Deep Learning Based Fault Detection from Bearing Vibration Data

Yıl 2024, , 1159 - 1175, 15.09.2024

Engin Oğuzay , Murat Balta

https://doi.org/10.31466/kfbd.1434595

Öz

Analysis of bearing vibrations can provide information on the overall health of a machine's mechanical components. In this study, deep learning algorithms were integrated in both 1-D and 2-D data spaces to detect defects in motor mechanics commonly utilized in industry, and to increase production efficiency. Ten different classes were studied using the popular and comprehensive Case Western Reserve University (CWRU) bearing dataset, which includes three types of faults - the outer race, the ball, and the inner race - as well as a healthy class. The bearing vibration signal was handled in four ways: using the original vibration data, extracting features from the original data, applying STFT to the original data, and extracting features from the STFT-applied data. Machine learning approaches such as KNN, SVM, and 1D WDCNN were applied to the 1-D data. Additionally, STFT transformation was applied in the 2-D data space, and performance measurements were made with different statistical metrics using EfficientNetB0, EfficientNetB1, ResNet18, and 2D WDCNN. In the 2-D space, deep learning methods achieved 100% accuracy.

Anahtar Kelimeler

Motor Bearing Vibration, Deep Learning, Signal Classification, Industrial Fault Recognition

Rulman Titreşim Verilerinden Derin Öğrenme Tabanlı Arıza Tespiti

Öz

Rulman titreşimlerinin analizi, bir makinenin mekanik bileşenlerinin genel sağlığı hakkında bilgi sağlayabilir. Bu çalışmada, endüstride yaygın olarak kullanılan motor mekaniklerindeki kusurları tespit etmek ve üretim verimliliğini artırmak için derin öğrenme algoritmaları hem 1 boyutlu hem de 2 boyutlu veri uzaylarına entegre edilmiştir. Popüler ve kapsamlı Case Western Reserve Üniversitesi (CWRU) rulman veri kümesi kullanılarak on farklı sınıf üzerinde çalışılmıştır; bu veri kümesi üç tür hata (dış bilezik, bilye ve iç bilezik) ve sağlıklı bir sınıf içermektedir. Rulman titreşim sinyali dört şekilde ele alınmıştır: orijinal titreşim verilerinin kullanılması, orijinal verilerden özelliklerin çıkarılması, orijinal verilere STFT uygulanması ve STFT uygulanmış verilerden özelliklerin çıkarılması. KNN, SVM ve 1D WDCNN gibi makine öğrenimi yaklaşımları 1 boyutlu verilere uygulanmıştır. Ayrıca 2 boyutlu veri uzayında STFT dönüşümü uygulanmış ve EfficientNetB0, EfficientNetB1, ResNet18 ve 2D WDCNN kullanılarak farklı istatistiksel metriklerle performans ölçümleri yapılmıştır. 2 boyutlu uzayda derin öğrenme yöntemleri %100 doğruluk elde etmiştir.

Anahtar Kelimeler

Motor Yatağı Titreşimi, Derin Öğrenme, Sinyal Sınıflandırma, Endüstriyel Arıza Tanıma

Kaynakça

• Anagün, Y., Işik, Ş., ve Çakir, F. H. (2023). Surface roughness classification of electro discharge machinedvsurfaces with deep ensemble learning. Measurement, 215, 112855.
• Aydın, İ., Aydın, E., Akın, E., Kaner, S. (2024). Derin Evrişimsel Sinir Ağ Mimarisi ve Zaman Frekans Gösterimini Kullanılarak Büyük Güçlü Motor Arızalarının Tespiti. EMO Bilimsel Dergi, 14(1), 51-59.
• Berghian-Grosan, C., Isik, S., Porav, A. S., Dag, I., Ay, K. O., ve Vithoulkas, G. (2024). Ultra-high dilutions analysis: Exploring the effects of potentization by electron microscopy, Raman spectroscopy and deep learning. Journal of Molecular Liquids, 401, 124537.
• Caesarendra, W., ve Tjahjowidodo, T. (2017). A Review of Feature Extraction Methods in Vibration-Based Condition Monitoring and Its Application for Degradation Trend Estimation of Low-Speed Slew Bearing. Machines, 5(4), 1-28. https://doi.org/10.3390/machines5040021
• Carvalhoa, T. P., Soares, F. A., Vita, R., Francisco, R. d., Basto, J. P., ve Alcalá, S. G. (2019). A systematic literature review of machine learning methods applied to predictive maintenance. Computers & Industrial Engineering, 137. https://doi.org/10.1016/j.cie.2019.106024"
• Ertarğın, M., Yıldırım, Ö., ve Orhan, A. (2023). Motor Yataklarında Meydana Gelen Arızaları Tespit Etmek için Yeni Bir Tek Boyutlu Konvolüsyonel Sinir Ağı Modeli. Fırat Üniversitesi Mühendislik Bilimleri Dergisi, 35(2), 669-678. https://doi.org/10.35234/fumbd.1292390
• Eren, L., Ince, T., ve Kiranyaz, S. (2019). A Generic Intelligent Bearing Fault Diagnosis System Using Compact Adaptive 1D CNN Classifier. Journal of Signal Processing Systems, 91, 179–189. doi:s11265-018-1378-3
• Fawaz, H. I., Forestier, G., Weber, J., Idoumghar, L., ve Muller, P.-A. (2019). Deep learning for time series classification: a review. Data Mining and Knowledge Discovery, 33, Lhassane Idoumghar & Pierre-Alain Muller. doi:10.1007/s10618-019-00619-1
• Han, S., ve Jeong, J. (2020). An Weighted CNN Ensemble Model with Small Amount of Data for Bearing Fault Diagnosis. Procedia Computer Science, 175, 88-95. doi:j.procs.2020.07.015
• Hendrickx, K., Meert, W., Mollet, Y., Gyselinck, J., Cornelis, B., Gryllias, K., ve Davis, J. (2020). A general anomaly detection framework for fleet-based condition monitoring of machines. Mechanical Systems and Signal Processing, 139, 1-21. doi:j.ymssp.2019.106585
• Hoang, D.-T., ve Kang, H.-J. (2019). A survey on Deep Learning based bearing fault diagnosis. Neurocomputing, 335, 327-335. doi:j.neucom.2018.06.078
• Khorram, A., Khalooei, M., ve Rezghi, M. (2021). End-to-end CNN + LSTM deep learning approach for bearing fault diagnosis. Applied Intelligence, 51, 736–751. doi:s10489-020-01859-1
• Kumar, P., ve Hati, A. S. (2020). Review on Machine Learning Algorithm Based Fault Detection in Induction Motors. Archives of Computational Methods in Engineering, 28, 1929–1940. doi:s11831-020-09446-w
• Längkvist, M., Karlsson, L., ve Loutfi, A. (2014). A review of unsupervised feature learning and deep learning for time-series modeling. Pattern Recognition Letters, 42, 11-24. doi:j.patrec.2014.01.008
• Lecun, Y., Member, Ieee, Bottou, L., Bengıo, Y., ve Haffner, P. (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86, 2278 - 2324. doi:10.1109/5.726791
• Lei, Y., Yang, B., Jiang, X., Jia, F., Li, N., ve Nandi, A. K. (2020). Applications of machine learning to machine fault diagnosis: A review and roadmap. Mechanical Systems and Signal Processing, 138, 1-39. doi:106587
• Magar, R., Ghule, L., Li, J., Zhao, Y., ve Farimani, A. B. (2021). FaultNet: A Deep Convolutional Neural Network for Bearing Fault Classification. IEEE Access, 9, 25189-25199. doi:10.1109/ACCESS.2021.3056944
• Miettinen, J., Nikula, R.-P., Keski-Rahkonen, J., Fagerholm, F., Tiainen, T., Sierla, S., ve Viitala, R. (2022). Whitening CNN-Based Rotor System Fault Diagnosis. Applied Sciences, 12(9), 1-22. doi:10.3390/app12094411
• Minsky, M. L., ve Papert, S. A. (1969). Perceptron: an introduction to computational geometry. ISBN.
• Ran, Y., Zhou, X., Lin, P., Wen, Y., ve Deng, R. (2019). A Survey of Predictive Maintenance: Systems, Purposes and Approaches. arXiv preprint arXiv:1912.07383., XX(XX), 1-36.
• Oğuzay, E. (2013). Veri madenciliği ile geliştirilen bir akıllı buzdolabı ve market sepet analizi sistemi. Doktora Tezi, Trakya Üniversitesi, Fen Bilimleri Enstitüsü , Edirne.
• Yoo, Y. J. (2019). Fault Detection of Induction Motor Using Fast Fourier Transform with Feature Selection via Principal Component Analysis. International Journal of Precision Engineering and Manufacturing, 20, 1543–1552. doi:10.1007/s12541-019-00176-z
• Yoo Y, Jo H ve Ban S-W. (2023). Lite Efficient Deep Learning Model for Bearing Fault Diagnosis Using the CWRU Dataset. Sensors. 2023; 23(6):3157. https://doi.org/10.3390/s23063157
• Zhang, N., Wu, L., Yang, J., ve Guan, Y. (2018). Naive Bayes Bearing Fault Diagnosis Based on Enhanced Independence of Data. sensors, 18(2), 1-17. doi:10.3390/s18020463
• Zhang, W., Peng, G., Li, C., Chen, Y., ve Zhang, Z. (2017). A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals. sensors, 17(2), 1-21. doi:10.3390/s17020425
• Zhang, X., Kong, J., Zhao, Y., Qian, W., ve Xu, X. (2022). A deep-learning model with improved capsule networks and LSTM filters for bearing fault diagnosis. Signal, Image and Video Processing, 17, 1325–1333. doi:10.1007/s11760-022-02340-x