Improved nonlinear fault detection strategy based on the Hellinger distance metric: Plug flow reactor monitoring

Fouzi Harrou, Muddu Madakyaru, Ying Sun

Research output: Contribution to journalArticle

9 Citations (Scopus)

Abstract

Fault detection has a vital role in the process industry to enhance productivity, efficiency, and safety, and to avoid expensive maintenance. This paper proposes an innovative multivariate fault detection method that can be used for monitoring nonlinear processes. The proposed method merges advantages of nonlinear projection to latent structures (NLPLS) modeling and those of Hellinger distance (HD) metric to identify abnormal changes in highly correlated multivariate data. Specifically, the HD is used to quantify the dissimilarity between current NLPLS-based residual and reference probability distributions obtained using fault-free data. Furthermore, to enhance further the robustness of these methods to measurement noise, and reduce the false alarms due to modeling errors, wavelet-based multiscale filtering of residuals is used before the application of the HD-based monitoring scheme. The performances of the developed NLPLS-HD fault detection technique is illustrated using simulated plug flow reactor data. The results show that the proposed method provides favorable performance for detection of faults compared to the conventional NLPLS method.

Original languageEnglish
Pages (from-to)149-161
Number of pages13
JournalEnergy and Buildings
Volume143
DOIs
Publication statusPublished - 15-05-2017

Fingerprint

Fault detection
Monitoring
Probability distributions
Productivity
Industry

All Science Journal Classification (ASJC) codes

  • Civil and Structural Engineering
  • Building and Construction
  • Mechanical Engineering
  • Electrical and Electronic Engineering

Cite this

@article{ed3f6c80a1ba4a5bb32afcc74c86ac7f,
title = "Improved nonlinear fault detection strategy based on the Hellinger distance metric: Plug flow reactor monitoring",
abstract = "Fault detection has a vital role in the process industry to enhance productivity, efficiency, and safety, and to avoid expensive maintenance. This paper proposes an innovative multivariate fault detection method that can be used for monitoring nonlinear processes. The proposed method merges advantages of nonlinear projection to latent structures (NLPLS) modeling and those of Hellinger distance (HD) metric to identify abnormal changes in highly correlated multivariate data. Specifically, the HD is used to quantify the dissimilarity between current NLPLS-based residual and reference probability distributions obtained using fault-free data. Furthermore, to enhance further the robustness of these methods to measurement noise, and reduce the false alarms due to modeling errors, wavelet-based multiscale filtering of residuals is used before the application of the HD-based monitoring scheme. The performances of the developed NLPLS-HD fault detection technique is illustrated using simulated plug flow reactor data. The results show that the proposed method provides favorable performance for detection of faults compared to the conventional NLPLS method.",
author = "Fouzi Harrou and Muddu Madakyaru and Ying Sun",
year = "2017",
month = "5",
day = "15",
doi = "10.1016/j.enbuild.2017.03.033",
language = "English",
volume = "143",
pages = "149--161",
journal = "Energy and Buildings",
issn = "0378-7788",
publisher = "Elsevier BV",

}

Improved nonlinear fault detection strategy based on the Hellinger distance metric : Plug flow reactor monitoring. / Harrou, Fouzi; Madakyaru, Muddu; Sun, Ying.

In: Energy and Buildings, Vol. 143, 15.05.2017, p. 149-161.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Improved nonlinear fault detection strategy based on the Hellinger distance metric

T2 - Plug flow reactor monitoring

AU - Harrou, Fouzi

AU - Madakyaru, Muddu

AU - Sun, Ying

PY - 2017/5/15

Y1 - 2017/5/15

N2 - Fault detection has a vital role in the process industry to enhance productivity, efficiency, and safety, and to avoid expensive maintenance. This paper proposes an innovative multivariate fault detection method that can be used for monitoring nonlinear processes. The proposed method merges advantages of nonlinear projection to latent structures (NLPLS) modeling and those of Hellinger distance (HD) metric to identify abnormal changes in highly correlated multivariate data. Specifically, the HD is used to quantify the dissimilarity between current NLPLS-based residual and reference probability distributions obtained using fault-free data. Furthermore, to enhance further the robustness of these methods to measurement noise, and reduce the false alarms due to modeling errors, wavelet-based multiscale filtering of residuals is used before the application of the HD-based monitoring scheme. The performances of the developed NLPLS-HD fault detection technique is illustrated using simulated plug flow reactor data. The results show that the proposed method provides favorable performance for detection of faults compared to the conventional NLPLS method.

AB - Fault detection has a vital role in the process industry to enhance productivity, efficiency, and safety, and to avoid expensive maintenance. This paper proposes an innovative multivariate fault detection method that can be used for monitoring nonlinear processes. The proposed method merges advantages of nonlinear projection to latent structures (NLPLS) modeling and those of Hellinger distance (HD) metric to identify abnormal changes in highly correlated multivariate data. Specifically, the HD is used to quantify the dissimilarity between current NLPLS-based residual and reference probability distributions obtained using fault-free data. Furthermore, to enhance further the robustness of these methods to measurement noise, and reduce the false alarms due to modeling errors, wavelet-based multiscale filtering of residuals is used before the application of the HD-based monitoring scheme. The performances of the developed NLPLS-HD fault detection technique is illustrated using simulated plug flow reactor data. The results show that the proposed method provides favorable performance for detection of faults compared to the conventional NLPLS method.

UR - http://www.scopus.com/inward/record.url?scp=85016004428&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85016004428&partnerID=8YFLogxK

U2 - 10.1016/j.enbuild.2017.03.033

DO - 10.1016/j.enbuild.2017.03.033

M3 - Article

AN - SCOPUS:85016004428

VL - 143

SP - 149

EP - 161

JO - Energy and Buildings

JF - Energy and Buildings

SN - 0378-7788

ER -