Detection of Incipient Inter-Turn Short-Circuit Faults by Artificial Intelligence Classifiers

Osman Örgüt; Ilker Şahin; Ece Olcay Güneş

Detection of Incipient Inter-Turn Short-Circuit Faults by Artificial Intelligence Classifiers

Osman Örgüt, Ilker Şahin, Ece Olcay Güneş

Department of Electronics and Communication Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

This paper presents two artificial intelligence (AI) based identification methods for inter-turn short-circuit fault (ISCF) detection in induction motors (IMs), driven by voltage source inverters (VSIs). It was previously observed that, for an IM driven by finite control set model predictive control (FCS-MPC), the ISCF occurrence disturbs the balanced distribution of the resultant switching vectors, which are merely the control outputs of the FCS-MPC scheme. This effect of the ISCFs is utilized for fault detection purposes. The proposed method successfully detects the ISCF using AI methods which are fed by histograms of switching vectors along with torque and speed. This is especially convenient from the motor driver's perspective since no additional sensor or hardware is required for fault detection. The dataset utilized in this paper was obtained from an experimental IM drive test setup, on which intentional ISCFs can be created. The test results proved that the average fault detection rate is 95.8%, for an ISCF of 2-turns in a 104-turns phase winding.

Original language	English
Title of host publication	24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9789075815399
Publication status	Published - 2022
Event	24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe - Hanover, Germany Duration: 5 Sept 2022 → 9 Sept 2022

Publication series

Name	24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe

Conference

Conference	24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe
Country/Territory	Germany
City	Hanover
Period	5/09/22 → 9/09/22

Bibliographical note

Publisher Copyright:
© 2022 EPE Association.

Keywords

Fault detection
Induction motor
Machine learning
Model pre-dictive control
Neural network

Cite this

Örgüt, O., Şahin, I., & Güneş, E. O. (2022). Detection of Incipient Inter-Turn Short-Circuit Faults by Artificial Intelligence Classifiers. In 24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe (24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe). Institute of Electrical and Electronics Engineers Inc..

Örgüt, Osman ; Şahin, Ilker ; Güneş, Ece Olcay. / Detection of Incipient Inter-Turn Short-Circuit Faults by Artificial Intelligence Classifiers. 24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe. Institute of Electrical and Electronics Engineers Inc., 2022. (24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe).

@inproceedings{017cec025a9548c29e30db4ec6621816,

title = "Detection of Incipient Inter-Turn Short-Circuit Faults by Artificial Intelligence Classifiers",

abstract = "This paper presents two artificial intelligence (AI) based identification methods for inter-turn short-circuit fault (ISCF) detection in induction motors (IMs), driven by voltage source inverters (VSIs). It was previously observed that, for an IM driven by finite control set model predictive control (FCS-MPC), the ISCF occurrence disturbs the balanced distribution of the resultant switching vectors, which are merely the control outputs of the FCS-MPC scheme. This effect of the ISCFs is utilized for fault detection purposes. The proposed method successfully detects the ISCF using AI methods which are fed by histograms of switching vectors along with torque and speed. This is especially convenient from the motor driver's perspective since no additional sensor or hardware is required for fault detection. The dataset utilized in this paper was obtained from an experimental IM drive test setup, on which intentional ISCFs can be created. The test results proved that the average fault detection rate is 95.8%, for an ISCF of 2-turns in a 104-turns phase winding.",

keywords = "Fault detection, Induction motor, Machine learning, Model pre-dictive control, Neural network",

author = "Osman {\"O}rg{\"u}t and Ilker {\c S}ahin and G{\"u}ne{\c s}, {Ece Olcay}",

note = "Publisher Copyright: {\textcopyright} 2022 EPE Association.; 24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe ; Conference date: 05-09-2022 Through 09-09-2022",

year = "2022",

language = "English",

series = "24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe",

address = "United States",

}

Örgüt, O, Şahin, I & Güneş, EO 2022, Detection of Incipient Inter-Turn Short-Circuit Faults by Artificial Intelligence Classifiers. in 24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe. 24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe, Institute of Electrical and Electronics Engineers Inc., 24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe, Hanover, Germany, 5/09/22.

Detection of Incipient Inter-Turn Short-Circuit Faults by Artificial Intelligence Classifiers. / Örgüt, Osman; Şahin, Ilker; Güneş, Ece Olcay.
24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe. Institute of Electrical and Electronics Engineers Inc., 2022. (24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Detection of Incipient Inter-Turn Short-Circuit Faults by Artificial Intelligence Classifiers

AU - Örgüt, Osman

AU - Şahin, Ilker

AU - Güneş, Ece Olcay

PY - 2022

Y1 - 2022

N2 - This paper presents two artificial intelligence (AI) based identification methods for inter-turn short-circuit fault (ISCF) detection in induction motors (IMs), driven by voltage source inverters (VSIs). It was previously observed that, for an IM driven by finite control set model predictive control (FCS-MPC), the ISCF occurrence disturbs the balanced distribution of the resultant switching vectors, which are merely the control outputs of the FCS-MPC scheme. This effect of the ISCFs is utilized for fault detection purposes. The proposed method successfully detects the ISCF using AI methods which are fed by histograms of switching vectors along with torque and speed. This is especially convenient from the motor driver's perspective since no additional sensor or hardware is required for fault detection. The dataset utilized in this paper was obtained from an experimental IM drive test setup, on which intentional ISCFs can be created. The test results proved that the average fault detection rate is 95.8%, for an ISCF of 2-turns in a 104-turns phase winding.

AB - This paper presents two artificial intelligence (AI) based identification methods for inter-turn short-circuit fault (ISCF) detection in induction motors (IMs), driven by voltage source inverters (VSIs). It was previously observed that, for an IM driven by finite control set model predictive control (FCS-MPC), the ISCF occurrence disturbs the balanced distribution of the resultant switching vectors, which are merely the control outputs of the FCS-MPC scheme. This effect of the ISCFs is utilized for fault detection purposes. The proposed method successfully detects the ISCF using AI methods which are fed by histograms of switching vectors along with torque and speed. This is especially convenient from the motor driver's perspective since no additional sensor or hardware is required for fault detection. The dataset utilized in this paper was obtained from an experimental IM drive test setup, on which intentional ISCFs can be created. The test results proved that the average fault detection rate is 95.8%, for an ISCF of 2-turns in a 104-turns phase winding.

KW - Fault detection

KW - Induction motor

KW - Machine learning

KW - Model pre-dictive control

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=85141618959&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85141618959

T3 - 24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe

BT - 24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 24th European Conference on Power Electronics and Applications, EPE 2022 ECCE Europe

Y2 - 5 September 2022 through 9 September 2022

ER -

Detection of Incipient Inter-Turn Short-Circuit Faults by Artificial Intelligence Classifiers

Abstract

Publication series

Conference

Bibliographical note

Keywords

Other files and links

Fingerprint

Cite this