Hidden Markov model based principal component analysis for intelligent fault diagnosis of wind energy converter systems

Abdelmalek Kouadri, Mansour Hajji, Mohamed Faouzi Harkat, Kamaleldin Abodayeh, Majdi Mansouri, Hazem Nounou, Mohamed Nounou

Research output: Contribution to journalArticle

Abstract

Fault Detection and Diagnosis (FDD) for overall modern Wind Energy Conversion (WEC) systems, particularly its converter, is still a challenge due to the high randomness to their operating environment. This paper presents an advanced FDD approach aims to increase the availability, reliability and required safety of WEC Converters (WECC) under different conditions. The developed FDD approach must be able to detect and correctly diagnose the occurrence of faults in WEC systems. The developed approach exploits the benefits of the machine learning (ML)-based Hidden Markov model (HMM) and the principal component analysis (PCA) model. The PCA technique is used for efficiently extracting and selecting features to be fed to HMM classifier. The effectiveness and higher classification accuracy of the developed PCA-based HMM approach are demonstrated via simulated data collected from the WEC. The obtained results demonstrate the efficiency of the PCA-based HMM method over the PCA-based support vector machine (SVM) method. The comparison is made based on several performance metrics through different operating conditions of the WEC systems.

Original languageEnglish
Pages (from-to)598-606
Number of pages9
JournalRenewable Energy
Volume150
DOIs
Publication statusPublished - May 2020

Fingerprint

Hidden Markov models
Energy conversion
Principal component analysis
Wind power
Failure analysis
Fault detection
Support vector machines
Learning systems
Classifiers
Availability

Keywords

  • Fault Detection and Diagnosis (FDD)
  • Hidden Markov Model (HMM)
  • Machine Learning (ML)
  • Principal Component Analysis (PCA)
  • Wind Energy Conversion Converter (WECC) Systems

ASJC Scopus subject areas

  • Renewable Energy, Sustainability and the Environment

Cite this

Hidden Markov model based principal component analysis for intelligent fault diagnosis of wind energy converter systems. / Kouadri, Abdelmalek; Hajji, Mansour; Harkat, Mohamed Faouzi; Abodayeh, Kamaleldin; Mansouri, Majdi; Nounou, Hazem; Nounou, Mohamed.

In: Renewable Energy, Vol. 150, 05.2020, p. 598-606.

Research output: Contribution to journalArticle

Kouadri, Abdelmalek ; Hajji, Mansour ; Harkat, Mohamed Faouzi ; Abodayeh, Kamaleldin ; Mansouri, Majdi ; Nounou, Hazem ; Nounou, Mohamed. / Hidden Markov model based principal component analysis for intelligent fault diagnosis of wind energy converter systems. In: Renewable Energy. 2020 ; Vol. 150. pp. 598-606.
@article{585cd1d122354bcebc8397e01afd2a0d,
title = "Hidden Markov model based principal component analysis for intelligent fault diagnosis of wind energy converter systems",
abstract = "Fault Detection and Diagnosis (FDD) for overall modern Wind Energy Conversion (WEC) systems, particularly its converter, is still a challenge due to the high randomness to their operating environment. This paper presents an advanced FDD approach aims to increase the availability, reliability and required safety of WEC Converters (WECC) under different conditions. The developed FDD approach must be able to detect and correctly diagnose the occurrence of faults in WEC systems. The developed approach exploits the benefits of the machine learning (ML)-based Hidden Markov model (HMM) and the principal component analysis (PCA) model. The PCA technique is used for efficiently extracting and selecting features to be fed to HMM classifier. The effectiveness and higher classification accuracy of the developed PCA-based HMM approach are demonstrated via simulated data collected from the WEC. The obtained results demonstrate the efficiency of the PCA-based HMM method over the PCA-based support vector machine (SVM) method. The comparison is made based on several performance metrics through different operating conditions of the WEC systems.",
keywords = "Fault Detection and Diagnosis (FDD), Hidden Markov Model (HMM), Machine Learning (ML), Principal Component Analysis (PCA), Wind Energy Conversion Converter (WECC) Systems",
author = "Abdelmalek Kouadri and Mansour Hajji and Harkat, {Mohamed Faouzi} and Kamaleldin Abodayeh and Majdi Mansouri and Hazem Nounou and Mohamed Nounou",
year = "2020",
month = "5",
doi = "10.1016/j.renene.2020.01.010",
language = "English",
volume = "150",
pages = "598--606",
journal = "Renewable Energy",
issn = "0960-1481",
publisher = "Elsevier BV",

}

TY - JOUR

T1 - Hidden Markov model based principal component analysis for intelligent fault diagnosis of wind energy converter systems

AU - Kouadri, Abdelmalek

AU - Hajji, Mansour

AU - Harkat, Mohamed Faouzi

AU - Abodayeh, Kamaleldin

AU - Mansouri, Majdi

AU - Nounou, Hazem

AU - Nounou, Mohamed

PY - 2020/5

Y1 - 2020/5

N2 - Fault Detection and Diagnosis (FDD) for overall modern Wind Energy Conversion (WEC) systems, particularly its converter, is still a challenge due to the high randomness to their operating environment. This paper presents an advanced FDD approach aims to increase the availability, reliability and required safety of WEC Converters (WECC) under different conditions. The developed FDD approach must be able to detect and correctly diagnose the occurrence of faults in WEC systems. The developed approach exploits the benefits of the machine learning (ML)-based Hidden Markov model (HMM) and the principal component analysis (PCA) model. The PCA technique is used for efficiently extracting and selecting features to be fed to HMM classifier. The effectiveness and higher classification accuracy of the developed PCA-based HMM approach are demonstrated via simulated data collected from the WEC. The obtained results demonstrate the efficiency of the PCA-based HMM method over the PCA-based support vector machine (SVM) method. The comparison is made based on several performance metrics through different operating conditions of the WEC systems.

AB - Fault Detection and Diagnosis (FDD) for overall modern Wind Energy Conversion (WEC) systems, particularly its converter, is still a challenge due to the high randomness to their operating environment. This paper presents an advanced FDD approach aims to increase the availability, reliability and required safety of WEC Converters (WECC) under different conditions. The developed FDD approach must be able to detect and correctly diagnose the occurrence of faults in WEC systems. The developed approach exploits the benefits of the machine learning (ML)-based Hidden Markov model (HMM) and the principal component analysis (PCA) model. The PCA technique is used for efficiently extracting and selecting features to be fed to HMM classifier. The effectiveness and higher classification accuracy of the developed PCA-based HMM approach are demonstrated via simulated data collected from the WEC. The obtained results demonstrate the efficiency of the PCA-based HMM method over the PCA-based support vector machine (SVM) method. The comparison is made based on several performance metrics through different operating conditions of the WEC systems.

KW - Fault Detection and Diagnosis (FDD)

KW - Hidden Markov Model (HMM)

KW - Machine Learning (ML)

KW - Principal Component Analysis (PCA)

KW - Wind Energy Conversion Converter (WECC) Systems

UR - http://www.scopus.com/inward/record.url?scp=85077659403&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85077659403&partnerID=8YFLogxK

U2 - 10.1016/j.renene.2020.01.010

DO - 10.1016/j.renene.2020.01.010

M3 - Article

AN - SCOPUS:85077659403

VL - 150

SP - 598

EP - 606

JO - Renewable Energy

JF - Renewable Energy

SN - 0960-1481

ER -