Adaptive Arc Detection Based Image Segmentation in Pantograph Catenary Systems

Öz

In recent years, through the development of electric trains, the rail system has become a popular mode of transport. This type of transport is reliable and cost-effective compared to other modes of transport. Furthermore, the rail transport is more preferred with the emergence of the electric train.  In order to provide the electrical energy used by electric trains, pantograph catenary system was developed. Pantograph system, receives power from the catenary wire and transmits to train. The catenary system, located along the railway line, it transmits electricity from the substation to the pantograph system. During contact with pantograph and catenary system many failures may occur. Early diagnosis of failures are preventing larger defect.  In this study, a new image processing based method for arc detection in pantograph catenary system, which is a part of the rail system, is proposed.  Real-time images of the catenary pantograph is taken by cameras placed on the roof of two different locomotives. The image segmentation is used to identify the differences that occur in images taken. Also, the Sobel edge extraction algorithm is used for detecting contact of a pantograph. The arcing at the contacts of the pantograph is determined by combining properties obtained. The proposed method has been carried out both in the FPGA environment MATLAB and the results were compared.

Anahtar Kelimeler

• Pantograph Catenary Systems,Image Processing,FPGA,Condition Monitoring,Fault Diagnosis

Pantograf Katener Sistemlerde Görüntü Segmantasyon Tabanlı Adaptif Ark Tespiti

Öz

Son yıllarda elektrikli trenlerin gelişmesiyle birlikte raylı sistemler popüler bir ulaşım türü haline gelmiştir. Bu ulaşım türü diğer ulaşım türlerine göre düşük maliyetli ve güvenilirdir. Ayrıca elektrikli trenlerin ortaya çıkmasıyla birlikte demiryolu ulaşımı daha çok tercih edilmiştir. Elektrikli trenlerin kullandığı elektrik enerjisinin temin edilmesi için pantograf katener sistemleri geliştirilmiştir. Pantograf sistemi, trenin üzerinde bulunan katener telinden aldığı elektriği trene ileten sistemdir. Katener sistemi ise, demiryolu hattı boyunca bulunur ve trafo merkezinden alınan elektriği pantograf sistemine iletmektedir. Pantograf ve katener sistemlerinin birbiri ile teması sırasında çeşitli arızalar ortaya çıkmaktadır. Oluşan arızaların erken teşhis edilmesi daha büyük arızaların oluşmasını engellemektedir. Bu çalışmada, raylı sistemlerin bir parçası olan pantograf katener sistemlerde ark tespiti için görüntü işleme tabanlı yeni bir yöntem önerilmektedir. İki farklı lokomotifin çatısına kamera yerleştirilerek pantograf katener sisteminin gerçek zamanlı görüntüsü alınmıştır. Alınan görüntülerde oluşan arkların tespiti için görüntü segmantasyonu kullanılmıştır. Ayrıca pantograf temas bölgesinin tespit edilmesi için Sobel kenar çıkarım algoritması kullanılmıştır. Elde edilen özellikler bileştirilerek pantograf temas bölgesinde oluşan arkların tespiti yapılmaktadır. Önerilen yöntem hem MATLAB hem de FPGA ortamında gerçekleştirilmiştir ve sonuçları karşılaştırılmıştır. 

Anahtar Kelimeler

• Pantograf Katener Sistemler,Görüntü İşleme,FPGA,Durum İzleme,Arıza Teşhisi

Kaynakça

1. Karakose, E., Gencoglu, M.T., Karakose, M., Yaman, O., Aydin, I., and Akin, E., A new arc detection method based on fuzzy logic using S-transform for pantograph–catenary systems. Journal of Intelligent Manufacturing, 1-18, 2015.
2. Karakose E., Gencoglu MT. An investigation of pantograph parameter effects for pantograph-catenary systems. Innovations in Intelligent Systems and Applications (INISTA) Proceedings, 2014 IEEE International Symposium on. IEEE, 2014.
3. Aydin I, Karakose M, Akin E. Anomaly detection using a modified kernel-based tracking in the pantograph–catenary system. Expert Systems with Applications 42.2, 938-948, 2015.
4. Liu Y, Chang GW, Huang HM. Mayr's Equation-Based Model for Pantograph Arc of High-Speed Railway Traction System, IEEE Transactions on Power Delivery, (25), 2025-2027, 2010.
5. Midya S, Bormann D, Schütte T, Thottappillil R. DC Component From Pantograph Arcing in AC Traction System—Influencing Parameters, Impact, and Mitigation Techniques, IEEE Transactions on Electromagnetic Compatibility, (53), 18-27, 2011.
6. Barmada S, Raugi M, Tucci M, Romano F. Arc detection in pantograph-catenary systems by the use of support vector machines-based classification, IET Electrical Systems in Transportation Institution of Engineering and Technology, 2013.
7. Ostlund S, Gustafsson A, Buhrkall L, Skoglund M. Condition monitoring of pantograph contact strip, International Conference on Railway Condition Monitoring, 1-6, 2008.
8. Hamey LGC, Watkins T, Yen SWT. Pancam: In-Service Inspection of Locomotive Pantographs, 9th Biennial Conference of the Australian Pattern Recognition Society on Digital Image Computing Techniques and Applications, 439-499, 2007.

9. Sacchi M, Cagnoni S, Spagnoletti D, Ascari L, Zunino G, Piazzi A. PAVISYS: A computer vision system for the inspection of locomotive pantographs, Pantograph Catenary Interaction Framework for Intelligent Control, 2011.
10. Ocoleanu CF, Popa I, Manolea G, Dolan AI, Vlase S. Temperature Investigation in Contact Pantograph - AC Contact Line, International Journal Of Circuits. Systems and Signal Processing, 154-163, 2009.
11. Facchinetti A, Bruni S. Hardware-in-the-loop hybrid simulation of pantograph–catenary interaction, Journal of Soundand Vibration, 2783-2797, 2012.
12. Midya S, Bormann D, Schütte T, Thottappillil R. Pantograph Arcing in Electrified Railways—Mechanism and Influence of Various Parameters—Part I: With DC Traction Power Supply, IEEE Transactions on Power Delivery, 1931- 1939, 2009.
13. Boguslavskii AA, Sokolov SM. Detecting Objects in Images in Real-Time Computer Vision Systems Using Structured Geometric Models, Pleiades Publishing, 177–187, 2006.
14. Li M, Ze-yong W, Xiao-rong G, Li W, Kai Y. Edge Detection on Pantograph Slide Image, International Congress on Image and Signal Processing, 1 – 3, 2009.
15. Landi A, Menconi L, Sani L, Hough transform and thermo-vision for monitoring pantograph–catenary system, Proceedings of the Institution of Mechanical Engineers, (220), 435– 447, 2006.
16. Xiao-heng Z, Xiao-rong G, Ze-yong W, Li W, Kai Y. Study on the Edge Detection and Extraction Algorithm in the Pantographslipper's Abrasion, International Conference on Computational and Information Sciences, 474–477, 2010.
17. Aydin, İ., Karaköse, E., Karaköse, M., Gençoğlu, M. T. and Akın, E. A new computer vision approach for active pantograph control. IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA), 1-5, 2013.
18. Chen Q, Zhao L, Lu J, Kuang G, Wang N, Jiang Y. Modified two-dimensional otsu image segmentation algorithm and fast realisation, IET Image Processing, (6)4, 426-433, 2012.
19. AlSaeed DH, Bouridane A, Elzaart A, Sammouda R. Two modified Otsu image segmentation methods based on Lognormal and Gamma distribution models, International Conference on Information Technology and e-Services, 1-5, 2012.
20. BahadarKhan, K., Khaliq, A. A., and Shahid, M.. A Morphological Hessian Based Approach for Retinal Blood Vessels Segmentation and Denoising Using Region Based Otsu Thresholding. PloS one, 11(7), 2016.
21. Li Y, Yao Q, Tian B, Xu W. Fast double-parallel image processing based on FPGA, IEEE International Conference on Vehicular Electronics and Safety, 97-102, 2011.
22. Rao, M. G., Kumar, P. R., and Prasad, A. M. Implementation of real time image processing system with FPGA and DSP. International Conference on Microelectronics, Computing and Communications (MicroCom), 1-4, 2016.