An efficient bearing fault detection strategy based on a hybrid machine learning technique

Abstract This study introduces an innovative method for addressing the bearing fault detection problem in rotating machinery. The proposed approach integrates multi-feature extraction, advanced feature selection, and state-of-the-art classification techniques using convolutional neural network (CNN)...

Full description

Saved in:
Bibliographic Details
Main Authors: Khalid Alqunun, Mohammed Bachir Bechiri, Mohamed Naoui, Abderrahmane Khechekhouche, Ismail Marouani, Tawfik Guesmi, Badr M. Alshammari, Amer AlGhadhban, Abderrahim Allal
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-02439-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850242576619143168
author Khalid Alqunun
Mohammed Bachir Bechiri
Mohamed Naoui
Abderrahmane Khechekhouche
Ismail Marouani
Tawfik Guesmi
Badr M. Alshammari
Amer AlGhadhban
Abderrahim Allal
author_facet Khalid Alqunun
Mohammed Bachir Bechiri
Mohamed Naoui
Abderrahmane Khechekhouche
Ismail Marouani
Tawfik Guesmi
Badr M. Alshammari
Amer AlGhadhban
Abderrahim Allal
author_sort Khalid Alqunun
collection DOAJ
description Abstract This study introduces an innovative method for addressing the bearing fault detection problem in rotating machinery. The proposed approach integrates multi-feature extraction, advanced feature selection, and state-of-the-art classification techniques using convolutional neural network (CNN) models. Leveraging the comprehensive Fault Bearing Dataset from Case Western Reserve University (CWRU), continuous wavelet transforms (CWT) and CNNs are utilized for feature extraction. The methodology also incorporates machine learning model tuning through Tree-Structured Parzen Estimators (TPE) for optimal hyperparameter adjustment, ensuring high-performance classification. Experimental results, based on the ResNet-50-SVM hybrid model, showed the effectiveness of the proposed approach in achieving an impressive accuracy of 95.51%. This confirms that the proposed methodology represents a significant advancement in bearing fault detection, providing an effective solution for predictive and preventive maintenance in industrial applications.
format Article
id doaj-art-e49f71c38bd34b9d9d26fb657502ffbe
institution OA Journals
issn 2045-2322
language English
publishDate 2025-05-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-e49f71c38bd34b9d9d26fb657502ffbe2025-08-20T02:00:14ZengNature PortfolioScientific Reports2045-23222025-05-0115111510.1038/s41598-025-02439-4An efficient bearing fault detection strategy based on a hybrid machine learning techniqueKhalid Alqunun0Mohammed Bachir Bechiri1Mohamed Naoui2Abderrahmane Khechekhouche3Ismail Marouani4Tawfik Guesmi5Badr M. Alshammari6Amer AlGhadhban7Abderrahim Allal8Department of Electrical Engineering, College of Engineering, University of Ha’ilLaboratory of New Technologies and Local Development, University of El OuedResearch Unit of Energy Processes Environment and Electrical Systems, National Engineering School of Gabes, University of GabesFaculty of Technology, University of El OuedDepartment of Electronics Engineering, Applied College, University of Ha’ilDepartment of Electrical Engineering, College of Engineering, University of Ha’ilDepartment of Electrical Engineering, College of Engineering, University of Ha’ilDepartment of Electrical Engineering, College of Engineering, University of Ha’ilDepartment of Electrical Engineering, University of El OuedAbstract This study introduces an innovative method for addressing the bearing fault detection problem in rotating machinery. The proposed approach integrates multi-feature extraction, advanced feature selection, and state-of-the-art classification techniques using convolutional neural network (CNN) models. Leveraging the comprehensive Fault Bearing Dataset from Case Western Reserve University (CWRU), continuous wavelet transforms (CWT) and CNNs are utilized for feature extraction. The methodology also incorporates machine learning model tuning through Tree-Structured Parzen Estimators (TPE) for optimal hyperparameter adjustment, ensuring high-performance classification. Experimental results, based on the ResNet-50-SVM hybrid model, showed the effectiveness of the proposed approach in achieving an impressive accuracy of 95.51%. This confirms that the proposed methodology represents a significant advancement in bearing fault detection, providing an effective solution for predictive and preventive maintenance in industrial applications.https://doi.org/10.1038/s41598-025-02439-4Bearing fault detectionContinuous wavelet transformConvolutional neural networks modelsMachine learning techniquesTree-structured Parzen estimatorsFault diagnosis
spellingShingle Khalid Alqunun
Mohammed Bachir Bechiri
Mohamed Naoui
Abderrahmane Khechekhouche
Ismail Marouani
Tawfik Guesmi
Badr M. Alshammari
Amer AlGhadhban
Abderrahim Allal
An efficient bearing fault detection strategy based on a hybrid machine learning technique
Scientific Reports
Bearing fault detection
Continuous wavelet transform
Convolutional neural networks models
Machine learning techniques
Tree-structured Parzen estimators
Fault diagnosis
title An efficient bearing fault detection strategy based on a hybrid machine learning technique
title_full An efficient bearing fault detection strategy based on a hybrid machine learning technique
title_fullStr An efficient bearing fault detection strategy based on a hybrid machine learning technique
title_full_unstemmed An efficient bearing fault detection strategy based on a hybrid machine learning technique
title_short An efficient bearing fault detection strategy based on a hybrid machine learning technique
title_sort efficient bearing fault detection strategy based on a hybrid machine learning technique
topic Bearing fault detection
Continuous wavelet transform
Convolutional neural networks models
Machine learning techniques
Tree-structured Parzen estimators
Fault diagnosis
url https://doi.org/10.1038/s41598-025-02439-4
work_keys_str_mv AT khalidalqunun anefficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT mohammedbachirbechiri anefficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT mohamednaoui anefficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT abderrahmanekhechekhouche anefficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT ismailmarouani anefficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT tawfikguesmi anefficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT badrmalshammari anefficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT ameralghadhban anefficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT abderrahimallal anefficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT khalidalqunun efficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT mohammedbachirbechiri efficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT mohamednaoui efficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT abderrahmanekhechekhouche efficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT ismailmarouani efficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT tawfikguesmi efficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT badrmalshammari efficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT ameralghadhban efficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique
AT abderrahimallal efficientbearingfaultdetectionstrategybasedonahybridmachinelearningtechnique