Implementation and Evaluation of Machine Learning Algorithms in Ball Bearing Fault Detection

The subject of this research is the development of a classifier based on machine learning (ML) that is able to recognize defective and healthy ball bearings. For this purpose, vibration measurements were performed on the bearings, on a total of 196 samples. For each recorded vibration signal, a feat...

Full description

Saved in:
Bibliographic Details
Main Authors: Stepanić Pavle, Dučić Nedeljko, Vidaković Jelena, Baralić Jelena, Popović Marko
Format: Article
Language:English
Published: Sciendo 2025-04-01
Series:Measurement Science Review
Subjects:
Online Access:https://doi.org/10.2478/msr-2025-0004
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849699291269955584
author Stepanić Pavle
Dučić Nedeljko
Vidaković Jelena
Baralić Jelena
Popović Marko
author_facet Stepanić Pavle
Dučić Nedeljko
Vidaković Jelena
Baralić Jelena
Popović Marko
author_sort Stepanić Pavle
collection DOAJ
description The subject of this research is the development of a classifier based on machine learning (ML) that is able to recognize defective and healthy ball bearings. For this purpose, vibration measurements were performed on the bearings, on a total of 196 samples. For each recorded vibration signal, a feature extraction was performed by digital processing in the time domain. The following ML algorithms were used to develop the classifier: K-nearest neighbor (KNN) and support vector machine (SVM) as well as improved versions of the aforementioned algorithms. Improved versions of the mentioned algorithms were obtained by optimizing their hyperparameters. The corresponding models of the KNN and SVM algorithms showed a high percentage of success in classification, 98.5 % and 99.5 %, respectively. By optimizing the hyperparameters, models with a maximum classification success of 100 % were achieved.
format Article
id doaj-art-e9be7dd2217143ef9adb0bdb7936c21e
institution DOAJ
issn 1335-8871
language English
publishDate 2025-04-01
publisher Sciendo
record_format Article
series Measurement Science Review
spelling doaj-art-e9be7dd2217143ef9adb0bdb7936c21e2025-08-20T03:18:38ZengSciendoMeasurement Science Review1335-88712025-04-01251222910.2478/msr-2025-0004Implementation and Evaluation of Machine Learning Algorithms in Ball Bearing Fault DetectionStepanić Pavle0Dučić Nedeljko1Vidaković Jelena2Baralić Jelena3Popović Marko4Research and Development Institute Lola L.t.d., Kneza Viseslava, 70A, 11030, Belgrade, SerbiaFaculty of Technical Sciences Čačak, University of Kragujevac, Svetog Save 65, 32102, Čačak, SerbiaResearch and Development Institute Lola L.t.d., Kneza Viseslava, 70A, 11030, Belgrade, SerbiaFaculty of Technical Sciences Čačak, University of Kragujevac, Svetog Save 65, 32102, Čačak, SerbiaFaculty of Technical Sciences Čačak, University of Kragujevac, Svetog Save 65, 32102, Čačak, SerbiaThe subject of this research is the development of a classifier based on machine learning (ML) that is able to recognize defective and healthy ball bearings. For this purpose, vibration measurements were performed on the bearings, on a total of 196 samples. For each recorded vibration signal, a feature extraction was performed by digital processing in the time domain. The following ML algorithms were used to develop the classifier: K-nearest neighbor (KNN) and support vector machine (SVM) as well as improved versions of the aforementioned algorithms. Improved versions of the mentioned algorithms were obtained by optimizing their hyperparameters. The corresponding models of the KNN and SVM algorithms showed a high percentage of success in classification, 98.5 % and 99.5 %, respectively. By optimizing the hyperparameters, models with a maximum classification success of 100 % were achieved.https://doi.org/10.2478/msr-2025-0004vibration measurementball bearingsmachine learningfault detection
spellingShingle Stepanić Pavle
Dučić Nedeljko
Vidaković Jelena
Baralić Jelena
Popović Marko
Implementation and Evaluation of Machine Learning Algorithms in Ball Bearing Fault Detection
Measurement Science Review
vibration measurement
ball bearings
machine learning
fault detection
title Implementation and Evaluation of Machine Learning Algorithms in Ball Bearing Fault Detection
title_full Implementation and Evaluation of Machine Learning Algorithms in Ball Bearing Fault Detection
title_fullStr Implementation and Evaluation of Machine Learning Algorithms in Ball Bearing Fault Detection
title_full_unstemmed Implementation and Evaluation of Machine Learning Algorithms in Ball Bearing Fault Detection
title_short Implementation and Evaluation of Machine Learning Algorithms in Ball Bearing Fault Detection
title_sort implementation and evaluation of machine learning algorithms in ball bearing fault detection
topic vibration measurement
ball bearings
machine learning
fault detection
url https://doi.org/10.2478/msr-2025-0004
work_keys_str_mv AT stepanicpavle implementationandevaluationofmachinelearningalgorithmsinballbearingfaultdetection
AT ducicnedeljko implementationandevaluationofmachinelearningalgorithmsinballbearingfaultdetection
AT vidakovicjelena implementationandevaluationofmachinelearningalgorithmsinballbearingfaultdetection
AT baralicjelena implementationandevaluationofmachinelearningalgorithmsinballbearingfaultdetection
AT popovicmarko implementationandevaluationofmachinelearningalgorithmsinballbearingfaultdetection