A Similarity Based Index for Stator Inter-Turn Fault Detection in Induction Motors

Mohsen Tajdinian; Behzad Behdani; Harold R. Chamorro; Vijay K. Sood

doi:10.1109/CCECE59415.2024.10667235

A Similarity Based Index for Stator Inter-Turn Fault Detection in Induction Motors

Mohsen Tajdinian^*, Behzad Behdani, Harold R. Chamorro, Vijay K. Sood

^*Corresponding author for this work

Intelligent Electrical Power Grids

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

Abstract

Failures of Induction Motors (IMs) can lead to unscheduled downtime and interruption in industry processes. This paper concentrates on the detection of the stator's inter-turn faults which are one of the most frequent causes of failures in IMs. The proposed detection method is based on a similarity index that uses the current waveform. To be more specific, the proposed algorithm presents a full-cycle sliding-window-based index based on cosine similarity that only uses current signals for detection of the stator's inter-turn faults. The proposed index cuts the phase difference before/after the disturbance and, as a result, it only depends on the size variations of the current waveform. The proposed method is technically unaffected by non-fault transient conditions including voltage imbalance, voltage sag, voltage swell, and heavy load changes. The performance of the proposed method is validated with numerous simulated scenarios and has good accuracy and speed of convergence.

Original language	English
Title of host publication	Proceedings of the 2024 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)
Publisher	IEEE
Pages	346-351
Number of pages	6
ISBN (Electronic)	979-8-3503-7162-8
ISBN (Print)	979-8-3503-7163-5
DOIs	https://doi.org/10.1109/CCECE59415.2024.10667235
Publication status	Published - 2024
Event	2024 Annual IEEE Canadian Conference on Electrical and Computer Engineering, CCECE 2024 - Kingston, Canada Duration: 6 Aug 2024 → 9 Aug 2024

Publication series

Name	Canadian Conference on Electrical and Computer Engineering
ISSN (Print)	0840-7789

Conference

Conference	2024 Annual IEEE Canadian Conference on Electrical and Computer Engineering, CCECE 2024
Country/Territory	Canada
City	Kingston
Period	6/08/24 → 9/08/24

Bibliographical note

Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care
Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

Keywords

Cosine similarity
electrical motor protection
induction motors (IMs)
short circuit
stator inter-turn fault

Access to Document

10.1109/CCECE59415.2024.10667235

A_Similarity_Based_Index_for_Stator_Inter-Turn_Fault_Detection_in_Induction_MotorsFinal published version, 1.07 MB

Cite this

Tajdinian, M., Behdani, B., Chamorro, H. R., & Sood, V. K. (2024). A Similarity Based Index for Stator Inter-Turn Fault Detection in Induction Motors. In Proceedings of the 2024 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE) (pp. 346-351). (Canadian Conference on Electrical and Computer Engineering). IEEE. https://doi.org/10.1109/CCECE59415.2024.10667235

@inproceedings{38ffb3f185a447c0a6ab106178109305,

title = "A Similarity Based Index for Stator Inter-Turn Fault Detection in Induction Motors",

abstract = "Failures of Induction Motors (IMs) can lead to unscheduled downtime and interruption in industry processes. This paper concentrates on the detection of the stator's inter-turn faults which are one of the most frequent causes of failures in IMs. The proposed detection method is based on a similarity index that uses the current waveform. To be more specific, the proposed algorithm presents a full-cycle sliding-window-based index based on cosine similarity that only uses current signals for detection of the stator's inter-turn faults. The proposed index cuts the phase difference before/after the disturbance and, as a result, it only depends on the size variations of the current waveform. The proposed method is technically unaffected by non-fault transient conditions including voltage imbalance, voltage sag, voltage swell, and heavy load changes. The performance of the proposed method is validated with numerous simulated scenarios and has good accuracy and speed of convergence.",

keywords = "Cosine similarity, electrical motor protection, induction motors (IMs), short circuit, stator inter-turn fault",

author = "Mohsen Tajdinian and Behzad Behdani and Chamorro, {Harold R.} and Sood, {Vijay K.}",

note = "Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.; 2024 Annual IEEE Canadian Conference on Electrical and Computer Engineering, CCECE 2024 ; Conference date: 06-08-2024 Through 09-08-2024",

year = "2024",

doi = "10.1109/CCECE59415.2024.10667235",

language = "English",

isbn = "979-8-3503-7163-5",

series = "Canadian Conference on Electrical and Computer Engineering",

publisher = "IEEE",

pages = "346--351",

booktitle = "Proceedings of the 2024 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)",

address = "United States",

}

Tajdinian, M, Behdani, B, Chamorro, HR & Sood, VK 2024, A Similarity Based Index for Stator Inter-Turn Fault Detection in Induction Motors. in Proceedings of the 2024 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE). Canadian Conference on Electrical and Computer Engineering, IEEE, pp. 346-351, 2024 Annual IEEE Canadian Conference on Electrical and Computer Engineering, CCECE 2024, Kingston, Canada, 6/08/24. https://doi.org/10.1109/CCECE59415.2024.10667235

A Similarity Based Index for Stator Inter-Turn Fault Detection in Induction Motors. / Tajdinian, Mohsen; Behdani, Behzad; Chamorro, Harold R. et al.
Proceedings of the 2024 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE). IEEE, 2024. p. 346-351 (Canadian Conference on Electrical and Computer Engineering).

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - A Similarity Based Index for Stator Inter-Turn Fault Detection in Induction Motors

AU - Tajdinian, Mohsen

AU - Behdani, Behzad

AU - Chamorro, Harold R.

AU - Sood, Vijay K.

N1 - Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public.

PY - 2024

Y1 - 2024

N2 - Failures of Induction Motors (IMs) can lead to unscheduled downtime and interruption in industry processes. This paper concentrates on the detection of the stator's inter-turn faults which are one of the most frequent causes of failures in IMs. The proposed detection method is based on a similarity index that uses the current waveform. To be more specific, the proposed algorithm presents a full-cycle sliding-window-based index based on cosine similarity that only uses current signals for detection of the stator's inter-turn faults. The proposed index cuts the phase difference before/after the disturbance and, as a result, it only depends on the size variations of the current waveform. The proposed method is technically unaffected by non-fault transient conditions including voltage imbalance, voltage sag, voltage swell, and heavy load changes. The performance of the proposed method is validated with numerous simulated scenarios and has good accuracy and speed of convergence.

AB - Failures of Induction Motors (IMs) can lead to unscheduled downtime and interruption in industry processes. This paper concentrates on the detection of the stator's inter-turn faults which are one of the most frequent causes of failures in IMs. The proposed detection method is based on a similarity index that uses the current waveform. To be more specific, the proposed algorithm presents a full-cycle sliding-window-based index based on cosine similarity that only uses current signals for detection of the stator's inter-turn faults. The proposed index cuts the phase difference before/after the disturbance and, as a result, it only depends on the size variations of the current waveform. The proposed method is technically unaffected by non-fault transient conditions including voltage imbalance, voltage sag, voltage swell, and heavy load changes. The performance of the proposed method is validated with numerous simulated scenarios and has good accuracy and speed of convergence.

KW - Cosine similarity

KW - electrical motor protection

KW - induction motors (IMs)

KW - short circuit

KW - stator inter-turn fault

UR - http://www.scopus.com/inward/record.url?scp=85204965377&partnerID=8YFLogxK

U2 - 10.1109/CCECE59415.2024.10667235

DO - 10.1109/CCECE59415.2024.10667235

M3 - Conference contribution

AN - SCOPUS:85204965377

SN - 979-8-3503-7163-5

T3 - Canadian Conference on Electrical and Computer Engineering

SP - 346

EP - 351

BT - Proceedings of the 2024 IEEE Canadian Conference on Electrical and Computer Engineering (CCECE)

PB - IEEE

T2 - 2024 Annual IEEE Canadian Conference on Electrical and Computer Engineering, CCECE 2024

Y2 - 6 August 2024 through 9 August 2024

ER -

A Similarity Based Index for Stator Inter-Turn Fault Detection in Induction Motors

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this