Accès libre

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

Pavle Stepanić

Pavle Stepanić

Research and Development Institute Lola L.t.d.Belgrade, Serbia
Profil Orcid
Recherchez cet auteur sur
Sciendo|Google Scholar
Stepanić, Pavle
, 
Nedeljko Dučić

Nedeljko Dučić

Faculty of Technical Sciences Čačak, University of KragujevacČačak, Serbia
Profil Orcid
Recherchez cet auteur sur
Sciendo|Google Scholar
Dučić, Nedeljko
, 
Jelena Vidaković

Jelena Vidaković

Research and Development Institute Lola L.t.d.Belgrade, Serbia
Profil Orcid
Recherchez cet auteur sur
Sciendo|Google Scholar
Vidaković, Jelena
, 
Jelena Baralić

Jelena Baralić

Faculty of Technical Sciences Čačak, University of KragujevacČačak, Serbia
Profil Orcid
Recherchez cet auteur sur
Sciendo|Google Scholar
Baralić, Jelena
 et 
Marko Popović

Marko Popović

Faculty of Technical Sciences Čačak, University of KragujevacČačak, Serbia
Profil Orcid
Recherchez cet auteur sur
Sciendo|Google Scholar
Popović, Marko
  
12 avr. 2025
Implementation and Evaluation of Machine Learning Algorithms in Ball Bearing Fault Detection's Cover Image
À propos de cet article
Article précédent
Article suivant
Citez
Télécharger la couverture
Publié en ligne: 12 avr. 2025
Pages: 22 - 29
Reçu: 12 avr. 2024
Accepté: 07 mars 2025
DOI: https://doi.org/10.2478/msr-2025-0004
Mots clés
© 2025 Pavle Stepanić et al., published by Sciendo
This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Fig. 1.

The developed ball bearing test station.
The developed ball bearing test station.

Fig. 2.

Confusion matrix for the cosine KNN algorithm.
Confusion matrix for the cosine KNN algorithm.

Fig. 3.

ROC curve for the cosine KNN algorithm.
ROC curve for the cosine KNN algorithm.

Fig. 4.

Confusion matrix for the quadratic SVM algorithm.
Confusion matrix for the quadratic SVM algorithm.

Fig. 5.

ROC curve for the quadratic SVM algorithm.
ROC curve for the quadratic SVM algorithm.

Fig. 6.

The optimization flow for the SVM algorithm.
The optimization flow for the SVM algorithm.

Fig. 7.

The optimization flow for the KNN algorithm.
The optimization flow for the KNN algorithm.

The optimized hyperparameters of the KNN algorithm_

Hyperparameter Range
Number of neighbors 1
Distance metric Correlation
Distance weight Inverse
Standardize data true
Accuracy 100 %

Hybrid ML models_

Applied ML model Research description
SVM with GA A study applied SVM combined with GA to develop optimal classifiers for distinguishing healthy and faulty bearings in ASD systems, achieving 97.5 % accuracy [21].
SVM and ANN with CWT This study explored the use of SVM and ANN alongside CWT to analyze frame vibrations during motor start-up, achieving 96.67 % accuracy with SVM and 90 % with ANN [22].
PCA and SVDD PCA and SVDD were used to predict bearing failures, achieving 93.45 % accuracy [23].
GA-based SVM A GA-based kernel discriminative feature analysis was combined with one-against-all multicategory SVMs (OAA MCSVMs) for fault diagnosis in low-speed bearings, achieving the highest reported accuracy of 98.66 % [24].
FEM and WPT with SVM A hybrid approach integrating FEM, WPT, and SVM was proposed for fault classification, achieving 81 % accuracy for inner race faults and 79 % for rolling body faults [25].
FFT-based feature extraction with SVM The frequency domain features derived from FFT were used to train an SVM model for bearing fault classification, achieving 87.35 % accuracy [26].

The optimized hyperparameters of the SVM algorithm_

Hyperparameter Value
Box constraint level 977.88
Kernel scale 1
Kernel function Quadratic
Standardize data true
Accuracy 100 %

KNN hyperparameter search range_

Hyperparameter Range
Number of neighbors 1–98
Distance metric Euclidean, Cosine, Euclidean, Correlation, Chebyshev, Hamming, Minakowski, Spearman, Jaccard, City block, Mahalanobis
Distance weight Equal, Inverse, Squared, Inverse
Standardize data true, false

SVM hyperparameter search range_

Hyperparameter Range
Box constraint level 0.001-1000
Kernel scale 0.001-1000
Kernel function Gaussian, Linear, Quadratic, Cubic
Standardize data true, false

SVM classification_

Model No Kernel function Classification success rate
1 Linear 93.9 %
2 Polynomial (ρ = 2) 99.5 %
3 RBF 99 %

The k-nearest neighbor (KNN) classification_

Model No Model name Distance metric Distance weight Number of neighbors Classification success rate
1 Cosine KNN Cosine Equal 10 98.5 %
2 Coarse KNN Euclidean Equal 100 74 %
3 Fine KNN Euclidean Equal 1 97.4 %
4 Weighted KNN Euclidean Squared inverse 10 97.4 %
5 Medium KNN Euclidean Equal 1 98 %
6 Cubic KNN Minkowski Equal 10 98.2 %
Langue:
Anglais
Périodicité:
6 fois par an
Sujets de la revue:
Ingénierie, Ingénierie électrique, Ingénierie de contrôle, métrologie et essais
RSS Feed de la revue