Journal of Lightning Research

2013, 5 : 1-10
Published online 2013 March 08. DOI: 10.2174/1652803401204010101
Publisher ID: JLR-5-1

An ANN-Based Approach for Lightning-Caused VFT Detection in GIS

Ebrahim A. Badran , Mohammad H. Abdelrahem and Mansour H. Abdel-Rahman
Electrical Engineering Department, Mansoura University, Mansoura, Egypt.

ABSTRACT

This paper introduces an artificial neural network (ANN) approach for the detection and identification of lightning-caused very fast transient (VFT) in gas insulated substation (GIS). VFT in GIS can be due to faults, lightning and switching operations. VFT in GIS has to be located and classified as soon as possible to start the processes of reconfiguration and restoration of the normal power supply. A practical case study is investigated in Talkha 220-kV GIS which represents a critical generation point in the Egyptian Electric Power Network. The layout of the Talkha 220-kV GIS is discussed and modeled using ATP/EMTP. The ANN-based approach is built and trained. Finally, the proposed approach is tested using bolt ground faults, high impedance faults, and lightning on the connected transmission lines. The results ensure the success of the proposed approach to classify and discriminate the faults and the lightning-caused VFT.

Keywords:

GIS, Lightning, VFT.