Analysis of Leakage Current to Predict Insulator Flashover Using Artificial Neural Network | Science Publications

Journal of Computer Science

N. Narmadhai¹  A. E. Jeyakumar¹ 

关键词: Flashover voltage;    insulator model;    leakage current;    artificial neural network;    Equivalent Salt Deposit Density (ESDD);    Non-Soluble Deposit Density (NSDD);    Backpr Opagation (BP);    Root-Meansquare (RMS);    various contamination;   

DOI  :  10.3844/jcssp.2011.167.172

学科分类：计算机科学（综合）

来源: Science Publications

【 摘 要 】

Problem statement: The phenomenon of flashover in polluted insulators has beencontinued by the study of the characteristics of contaminating layers deposited on the surface ofinsulators in high voltage laboratories. In the literature, Experimental investigations have been carriedout on a real insulator or a flat plate model of insulators under high voltage application. This studyproposed the Equivalent insulator flat plate model for studying the flashover phenomena due topollution under wet conditions even at low voltage. Laboratory based tests were carried out on themodel under AC voltage at different pollution levels. Different concentrations of salt solution has beenprepared using sodium chloride, Kaolin and distilled water representing the various contaminations.Leakage current during the experimental studies were measured for various polluted conditions.Approach: A new model of Vc = f (V, I_initial, I_em, I_emax and I_σ) based on artificial neural network has beendeveloped to predict flashover from the analysis of leakage current. The input variable to the artificialneural network are mean (I_mean), Maximum(Imax) and standard deviation(I_σ) of leakage current extractedalong with the initial value of leakage current I_initial and the input voltage(V).The target obtained was usedto evaluate the performance of the neural network model. Results: The optimum process has been carriedout based on the training accuracy measured by RMSE, the network converged to a threshold of0.0001.The trained model prediction is in good agreement with the actual results and the R² value of thedeveloped model is 0.99996. Conclusion: The developed ANN model is well-suited for the analysis ofleakage current to predict flashover on the insulator surface with high accuracy.

【 授权许可】

Unknown