TKEO-Enhanced Machine Learning for Classification of Bearing Faults in Predictive Maintenance
Source abstract
Abstract
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.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Engineering Diagnostics and Reliability · Machine Fault Diagnosis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Laboratory for Design, Optimization, and Modeling of Systems (EA 7306), University of Lorraine, 54000 Nancy, France
References (30)
Show source-provided references
1. (2025, March 17). SKF Annual Report 2017. Available online: https://investors.skf.com/sites/skf-ir/files/pr/201803059585-1.pdf.
2. Achouch, M., Dimitrova, M., Ziane, K., Sattarpanah Karganroudi, S., Dhouib, R., Ibrahim, H., and Adda, M. (2022). On Predictive Maintenance in Industry 4.0: Overview, Models, and Challenges. Appl. Sci., 12.10.3390/app12168081 ↗
3. Vachtsevanos, G., Lewis, F., Roemer, M., Hess, A., and Wu, B. (2006). Fault Diagnosis. Intelligent Fault Diagnosis and Prognosis for Engineering Systems, John Wiley & Sons, Inc.10.1002/9780470117842 ↗
4. Insights into modern machine learning approaches for bearing fault classification: A systematic literature review10.1016/j.rineng.2024.102700 ↗
5. A novel deep stacking least squares support vector machine for rolling bearing fault diagnosis10.1016/j.compind.2019.05.005 ↗
6. Yoo, Y., Jo, H., and Ban, S.-W. (2023). Lite and Efficient Deep Learning Model for Bearing Fault Diagnosis Using the CWRU Dataset. Sensors, 23.10.3390/s23063157 ↗
7. Machine Learning for Bearing Fault Diagnosis
8. Bearing Fault Diagnosis With Envelope Analysis and Machine Learning Approaches Using CWRU Dataset10.1109/ACCESS.2023.3283466 ↗
9. Wei, X., and Söffker, D. (2021). Comparison of CWRU Dataset-Based Diagnosis Approaches: Review of Best Approaches and Results. European Workshop on Structural Health Monitoring, Springer.10.1007/978-3-030-64594-6_51 ↗
10. Application of the Teager–Kaiser energy operator in bearing fault diagnosis10.1016/j.isatra.2012.12.006 ↗
11. Rolling Element Bearing Fault Diagnosis Using an Integrated Approach Incorporating Teager–Kaiser Energy Operator and Singular Spectrum Analysis10.1007/s42417-022-00787-3 ↗
12. Bearing fault classification using TKEO statistical features and artificial intelligence10.3233/JIFS-224221 ↗
13. Bearing Fault Diagnosis Using Deep Sparse Autoencoder10.1088/1757-899X/1062/1/012002 ↗
14. (2023, September 07). Case School of Engineering, Case Western Reserve University. Bearing Data Center. Available online: https://engineering.case.edu/bearingdatacenter.
15. Teager–Kaiser energy methods for signal and image analysis: A review10.1016/j.dsp.2018.03.010 ↗
16. Kaiser, J.F. (1990, January 3–6). On a simple algorithm to calculate the “energy” of a signal. Proceedings of the International Conference on Acoustics, Speech, and Signal Processing, 1990, ICASSP-90, Albuquerque, NM, USA.
17. Kvedalen, E. (2003). Signal Processing Using the Teager Energy Operator and Other Nonlinear Operators. [Master’s Thesis, University of Oslo]. Available online: https://api.semanticscholar.org/CorpusID:113672443.
18. (2025, March 17). Introduction to Statistical Learning Using R Book Club. Available online: https://r4ds.github.io/bookclub-islr/hyperplane.html.
19. A review on support vector machine for data classification
20. The Elements of Statistical Learning: Data Mining, Inference, and Prediction
21. Parmar, A., Katariya, R., and Patel, V. (2019). A review on random forest: An ensemble classifier. International Conference on Intelligent Data Communication Technologies and Internet of Things (ICICI) 2018, Springer.10.1007/978-3-030-03146-6_86 ↗
22. (2025, March 17). Random Forest Algorithm in Machine Learning. Available online: https://www.geeksforgeeks.org/random-forest-algorithm-in-machine-learning/.
23. (2025, March 17). Introduction Random Forest Classification by Example. Available online: https://medium.com/@mrmaster907/introduction-random-forest-classification-by-example-6983d95c7b91.
24. (2023, September 07). CRWU Bearings SVM_Fault_Classification. Available online: https://kaggle.com/code/brjapon/crwu-bearings-svm-fault-classification.
25. (2023, September 07). Course3 Solution: CRWU Bearing Feat. Importance. Available online: https://kaggle.com/code/brjapon/course3-solution-crwu-bearing-feat-importance.
26. Condition-based maintenance optimization for multi-component systems considering prognostic information and degraded working efficiency10.1016/j.ress.2023.109167 ↗
27. Lee, S., and Jeong, J. (2022). SSA-SL Transformer for Bearing Fault Diagnosis under Noisy Factory Environments. Electronics, 11.10.3390/electronics11091504 ↗
28. Hadi, R.H., Hady, H.N., Hasan, A.M., Al-Jodah, A., and Humaidi, A.J. (2023). Improved Fault Classification for Predictive Maintenance in Industrial IoT Based on AutoML: A Case Study of Ball-Bearing Faults. Processes, 11.10.3390/pr11051507 ↗
29. Shi, X., Zhang, Z., Xia, Z., Li, B., Gu, X., and Shi, T. (2022). Application of Teager–Kaiser Energy Operator in the Early Fault Diagnosis of Rolling Bearings. Sensors, 22.10.3390/s22176673 ↗
30. A review of the inerter and inerter-based vibration isolation: Theory, devices, and applications10.1016/j.jfranklin.2022.07.030 ↗