İlhan AYDIN, Mehmet KARAKÖSE, Erhan AKIN

Zaman serisi veri madenciliği ve destek vektör makinalar kullanan yeni bir akıllı arıza sınıflandırma yöntemi

Asenkron motorlar endüstriyel uygulamalarda en çok kullanılan makinelerdir. Bu motorlar genellikle güvenilir olmalarına rağmen ortam ve eskimeye bağlı sebeplerden dolayı birçok arızaya maruz kalabilirler. Bu çalışmada, bir asenkron motorda oluşan kırık rotor çubuğu arızaları, destek vektör makinalar ve zaman serisi veri madenciliği ile sınıflandırılmıştır. Arıza sınıflandırma için kullanılacak zaman serisi park vektör yaklaşımının iki bileşeni kullanılarak elde edilmektedir. Her bir arıza durumu için elde edilen yeni zaman serisi bir faz alanına dönüştürülmektedir. Sağlam ve arızalı faz alanlarını ayırt etmek için destek vektör makinalar kullanılmaktadır. Destek vektör makinaların eğitim hızını arttırmak için bulanık küme merkezleri eğitim verisi olarak alınmaktadır. Geliştirilen yöntem ile bir, iki, üç kırık rotor çubuğu arızaları ve sağlam durum, dört farklı çalışma hızında başarılı bir şekilde sınıflandırılmaktadır.

A new intelligent fault classification method using time series data mining and support vector machines

Induction motors are the most used machines in industrial applications. Although these motors are generally reliably, they can be exposed many faults due to environmental and wear reasons. In this study, broken rotor bar faults occurred in an induction motor are classified using support vector machines and time series data mining methods. Time series to be used for fault diagnosis is obtained by using two components of park’s vector approach. The new time series which is obtained for each fault condition is transformed to a phase space. Support vector machines are used to separate healthy and faulty phase spaces. Fuzzy cluster centers are taken as training data to increase training speed of support vector machines. Healthy motor condition and one, two and three broken rotor bar faults are successfully classified at four different operation speeds with developing method.

PDF

___

1. Benbouzid M.E., Kliman G.B., “What Stator Current Processing based technique to use for induction motors rotor faults?”, IEEE Trans. on Energy Conversion, Cilt 18, No 2, 238-244, 2003.
2. Chow M. Y., Methodologies of Using Neural Network and Fuzzy Logic Technologies for Motor Incipient Fault Detection, World Scientific, 1997.
3. Czeslaw, T. K., T. O. Kowalska, “Neural Network Application for Induction Motor Fault Diagnosis”, Mathematics and Computers in Simulation, Cilt 63, 435-448, 2003.
4. Kim K., Parlos A.G., Bharadwaj R. M., “Sensorless Fault Diagnosis of Induction Motors”, IEEE Trans. on Industrial Electronics, Cilt 50, No 5, 1038-1051, 2003.
5. Aderiano M. da Silva, Induction Motor Fault Diagnostic and Monitoring Methods, Master Thesis, Marquette University, Milwaukee, WI, 2006.
6. Filipetti F., Franceschini G., Tassoni C., Vas P., “Recent Developments of Induction Motor Drives Fault Diagnosis Using AI Techniques”, IEEE Trans. on Industrial Electronics, Cilt 47, No 5, 994–1004, 2000.
7. Kolla S., Varatharasa L., “Identifying Three- phase Induction Motor Faults using Artificial Neural Networks”, ISA Transactions, Cilt 39, No 4, 433-439, 2000.
8. Benbouzid M.E.H., Nejjari H., “A Simple Fuzzy Logic Approach for Induction Motors Stator Condition Monitoring”, IEEE Electrical Machines and Drives Conference (IEMDC), Cambridge, MA, June 17-20, 2001.
9. Ayhan B., Chow M.Y., Song M.H., “Multiple Discriminant Analysis and Neural-Network- Based Monolith and Partition Fault-Detection Schemes for Broken Rotor Bar in Induction Motors”, IEEE Trans. on Industrial Electronics, Cilt 53 , No 4, 1298-1308, August 2006.
10. Ondel O., Boutleux E., Clerc G., “A method to Detect Broken Rotor Bars in Induction Machine Using Pattern Recognition Techniques”, IEEE Trans. on Industry Applications, Cilt 2, No 4, 916-923, 2006.
11. Pöyhönen, S., Support Vector Machine Based Classification in Condition Monitoring of Induction Motors, Doktora Tezi, Helsinki University of Technology Control Engineering Laboratory, 2004.
12. Shin H. J., Eom D. H., Kim S. S., “One-class Support Vector Machines—An Application in Machine Fault Detection and Classification”, Computer & Industrial Engineering, Cilt 48, No 2, 396-408, 2005.
13. Bangura J. F., Povinelli R. J., Demerdash, N.A.O., Brown R. H., “Diagnostics of Eccentricities and Bar/End-Ring Connector Breakages in Polyphase Induction Motors Through a Combination of Time-Series Data Mining and Time-Stepping Coupled FE–State Space Techniques”, IEEE Trans. On Industry Applications, Cilt 39, No 4, 1005-1013, 2003.
14. Aydın İ., KARAKÖSE M., AKIN E., “A Simple and Efficient Method for Fault Diagnosis Using Time Series Data Mining”, IEEE Electrical Machines and Drives Conference (IEMDC07), 597-600, 2007.
15. Benbouzza N., Benyettou A., Bendiabdellah A., “An Advanced Park’s Vectors Approach for Rotor Cage Diagnosis”,IEEE First International Symposium On Control, Communications and Signal Processing, 461- 464, 2004.
16. Aydın İ., Arıza Teşhisinde Veri Madenciliği ve Yumuşak Hesaplama Tekniklerinin Kullanımı, Yüksek Lisans Tezi, Fırat Üniversitesi Fen Bilimleri Enstitüsü, 2006.
17. Aydın İ., Karaköse M., Akın E., “Yapay Bağışıklık Sistemi Tabanlı Arıza Teşhis Algoritması”, IEEE 14. Sinyal İşleme Ve İletişim Uygulamalari Kurultayi (SIU’2006), 17-19 Nisan, Antalya, 2006 . 18. Haji M., Toliyat H.A., “Pattern Recognition-A Technique for Induction Machines Rotor Fault Detection-Eccentricity and Broken Bar Fault”, IEEE Industry Applications Conference (IAS), 1572-1578, 2001.
19. Feng X., Huang H., “A Fuzzy Set Based Reconstructed Phase Method for Identification of Temporal Patterns in Complex Time Series”, IEEE Trans. On Knowledge and Data Engineering, Cilt 17, No 5, 601-613, 2005.
20. Bezdek J. C., Pattern Recognition with Fuzzy Objective Function Algorithms, Plenum Press, New York, 1981
21. Cristianini N., Shawe Taylor J., An Introduction to Support Vector Machines and Other Kernel-based Learning Methods, Cambridge University Press, 2001.
22. Kecman V., Learning and Soft Computing: Support Vector Machines, neural Networks and Fuzzy Logic, The MIT Press., 2001.
23. Burges, C., “A Tutorial on Support Vector Machines for Pattern Recognition”, Journal of Data Mining and Knowledge Discovery, Cilt 2, No 2, 121-167, 1998