A Machine Learning Framework for Bearing Fault Detection in Three-Phase Induction Motors

Wesam Rohouma; Ayham Zaitouny; Md Ferdous Wahid; Hassan Ali; Shady S. Refaat

doi:10.1109/SGRE59715.2024.10429024

A Machine Learning Framework for Bearing Fault Detection in Three-Phase Induction Motors

Wesam Rohouma, Ayham Zaitouny, Md Ferdous Wahid, Hassan Ali, Shady S. Refaat

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

Abstract

Three-phase induction motors are widely employed in industry due to their rugged performance and easy maintenance. Bearing faults in three phase induction motors are responsible for 40%-50% of unplanned shutdowns in industrial settings. Therefore, early detection of bearing faults is essential to implement preventive measures and enhance planning of maintenance strategies. This paper thus proposes a machine learning (ML) framework that consistently monitors acceleration and temperature of bearing to detect bearing faults. The results show that the ML framework using k-nearest neighbor (k-NN) and support vector machine (SVM) approaches is better than the variation-based thresholding approach, where the former method is able to detect faulty conditions with more than 99% accuracy.

Original language	English
Title of host publication	2024 4th International Conference on Smart Grid and Renewable Energy (SGRE)
Place of Publication	Doha, Qatar
Publisher	Institute of Electrical and Electronics Engineers (IEEE)
Pages	1-5
Number of pages	5
ISBN (Electronic)	979-8-3503-0626-2
ISBN (Print)	979-8-3503-0627-9
DOIs	https://doi.org/10.1109/SGRE59715.2024.10429024
Publication status	Published - 10 Jan 2024
Event	2024 4th International Conference on Smart Grid and Renewable Energy (SGRE) - Doha, Qatar Duration: 8 Jan 2024 → 10 Jan 2024 Conference number: 4 https://www.sgre-qa.org/

Conference

Conference	2024 4th International Conference on Smart Grid and Renewable Energy (SGRE)
Abbreviated title	SGRE 2024
Country/Territory	Qatar
City	Doha
Period	8/01/24 → 10/01/24
Internet address	https://www.sgre-qa.org/

Keywords

Support vector machines
Temperature measurement
Induction motors
Machine learning
Maintenance engineering
Feature extraction
Monitoring
Bearing fault
electric motors
machine learning
fault detection
condition monitoring

Access to Document

10.1109/SGRE59715.2024.10429024Licence: Unspecified

Cite this

@inproceedings{51708419e1c84c4ca00e4586abfee005,

title = "A Machine Learning Framework for Bearing Fault Detection in Three-Phase Induction Motors",

abstract = "Three-phase induction motors are widely employed in industry due to their rugged performance and easy maintenance. Bearing faults in three phase induction motors are responsible for 40%-50% of unplanned shutdowns in industrial settings. Therefore, early detection of bearing faults is essential to implement preventive measures and enhance planning of maintenance strategies. This paper thus proposes a machine learning (ML) framework that consistently monitors acceleration and temperature of bearing to detect bearing faults. The results show that the ML framework using k-nearest neighbor (k-NN) and support vector machine (SVM) approaches is better than the variation-based thresholding approach, where the former method is able to detect faulty conditions with more than 99% accuracy.",

keywords = "Support vector machines, Temperature measurement, Induction motors, Machine learning, Maintenance engineering, Feature extraction, Monitoring, Bearing fault, electric motors, machine learning, fault detection, condition monitoring",

author = "Wesam Rohouma and Ayham Zaitouny and Wahid, {Md Ferdous} and Hassan Ali and Refaat, {Shady S.}",

note = "{\textcopyright} 2024 IEEE.; 2024 4th International Conference on Smart Grid and Renewable Energy (SGRE), SGRE 2024 ; Conference date: 08-01-2024 Through 10-01-2024",

year = "2024",

month = jan,

day = "10",

doi = "10.1109/SGRE59715.2024.10429024",

language = "English",

isbn = "979-8-3503-0627-9",

pages = "1--5",

booktitle = "2024 4th International Conference on Smart Grid and Renewable Energy (SGRE)",

publisher = "Institute of Electrical and Electronics Engineers (IEEE)",

address = "United States",

url = "https://www.sgre-qa.org/",

}

Rohouma, W, Zaitouny, A, Wahid, MF, Ali, H & Refaat, SS 2024, A Machine Learning Framework for Bearing Fault Detection in Three-Phase Induction Motors. in 2024 4th International Conference on Smart Grid and Renewable Energy (SGRE). Institute of Electrical and Electronics Engineers (IEEE), Doha, Qatar, pp. 1-5, 2024 4th International Conference on Smart Grid and Renewable Energy (SGRE), Doha, Qatar, 8/01/24. https://doi.org/10.1109/SGRE59715.2024.10429024

A Machine Learning Framework for Bearing Fault Detection in Three-Phase Induction Motors. / Rohouma, Wesam; Zaitouny, Ayham; Wahid, Md Ferdous et al.
2024 4th International Conference on Smart Grid and Renewable Energy (SGRE). Doha, Qatar: Institute of Electrical and Electronics Engineers (IEEE), 2024. p. 1-5.

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

TY - GEN

T1 - A Machine Learning Framework for Bearing Fault Detection in Three-Phase Induction Motors

AU - Rohouma, Wesam

AU - Zaitouny, Ayham

AU - Wahid, Md Ferdous

AU - Ali, Hassan

AU - Refaat, Shady S.

N1 - Conference code: 4

PY - 2024/1/10

Y1 - 2024/1/10

N2 - Three-phase induction motors are widely employed in industry due to their rugged performance and easy maintenance. Bearing faults in three phase induction motors are responsible for 40%-50% of unplanned shutdowns in industrial settings. Therefore, early detection of bearing faults is essential to implement preventive measures and enhance planning of maintenance strategies. This paper thus proposes a machine learning (ML) framework that consistently monitors acceleration and temperature of bearing to detect bearing faults. The results show that the ML framework using k-nearest neighbor (k-NN) and support vector machine (SVM) approaches is better than the variation-based thresholding approach, where the former method is able to detect faulty conditions with more than 99% accuracy.

AB - Three-phase induction motors are widely employed in industry due to their rugged performance and easy maintenance. Bearing faults in three phase induction motors are responsible for 40%-50% of unplanned shutdowns in industrial settings. Therefore, early detection of bearing faults is essential to implement preventive measures and enhance planning of maintenance strategies. This paper thus proposes a machine learning (ML) framework that consistently monitors acceleration and temperature of bearing to detect bearing faults. The results show that the ML framework using k-nearest neighbor (k-NN) and support vector machine (SVM) approaches is better than the variation-based thresholding approach, where the former method is able to detect faulty conditions with more than 99% accuracy.

KW - Support vector machines

KW - Temperature measurement

KW - Induction motors

KW - Machine learning

KW - Maintenance engineering

KW - Feature extraction

KW - Monitoring

KW - Bearing fault

KW - electric motors

KW - machine learning

KW - fault detection

KW - condition monitoring

UR - http://www.scopus.com/inward/record.url?scp=85186690954&partnerID=8YFLogxK

U2 - 10.1109/SGRE59715.2024.10429024

DO - 10.1109/SGRE59715.2024.10429024

M3 - Conference contribution

SN - 979-8-3503-0627-9

SP - 1

EP - 5

BT - 2024 4th International Conference on Smart Grid and Renewable Energy (SGRE)

PB - Institute of Electrical and Electronics Engineers (IEEE)

CY - Doha, Qatar

T2 - 2024 4th International Conference on Smart Grid and Renewable Energy (SGRE)

Y2 - 8 January 2024 through 10 January 2024

ER -

A Machine Learning Framework for Bearing Fault Detection in Three-Phase Induction Motors

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this