Parametre Tahmini ve Bilgi Entropisi Kullanan Yeni Bir Dijital İkiz Tabanlı Arıza Teşhis Yaklaşımı

Abstract

Asenkron motorlar endüstride kullanılan önemli motor tiplerinden biridir. Bu motorlar genellikle sağlam bir yapıya sahip olmalarına rağmen, ortam çalışma koşullarından dolayı arızalara tabidirler. Geleneksel teşhis yöntemleri, iyi ve hatalı motorlar için deneysel bir kurulumdan akım, titreşim, sıcaklık ve hız gibi sinyallerin ölçülmesine dayanır. Ancak endüstride kullanılan motorla karşılaştırılabilecek muadil bir motor bulmak her zaman zordur. Dolayısıyla gerçek motorun dijital ikizi oluşturularak, sektördeki motora eşdeğer sağlıklı motora ait sinyaller alınabilmektedir. Bu çalışmada, gerçek bir deney düzeneğinden elde edilen dijital ikiz ve motor sinyalleri kullanılarak motor stator arızaları teşhis edilmeye çalışılmıştır. Motor akımı ile ilgili parametreler tahmin edilerek spektrumda hatalı frekans bölgesi belirlenir ve bilgi entropisine göre hatalar belirlenir. Önerilen sistemin çalışması hem dijital ikizden hem de gerçek motordan alınan verilerle test edilmiş ve başarılı sonuçlar alınmıştır.

Keywords

• Asenkron motor
• bilgi entropisi
• teşhis
• stator arızaları
• özellik çıkarımı
• dijital ikiz

A New Digital Twin-Based Fault Diagnosis Approach Using Parameter Estimation and Information Entropy

Abstract

Induction motors are one of the important motor types used in industry. Although these motors are generally of robust construction, they are subject to failures due to ambient operating conditions. The traditional diagnostic methods are based on measuring signals such as current, vibration, temperature, and speed from an experimental setup for good and faulty motors. But finding an equivalent motor that can compare with the motor used in the industry is always difficult. Therefore, by constructing a digital twin of the real motor, signals belonging to the healthy motor can be obtained, which is equivalent to the motor in the industry. In this study, motor stator faults were tried to be diagnosed using digital twin and motor signals obtained from a real experimental setup. The faulty frequency region is determined in the spectrum by estimating the parameters related to the motor current, and the faults are determined according to the information entropy. The operation of the proposed system has been tested with data from both the digital twin and the real motor, and successful results have been obtained.

Keywords

• Induction motor
• information entropy
• diagnostics
• stator faults
• feature extraction
• digital twin

References

1. Benbouzid, Mohamed (2021) Signal processing for fault detection and diagnosis in electric machines and systems. Institution of Engineering and Technology, London.
2. Habbouche, H., Amirat, Y., Benkedjouh, T., and Benbouzid, M (2021) Bearing fault event-triggered diagnosis using a variational mode decomposition-based machine learning approach. IEEE Transactions on Energy Conversion, 37(1), 466-474.
3. Almounajjed, A., Sahoo, A. K., Kumar, M. K., and Assaf, T (2022) Fault diagnosis and investigation techniques for induction motor. International Journal of Ambient Energy, 43(1), 6341-6361.
4. Aydin, I., Kaner, S (2020) A New Hybrid Diagnosis of Bearing Faults Based on Time-Frequency Images and Sparse Representation. Traitement du Signal, 37(6).
5. Zhao, R., Yan, R., Chen, Z., Mao, K., Wang, P., and Gao, R. X (2019) Deep learning and its applications to machine health monitoring. Mechanical Systems and Signal Processing, 115, 213-237.
6. Zhang, S., Zhang, S., Wang, B., and Habetler, T. G (2020) Deep learning algorithms for bearing fault diagnostics—A comprehensive review. IEEE Access, 8, 29857-29881.
7. Almounajjed, A., Sahoo, A. K., Kumar, M. K., and Subudhi, S. K (2023) Stator Fault Diagnosis of Induction Motor Based on Discrete Wavelet Analysis and Neural Network Technique. Chinese Journal of Electrical Engineering, 9(1), 142-157.
8. Husari, F., Seshadrinath, J (2021) Early stator fault detection and condition identification in induction motor using novel deep network. IEEE Transactions on Artificial Intelligence, 3(5), 809-818.

9. Okwuosa, C. N., Hur, J. W (2023) An intelligent hybrid feature selection approach for SCIM inter-turn fault classification at minor load conditions using supervised learning. IEEE Access.
10. [Aishwarya, M., Brisilla, R. M (2023) Design and Fault Diagnosis of Induction Motor Using ML-Based Algorithms for EV Application. IEEE Access, 11, 34186-34197.
11. Lucas, G. B., De Castro, B. A., Ardila-Rey, J. A., Glowacz, A., Leão, J. V. F., and Andreoli, A. L (2023) A Novel Approach Applied to Transient Short-Circuit Diagnosis in TIMs by Piezoelectric Sensors, PCA, and Wavelet Transform. IEEE Sensors Journal, 23(8), 8899-8908.
12. Das, A. K., Das, S., Pradhan, A. K., Chatterjee, B., and Dalai, S (2023) RPCNNet: A Deep Learning Approach to Sense Minor Stator Winding Inter-Turn Fault Severity in Induction Motor under Variable Load Condition. IEEE Sensors Journal, 23(4), 3965-3972.
13. Wang, J., Ye, L., Gao, R. X., Li, C., and Zhang, L (2019) Digital Twin for rotating machinery fault diagnosis in smart manufacturing. International Journal of Production Research, 57(12), 3920-3934.
14. Şahin, İ. L. K. E. R., Bayazıt, G. H., and Keysan, O. (2020) A simulink model for the induction machine with an inter-turn short circuit fault. IEEE International Conference on Electrical Machines (ICEM) pp. Gothenburg, Sweden 1273-1279.