Multi-Sensor Fault Diagnosis of Induction Motors Using Random Forests and Support Vector Machine

Alireza Nemat Saberi; Sarvavignoban Sandirasegaram; Anouar Belahcen; Toomas Vaimann; Jan Sobra

doi:10.1109/icem49940.2020.9270689

Multi-Sensor Fault Diagnosis of Induction Motors Using Random Forests and Support Vector Machine

Alireza Nemat Saberi, Sarvavignoban Sandirasegaram, Anouar Belahcen, Toomas Vaimann, Jan Sobra

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

1 Citation (Scopus)

87 Downloads (Pure)

Abstract

This paper presents a fault diagnosis scheme for induction machines (IMs) using Support Vector Machine (SVM) and Random Forests (RFs). First, a number of time domain and frequency-domain features are extracted from vibration and current signals in different operating conditions of IM. Then, these features are combined and considered as the input of SVM-based classification model. To avoid overfitting, RF is utilized to determine the most dominant features contributing to accurate classification. It is proved that the proposed method is capable of achieving highly accurate fault diagnosis results for broken rotor bar and eccentricity faults and it can appropriately handle the high dimensionality of the combined data.

Original language	English
Title of host publication	Proceedings of the International Conference on Electrical Machines, ICEM 2020
Publisher	IEEE
Number of pages	7
ISBN (Electronic)	9781728199450
ISBN (Print)	978-1-7281-9945-0
DOIs	https://doi.org/10.1109/icem49940.2020.9270689
Publication status	Published - 2020
MoE publication type	A4 Article in a conference publication
Event	International Conference on Electrical Machines - Virtual, Online Duration: 23 Aug 2020 → 26 Aug 2020 Conference number: 25

Publication series

Name	Proceedings (International Conference on Electrical Machines)
Publisher	IEEE
ISSN (Print)	2381-4802
ISSN (Electronic)	2473-2087

Conference

Conference	International Conference on Electrical Machines
Abbreviated title	ICEM
City	Virtual, Online
Period	23/08/2020 → 26/08/2020
Other	Virtual Conference

Keywords

Fault diagnosis
Induction motors
Machine learning
Multible signal classification
Support vector machine

Access to Document

10.1109/icem49940.2020.9270689

ELEC_Saberi_etal_Multi-Sensor-Fault_ICEM2020_acceptedauthormanuscriptAccepted author manuscript, 937 KB

Cite this

Nemat Saberi, A., Sandirasegaram, S., Belahcen, A., Vaimann, T., & Sobra, J. (2020). Multi-Sensor Fault Diagnosis of Induction Motors Using Random Forests and Support Vector Machine. In Proceedings of the International Conference on Electrical Machines, ICEM 2020 [9270689] (Proceedings (International Conference on Electrical Machines)). IEEE. https://doi.org/10.1109/icem49940.2020.9270689

@inproceedings{19179deb100f438aba750910f8d3b9c7,

title = "Multi-Sensor Fault Diagnosis of Induction Motors Using Random Forests and Support Vector Machine",

abstract = "This paper presents a fault diagnosis scheme for induction machines (IMs) using Support Vector Machine (SVM) and Random Forests (RFs). First, a number of time domain and frequency-domain features are extracted from vibration and current signals in different operating conditions of IM. Then, these features are combined and considered as the input of SVM-based classification model. To avoid overfitting, RF is utilized to determine the most dominant features contributing to accurate classification. It is proved that the proposed method is capable of achieving highly accurate fault diagnosis results for broken rotor bar and eccentricity faults and it can appropriately handle the high dimensionality of the combined data.",

keywords = "Fault diagnosis, Induction motors, Machine learning, Multible signal classification, Support vector machine",

author = "{Nemat Saberi}, Alireza and Sarvavignoban Sandirasegaram and Anouar Belahcen and Toomas Vaimann and Jan Sobra",

year = "2020",

doi = "10.1109/icem49940.2020.9270689",

language = "English",

isbn = "978-1-7281-9945-0",

series = "Proceedings (International Conference on Electrical Machines)",

publisher = "IEEE",

booktitle = "Proceedings of the International Conference on Electrical Machines, ICEM 2020",

address = "United States",

note = "International Conference on Electrical Machines, ICEM ; Conference date: 23-08-2020 Through 26-08-2020",

}

Nemat Saberi, A, Sandirasegaram, S, Belahcen, A, Vaimann, T & Sobra, J 2020, Multi-Sensor Fault Diagnosis of Induction Motors Using Random Forests and Support Vector Machine. in Proceedings of the International Conference on Electrical Machines, ICEM 2020., 9270689, Proceedings (International Conference on Electrical Machines), IEEE, International Conference on Electrical Machines, Virtual, Online, 23/08/2020. https://doi.org/10.1109/icem49940.2020.9270689

Multi-Sensor Fault Diagnosis of Induction Motors Using Random Forests and Support Vector Machine. / Nemat Saberi, Alireza; Sandirasegaram, Sarvavignoban; Belahcen, Anouar; Vaimann, Toomas; Sobra, Jan.

Proceedings of the International Conference on Electrical Machines, ICEM 2020. IEEE, 2020. 9270689 (Proceedings (International Conference on Electrical Machines)).

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

TY - GEN

T1 - Multi-Sensor Fault Diagnosis of Induction Motors Using Random Forests and Support Vector Machine

AU - Nemat Saberi, Alireza

AU - Sandirasegaram, Sarvavignoban

AU - Belahcen, Anouar

AU - Vaimann, Toomas

AU - Sobra, Jan

N1 - Conference code: 25

PY - 2020

Y1 - 2020

N2 - This paper presents a fault diagnosis scheme for induction machines (IMs) using Support Vector Machine (SVM) and Random Forests (RFs). First, a number of time domain and frequency-domain features are extracted from vibration and current signals in different operating conditions of IM. Then, these features are combined and considered as the input of SVM-based classification model. To avoid overfitting, RF is utilized to determine the most dominant features contributing to accurate classification. It is proved that the proposed method is capable of achieving highly accurate fault diagnosis results for broken rotor bar and eccentricity faults and it can appropriately handle the high dimensionality of the combined data.

AB - This paper presents a fault diagnosis scheme for induction machines (IMs) using Support Vector Machine (SVM) and Random Forests (RFs). First, a number of time domain and frequency-domain features are extracted from vibration and current signals in different operating conditions of IM. Then, these features are combined and considered as the input of SVM-based classification model. To avoid overfitting, RF is utilized to determine the most dominant features contributing to accurate classification. It is proved that the proposed method is capable of achieving highly accurate fault diagnosis results for broken rotor bar and eccentricity faults and it can appropriately handle the high dimensionality of the combined data.

KW - Fault diagnosis

KW - Induction motors

KW - Machine learning

KW - Multible signal classification

KW - Support vector machine

UR - http://www.scopus.com/inward/record.url?scp=85098620675&partnerID=8YFLogxK

U2 - 10.1109/icem49940.2020.9270689

DO - 10.1109/icem49940.2020.9270689

M3 - Conference contribution

SN - 978-1-7281-9945-0

T3 - Proceedings (International Conference on Electrical Machines)

BT - Proceedings of the International Conference on Electrical Machines, ICEM 2020

PB - IEEE

T2 - International Conference on Electrical Machines

Y2 - 23 August 2020 through 26 August 2020

ER -

Nemat Saberi A, Sandirasegaram S, Belahcen A, Vaimann T, Sobra J. Multi-Sensor Fault Diagnosis of Induction Motors Using Random Forests and Support Vector Machine. In Proceedings of the International Conference on Electrical Machines, ICEM 2020. IEEE. 2020. 9270689. (Proceedings (International Conference on Electrical Machines)). https://doi.org/10.1109/icem49940.2020.9270689

Multi-Sensor Fault Diagnosis of Induction Motors Using Random Forests and Support Vector Machine

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this