Makine öğrenimi ve derin öğrenme yaklaşımlarını kullanarak frekans tabanlı öznitelik çıkarımı ile endüstriyel makinelerde dengesizlik hatalarının tespiti

Yıl 2025, Cilt: 40 Sayı: 3, 581 - 592, 26.09.2025

Feyyaz Alpsalaz

https://doi.org/10.21605/cukurovaumfd.1660218

Öz

Bu çalışmada, endüstriyel makinelerde dengesizlik hatalarının teşhisinde makine öğrenimi ve derin öğrenme modellerinin etkinliği incelenmiş, frekans tabanlı özellik çıkarımı için Hızlı Fourier Dönüşümü (FFT) kullanılmıştır. Dengesizlik, ekipman ömrünü kısaltıp bakım maliyetlerini artırdığından, titreşim verileri analiz edilerek FFT ile frekans bileşenleri çıkarılmış ve sınıflandırma yapılmıştır. Destek Vektör Makinaları, Rastgele Ormanlar ve Çok Katmanlı Algılayıcı modelleri; doğruluk, hassasiyet, geri çağırma ve F1-skoru metrikleriyle karşılaştırılmıştır. Çok Katmanlı Algılayıcı, %99 doğrulukla en iyi performansı göstermiş, FFT ile çıkarılan örüntüleri en iyi yakalamıştır. Rastgele Ormanlar başarılı tahminler yapmış ancak bazı sınıflarda hata oranı yüksek bulunmuştur. Destek Vektör Makinaları ise daha düşük doğruluk sunmuştur. FFT ve makine öğrenimi kombinasyonu, döner makine arıza teşhisine katkı sağlamaktadır. Gelecekte, daha büyük veri setleri, hiperparametre optimizasyonu ve dalgacık dönüşümü gibi yöntemlerle model performansı artırılabilir.

Anahtar Kelimeler

Makine Dengesizlik Arızası , MLP , Titreşim Analizi , Derin öğrenme

Detection of imbalance faults in industrial machines by means of frequency-based feature extraction using machine learning and deep learning approaches

Öz

This study investigated the effectiveness of machine learning and deep learning models in diagnosing imbalance faults in industrial machines, using Fast Fourier Transform (FFT) for frequency-based feature extraction. As imbalance shortens equipment life and increases maintenance costs, vibration data was analysed and frequency components were extracted using FFT for classification. Support Vector Machine, Random Forest and Multi-Layer Perceptron models were then compared using the metrics of accuracy, precision, recall and F1 score. The Multi-Layer Perceptron model performed best with 99% accuracy, capturing the patterns extracted by FFT most effectively. Random Forests made successful predictions, but had a high error rate in some classes. Support Vector Machines, on the other hand, offered lower accuracy. Combining FFT with machine learning contributes to the diagnosis of faults in rotating machines. Model performance could be improved in future using larger data sets, hyperparameter optimisation and methods such as wavelet transformation.

Anahtar Kelimeler

Machine Imbalance Fault , MLP , Vibration Analysis , Deep Learning

Kaynakça

• 1. Çınar, M., Aslan, E. & Özüpak, Y. (2025). Comparison and optimization of machine learning methods for fault detection in district heating and cooling systems. Bulletin of the Polish Academy of Sciences Technical Sciences, 154063-154063.
• 2. Li, L., Liu, K., Wang, L., Sun, L., Zhang, Z. & Guo, H. (2022). Fault diagnosis of balancing machine based on ISSA-ELM. Computational Intelligence and Neuroscience, 2022(1), 4981022.
• 3. Hu, Y., Lv, W., Wang, Z., Liu, L. & Liu, H. (2023). Error prediction of balancing machine calibration based on machine learning method. Mechanical Systems and Signal Processing, 184, 109736.
• 4. Benkaihoul, S., Mazouz, L., Naas, T. T., Yildirim, Ö. & Mohammedi, R.D. (2024). Broken magnets fault detection in PMSM using a convolutional neural network and SVM. ITEGAM-JETIA, 10(48), 55-62.
• 5. Zhang, W., Li, X., Jia, X.D., Ma, H., Luo, Z. & Li, X. (2020). Machinery fault diagnosis with imbalanced data using deep generative adversarial networks. Measurement, 152, 107377.
• 6. Jiang, Z., Liu, D. & Cui, L. (2025). A temporal-spatial multi-order weighted graph convolution network with refined feature topology graph for imbalance fault diagnosis of rotating machinery. Measurement Science and Technology, 36(2), 110830.
• 7. Zhao, Y., Yang, X., Huang, J., Gao, J. & Cui, J. (2024). Improved weighted extreme learning machine with adaptive cost-sensitive strategy for imbalanced fault diagnosis of rotating machinery. Mechanical Systems and Signal Processing, 217, 111526.
• 8. Jia, F., Lei, Y., Lu, N. & Xing, S. (2018). Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization. Mechanical Systems and Signal Processing, 110, 349-367.
• 9. He, S., Cui, Q., Chen, J., Pan, T. & Hu, C. (2024). Contrastive feature-based learning-guided elevated deep reinforcement learning: Developing an imbalanced fault quantitative diagnosis under variable working conditions. Mechanical Systems and Signal Processing, 211, 111192.
• 10. Shi, M., Ding, C., Wang, R., Shen, C., Huang, W. & Zhu, Z. (2023). Graph embedding deep broad learning system for data imbalance fault diagnosis of rotating machinery. Reliability Engineering & System Safety, 240, 109601.
• 11. Pan, H., Li, B., Zheng, J., Tong, J., Liu, Q. & Deng, S. (2024). Research on roller bearing fault diagnosis based on robust smooth constrained matrix machine under imbalanced data. Advanced Engineering Informatics, 62, 102667.
• 12. Wang, X., Jiang, H., Mu, M. & Dong, Y. (2025). A trackable multi-domain collaborative generative adversarial network for rotating machinery fault diagnosis. Mechanical Systems and Signal Processing, 224, 111950.
• 13. Wu, Z., Xu, R., Luo, Y. & Shao, H. (2024). A holistic semi-supervised method for imbalanced fault diagnosis of rotational machinery with out-of-distribution samples. Reliability Engineering & System Safety, 250, 110297.
• 14. Lin, C., Kong, Y., Huang, G., Han, Q., Dong, M., Liu, H. & Chu, F. (2025). Generalization classification regularization generative adversarial network for machinery fault diagnostics under data imbalance. Reliability Engineering & System Safety, 256, 110791.
• 15. Yang, W., Zhang, H., Lim, J.B., Zhang, Y. & Meng, H. (2024). A new chiller fault diagnosis method under the imbalanced data environment via combining an improved generative adversarial network with an enhanced deep extreme learning machine. Engineering Applications of Artificial Intelligence, 137, 109218.
• 16. Chang, S., Wang, L., Shi, M., Zhang, J., Yang, L. & Cui, L. (2024). Extended attention signal transformer with adaptive class imbalance loss for Long-tailed intelligent fault diagnosis of rotating machinery. Advanced Engineering Informatics, 60, 102436.
• 17. Li, Z., Zheng, T., Wang, Y., Cao, Z., Guo, Z. & Fu, H. (2021). A novel method for imbalanced fault diagnosis of rotating machinery based on generative adversarial Networks. IEEE Transactions on Instrumentation and Measurement, 70.
• 18. Ribeiro, F.M.L. (2021). Machinery fault database. Signals, Multimedia, and Telecommunications Laboratory. https://www02.smt.ufrj.br/~offshore/mfs/page_01.html
• 19. Alpsalaz, F. (2025). Fault detection in power transmission lines: Comparison of chirp-Z algorithm and machine learning based prediction models. Eksploatacja i Niezawodność - Maintenance and Reliability 27(4), 203949.
• 20. Aslan, E., Özüpak, Y., Alpsalaz, F. & Elbarbary, Z.M.S. (2025). A hybrid machine learning approach for predicting power transformer failures using internet of things-based monitoring and explainable artificial intelligence. IEEE Access, 13, 113618-113633.
• 21. Aslan, E. & Özüpak, Y. (2025). Comparison of machine learning algorithms for automatic prediction of alzheimer disease. Journal of the Chinese Medical Association, 88(2), 98-107.
• 22. Turkay, Y. & Tamay, Z.S. (2024). Pistachio classification based on acoustic systems and machine learning. Elektronika Ir Elektrotechnika, 30(5), 4-13.
• 23. Khan, M.A., Asad, B., Vaimann, T., Kallaste, A., Pomarnacki, R. & Hyunh, V.K. (2023). Improved fault classification and localization in power transmission networks using VAE-generated synthetic data and machine learning algorithms. Machines 11(10), 963.
• 24. Özüpak, Y. (2025). Machine learning-based fault detection in transmission lines: A comparative study with random search optimization. Bulletin of the Polish Academy of Sciences Technical Sciences, 153229-153229.
• 25. Aslan, E. (2024). Araçlarda CO2 emisyonlarının farklı yapay sinir ağı modelleri kullanılarak tahminlerinin karşılaştırılması. Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, 39(2), 309-324.
• 26. Özüpak, Y. (2024). Evrişimli sinir ağı (ESA) mimarileri ile hücre görüntülerinden sıtmanın tespit edilmesi. Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, 39(1), 197-210.
• 27. Uluocak, İ. (2025). Comparative study of emission prediction using deep learning models. Çukurova Üniversitesi Mühendislik Fakültesi Dergisi, 40(2), 337-346.