Asenkron Motor Eş Zamanlı Çoklu Arızalarının Titreşim Sinyalleri ile Çok Etiketli Sınıflandırılması

Abstract

Endüstride yaygın olarak kullanılan asenkron motorlarda meydana gelen arızaların tespiti büyük öneme sahiptir. Asenkron motorlarda yaygın olarak meydana gelen arızalar elektriksel ve mekanik arızalardan oluşmaktadır. Arızaların tespiti için çeşitli yöntemler kullanılmaktadır. Yaygın kullanılan arıza tespit yöntemleri stator akımı, besleme gerilimi, titreşim, ısı ve ses gibi verileri kullanmaktadır. Bu yöntemlerde genel olarak her bir arıza türü için belirli bir yöntem kullanılmaktadır. Birden çok arızanın eş zamanlı olarak meydana geldiği durumlar için ileri seviye arıza tespit yöntemlerinin kullanılması gerekir. Bu çalışmada, asenkron motorlarda meydana gelen rotor kırığı, dış-bilezik rulman arızası, iç-bilezik rulman arızası, eksenel kaçıklık ve stator sargısı kısa-devre arızaları tekil, eş zamanlı-ikili ve eş zamanlı-üçlü olarak incelenmiştir. İncelemede 3-eksen titreşim verileri kullanılmıştır. Titreşim verilerinin istatistiksel değerlerinden öznitelik vektörleri çıkarılmıştır. Öznitelik vektörü çok etiketli sınıflandırma yönteminde girdi olarak kullanılmıştır. Çok etiketli sınıflandırma için İkili Alâka Düzeyi (Binary Relevance, BR), Etiket Güç Seti (Label Powerset, LP) ve Sınıflandırıcı Zinciri (Classifier Chain, CC) problem dönüşüm yöntemleri kullanılmıştır. Temel sınıflandırıcı olarak ise Naive Bayes (NB), K-En Yakın Komşu (K-Nearest Neighbors, K-NN), Karar Ağacı (Decision Tree, DT) ve Destek Vektör Makinesi (Support Vector Machine, SVM) yöntemleri kullanılmıştır. LP yöntemi ile NB sınıflandırıcısının birlikte kullanımında %99,9 doğrulukta, CC yöntemi ile DT sınıflandırıcısının birlikte kullanımında %99,3 doğrulukta ve BR yöntemi ile DT sınıflandırıcısının birlikte kullanımında %97,8 doğrulukta sınıflandırma başarımına ulaşılmıştır. Problem dönüştürme yöntemi olarak LP, sınıflandırıcı olarak ise DT en yüksek başarım oranını vermektedir.

Keywords

• Çok etiketli sınıflandırma
• Asenkron motor arızaları
• Titreşim analizi
• Çoklu arıza

Multi-Label Classification of Simultaneous Faults of Induction Motors by Vibration Signals

Abstract

It is important to diagnose the fault of induction motors which are widely used in the industry. The common faults of induction motors consist of mechanical and electrical faults. Various methods are used to detect faults. Commonly used fault detection methods use stator current, supply voltage, vibration, heat, and sound data. In general, a specific method is generally used for each type of fault. Advanced diagnostic methods should be when the simultaneous multiple faults are present. It this study, broken rotor bars, inner-race bearing faults, outer-race bearing faults, short-circuit stator winding faults, and eccentricity faults are investigated individually, in simultaneous two and three groups. Three-axis vibration signals are used in the study. The feature vectors are calculated from the statistical features of vibration signals. The feature vector are used as input in the multi-label classification method. For the multi-label classification, Binary Relevance (BR), Label Powerset (LP) and Classifier Chain (CC) problem transformation methods are used. Naïve Bayes (NB), K-Nearest Neighbors (K-NN), Decision Tree (DT) and Support Vector Machine (SVM) methods are used as base classifier. When LP method and NB classifier are used together, 99.9% accuracy was achieved. When CC method and DT classifier are used together 99.3% accuracy was achieved. When BR method and DT classifier are used together 97.8% accuracy was achieved. LP as the problem transformation method and DT as the classifier give the best accuracy rate among the other methods.

Keywords

• Multi Label Classification
• Induction Motor Faults
• Vibration Analysis
• Multi Faults

References

1. [1] Y. B. Koca ve A. Ünsal, “Asenkron motor arızalarının değerlendirilmesi,” Teknik Bilimler Dergisi, c. 7, s. 2, ss. 37-46, 2017.
2. [2] A. Dineva, A. Mosavi, M. Gyimesi, I. Vajda, N. Nabipour, and T. Rabczuk, “Fault Diagnosis of Rotating Electrical Machines Using Multi-Label Classification,” Applied Sciences, vol. 9, no. 23, p. 5086, 2019, doi: 10.3390/app9235086.
3. [3] M. Juez-Gil, J. J. Saucedo-Dorantes, Á. Arnaiz-González, C. López-Nozal, C. García-Osorio, and D. Lowe, “Early and extremely early multi-label fault diagnosis in induction motors,” ISA transactions, vol. 106, pp. 367-381, 2020
4. [4] C. M. Vong, P. K. Wong, and W. F. Ip, “A New Framework of Simultaneous-Fault Diagnosis Using Pairwise Probabilistic Multi-Label Classification for Time-Dependent Patterns,” IEEE Transactions on Industrial Electronics, vol. 60, no. 8, pp. 3372-3385, 2013
5. [5] G. Georgoulas, V. Climente-Alarcon, J. A. Antonino-Daviu, I. P. Tsoumas, C. D. Stylios, A. Arkkio, and G. Nikolakopoulos, “The use of a multilabel classification framework for the detection of broken bars and mixed eccentricity faults based on the start-up transient,” IEEE Transactions on Industrial Informatics, vol. 13, no. 2, pp. 625-634, 2016
6. [6] J. Shen, S. Li, F. Jia, H. Zuo, and J. Ma, “A deep multi-label learning framework for the intelligent fault diagnosis of machines,” IEEE Access, vol. 8, pp 113557-113566, 2020
7. [7] S. Han, S. Zhang, Y. Li, and L. Chen, “The multilabel fault diagnosis model of bearing based on integrated convolutional neural network and gated recurrent unit,” International Journal of Intelligent Computing and Cybernetics, vol. 15, no. 3, pp 401-413, 2021
8. [8] C. Yu, Y. Ning, Y. Qin, W. Su, and X. Zhao, “Multi-label fault diagnosis of rolling bearing based on meta-learning,” Neural Computing and Applications, vol. 33, no. 10, pp. 5393-5407. 2021

9. [9] F. Li, X. Ma, and Y. Wang, “A multi-label method of state partition and fault diagnosis based on binary relevance algorithm,” in 2020 IEEE 9th Data Driven Control and Learning Systems Conference (DDCLS), Liuzhou, China, 2020, pp. 567-572
10. [10] P. Gangsar, and R. Tiwari, “Signal based condition monitoring techniques for fault detection and diagnosis of induction motors: A state-of-the-art review,” Mechanical Systems and Signal Processing, vol. 144, 106908, 2020
11. [11] J. J. Saucedo-Dorantes, M. Delgado-Prieto, J. A. Ortega-Redondo, R. A. Osornio-Rios, and R. D. J. Romero-Troncoso, “Multiple-fault detection methodology based on vibration and current analysis applied to bearings in induction motors and gearboxes on the kinematic chain,” Shock and Vibration, vol. 2016, no. Special Issue, pp. 1–13, 2016
12. [12] A. Alwodai, F. Gu, and A. D. Ball, “A comparison of different techniques for induction motor rotor fault diagnosis,” Journal of Physics: Conference Series, vol. 364, no. 1, p. 012066, 2012
13. [13] M. K. Saini, and A. Aggarwal, “Detection and diagnosis of induction motor bearing faults using multiwavelet transform and naive Bayes classifier,” International Transactions on Electrical Energy Systems, vol. 28, no. 8, e2577, 2018
14. [14] G. Tsoumakas, and I. Katakis, “Multi-label classification: An overview,” International Journal of Data Warehousing and Mining (IJDWM), vol. 3, no. 3, pp. 1-13, 2007
15. [15] H. Modi, and M. Panchal, “Experimental comparison of different problem transformation methods for multi-label classification using MEKA,” International Journal of Computer Applications, vol. 59, no. 15, pp. 10-15, 2012
16. [16] J. M. Nareshpalsingh, and H. N. Modi, “Multi-label classification methods: A comparative study,” International Research Journal of Engineering and Technology (IRJET), vol. 4, no. 12, pp. 263-270, 2017.
17. [17] G. Tsoumakas, I. Katakis, and I. Vlahavas, “Mining multi-label data” in Data mining and knowledge discovery handbook, 2nd ed., Boston, USA : Springer, 2009, pp. 667-685.
18. [18] E. A. Cherman, M. C. Monard, and J. Metz, “Multi-label problem transformation methods: a case study,” CLEI Electronic Journal, vol. 14, no. 1, pp. 1-10, 2011.
19. [19] S. Vogrinčič, and Z. Bosnić, “Ontology-based multi-label classification of economic articles,” Computer Science and Information Systems, vol. 8, no. 1, pp. 101-119, 2011
20. [20] J. Read, “Scalable multi-label classification,” Ph.D. dissertation, Department of Computer Science, University of Waikato, Hamilton, New Zealand, 2010.
21. [21] A. Santos, A. Canuto, and A. F. Neto, “A comparative analysis of classification methods to multi-label tasks in different application domains,” International Journal of Computer Information Systems and Industrial Management Applications, vol. 3, pp. 218-227, 2011.
22. [22] R. Cerri, R. R. da Silva, and A. C. P. L. F. de Carvalho, “Comparing methods for multilabel classification of proteins using machine learning techniques”, Brazilian Symposium on Bioinformatics (BSB), Porto Alegre, Brazil, 2009, pp. 109-120
23. [23] D. Ganda, and R. Buch, “A survey on multi label classification,” Recent Trends in Programming Languages, vol. 5, no. 1, pp. 19-23, 2018.
24. [24] N. Endut, W. A. F. W. Hamzah, I. Ismail, M. K. Yusof, Y. A. Baker, and H. Yusoff, “A Systematic Literature Review on Multi-Label Classification based on Machine Learning Algorithms,” TEM Journal, vol. 11, no. 2, pp. 658-666, 2022
25. [25] I. Rish, “An empirical study of the naive Bayes classifier,” IJCAI 2001 workshop on empirical methods in artificial intelligence, vol. 3, no. 22, pp. 41-46, 2001.
26. [26] P. Domingos, and M. Pazzani, “Beyond independence: Conditions for the optimality of the simple bayesian classifier,” 13th International Conference Machine Learning (ICML), Bari, Italy, 1996, pp. 105-112.
27. [27] WEKA, Bilgisayar Programı, Versiyon 3.8.6, Hamilton – New Zealand: The University of Waikato, 2022.
28. [28] S. Ruggieri, “Efficient C4. 5 [classification algorithm]”, IEEE transactions on knowledge and data engineering, vol. 14 no. 2, pp. 438-444, 2002
29. [29] K. Taunk, S. De, S. Verma, and A. Swetapadma, “A Brief Review of Nearest Neighbor Algorithm for Learning and Classification,” 2019 International Conference on Intelligent Computing and Control Systems (ICCS), Madurai, India, 2019, pp. 1255-1260
30. [30] P. Cunningham, and S. J. Delany, “k-Nearest Neighbour Classifiers - A Tutorial,” ACM Computing Surveys (CSUR), vol. 54, no. 6, pp. 1-25, 2021
31. [31] V. Jakkula, “Tutorial on support vector machine (SVM),” School of EECS - Washington State University, vol. 37, no. 2.5, pp. 1-13, 2006.
32. [32] L. Nguyen, “Tutorial on support vector machine,” Applied and Computational Mathematics, vol. 6, no. 4-1, pp. 1-15, 2017
33. [33] E. K. Yapp, X. Li, W. F. Lu, and P. S. Tan, “Comparison of base classifiers for multi-label learning,” Neurocomputing, vol. 394, pp. 51-60, 2020
34. [34] R. E. Schapire, and Y. Singer, “BoosTexter: A boosting-based system for text categorization,” Machine Learning, vol. 39, pp. 135-168, 2000
35. [35] S. Godbole, and S. Sarawagi, “Discriminative methods for multi-labeled classification,” in Pacific-Asia conference on knowledge discovery and data mining, Berlin, Heidelberg, 2004, pp. 22-30
36. [36] N. Ghamrawi, and A. McCallum, “Collective multi-label classification,” in Proceedings of the 14th ACM international conference on Information and knowledge management, Shanghal, China, 2005, pp. 195-200
37. [37] Y. Yang, “An evaluation of statistical approaches to text categorization,” Information retrieval, vol. 1, no. 1-2, pp. 69-90, 1999
38. [38] A. Ünsal, “Asenkron Motorlar Arızalarının Tespiti ve Entropi Analizi ile Arıza Şiddetinin Belirlenmesi,” Türkiye Bilimsel ve Teknolojik Araştırma Kurumu (TÜBİTAK), Türkiye, Rap. 116E302, 2019.
39. [39] J. Read, P. Reutemann, B. Pfahringer, and G. Holmes, “Meka: A Multi-label/Multi-target Extension to WEKA,” Journal of Machine Learning Research, vol. 17, pp. 1-5, 2016.