Novel Machine Learning Techniques for Classification of Rolling Bearings

Rolling bearing faults frequently cause rotating equipment failure, leading to costly downtime and maintenance expenses. As a result, researchers have focused on developing effective methods for diagnosing these faults. In this paper, we explore the potential of Machine Learning (ML) techniques for...

Full description

Saved in:
Bibliographic Details
Main Authors: Quynh Nguyen Xuan Phan, Tuan Minh Le, Hieu Minh Tran, Ly van Tran, Son Vu Truong Dao
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10604807/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846141966831583232
author Quynh Nguyen Xuan Phan
Tuan Minh Le
Hieu Minh Tran
Ly van Tran
Son Vu Truong Dao
author_facet Quynh Nguyen Xuan Phan
Tuan Minh Le
Hieu Minh Tran
Ly van Tran
Son Vu Truong Dao
author_sort Quynh Nguyen Xuan Phan
collection DOAJ
description Rolling bearing faults frequently cause rotating equipment failure, leading to costly downtime and maintenance expenses. As a result, researchers have focused on developing effective methods for diagnosing these faults. In this paper, we explore the potential of Machine Learning (ML) techniques for classifying the health status of bearings. Our approach involves decomposing the signal, extracting statistical features, and using a feature selection employing Binary Grey Wolf Optimization. We then employ four different classifiers such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Decision Tree (DT), and Random Forest (RF) to diagnose faults based on the reduced set of features. To evaluate the performance of our methods, we utilize several performance indicators. Our results demonstrate that four Machine Learning methods can achieve a high-accuracy fault classification result of 99.85%, better than state-of-the-art methods, highlighting their potential for use in predictive maintenance applications.
format Article
id doaj-art-4f13c72fc8ed423ca59272e3f0f49e14
institution Kabale University
issn 2169-3536
language English
publishDate 2024-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-4f13c72fc8ed423ca59272e3f0f49e142024-12-04T00:01:35ZengIEEEIEEE Access2169-35362024-01-011217686317687910.1109/ACCESS.2024.343104010604807Novel Machine Learning Techniques for Classification of Rolling BearingsQuynh Nguyen Xuan Phan0https://orcid.org/0009-0009-5540-7020Tuan Minh Le1https://orcid.org/0000-0002-5917-3091Hieu Minh Tran2https://orcid.org/0000-0002-5541-2577Ly van Tran3https://orcid.org/0000-0001-7621-7511Son Vu Truong Dao4https://orcid.org/0000-0001-9281-4869School of Industrial Engineering and Management, International University, Vietnam National University at Ho Chi Minh City, Ho Chi Minh City, VietnamSchool of Electrical Engineering, International University, Vietnam National University at Ho Chi Minh City, Ho Chi Minh City, VietnamSchool of Electrical Engineering, International University, Vietnam National University at Ho Chi Minh City, Ho Chi Minh City, VietnamSchool of Industrial Engineering and Management, International University, Vietnam National University at Ho Chi Minh City, Ho Chi Minh City, VietnamSchool of Industrial Engineering and Management, International University, Vietnam National University at Ho Chi Minh City, Ho Chi Minh City, VietnamRolling bearing faults frequently cause rotating equipment failure, leading to costly downtime and maintenance expenses. As a result, researchers have focused on developing effective methods for diagnosing these faults. In this paper, we explore the potential of Machine Learning (ML) techniques for classifying the health status of bearings. Our approach involves decomposing the signal, extracting statistical features, and using a feature selection employing Binary Grey Wolf Optimization. We then employ four different classifiers such as Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Decision Tree (DT), and Random Forest (RF) to diagnose faults based on the reduced set of features. To evaluate the performance of our methods, we utilize several performance indicators. Our results demonstrate that four Machine Learning methods can achieve a high-accuracy fault classification result of 99.85%, better than state-of-the-art methods, highlighting their potential for use in predictive maintenance applications.https://ieeexplore.ieee.org/document/10604807/Fault diagnosisfeature selectiongrey wolf optimizationmachine learningrolling bearing
spellingShingle Quynh Nguyen Xuan Phan
Tuan Minh Le
Hieu Minh Tran
Ly van Tran
Son Vu Truong Dao
Novel Machine Learning Techniques for Classification of Rolling Bearings
IEEE Access
Fault diagnosis
feature selection
grey wolf optimization
machine learning
rolling bearing
title Novel Machine Learning Techniques for Classification of Rolling Bearings
title_full Novel Machine Learning Techniques for Classification of Rolling Bearings
title_fullStr Novel Machine Learning Techniques for Classification of Rolling Bearings
title_full_unstemmed Novel Machine Learning Techniques for Classification of Rolling Bearings
title_short Novel Machine Learning Techniques for Classification of Rolling Bearings
title_sort novel machine learning techniques for classification of rolling bearings
topic Fault diagnosis
feature selection
grey wolf optimization
machine learning
rolling bearing
url https://ieeexplore.ieee.org/document/10604807/
work_keys_str_mv AT quynhnguyenxuanphan novelmachinelearningtechniquesforclassificationofrollingbearings
AT tuanminhle novelmachinelearningtechniquesforclassificationofrollingbearings
AT hieuminhtran novelmachinelearningtechniquesforclassificationofrollingbearings
AT lyvantran novelmachinelearningtechniquesforclassificationofrollingbearings
AT sonvutruongdao novelmachinelearningtechniquesforclassificationofrollingbearings