Yüksek Gerilim Kablolarında k-NN ile Arıza Konumu Belirleme ve Veri Boyutunun Sınıflandırmaya Etkileri

Year 2021, , 93 - 98, 15.12.2021

Tuba Nur Serttaş , Fatih Serttaş , Fatih Onur Hocaoğlu

https://doi.org/10.53448/akuumubd.993745

Abstract

Yüksek gerilim elektrik tesislerindeki kablolarda meydana gelen arızaların büyük bir kısmı, kısmi boşalma kaynaklı yalıtım sorunlarından oluşmaktadır. Bu tür arızalar, genellikle kablolar üzerindeki montaj kusurlarından, nadir olarak da üretim hatalarından kaynaklanmaktadır. Bu çalışmada, yüksek ve orta gerilim sistemlerinde kullanılan çapraz bağlı polietilen yer altı kabloları (XLPE) üzerindeki kusurların konumlarının belirlenmesi amacıyla, bir dizi deneysel çalışmalar gerçekleştirilmiştir. Laboratuvar ortamında, farklı mesafelerde kusurları bulunan aynı türde XLPE kablo numunelerine aynı orta gerilim seviyesinde gerilim belirli periyotlarda uygulanmış ve elde edilen kısmi boşalma sinyalleri zaman serisi olarak dijital ortama kaydedilmiştir. Kaydedilen veriler k En Yakın Komşuluklar (k-NN) yöntemiyle sınıflandırılmış ve sınıflandırma doğrulukları, veri azaltma yöntemi ile analiz edilmiştir. Veri azaltmadaki amaç, pek çok farklı ölçüm frekansında modelin doğru sınıflandırmalar yapabildiğini gözlemlemek ve daha düşük frekans bandında çalışan cihazlarla yapılacak ölçümlerin doğruluğunu test etmektir. Sonuçlar k-NN yönteminin, kısmi boşalma sinyallerinin incelenmesinde yüksek oranda başarılı sonuçlar verdiğini göstermekte ve verilerin büyük oranda azaltılmasının, istatistiksel öznitelikler kullanıldığında, sınıflandırma doğruluğunu etkilemediğini göstermektedir.

Keywords

Kısmi boşalma, yüksek gerilim, K-NN, arıza tanılama

Fault Location Detection with k-NN in High Voltage Cables and Effects of Data Size on Classification

Abstract

In high voltage electrical installations, most of the faults in cables are caused by insulation problems caused by the partial discharge. Such failures are usually caused by assembly defects on the cables and rarely by manufacturing defects. In this study, a series of experimental studies were carried out to determine the locations of defects on cross-linked polyethylene underground cables (XLPE) used in high and medium voltage systems. The same medium voltage level was applied to the same type of XLPE -cable samples with defects at different distances at specific periods in the laboratory environment. The partial discharge signals obtained were recorded in the digital environment as time series. Recorded data were classified by the k Nearest Neighborhood (k-NN) method, and classification accuracies were analyzed by the data reduction method. The purpose of data reduction is to observe that the model can make accurate classifications at many different measurement frequencies and test the accuracy of the measurements with devices operating in the lower frequency band. The results show that the k-NN method gives highly successful results in analyzing partial discharge signals and shows that the considerable reduction of data does not affect the classification accuracy when statistical features are utilized.

Keywords

Partial discharge, high voltage, K-NN, failure diagnostic.

References

• Adhikari, N., and Kalla, U. K. (2020). Analysis of Partial Discharge Measurements in High Voltage XLPE Cable. In 2020 IEEE 9th Power India International Conference (PIICON) (pp. 1-5). IEEE.
• Cavallini, A., Montanar, G.C. and Puletti, F., 2007. A novel method to locate PD in polymeric cable systems based on amplitude-frequency (AF) map. IEEE Transactions on Dielectrics and Electrical Insulation, 14, 3, 726–734.
• Dukanac, D. (2018). Application of UHF method for partial discharge source location in power transformers. IEEE Transactions on Dielectrics and Electrical Insulation, 25(6), 2266-2278.
• Jahangir, H., Akbari, A., Werle, P., and Szczechowski, J. (2017). UHF PD measurements on power transformers-advantages and limitations. IEEE Transactions on Dielectrics and Electrical Insulation, 24(6), 3933-3940.
• Joseph, J., Mohan, S. and Krishnan, S.T., 2019. Numerical modelling, simulation and experimental validation of partial discharge in cross-linked polyethylene cables. IET Science, Measurement and Technology, 13, 2, 309–317.
• Khan, Q., Refaat, S.S., Abu-Rub, H., Toliyat, H.A., Olesz, M. and Darwish, A., 2021. Characterization of Defects Inside the Cable Dielectric With Partial Discharge Modeling. IEEE Transactions on Instrumentation and Measurement, 70, 1–11. Lan, S., Hu, Y.Q. and Kuo, C.C., 2019. Partial discharge location of power cables based on an improved phase difference method. IEEE Transactions on Dielectrics and Electrical Insulation, 26, 5, 1612 – 1619.
• Liu, F., Zhang, Y., Yao, X., Peng, Q., Nie, H., Li, J. and Zhou, Q., 2013. Recognition of PD mode based on KNN algorithm for converter transformer. Dianli Zidonghua Shebei/Electric Power Automation Equipment, 33, 5, 89–93.
• Mardiana, R. and Su, C.Q., 2010. Partial discharge location in power cables using a phase difference method. IEEE Transactions on Dielectrics and Electrical Insulation, 17, 6, 1738–1746.
• Mashikian, M.S., Bansal, R. and Northrop, R.B., 1990. Location and characterization of partial discharge sites in shielded power cables. IEEE Transaction Power Delivery, 5, 2, 833–839.
• Muhr, M. and Woschitz, R., 2000. Partial discharge diagnostic. Proceedings of the 6th International Conference on Properties and Applications of Dielectric Materials, 1, 223-226.
• Muslim, J., Susilo, A., Nishigouchi, K., Kozako, M., Hikita, M., Arief, Y. Z., and Khayam, U. (2013, September). Enhanced bowtie UHF antenna for detecting partial discharge in gas insulated substation. In 2013 48th International Universities' Power Engineering Conference (UPEC) (pp. 1-5). IEEE.
• Pattanadech, N. and Nimsanong, P., 2014. Effect of noise signals on partial discharge classification models. TENCON 2014 - 2014 IEEE Region 10 Conference, 1–5.
• Sheng, B., Zhou, C., Hepburn, D.M., Dong, X., Peers, G., Zhou, W. and Tang, Z., 2015. A novel on-line cable pd localisation method based on cable transfer function and detected pd pulse rise-time. IEEE Transactions on Dielectrics and Electrical Insulation, 22, 4, 2087–2096.
• Yii, C. C., Rohani, M. N. K. H., Isa, M., Hassan, S. I. S., Ismail, B., and Hussin, N. (2015, December). Multi-end partial discharge location algorithm based on trimmed mean data filtering technique for MV underground cable. In 2015 IEEE Student Conference on Research and Development (SCOReD) (pp. 345-350). IEEE