Sheath induced voltage prediction of high voltage cable based on artificial neural network. (October 2020)

• Record Type: Journal Article
• Authors: Ledari, Shiva Abdollahzadeh; Mirzaie, Mohammad
• Is Part Of: Computers & electrical engineering. Volume 87(2020)
• Publication Date: 2020-10
• Subjects: Cable sheath -- Induced voltages -- Lightning -- Emtp/rv -- Prediction -- Artificial neural network (ann); Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2020.106788
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: The cable sheath induced voltage in combined overhead-cable lines using EMTP/RV software is calculated and the results are analyzed. The effect of different parameters such as type of ground connection of cable sheath, cable length, lightning strike location, tower footing resistance and … on cable sheath induced voltage under lightning surge is investigated. Artificial neural network (ANN) model is designed for maximum induced voltage prediction of cable sheath under lightning surge and different condition. The optimal response has been obtained at epoch 115 that the mean squared error is about 0.00019. The absolute values of relative errors between induced voltages of simulation and prediction are less than 8%. This indicates a high efficiency of ANN technique in the cable sheath induced voltage prediction. Abstract: This paper aims to propose an Artificial Neural Network (ANN) model for voltage prediction in cable sheath of combined overhead-cable line under lightning condition. To this end, the effect of different parameters, including tower footing resistance, sheath ground resistance, a kind of ground connection of sheath on the maximum induced voltage of cable sheath in 132 kV combined line are investigated using EMTP/RV software. It is assumed, in this study, that lightning strike to the Guard wire and back-flashover occurred and/or lightning strike to the overhead line. With these results in mind, the proposed model is designed with ten inputs data and four outputs data. The validation of the model indicates that the absolute values of relative errors between induced voltages of simulation and prediction are less than 8%. This indicates high efficiency of ANN technique in the maximum induced voltage prediction of cable sheath under lightning surge.