Stator inter-turn faults detection and localization using stator currents and concordia patterns - Neural network applications

Ibrahim F. El-Arabawy, Mahmoud I. Masoud, Abd El-Kader Mokhtari

Research output: Chapter in Book/Report/Conference proceedingConference contribution

5 Citations (Scopus)

Abstract

An inter-turn fault is one of the most difficult failures to detect Depending on the motor protection, the motor may continue to run but, soon or later, the heating in the short-circuited turns will cause severe failures. In this paper, the stator inter-turn faults are detected by observing the Concordia patterns and the behavior of the effective current values (RMS). These fault indicators have a specific behavior corresponding to each fault and can be used detect, locate and evaluate faults. Also two strategies are proposed to use multilayer feedforward neural networks (FFNN) in the fault detection, and both strategies are sketched and the best configuration is used. The network output can be interpreted, using a table, as a diagnosis report of the machine health. In addition, the use of two neural networks at the same time is proposed to improve the prediction accuracy.

Original languageEnglish
Title of host publication5th International Conference-Workshop Compatibility in Power Electronics, CPE 2007
DOIs
Publication statusPublished - 2007
Event5th International Conference-Workshop Compatibility in Power Electronics, CPE 2007 - Gdansk, Poland
Duration: May 29 2007Jun 1 2007

Other

Other5th International Conference-Workshop Compatibility in Power Electronics, CPE 2007
CountryPoland
CityGdansk
Period5/29/076/1/07

Fingerprint

Fault detection
Stators
Neural networks
Feedforward neural networks
Multilayer neural networks
Health
Heating

Keywords

  • Fault detection
  • Inter-turns
  • Neural networks
  • Park's current vector
  • RMS behavior

ASJC Scopus subject areas

  • Energy Engineering and Power Technology
  • Electrical and Electronic Engineering

Cite this

El-Arabawy, I. F., Masoud, M. I., & El-Kader Mokhtari, A. (2007). Stator inter-turn faults detection and localization using stator currents and concordia patterns - Neural network applications. In 5th International Conference-Workshop Compatibility in Power Electronics, CPE 2007 [4296552] https://doi.org/10.1109/CPE.2007.4296552

Stator inter-turn faults detection and localization using stator currents and concordia patterns - Neural network applications. / El-Arabawy, Ibrahim F.; Masoud, Mahmoud I.; El-Kader Mokhtari, Abd.

5th International Conference-Workshop Compatibility in Power Electronics, CPE 2007. 2007. 4296552.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

El-Arabawy, IF, Masoud, MI & El-Kader Mokhtari, A 2007, Stator inter-turn faults detection and localization using stator currents and concordia patterns - Neural network applications. in 5th International Conference-Workshop Compatibility in Power Electronics, CPE 2007., 4296552, 5th International Conference-Workshop Compatibility in Power Electronics, CPE 2007, Gdansk, Poland, 5/29/07. https://doi.org/10.1109/CPE.2007.4296552
El-Arabawy IF, Masoud MI, El-Kader Mokhtari A. Stator inter-turn faults detection and localization using stator currents and concordia patterns - Neural network applications. In 5th International Conference-Workshop Compatibility in Power Electronics, CPE 2007. 2007. 4296552 https://doi.org/10.1109/CPE.2007.4296552
El-Arabawy, Ibrahim F. ; Masoud, Mahmoud I. ; El-Kader Mokhtari, Abd. / Stator inter-turn faults detection and localization using stator currents and concordia patterns - Neural network applications. 5th International Conference-Workshop Compatibility in Power Electronics, CPE 2007. 2007.
@inproceedings{d9c537360575480db4ff0779d85bfe4b,
title = "Stator inter-turn faults detection and localization using stator currents and concordia patterns - Neural network applications",
abstract = "An inter-turn fault is one of the most difficult failures to detect Depending on the motor protection, the motor may continue to run but, soon or later, the heating in the short-circuited turns will cause severe failures. In this paper, the stator inter-turn faults are detected by observing the Concordia patterns and the behavior of the effective current values (RMS). These fault indicators have a specific behavior corresponding to each fault and can be used detect, locate and evaluate faults. Also two strategies are proposed to use multilayer feedforward neural networks (FFNN) in the fault detection, and both strategies are sketched and the best configuration is used. The network output can be interpreted, using a table, as a diagnosis report of the machine health. In addition, the use of two neural networks at the same time is proposed to improve the prediction accuracy.",
keywords = "Fault detection, Inter-turns, Neural networks, Park's current vector, RMS behavior",
author = "El-Arabawy, {Ibrahim F.} and Masoud, {Mahmoud I.} and {El-Kader Mokhtari}, Abd",
year = "2007",
doi = "10.1109/CPE.2007.4296552",
language = "English",
isbn = "142441055X",
booktitle = "5th International Conference-Workshop Compatibility in Power Electronics, CPE 2007",

}

TY - GEN

T1 - Stator inter-turn faults detection and localization using stator currents and concordia patterns - Neural network applications

AU - El-Arabawy, Ibrahim F.

AU - Masoud, Mahmoud I.

AU - El-Kader Mokhtari, Abd

PY - 2007

Y1 - 2007

N2 - An inter-turn fault is one of the most difficult failures to detect Depending on the motor protection, the motor may continue to run but, soon or later, the heating in the short-circuited turns will cause severe failures. In this paper, the stator inter-turn faults are detected by observing the Concordia patterns and the behavior of the effective current values (RMS). These fault indicators have a specific behavior corresponding to each fault and can be used detect, locate and evaluate faults. Also two strategies are proposed to use multilayer feedforward neural networks (FFNN) in the fault detection, and both strategies are sketched and the best configuration is used. The network output can be interpreted, using a table, as a diagnosis report of the machine health. In addition, the use of two neural networks at the same time is proposed to improve the prediction accuracy.

AB - An inter-turn fault is one of the most difficult failures to detect Depending on the motor protection, the motor may continue to run but, soon or later, the heating in the short-circuited turns will cause severe failures. In this paper, the stator inter-turn faults are detected by observing the Concordia patterns and the behavior of the effective current values (RMS). These fault indicators have a specific behavior corresponding to each fault and can be used detect, locate and evaluate faults. Also two strategies are proposed to use multilayer feedforward neural networks (FFNN) in the fault detection, and both strategies are sketched and the best configuration is used. The network output can be interpreted, using a table, as a diagnosis report of the machine health. In addition, the use of two neural networks at the same time is proposed to improve the prediction accuracy.

KW - Fault detection

KW - Inter-turns

KW - Neural networks

KW - Park's current vector

KW - RMS behavior

UR - http://www.scopus.com/inward/record.url?scp=47149100968&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=47149100968&partnerID=8YFLogxK

U2 - 10.1109/CPE.2007.4296552

DO - 10.1109/CPE.2007.4296552

M3 - Conference contribution

SN - 142441055X

SN - 9781424410552

BT - 5th International Conference-Workshop Compatibility in Power Electronics, CPE 2007

ER -