Değişken Hızlı Senkron Jeneratörlerde Makine Öğrenmesine Dayalı Arıza Teşhisi

Abstract

Bu çalışmada, değişken hızlı senkron jeneratörlerde arıza teşhisi amacıyla beş farklı makine öğrenmesi algoritması olan Karar Ağacı, Rastgele Orman, En Yakın Komşular, Destek Vektör Makineleri ve Lojistik Regresyonun performansları incelenmiştir. Gerçek deneysel verilerden oluşan veri seti, jeneratörün hem sağlıklı hem de arızalı çalışma durumlarını içermektedir. Veri üzerinde Normalizasyon, Z-Score Standartlaştırması ve Özellik Seçimi gibi ön işleme adımları uygulanarak, bu işlemlerin sınıflandırma performansına etkileri değerlendirilmiştir. Elde edilen bulgulara göre, Karar Ağacı algoritması %99.43 doğruluk oranı ve 0.975 MCC değeri ile en yüksek performansı göstermiştir. Rastgele Orman algoritması benzer sonuçlar verirken, En Yakın Komşular, Destek Vektör Makineleri ve Lojistik Regresyon algoritmaları daha düşük doğruluk değerlerine ulaşmıştır. Ön işleme adımlarının model performansında anlamlı bir artış sağlamadığı, veri setinin ölçek açısından zaten dengeli olduğu belirlenmiştir. Sonuçlar, Karar Ağacı algoritmasının değişken hızlı senkron jeneratörlerde arıza tespiti için en uygun ve güvenilir yöntem olduğunu ortaya koymuştur. Bu çalışma, makine öğrenmesi tabanlı yaklaşımların jeneratörlerde erken arıza teşhisinde etkin bir şekilde kullanılabileceğini göstermektedir.

Keywords

• Senkron jeneratör
• makine öğrenmesi
• arıza teşhisi.

Machine Learning Based Fault Diagnosis in Variable Speed Synchronous Generators

Abstract

In this study, the performance of five different machine learning algorithms, decision tree, random forest, K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and logistic regression, was investigated for fault diagnosis in variable-speed synchronous generators. The dataset, consisting of real-world experimental data, includes both healthy and faulty generator operating states. Pre-processing steps such as normalization, Z-Score standardization, and feature selection were applied to the data, and the effects of these processes on classification performance were evaluated. According to the findings, the decision tree algorithm achieved the highest performance with an accurate rate of 99.43% and Matthews Correlation Coefficient (MCC) value of 0.975. While the random forest algorithm yielded similar results, the KNN, SVM, and logistic regression algorithms achieved lower accuracy values. It was determined that the pre-processing steps did not provide a significant increase in model performance, and the dataset was already balanced in terms of scale. The results revealed that the decision tree algorithm is the most suitable and reliable method for fault detection in variable-speed synchronous generators. This study demonstrates that machine learning-based approaches can be used effectively in early fault diagnosis in generators.

Keywords

• Synchronous generator
• Machine learning
• Fault diagnosis

References

1. Agrawal, E., & Ali, S. (2024). Advancements in machine learning algorithms for enhanced fault analysis and categorization in power systems. International Journal for Multidisciplinary Research, 6(4), 1-18. https://doi.org/10.36948/ijfmr.2024.v06i04.25682
2. Biau, G., & Scornet, E. (2016). A random forest guided tour. TEST, 25, 197–227. https://doi.org/10.1007/s11749-016-0481-7
3. Bisong, E. (2019). Logistic regression. In Building machine learning and deep learning models on Google Cloud Platform (pp. 243–250). Apress. https://doi.org/10.1007/978-1-4842-4470-8_20
4. Charbuty, B., & Abdulazeez, A. (2021). Classification based on decision tree algorithm for machine learning. Journal of Applied Science and Technology Trends, 2(1), 20–28. https://doi.org/10.38094/jastt20165
5. Chen, J., & Huang, W. (2025). GNSS-R based sea ice classification using track normalized observables. In Proceedings of OCEANS 2025 Brest (pp. 1–4). https://doi.org/10.1109/OCEANS58557.2025.11104660
6. Chen, X., Yang, R., Xue, Y., Huang, M., Ferrero, R., & Wang, Z. (2023). Deep transfer learning for bearing fault diagnosis: A systematic review since 2016. IEEE Transactions on Instrumentation and Measurement, 72, 1–21. https://doi.org/10.1109/tim.2023.3244237
7. Çınar, Z., Nuhu, A., Zeeshan, Q., Korhan, O., Asmael, M., & Safaei, B. (2020). Machine learning in predictive maintenance towards sustainable smart manufacturing in Industry 4.0. Sustainability, 12(19), Article 8211. https://doi.org/10.3390/su12198211
8. Gong, W., Chen, H., Zhang, Z., Zhang, M., Wang, R., Guan, C., & Wang, Q. (2019). A novel deep learning method for intelligent fault diagnosis of rotating machinery based on improved CNN-SVM and multichannel data fusion. Sensors, 19(7), Article 1693. https://doi.org/10.3390/s19071693

9. Gopinath, R., Kumar, C., Vishnuprasad, K., & Ramachandran, K. (2020). Feature mapping techniques for improving the performance of fault diagnosis of synchronous generator. International Journal of Prognostics and Health Management, 6(2), 1-12. https://doi.org/10.36001/ijphm.2015.v6i2.2256
10. Guo, J., Li, X., Wang, Y., Zhang, H., & Liu, J. (2025). Robust multi-task adversarial attacks using min-max optimization. In ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) (pp. 1–5). https://doi.org/10.1109/ICASSP49660.2025.10888541
11. Jiao, J., Zhao, M., Lin, J., & Liang, K. (2020). A comprehensive review on convolutional neural network in machine fault diagnosis. Neurocomputing, 417, 36–63. https://doi.org/10.1016/j.neucom.2020.07.088
12. Lei, Y., Yang, B., Jiang, X., Jia, F., Li, N., & Nandi, A. (2020). Applications of machine learning to machine fault diagnosis: A review and roadmap. Mechanical Systems and Signal Processing, 138, Article 106587. https://doi.org/10.1016/j.ymssp.2019.106587
13. Ma, P., Zhang, H., Fan, W., Wang, C., Wen, G., & Zhang, X. (2019). A novel bearing fault diagnosis method based on 2D image representation and transfer learning-convolutional neural network. Measurement Science and Technology, 30(5), Article 055402. https://doi.org/10.1088/1361-6501/ab0793
14. Mazaheri‐Tehrani, E., & Faiz, J. (2021). Airgap and stray magnetic flux monitoring techniques for fault diagnosis of electrical machines: An overview. IET Electric Power Applications, 16(3), 277–299. https://doi.org/10.1049/elp2.12157
15. Nguyen, K., & Medjaher, K. (2019). A new dynamic predictive maintenance framework using deep learning for failure prognostics. Reliability Engineering & System Safety, 188, 251–262. https://doi.org/10.1016/j.ress.2019.03.018
16. Önder, M., Dogan, M. U., & Polat, K. (2023). Classification of smart grid stability prediction using cascade machine learning methods and the internet of things in smart grid. Neural Computing & Applications, 35, 17851–17869. https://doi.org/10.1007/s00521-023-08605-x
17. Peng, D., Liu, Z., Wang, H., Qin, Y., & Jia, L. (2019). A novel deeper one-dimensional CNN with residual learning for fault diagnosis of wheelset bearings in high-speed trains. IEEE Access, 7, 10278–10293. https://doi.org/10.1109/access.2018.2888842
18. Rahnama, M., Vahedi, A., Mohammad‐Alikhani, A., & Takorabet, N. (2020). Diagnosis of brushless synchronous generator using numerical modeling. Compel - The International Journal for Computation and Mathematics in Electrical and Electronic Engineering, 39(5), 1241–1254. https://doi.org/10.1108/compel-01-2020-0018
19. Salomon, C. P., Ferreira, C., Sant’Ana, W. C., Lambert-Torres, G., Borges da Silva, L. E., Bonaldi, E. L., de Oliveira, L. E. d. L., & Torres, B. S. (2019). A study of fault diagnosis based on electrical signature analysis for synchronous generators predictive maintenance in bulk electric systems. Energies, 12(8), Article 1506. https://doi.org/10.3390/en12081506
20. Silva, A., Cortez, P., Pereira, C., & Pilastri, A. (2021). Business analytics in Industry 4.0: A systematic review. Expert Systems, 38(7), Article e12741. https://doi.org/10.1111/exsy.12741
21. Soucy, P., & Mineau, G. W. (2001). A simple KNN algorithm for text categorization. In Proceedings 2001 IEEE International Conference on Data Mining (pp. 647–648). https://doi.org/10.1109/ICDM.2001.989592
22. Tama, B. A., Vania, M., Lee, S., & Lim, S. (2022). Recent advances in the application of deep learning for fault diagnosis of rotating machinery using vibration signals. Artificial Intelligence Review, 56(5), 4667–4709. https://doi.org/10.1007/s10462-022-10293-3
23. Tang, S., Yuan, S., & Zhu, Y. (2020a). Convolutional neural network in intelligent fault diagnosis toward rotatory machinery. IEEE Access, 8, 86510–86519. https://doi.org/10.1109/access.2020.2992692
24. Tang, S., Yuan, S., & Zhu, Y. (2020b). Deep learning-based intelligent fault diagnosis methods toward rotating machinery. IEEE Access, 8, 9335–9346. https://doi.org/10.1109/access.2019.2963092
25. Tominaga, R. N., Sousa, L. A., Rocha, R. V., Monaro, R. M., Ávila, S. L., de Camargo Salles, M. B., & Carmo, B. S. (2024). Electrical signals dataset from fixed-speed and variable-speed synchronous generators under healthy and faulty conditions. Data in Brief, 57, Article 111018. https://doi.org/10.1016/j.dib.2024.111018
26. Tominaga, R. N., Rocha, R. V., Avila, S. L., Monaro, R. M., Salles, M. B. C., & Carmo, B. S. (2025a). Simulation-based neural network for robust short-circuit detection in wind turbines. In 2025 International Conference on Clean Electrical Power (ICCEP). https://doi.org/10.1109/ICCEP65222.2025.11143686
27. Tominaga, R. N., Rocha, R. V., Avila, S. L., Monaro, R. M., Salles, M. B. C., & Carmo, B. S. (2025b). Modular and compact neural network framework for internal fault detection in generators using current signature data. In 2025 IEEE International Electric Machines & Drives Conference (IEMDC). https://doi.org/10.1109/IEMDC60492.2025.11061103
28. Xu, J., Gao, L., Liu, Z., & Yun, Q. (2025). Research on fault diagnosis method of synchronous generator based on ResNet-18. Journal of Physics Conference Series, 2963(1), Article 012021. https://doi.org/10.1088/1742-6596/2963/1/012021
29. Xu, J., Wang, X., Lu, J., & Hou, H. (2025). Xu weight is all you need! Short-term power load forecasting based on a novel adaptive feature selection method and Xu weight. In 2025 IEEE 4th International Conference on Computing and Machine Intelligence (ICMI) (pp. 1–8). https://doi.org/10.1109/ICMI65310.2025.1114133
30. Yedla, H., Koppada, L. R., & Bodala, R. S. (2024). Advanced battery management: Forecasting health, state of charge & maintenance needs using AI & ML models (LSTM, gradient boosting, SVR, random forest). Asian Journal of Research in Computer Science, 17(8), 46-57. https://doi.org/10.9734/ajrcos/2024/v17i7489
31. Zhang, S., Zhang, S., Wang, B., & Habetler, T. (2020). Deep learning algorithms for bearing fault diagnostics: A comprehensive review. IEEE Access, 8, 29857–29881. https://doi.org/10.1109/access.2020.2972859
32. Zhang, Y. (2012). Support vector machine classification algorithm and its application. In C. Liu, L. Wang, & A. Yang (Eds.), Information computing and applications (pp. 179–186). Springer. https://doi.org/10.1007/978-3-642-34041-3_27
33. Zhao, R., Yan, R., Chen, Z., Mao, K., Wang, P., & Gao, R. X. (2019). Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing, 115, 213–237. https://doi.org/10.1016/j.ymssp.2018.05.050