TKEO-Enhanced Machine Learning for Classification of Bearing Faults in Predictive Maintenance

Predictive maintenance is essential for improving the efficiency of equipment and reducing downtime in industrial operations. This study investigates the application of machine learning in predictive maintenance, specifically emphasizing data preprocessing and classification techniques using the Tea...

Full description

Saved in:
Bibliographic Details
Main Authors: Xuanbai Yu, Olivier Caspary
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/7/3774
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850188214565863424
author Xuanbai Yu
Olivier Caspary
author_facet Xuanbai Yu
Olivier Caspary
author_sort Xuanbai Yu
collection DOAJ
description Predictive maintenance is essential for improving the efficiency of equipment and reducing downtime in industrial operations. This study investigates the application of machine learning in predictive maintenance, specifically emphasizing data preprocessing and classification techniques using the Teager–Kaiser Energy Operator (TKEO) method, which captures dynamic variation in signals. The effectiveness of TKEO was compared against conventional methods, using the Case Western Reserve University (CWRU) dataset, with vibration data collected from bearings operating under different load conditions. Different data segmentation lengths (2400 and 12,000 samples) were evaluated to assess the impact of segment size on classification accuracy. The study also investigated the effects of various feature selection strategies by comparing four- and six-feature combinations. Advanced classifiers, including support vector machines and random forests, demonstrated that TKEO effectively improved model accuracy in the capture of fault-related signal dynamics. These findings offer new insights to support reliable predictive maintenance in industrial settings and provide a new perspective for future research into active vibration control, where vibration signal analysis, feature extraction, and mathematical modeling play key roles in optimizing control algorithms and enhancing the efficiency of adaptive control systems.
format Article
id doaj-art-d2e2afb8c9694ce6b97a4ed95cf78a8c
institution OA Journals
issn 2076-3417
language English
publishDate 2025-03-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-d2e2afb8c9694ce6b97a4ed95cf78a8c2025-08-20T02:15:55ZengMDPI AGApplied Sciences2076-34172025-03-01157377410.3390/app15073774TKEO-Enhanced Machine Learning for Classification of Bearing Faults in Predictive MaintenanceXuanbai Yu0Olivier Caspary1Laboratory for Design, Optimization, and Modeling of Systems (EA 7306), University of Lorraine, 54000 Nancy, FranceLaboratory for Design, Optimization, and Modeling of Systems (EA 7306), University of Lorraine, 54000 Nancy, FrancePredictive maintenance is essential for improving the efficiency of equipment and reducing downtime in industrial operations. This study investigates the application of machine learning in predictive maintenance, specifically emphasizing data preprocessing and classification techniques using the Teager–Kaiser Energy Operator (TKEO) method, which captures dynamic variation in signals. The effectiveness of TKEO was compared against conventional methods, using the Case Western Reserve University (CWRU) dataset, with vibration data collected from bearings operating under different load conditions. Different data segmentation lengths (2400 and 12,000 samples) were evaluated to assess the impact of segment size on classification accuracy. The study also investigated the effects of various feature selection strategies by comparing four- and six-feature combinations. Advanced classifiers, including support vector machines and random forests, demonstrated that TKEO effectively improved model accuracy in the capture of fault-related signal dynamics. These findings offer new insights to support reliable predictive maintenance in industrial settings and provide a new perspective for future research into active vibration control, where vibration signal analysis, feature extraction, and mathematical modeling play key roles in optimizing control algorithms and enhancing the efficiency of adaptive control systems.https://www.mdpi.com/2076-3417/15/7/3774Teager–kaiser energy operator methodpredictive maintenancevibration signalsmachine learningclassification
spellingShingle Xuanbai Yu
Olivier Caspary
TKEO-Enhanced Machine Learning for Classification of Bearing Faults in Predictive Maintenance
Applied Sciences
Teager–kaiser energy operator method
predictive maintenance
vibration signals
machine learning
classification
title TKEO-Enhanced Machine Learning for Classification of Bearing Faults in Predictive Maintenance
title_full TKEO-Enhanced Machine Learning for Classification of Bearing Faults in Predictive Maintenance
title_fullStr TKEO-Enhanced Machine Learning for Classification of Bearing Faults in Predictive Maintenance
title_full_unstemmed TKEO-Enhanced Machine Learning for Classification of Bearing Faults in Predictive Maintenance
title_short TKEO-Enhanced Machine Learning for Classification of Bearing Faults in Predictive Maintenance
title_sort tkeo enhanced machine learning for classification of bearing faults in predictive maintenance
topic Teager–kaiser energy operator method
predictive maintenance
vibration signals
machine learning
classification
url https://www.mdpi.com/2076-3417/15/7/3774
work_keys_str_mv AT xuanbaiyu tkeoenhancedmachinelearningforclassificationofbearingfaultsinpredictivemaintenance
AT oliviercaspary tkeoenhancedmachinelearningforclassificationofbearingfaultsinpredictivemaintenance