A data-based technique for monitoring of wound rotor induction machines

A simulation study

Fouzi Harrou, Jacques F. Ramahaleomiarantsoa, Mohamed Nounou, Hazem Nounou

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

Detecting faults induction machines is crucial for a safe operation of these machines. The aim of this paper is to present a statistical fault detection methodology for the detection of faults in three-phase wound rotor induction machines (WRIM). The proposed fault detection approach is based on the use of principal components analysis (PCA). However, conventional PCA-based detection indices, such as the T2 and the Q statistics, are not well suited to detect small faults because these indices only use information from the most recent available samples. Detection of small faults is one of the most crucial and challenging tasks in the area of fault detection and diagnosis. In this paper, a new statistical system monitoring strategy is proposed for detecting changes resulting from small shifts in several variables associated with WRIM. The proposed approach combines modeling using PCA modeling with the exponentially weighted moving average (EWMA) control scheme. In the proposed approach, EWMA control scheme is applied on the ignored principal components to detect the presence of faults. The performance of the proposed method is compared with those of the traditional PCA-based fault detection indices. The simulation results clearly show the effectiveness of the proposed method over the conventional ones, especially in the presence of faults with small magnitudes.

Original languageEnglish
Pages (from-to)1424-1435
Number of pages12
JournalEngineering Science and Technology, an International Journal
Volume19
Issue number3
DOIs
Publication statusPublished - 1 Sep 2016

Fingerprint

Fault detection
Principal component analysis
Rotors
Monitoring
Information use
Failure analysis
Statistics

Keywords

  • EWMA control scheme
  • Fault detection
  • Hotelling T statistic
  • Principal components analysis
  • Q statistic
  • Wound rotor induction machines

ASJC Scopus subject areas

  • Fluid Flow and Transfer Processes
  • Computer Networks and Communications
  • Hardware and Architecture
  • Civil and Structural Engineering
  • Mechanical Engineering
  • Biomaterials
  • Electronic, Optical and Magnetic Materials
  • Metals and Alloys

Cite this

A data-based technique for monitoring of wound rotor induction machines : A simulation study. / Harrou, Fouzi; Ramahaleomiarantsoa, Jacques F.; Nounou, Mohamed; Nounou, Hazem.

In: Engineering Science and Technology, an International Journal, Vol. 19, No. 3, 01.09.2016, p. 1424-1435.

Research output: Contribution to journalArticle

@article{5392a90bd32f48c1965f264ce066ab55,
title = "A data-based technique for monitoring of wound rotor induction machines: A simulation study",
abstract = "Detecting faults induction machines is crucial for a safe operation of these machines. The aim of this paper is to present a statistical fault detection methodology for the detection of faults in three-phase wound rotor induction machines (WRIM). The proposed fault detection approach is based on the use of principal components analysis (PCA). However, conventional PCA-based detection indices, such as the T2 and the Q statistics, are not well suited to detect small faults because these indices only use information from the most recent available samples. Detection of small faults is one of the most crucial and challenging tasks in the area of fault detection and diagnosis. In this paper, a new statistical system monitoring strategy is proposed for detecting changes resulting from small shifts in several variables associated with WRIM. The proposed approach combines modeling using PCA modeling with the exponentially weighted moving average (EWMA) control scheme. In the proposed approach, EWMA control scheme is applied on the ignored principal components to detect the presence of faults. The performance of the proposed method is compared with those of the traditional PCA-based fault detection indices. The simulation results clearly show the effectiveness of the proposed method over the conventional ones, especially in the presence of faults with small magnitudes.",
keywords = "EWMA control scheme, Fault detection, Hotelling T statistic, Principal components analysis, Q statistic, Wound rotor induction machines",
author = "Fouzi Harrou and Ramahaleomiarantsoa, {Jacques F.} and Mohamed Nounou and Hazem Nounou",
year = "2016",
month = "9",
day = "1",
doi = "10.1016/j.jestch.2016.04.008",
language = "English",
volume = "19",
pages = "1424--1435",
journal = "Engineering Science and Technology, an International Journal",
issn = "2215-0986",
publisher = "Elsevier BV",
number = "3",

}

TY - JOUR

T1 - A data-based technique for monitoring of wound rotor induction machines

T2 - A simulation study

AU - Harrou, Fouzi

AU - Ramahaleomiarantsoa, Jacques F.

AU - Nounou, Mohamed

AU - Nounou, Hazem

PY - 2016/9/1

Y1 - 2016/9/1

N2 - Detecting faults induction machines is crucial for a safe operation of these machines. The aim of this paper is to present a statistical fault detection methodology for the detection of faults in three-phase wound rotor induction machines (WRIM). The proposed fault detection approach is based on the use of principal components analysis (PCA). However, conventional PCA-based detection indices, such as the T2 and the Q statistics, are not well suited to detect small faults because these indices only use information from the most recent available samples. Detection of small faults is one of the most crucial and challenging tasks in the area of fault detection and diagnosis. In this paper, a new statistical system monitoring strategy is proposed for detecting changes resulting from small shifts in several variables associated with WRIM. The proposed approach combines modeling using PCA modeling with the exponentially weighted moving average (EWMA) control scheme. In the proposed approach, EWMA control scheme is applied on the ignored principal components to detect the presence of faults. The performance of the proposed method is compared with those of the traditional PCA-based fault detection indices. The simulation results clearly show the effectiveness of the proposed method over the conventional ones, especially in the presence of faults with small magnitudes.

AB - Detecting faults induction machines is crucial for a safe operation of these machines. The aim of this paper is to present a statistical fault detection methodology for the detection of faults in three-phase wound rotor induction machines (WRIM). The proposed fault detection approach is based on the use of principal components analysis (PCA). However, conventional PCA-based detection indices, such as the T2 and the Q statistics, are not well suited to detect small faults because these indices only use information from the most recent available samples. Detection of small faults is one of the most crucial and challenging tasks in the area of fault detection and diagnosis. In this paper, a new statistical system monitoring strategy is proposed for detecting changes resulting from small shifts in several variables associated with WRIM. The proposed approach combines modeling using PCA modeling with the exponentially weighted moving average (EWMA) control scheme. In the proposed approach, EWMA control scheme is applied on the ignored principal components to detect the presence of faults. The performance of the proposed method is compared with those of the traditional PCA-based fault detection indices. The simulation results clearly show the effectiveness of the proposed method over the conventional ones, especially in the presence of faults with small magnitudes.

KW - EWMA control scheme

KW - Fault detection

KW - Hotelling T statistic

KW - Principal components analysis

KW - Q statistic

KW - Wound rotor induction machines

UR - http://www.scopus.com/inward/record.url?scp=85017377927&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85017377927&partnerID=8YFLogxK

U2 - 10.1016/j.jestch.2016.04.008

DO - 10.1016/j.jestch.2016.04.008

M3 - Article

VL - 19

SP - 1424

EP - 1435

JO - Engineering Science and Technology, an International Journal

JF - Engineering Science and Technology, an International Journal

SN - 2215-0986

IS - 3

ER -