Yapay Sinir Ağlarıyla Asenkron Motor Çoklu Arızalarının Tespiti ve Sınıflandırılması

Yıl 2022, Cilt: 25 Sayı: 4, 1687 - 1699, 16.12.2022

Kadir Kaya , Abdurrahman Ünsal

https://doi.org/10.2339/politeknik.933826

Cited By: 5

Öz

Asenkron motor arızalarının tespiti asenkron motorların bakımı için kritik bir konudur. Stator akımı analizi motor arızalarını tespit etmek için yaygın olarak kullanılan bir yöntemdir. Asenkron motor arızalarının tespitine yönelik çok sayıda çalışma bulunmaktadır. Ancak çoklu arıza tespiti ve sınıflandırılmasına yönelik sınırlı sayıda çalışma yapılmıştır. Bu çalışmada, 3 kW bilezikli bir asenkron motorun stator kısa-devre arızaları, kırık rotor çubuğu ile iç bilezik ve dış bilezik rulman arızalarının tespiti ve sınıflandırılması çok katmanlı geri yayılım algoritmasına sahip yapay sinir ağı (YSA) modelleri ile gerçekleştirilmektedir. Çalışma üç aşamada gerçekleştirildi. Birinci aşamada asenkron motor tekil arızalarla birlikte test edildi. Asenkron motor stator sargısı %1, %2, %3, %4 ve %5 oranında kısa-devre edilerek, rotorda üç çubuk kırılarak ve motorun yük tarafı rulmanının iç bileziğinde ve dış bileziğinde arızalar oluşturularak ayrı ayrı test edildi. İkinci aşamada motor, %3 ve %5 stator sargısı kısa-devre arızalarıyla birlikte üç çubuğu kırık rotor ile test edildi. Üçüncü aşamada ise asenkron motor %3 ve %5 stator sargısı kısa-devre arızası, üç çubuğu kırık rotor, iç bileziği ve dış bileziği arızalı rulman ile birlikte test edildi. Bütün testlerde motor tam yük altında çalıştırılmıştır. Sunulan yöntem ile çoklu arızaların tespiti ve sınıflandırılması gerçekleştirilmiştir. Yapılan çalışmada, çoklu arıza tespitinde en yüksek başarım oranı %87 olarak elde edildi. Elde edilen sonuçlarla sunulan yöntemin uygulanabilirliği gösterilmiştir.

Anahtar Kelimeler

Asenkron motorlar, arıza tipleri, çoklu arıza, arıza tespiti, geri yayılım yapay sinir ağları

Destekleyen Kurum

TÜBİTAK Başkanlığı

Proje Numarası

TÜBİTAK 116E302 no'lu projesi

Teşekkür

Bu çalışmada kullanılan deneysel veriler TÜBİTAK 116E302 nolu projesi kapsamında elde edilmiştir. TÜBİTAK Başkanlığına teşekkür ederiz.

Detection and Classification of Multiple Faults of Induction Motors by Using Artificial Neural Networks

Öz

Detection of induction motor faults is a critical issue for the maintenance of induction motors. Analysis of the stator current is a widely used method to detect the faults of induction motors. There are many of studies on the detection of faults of induction motors but few studies on the detection of multiple faults are reported. In this study, the detection and classification of short-circuit faults of stator winding, broken rotor bars and inner/outer race bearing faults of a 3 kW squarel-cage induction motor are implemented by ANN. The study was carried out in three stages. In the first stage, the induction motor was tested with single faults including 1%, 2%, 3%, 4% and 5% short-circuited stator windings, three broken rotor bars, and inner/outer race bearing faults. In the second stage, induction motor was tested with 3% and 5% short-circuit stator windings and with three broken rotor bars. In the third stage, induction motor was tested with 3% and 5% short-circuit stator windings, rotor with three broken bars and inner/outer race bearing faults. The induction motor has been tested under full load. The detection and classification of multiple faults were realized by the proposed method. The highest performance rate in the detection of multiple faults was achieved with 87% accuracy rate. The resuts shows the applicability of the proposed method.

Anahtar Kelimeler

Induction motors, fault types, multiple faults, fault detection, backpropagation artificial neural network

Proje Numarası

TÜBİTAK 116E302 no'lu projesi

Kaynakça

• [1] Yeh C., Sayed-Ahmed A., Povinelli R., “A Reconfigurable motor for experimental emulation of stator winding inter-turn and broken bar faults in polyphase induction machines”, IEEE Trans. Energy Convers, 23(4), 1005-1014, (2008).
• [2] Bonnet A.H., “Cause and analysis of stator and rotor failures in threephase squirrel-cage induction motors”, IEEE Transactıon on Industry Applıcatıons, 28(4), 921–437, (1992).
• [3] Eftekhari M., Moallem M., Sadri S., Shojaei A., “Review of induction motor testing and monitoring methods for inter turn stator winding faults”, Iranian Conference on Electrical Engineering,13–18, (2013).
• [4] Nandi S., Toliyat H.A., Li X.,” Condition monitoring and fault diagnosis of electrical motors—A Review”, IEEE Trans. Energy Convers., 20(4), 719-729, (2005).
• [5] Siddique A., Yadava G.S., and Singh B., “A Review of Stator Fault Monitoring Techniques of Induction Motors”. IEEE Transactions on Energy Conversion, 20(1), 106-114, (2005).
• [6] IEEE, IEEE Guide for Testing Turn Insulation of Form-Wound Stator Coils for Alternating-Current Electric Machines, (2004).
• [7] Bonnett A, Yung C.,” Increased efficiency versus increased reliability”, IEEE Ind. Appl. Mag., 14(1), 29-36, (2008).
• [8] Immovilli F., et al., “Diagnosis of bearing faults in induction machines by vibration or current signals: A critical comparison”, IEEE Trans. Ind. Appl., 46(4), 1350-1359, (2010).
• [9] Ukil A., Chen S., Andenna A., “Detection of stator short circuit faults in three-phase induction motors using motor current zero crossing instants”, Electric Power Systems Research, 81(4),1036-1044, (2011).
• [10] Leite V., Borges da Silva J.G., “Detection of localized bearing faults in induction machines by spectral kurtosis and envelope analysis of stator current”, IEEE Trans. Ind. Electron., 62(3), 1855-1865, (2015).
• [11] Frosini L, Bassi E., “Stator current and motor efficiency as indicators for different types of bearing faults in induction motors”, IEEE Trans. Ind. Electron., 57(1), 244-251, (2010).
• [12] Siddiqui K.M., Sahay K., Giri V.K., “Health-monitoring-and-fault-diagnosis-ininduction-motor-a-review”, International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 3(1),6549-6564, (2014).
• [13] Henao H., et al., “Trends in fault diagnosis for electrical machines: A review of diagnostic techniques”, IEEE ind. Electron. Mag.,8(2), 31-42, (2014).
• [14] Kang, M., Kim j., Kim J.M., “High-performance and energy-efficient fault diagnosis using effective envelope analysis and denoising on a general-purpose graphics processing unit”, IEEE Transactions on Power Electronics, 30(5), 2763-2776, (2015).
• [15] Puche Panadero R., et al., “Improved resolution of the MCSA method via hilbert transform, enabling the diagnosis of rotor asymmetries at very low slip” , IEEE Trans. Energy Convers, 24(1), 52-59, (2009).
• [16] Konar P., Chattopadhyay P., “Multi-class fault diagnosis of induction motor using hilbert and wavelet transform”. Applied Soft Computing, 30, 341-352, (2015).
• [17] Frosini L., Harlisca C., and Szabo L., “Induction Machine Bearing Fault Detection by Means of Statistical Processing of the Stray Flux Measurement”. IEEE Transactions on Industrial Electronics, 62(3),1846-1854, (2015).
• [18] Frosini L., et al. "Multiple faults detection in low voltage inverter-fed induction motors." 2019 IEEE 12th International Symposium on Diagnostics for Electrical Machines”, Power Electronics and Drives (SDEMPED), IEEE, 323-329, (2019).
• [19] Kaikaa, Mohamed Y., Marouane H., Adjami, and Abdelmalek K., “Effects of the simultaneous presence of static eccentricity and broken rotor bars on the stator current of induction machine”, IEEE Transactions on Industrial Electronics, 61(5), 2452-2463, (2013).
• [20] Ojaghi M., Sabouri M., Faiz, J., “Performance analysis of squirrel-cage induction motors under broken rotor bar and stator inter-turn fault conditions using analytical modeling”, IEEE Transactions on Magnetics, 54(11), 1-5,( 2018). [21] Soualhi A., Clerc G, Razik H., and Ondel O., “Detection of Induction Motor Faults by an Improved Artificial Ant Clustering”, In IECON 2011-37th Annual Conference of the IEEE Industrial Electronics Society ,3346-3451, (2011).
• [22] Kolla S.R., Altman S.D., “Artificial neural network based fault identification scheme implementation for a three-phase induction motor”, ISA Transactions, 46(2), 261 – 266, (2007).
• [23] Bazan G.H., Scalassara P.R., Endo W., Goedtel A., Godoy W.F., Palácios R.H.C., “Stator fault analysis of three-phase induction motors using information measures and artificial neural Networks”, Electric Power System Research, 143, 347–356, (2017).
• [24] Burriel Valencia J., Puche-Panadero R., Martinez-Roman J., Sapena-Bano A., Pineda-Sanchez M. , Perez-Cruz J., Riera-Guasp M., “Automatic fault diagnostic system for induction motors under transient regime optimized with expert systems”, Electronics, 8(6), 1-16, (2018).
• [25] Godoy W.F., Da Silva I.N., Goedtel A, Palácios R.H.C., Lopes T.D., “Application of intelligent tools to detect and classify broken rotor bars in three-phase induction motors fed by an inverter, IET Electr”. Power Appl., 10(5), 430–439, (2016).
• [26] Merabet H., Bahi T., Drici D., Halam N., “ Bedoud K., Diagnosis of rotor fault using neuro-fuzzy inference system, Journal of Fundamental and Applied Sciences”, 9(1), 170–182, (2017).
• [27] Lashkari N., Poshtan J., Azgomi H.F., “Simulative and experimental investigation on stator winding turn and unbalanced supply voltage fault diagnosis in induction motors using Artificial Neural Networks”, ISA Transactions, 59, 334-342, (2015).
• [28] Martins J.F., Ferno V., Pires A.J., “Unsupervised neural-network-based algorithm for an on-line diagnosis of three-phase induction motor stator fault”, IEEE Transactıons on industry applications, 54(1), 259-264, (2007).
• [29] Gupta K., Kaur A., “A Review on fault diagnosis of induction motor using artificial neural Networks”, International Journal of Science and Research, 3(7),680-684, (2014).
• [30] Arabaci H., Bilgin O., “Automatic detection and classification of rotor cage faults in squirrel cage induction motor”, Neural Computing And Applications, 19(5), 713-723, (2010).
• [31] Ali M.Z., Shabbir N.S.K., Liang X., Zhang Y., Hu T., “Machine learning-based fault diagnosis for single- and multi-faults in induction motors using measured stator currents and vibration signals”, Industry Applications IEEE Transactions , 55(3), 2378-2391, (2019).
• [32] Moraes R., Valiatı J.F., Neto W.P.G. , “Document-level sentiment classification: An empirical comparison between DVM and Ann”, Expert Systems with Application, 40(2), 621-633, (2013).
• [33] Ren J., Ann vs. “svm: Which one performs better in Classification of mccs in mammogram imaginig”, Knowledge-Based Systems, 26, 144-153, (2012).
• [34] Yabanova İ., Kaya K., “Kaynak değeri olan yaban hayvanlarının görüntü işleme tekniği ile tespiti ve sayımı”, Pamukkale Üniversitesi Mühendislik Bilimleri Dergisi, 25(2), 174-187,(2019).
• [35] Kazuyuki H., and Kenji N., “Selection of Activate Function for Multilayer Neural Networks”, Reports of the Tokyo Metropolitan Technical College, (2000).
• [36] Pedamonti, Dabal. "Comparison of non-linear activation functions for deep neural networks on MNIST classification task." arXiv preprint arXiv:1804.02763,(2018).
• [37] S. Haykin, Neural Networks and Learning Machines, Pearson. Upper Saddle River, NJ, USA, 3,(2009).
• [38] Arı, Ayşe, and Murat Erşen Berberler. "Yapay sinir ağları ile tahmin ve sınıflandırma problemlerinin çözümü için arayüz tasarımı." Acta Infologica 1.2, 55-73, (2017).
• [39] Rojas R “7. The backpropagation algorithm”, Neural networks: a systematic introduction, Springer Science & Business Media, Berlin, (2013).
• [40] Mohri, Mehryar, Afshin Rostamizadeh, and Ameet Talwalkar. "Foundations of Machine Learning. Adaptive computation and machine learning." MIT Press, 31:32, (2012).