

KW - Gaussian process regression (GPR)

KW - Generalized likelihood ratio test (GLRT)

KW - Machine learning (ML)

KW - Online reduced GPR

KW - Tennessee eastman (TE) process

UR - http://www.scopus.com/inward/record.url?scp=85074749770&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074749770&partnerID=8YFLogxK

U2 - 10.1016/j.jprocont.2019.11.002

DO - 10.1016/j.jprocont.2019.11.002

M3 - Article

AN - SCOPUS:85074749770

VL - 85

SP - 30

EP - 40

JO - Journal of Process Control

JF - Journal of Process Control

SN - 0959-1524

ER -