Benchmarking Machine Learning Algorithms for Bearing Fault Classification Using Vibration Data: A Deployment-Oriented Study
This study presents a comprehensive benchmarking of 33 machine learning (ML) algorithms for bearing fault classification using vibration data, with a focus on real-world deployment in condition monitoring systems. A total of 81,000 samples were collected from three case studies involving SKF7205, SK...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11045386/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850116912068952064 |
|---|---|
| author | Prasanta Kumar Samal R. Srinidhi Pramod Kumar Malik H. J. Manjunatha Imran M. Jamadar |
| author_facet | Prasanta Kumar Samal R. Srinidhi Pramod Kumar Malik H. J. Manjunatha Imran M. Jamadar |
| author_sort | Prasanta Kumar Samal |
| collection | DOAJ |
| description | This study presents a comprehensive benchmarking of 33 machine learning (ML) algorithms for bearing fault classification using vibration data, with a focus on real-world deployment in condition monitoring systems. A total of 81,000 samples were collected from three case studies involving SKF7205, SKF7206, and SKF7207 rolling element bearings under varying fault conditions. Feature selection using Principal Component Analysis (PCA) and correlation-based filtering was employed to reduce redundancy and enhance model performance. The classifiers were evaluated across multiple metrics including validation accuracy, test accuracy, misclassification cost, training time, and area under the receiver operating characteristic (ROC) curve (AUC). Ensemble Bagged Trees consistently outperformed other models across all case studies, demonstrating superior classification accuracy, robustness, and low misclassification cost. Fine Tree models also demonstrated competitive performance while maintaining low computational demand, while Wide Neural Networks exhibited high predictive performance with longer training times. This work provides a practical reference for researchers and practitioners by systematically comparing ML algorithms and elucidating the trade-offs between predictive accuracy, computational efficiency, and deployment readiness in real-world fault diagnosis applications. |
| format | Article |
| id | doaj-art-28097766649941ed9d1c85bb2caee8a4 |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-28097766649941ed9d1c85bb2caee8a42025-08-20T02:36:12ZengIEEEIEEE Access2169-35362025-01-011311398411400210.1109/ACCESS.2025.358171111045386Benchmarking Machine Learning Algorithms for Bearing Fault Classification Using Vibration Data: A Deployment-Oriented StudyPrasanta Kumar Samal0https://orcid.org/0000-0002-3688-259XR. Srinidhi1Pramod Kumar Malik2https://orcid.org/0000-0002-1889-3754H. J. Manjunatha3https://orcid.org/0009-0008-6243-5997Imran M. Jamadar4https://orcid.org/0000-0002-0717-0542Department of Mechanical Engineering, The National Institute of Engineering, Mysuru, Karnataka, IndiaDepartment of Mechanical Engineering, JSS Science and Technology University, Mysuru, Karnataka, India>School of Aerospace Engineering, KIIT Deemed to be University, Bhubaneswar, Odisha, IndiaDepartment of Mechanical Engineering, The National Institute of Engineering, Mysuru, Karnataka, IndiaDepartment of Mechanical Engineering, The National Institute of Engineering, Mysuru, Karnataka, IndiaThis study presents a comprehensive benchmarking of 33 machine learning (ML) algorithms for bearing fault classification using vibration data, with a focus on real-world deployment in condition monitoring systems. A total of 81,000 samples were collected from three case studies involving SKF7205, SKF7206, and SKF7207 rolling element bearings under varying fault conditions. Feature selection using Principal Component Analysis (PCA) and correlation-based filtering was employed to reduce redundancy and enhance model performance. The classifiers were evaluated across multiple metrics including validation accuracy, test accuracy, misclassification cost, training time, and area under the receiver operating characteristic (ROC) curve (AUC). Ensemble Bagged Trees consistently outperformed other models across all case studies, demonstrating superior classification accuracy, robustness, and low misclassification cost. Fine Tree models also demonstrated competitive performance while maintaining low computational demand, while Wide Neural Networks exhibited high predictive performance with longer training times. This work provides a practical reference for researchers and practitioners by systematically comparing ML algorithms and elucidating the trade-offs between predictive accuracy, computational efficiency, and deployment readiness in real-world fault diagnosis applications.https://ieeexplore.ieee.org/document/11045386/Bearing fault diagnosisML algorithmfeature selectionprincipal component analysis (PCA)predictive maintenanceindustrial deployment |
| spellingShingle | Prasanta Kumar Samal R. Srinidhi Pramod Kumar Malik H. J. Manjunatha Imran M. Jamadar Benchmarking Machine Learning Algorithms for Bearing Fault Classification Using Vibration Data: A Deployment-Oriented Study IEEE Access Bearing fault diagnosis ML algorithm feature selection principal component analysis (PCA) predictive maintenance industrial deployment |
| title | Benchmarking Machine Learning Algorithms for Bearing Fault Classification Using Vibration Data: A Deployment-Oriented Study |
| title_full | Benchmarking Machine Learning Algorithms for Bearing Fault Classification Using Vibration Data: A Deployment-Oriented Study |
| title_fullStr | Benchmarking Machine Learning Algorithms for Bearing Fault Classification Using Vibration Data: A Deployment-Oriented Study |
| title_full_unstemmed | Benchmarking Machine Learning Algorithms for Bearing Fault Classification Using Vibration Data: A Deployment-Oriented Study |
| title_short | Benchmarking Machine Learning Algorithms for Bearing Fault Classification Using Vibration Data: A Deployment-Oriented Study |
| title_sort | benchmarking machine learning algorithms for bearing fault classification using vibration data a deployment oriented study |
| topic | Bearing fault diagnosis ML algorithm feature selection principal component analysis (PCA) predictive maintenance industrial deployment |
| url | https://ieeexplore.ieee.org/document/11045386/ |
| work_keys_str_mv | AT prasantakumarsamal benchmarkingmachinelearningalgorithmsforbearingfaultclassificationusingvibrationdataadeploymentorientedstudy AT rsrinidhi benchmarkingmachinelearningalgorithmsforbearingfaultclassificationusingvibrationdataadeploymentorientedstudy AT pramodkumarmalik benchmarkingmachinelearningalgorithmsforbearingfaultclassificationusingvibrationdataadeploymentorientedstudy AT hjmanjunatha benchmarkingmachinelearningalgorithmsforbearingfaultclassificationusingvibrationdataadeploymentorientedstudy AT imranmjamadar benchmarkingmachinelearningalgorithmsforbearingfaultclassificationusingvibrationdataadeploymentorientedstudy |