Prediction of Flashover Voltage on 11 kV Composite Insulator Using Kernel Support Vector Machine
This paper presents the forecasting of flashover mechanism on polymeric insulator using nonlinear support vector machine regression (NLSVMR). In transmission and distribution systems, insulator plays a vital role in steadiness of the power systems. Flashover of composite insulators makes the whole system into danger. For the past decades, owing to good hydrophobicity properties of composite insulators made a replacement of porcelain insulators in service. To analyze the performance of composite insulator for long-term process, it is necessary to predict their pollution performance behavior before the breakdown occurs. In this proposed work, 11 kV composite insulator with three straight shed with clevis end fitting (Type A) and three alternate sheds with ball end fitting (Type B) are taken into consideration for flashover prediction. For experimental analysis, solid layer method was used in artificial pollution test, in which coastal, desert, and industrial pollution layer is used for further analysis. Using even-rising method, the flashover voltage has been obtained for different equivalent salt deposit density (ESDD) values. Finally, radial basis function (RBF) SVMR shows better flashover prediction when compared to linear and polynomial NLSVMR.
KeywordsSolid layer method Flashover mechanism ESDD NLSVMR RBF
We acknowledge the Department of Electrical and Electronics Engineering, National Engineering College for the support by permitting to do this research work in high-voltage laboratory.
- 4.Jiang, Xingliang, Wang, Shaohua, Zhang, Zhijin, Jianlin, Hu, Qin, Hu: Investigation of flashover voltage and non-uniform pollution correction coefficient of short samples of composite insulator intended for ±800 kV UHVDC. IEEE Trans. Dielectr. Electr. Insul. 17(1), 71–80 (2010)CrossRefGoogle Scholar
- 6.Belkheiri, M., Zegnini, B., Mahi, D.: Modeling the critical flashover voltage of high voltage insulators using artificial intelligence. J. Intell. Comput. Appl. (JICA) 2(2), 137–154 (2009). ISSN0974-410XGoogle Scholar
- 11.Xingliang, Jiang, Jihe, Yuan, LichunShu, Zhijin, Zhang, Jianlin, Hu, Feng, Mao: Comparison of DC pollution flashover performances of various types of porcelain, glass, and composite insulators. IEEE Trans. Power Delivery 23(2) (2008)Google Scholar
- 15.Zegnini, B., Mahdjoubi, A. H., Belkheiri, M.: A least squares support vector machines (LS-SVM) approach for predicting critical flashover voltage of polluted insulators. In: 2011 Annual Report Conference on Electrical Insulation and Dielectric Phenomena. https://doi.org/10.1109/ceidp.2011.6232680