Performance comparison of machine learning algorithms for condition monitoring of tapered roller bearings

This paper investigated the implementation of machine learning algorithms for health monitoring and fault detection of tapered roller bearings (TRBs) (30205 J2/Q, 30206 J2/Q and 30207 J2/Q). Three defect models were considered: inner race defect, outer race defect and roller defect, in addition to d...

Full description

Saved in:
Bibliographic Details
Main Authors: Harshal Aher, Nilesh Ghuge
Format: Article
Language:English
Published: Balkan Scientific Centre 2025-06-01
Series:Tribology and Materials
Subjects:
Online Access:https://www.tribomat.net/archive/2025/2025-02/TM-2025-02-05.pdf
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850114456788402176
author Harshal Aher
Nilesh Ghuge
author_facet Harshal Aher
Nilesh Ghuge
author_sort Harshal Aher
collection DOAJ
description This paper investigated the implementation of machine learning algorithms for health monitoring and fault detection of tapered roller bearings (TRBs) (30205 J2/Q, 30206 J2/Q and 30207 J2/Q). Three defect models were considered: inner race defect, outer race defect and roller defect, in addition to data from the healthy bearings condition. An L27 orthogonal array design was used to generate a comprehensive dataset for each defect model, considering various operational parameters such as load, unbalance, defect type, bearing type and speed. Kurtosis was extracted as the sole feature from the vibration signals for fault classification. Several machine learning models, including artificial neural network (ANN), decision tree, support vector machine (SVM), random forest, adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), gradient boosting and categorical boosting (CatBoost), were employed to predict fault severity. The results show that the ANN model accurately predicts faults based on the kurtosis metric. This study illustrates the capability of machine learning, particularly ANN, in enhancing the predictive maintenance strategies for TRBs, thereby enabling early fault detection under varying operational conditions.
format Article
id doaj-art-964bc19ba28b4d5fa8171bae60bf51a8
institution OA Journals
issn 2812-9717
language English
publishDate 2025-06-01
publisher Balkan Scientific Centre
record_format Article
series Tribology and Materials
spelling doaj-art-964bc19ba28b4d5fa8171bae60bf51a82025-08-20T02:36:53ZengBalkan Scientific CentreTribology and Materials2812-97172025-06-014210011510.46793/tribomat.2025.009Performance comparison of machine learning algorithms for condition monitoring of tapered roller bearingsHarshal Aher0https://orcid.org/0000-0002-3832-1905Nilesh Ghuge1https://orcid.org/0000-0002-0544-2006Matoshri College of Engineering and Research Center, Eklahare, IndiaMatoshri College of Engineering and Research Center, Eklahare, IndiaThis paper investigated the implementation of machine learning algorithms for health monitoring and fault detection of tapered roller bearings (TRBs) (30205 J2/Q, 30206 J2/Q and 30207 J2/Q). Three defect models were considered: inner race defect, outer race defect and roller defect, in addition to data from the healthy bearings condition. An L27 orthogonal array design was used to generate a comprehensive dataset for each defect model, considering various operational parameters such as load, unbalance, defect type, bearing type and speed. Kurtosis was extracted as the sole feature from the vibration signals for fault classification. Several machine learning models, including artificial neural network (ANN), decision tree, support vector machine (SVM), random forest, adaptive boosting (AdaBoost), extreme gradient boosting (XGBoost), gradient boosting and categorical boosting (CatBoost), were employed to predict fault severity. The results show that the ANN model accurately predicts faults based on the kurtosis metric. This study illustrates the capability of machine learning, particularly ANN, in enhancing the predictive maintenance strategies for TRBs, thereby enabling early fault detection under varying operational conditions.https://www.tribomat.net/archive/2025/2025-02/TM-2025-02-05.pdftapered rolling bearingsbearing defectannvibrationcondition monitoring
spellingShingle Harshal Aher
Nilesh Ghuge
Performance comparison of machine learning algorithms for condition monitoring of tapered roller bearings
Tribology and Materials
tapered rolling bearings
bearing defect
ann
vibration
condition monitoring
title Performance comparison of machine learning algorithms for condition monitoring of tapered roller bearings
title_full Performance comparison of machine learning algorithms for condition monitoring of tapered roller bearings
title_fullStr Performance comparison of machine learning algorithms for condition monitoring of tapered roller bearings
title_full_unstemmed Performance comparison of machine learning algorithms for condition monitoring of tapered roller bearings
title_short Performance comparison of machine learning algorithms for condition monitoring of tapered roller bearings
title_sort performance comparison of machine learning algorithms for condition monitoring of tapered roller bearings
topic tapered rolling bearings
bearing defect
ann
vibration
condition monitoring
url https://www.tribomat.net/archive/2025/2025-02/TM-2025-02-05.pdf
work_keys_str_mv AT harshalaher performancecomparisonofmachinelearningalgorithmsforconditionmonitoringoftaperedrollerbearings
AT nileshghuge performancecomparisonofmachinelearningalgorithmsforconditionmonitoringoftaperedrollerbearings