Entropy Analyses of Inner Race and Outer Race Bearing Faults of Induction Motor Based on Wavelet Transform

Öz

Bearing faults are the dominant fault of three phase induction motors. Vibration signals are commonly analysed signals for the detection of bearing faults. The Discrete Wavelet Transform (DWT) is one of the popular signal processing methods that is used to detect induction motor faults. DWT is a method that decomposes vibration signals into frequency components and analyses each component at a specified scale. DWT provides a practical approach in fault detection applications based on the feature extraction. Multiple statistical parameters are typically extracted in DWT analyses which can lead to computational complexity. Inner race and outer race bearing faults of induction motors cause slight variations in the standard deviations of the vibration signals if they are compared with the healthy operating condition of induction motor. Through entropy calculations, these small variations can be transformed into meaningful outputs for condition monitoring operations of induction motors. Information theory is a statistical based computational method that calculates the uncertainties/irregularities within a dataset. Shannon, Renyi and Tsallis entropies are prominent approaches of information theory found in the literature. In this paper, the statistical parameter required for entropy calculations is the standard deviation of the 6th level detail coefficients obtained from DWT that applied to the vibration signals. In this study, open-source vibration signals dataset from the Mendeley data port were used for bearing faults detection. A slope angle which depends on the change of the bearing fault conditions is calculated by applying entropy. The results show that slope angles of 75° and above are obtained for inner race and outer race bearing faults of varying severity in the induction motor by applying Renyi entropy. These high slope values suggest that Renyi entropy, in conjunction with single-feature DWT analysis, is a viable method for detecting bearing faults in induction motors.

Anahtar Kelimeler

• Bearing Faults
• Three Phase Induction Motors
• Vibration Signals
• DWT
• Renyi Entropy

Asenkron Motor İç Bilezik ve Dış Bilezik Rulman Arızalarının Dalgacık Dönüşümü Tabanlı Entropi Analizleri

Öz

Rulman arızaları, üç fazlı asenkron motorlarda karşılaşılan baskın arıza tipidir. Titreşim sinyalleri rulman arızalarının tespiti için yaygın olarak analiz edilen sinyallerdir. Ayrık Dalgacık Dönüşümü (DWT-Discrete Wavelet Transform) asenkron motor arızalarının tespitinde kullanılan popüler sinyal işleme yöntemlerinden bir tanesidir. DWT, titreşim sinyallerini frekans bileşenlerine ayırarak her bir bileşeni belirlenen ölçekte analiz eden bir yöntemdir. DWT, özellik çıkarma tabanlı arıza tespit uygulamalarında pratik bir yaklaşım sağlamaktadır. DWT analizlerinde genellikle birden çok istatistiki parametrenin çıkarımı yapılmakta, bu durum da hesaplama karmaşıklığına yol açabilmektedir. Asenkron motor iç bilezik ve dış bilezik rulman arızaları, titreşim sinyalleri standart sapmalarında motorun sağlam çalışma durumuna göre küçük değişimler meydana getirmektedir. Entropi hesaplamaları ile bu küçük değişimler anlamlı çıktılara dönüştürülerek asenkron motor durum izleme çalışmaları yapılabilmektedir. Bilgi teorisi bir veri kümesindeki belirsizlikleri/düzensizlikleri hesaplayan istatistiksel hesaplama tabanlı bir yöntemdir. Shannon, Renyi ve Tsallis entropileri literatürde öne çıkan bilgi teorisi yaklaşımlarıdır. Bu çalışmada entropi hesaplamalarının ihtiyaç duyduğu istatistiki parametre, titreşim sinyallerine uygulanan DWT sonucu elde edilen 6. seviye detay katsayıları sinyali standart sapmasıdır. Bu çalışmada Mendeley veri portundaki açık-kaynak titreşim verileri kullanılarak rulman arızaları tespiti yapılmıştır. Entropi ile rulman arıza durumları arasındaki geçişe bağlı olarak bir eğim açısı hesaplanmaktadır. Elde edilen sonuçlar göstermektedir ki Renyi entropi ile asenkron motorun farklı şiddetlerdeki iç bilezik ve dış bilezik rulman arızalarında 75° ve üzerinde eğim açıları elde edilmektedir. Bu yüksek değer, tek bir özellik çıkarma ve Renyi entropisine dayalı DWT analizinin asenkron motor rulman arızası tespitinde kullanılabileceğini göstermektedir.

Anahtar Kelimeler

• Rulman Arızaları
• Üç Fazlı Asenkron Motorlar
• Titreşim Sinyalleri
• DWT
• Renyi Entropi

Kaynakça

1. Choudhary, A., Goyal, D., Shimi, S. L., & Akula, A. (2019). Condition monitoring and fault diagnosis of induction motors: A review. Archives of Computational Methods in Engineering, 26, 1221-1238.
2. Zhang, W., Yang, D., & Wang, H. (2019). Data-driven methods for predictive maintenance of industrial equipment: A survey. IEEE Systems Journal, 13(3), 2213-2227.
3. Gangsar, P., & Tiwari, R. (2020). Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-the-art review. Mechanical Systems and Signal Processing, 144, 106908.
4. Yatsugi, K., Pandarakone, S. E., Mizuno, Y., & Nakamura, H. (2023). Common diagnosis approach to three-class induction motor faults using stator current feature and Support Vector Machine. IEEE Access, 11, 24945-24952.
5. Peeters, C., Guillaume, P., & Helsen, J. (2018). Vibration-based bearing fault detection for operations and maintenance cost reduction in wind energy. Renewable Energy, 116(B), 74-87.
6. Kaya, K., & Ünsal, A. (2022). Yapay sinir ağlarıyla asenkron motor çoklu arızalarının tespiti ve sınıflandırılması. Politeknik Dergisi, 25(4), 1687-1699.
7. Romero-Troncoso, R. D. J. (2017). Multirate signal processing to improve FFT-Based analysis for detecting faults in induction motors. IEEE Transactions on Industrial Informatics, 13(3), 1291-1300.
8. Himani, & Dahiya, R. (2018). Condition monitoring of wind turbine for rotor fault detection under non stationary conditions. Ain Shams Engineering Journal, 9(4), 2441-2452.

9. Lee, C.-Y., Le, T.-A., & Lin, Y. T. (2022). A feature selection approach Hybrid Grey Wolf and Heap-Based optimizer applied in bearing faults. IEEE Access, 10, 56691-56705.
10. Fan, W., Zhou, Q., Li, J., & Zhu, Z. (2018). A Wavelet-Based statistical approach for monitoring and diagnosis of compound faults with application to rolling bearings. IEEE Transactions on Automation Science and Engineering, 15(4), 1563-1572.
11. Bessous, N., Sbaa, S., & Megherbi, A.C. (2019). Mechanical fault detection in rotating electrical machines using MCSA-FFT and MCSA-DWT techniques. Bulletin of the Polish Academy of Sciences. Technical Sciences, 67(3), 571-582.
12. Polat, A., & Yılmaz, A. (2018). Investigation of the effects of eccentricity on induction motor via Multi-Resolution Wavelet Analysis. Electrica, 18(2), 187-197.
13. Tobi, M. A., Bevan, G., Wallace, P., Harrison, D., & Okedu, K.E. (2021). Faults diagnosis of a centrifugal pump using multilayer perceptron genetic algorithm back propagation and support vector machine with discrete wavelet transform-based feature extraction. Computational Intelligence, 37(1), 21-46.
14. Chikkam, S., & Singh, S. (2023). Condition monitoring and fault diagnosis of induction motor using DWT and ANN. Arab J Sci Eng 48, 6237–6252.
15. Ali, M. Z., Shabbir, M, N. S. K., Liang, X., Zhang, Y., & Hu, T. (2019). Machine learning-based fault diagnosis for single- and multi-faults in induction motors using measured stator currents and vibration signals. IEEE Transactions on Industry Applications, 55(3), 2378-2391.
16. Dhamande, L. S., & Chaudhari, M. B. (2018). Compound gear-bearing fault feature extraction using statistical features based on time-frequency method. Measurement, 125, 63-77.
17. Inturi, V., Pratyush, A. S., & Sabareesh, G. R. (2021). Detection of local gear tooth defects on a multistage gearbox operating under fluctuating speeds Using DWT and EMD analysis. Arab J Sci Eng, 46, 11999-12008.
18. Shi, E. (2022). Single feature extraction method of bearing fault signals based on slope entropy. Shock and Vibration, 2022, 6808641.
19. Ghosh, A., & Basu, A. (2021). A scale-invariant generalization of the Rényi Entropy, Associated divergences and their optimizations under Tsallis’ nonextensive framework. IEEE Transactions on Information Theory, 67( 4), 2141-2161.
20. Tsallis, C. (2022). Entropy. Encyclopedia, 2(1), 264-300.
21. Göktaş, F. (2023). Robust versions of the lower and upper possibilistic mean-variance models for the one period or two periods cases. Bilecik Şeyh Edebali Üniversitesi Fen Bilimleri Dergisi, 10(2), 373-382.
22. Guo, Z., Liu, M., Wang, Y., & Qin, H. (2020). A new fault diagnosis classifier for rolling bearing united multi-scale permutation entropy optimize VMD and Cuckoo Search SVM. IEEE Access, 8, 153610-153629.
23. Yang, Z., Kong, C., Wang, Y., Rong, X., & Wei, L. (2021). Fault diagnosis of mine asynchronous motor based on MEEMD energy entropy and ANN. Computers & Electrical Engineering, 92, 107070.
24. Ünsal, A. (2020). Asenkron motorlarda paralel hizalama hatalarının entropi analizi ile incelenmesi. Politeknik Dergisi, 23(4), 1037-1050.
25. Han, T., Gong, J. -C., Yang, Q., & An, L. -Z. (2022). Fault Diagnosis of Rolling Bearings Using Dual-Tree Complex Wavelet Packet Transform and Time-Shifted Multiscale Range Entropy. IEEE Access, 10, 59308-59326.
26. Sharma, S., Tiwari, S. K., & Singh, S. (2021). Integrated approach based on flexible analytical wavelet transform and permutation entropy for fault detection in rotary machines. Measurement, 169, 108389.
27. Malhotra, A., Minhas, A. S., Singh, S., Zuo, M. J., Kumar, R., & Kankar, P. K. (2021). Bearing fault diagnosis based on flexible analytical wavelet transform and fuzzy entropy approach. Materials Today: Proceedings, 43, 629-635.
28. Kumar, D., Mehran, S., Shaikh, M. Z., Hussain, M., Chowdhry, B. S., & Hussain, T. (2022). “Triaxial bearing vibration dataset of induction motor under varying load conditions”, Mendeley Data, V2.
29. Zuhaib, M., Shaikh, F. A., Tanweer, W., Alnajim, A. M., Alyahya, S., Khan, S., Usman, M., Islam, M., & Hasan, M. K. (2022). “Faults feature extraction using Discrete Wavelet Transform and Artificial Neural Network for induction motor availability monitoring-Internet of Things enabled environment”, Energies, 15(21), 7888.
30. Khusbaba, R. N., Kodagoda, S., Lal, S., & Dissanayake, G. (2011). “Driver drowsiness classification using fuzzy wavelet-packet-based feature-extraction algorithm”, IEEE Transactions on Biomedical Engineering, 58(1), 121-131.
31. Erişti, B. (2023). “Dalgacık paket dönüşümü, reliefF özellik seçimi ve topluluk öğrenme algoritması tabanlı bir kısmi deşarj arızası tespit yöntemi”, Fırat Üniversitesi Müh. Bil. Dergisi, 35(2), 505-516.
32. Ali, M. Z., & Liang, X. (2020). “Threshold-based induction motors single- and multifaults diagnosis using Discrete Wavelet Transform and measured stator current signal,” Canadian Journal of Electrical and Computer Engineering, 43(3), 136-145.
33. Bouzida, A., Touhami, O., Ibtiouen, R., Belouchrani, A., Fadel, M., & Rezzoug, A. “Fault diagnosis in industrial induction machines through Discrete Wavelet Transform,” IEEE Transactions on Industrial Electronics, 58(9), 4385-4395.
34. Vashishtha, G., Kumar, R. (2022). “Pelton wheel bucket fault diagnosis using improved Shannon entropy and expectation maximization principal component analysis,” J. Vib. Eng. Technol. 10, 335–349.
35. Sönmez, D. (2013). Asenkron motor rulman arızasının titreşim işaretleri üzerinden entropi tabanlı analizi. Doktora Tezi, İstanbul Teknik Üniversitesi, Fen Bilimleri Enstitüsü/Kontrol ve Otomasyon Mühendisliği ABD, İstanbul.
36. Huo, Z., Martinez-Harcia, M., Zhang, Y., Yan, R., & Shu, L. (2020). “Entropy Measures in Machine Fault Diagnosis: Insights and Applications”, IEEE Transactions on Instrumentation and Measurement, 69(6), 2607-2620.
37. Renyi, A. (1961). On measures of entropy and information. 4th Berkeley Symposium on Mathematics, Statistics and Probability, 1961, 1, 547-561.
38. Crooks, G. A. (2021). On Measures of Entropy and Information. Tech. Note 009 v0.8, http://threeplusone.com/info, (10.01.2024).
39. Nicolis, O., Mateu, J., & Contreras-Reyes, J. E. (2020). “Wavelet-based entropy measures to characterize two-dimensional fractional brownian fields,” Entropy, 22(2), 196.
40. Tsallis, C. (1988). “Possible generalization of Boltzmann-Gibbs statistics,” J Stat Phys 52, 479–487.
41. Kumar, D., Mehran, S., Shaikh, M. Z., Hussain, M., Chowdhry, B. S., & Hussain, T. (2022). “Triaxial bearing vibration dataset of induction motor under varying load conditions,” Data in Brief, 42, 108315.
42. Kompella, K. C. D., Mannam, V. G. R., & Rayapudi, S. R. (2016). “DWT based bearing fault detection in induction motor using noise cancellation”, Journal of Electrical Systems and Information Technology, 3(3), 411-427.