Detecção de Faltas de Alta Impedância Utilizando os Vetores de Energia dos Centroides das Sub-bandas Espectrais

Abstract

In many situations, conductor rupture in distribution systems or even their contact with structures external to the systems (such as trees) does not sensitize protection systems. This type of occurrence and its variations are typically called high impedance faults, considered to be of high severity by the concessionaires. The present work aims to present a method for detecting high impedance faults based on the Energy Vectors of the Centroids of the Spectral Sub-bands. Regarding the validation of the method, a database was created through simulations performed in the Alternative Transients Program, based on a real distribution system. In addition to high impedance faults, load energization and capacitor bank switching situations were also simulated to test the robustness of the method against probable false positives. A database containing real oscillography of high impedance faults was also used. An Artificial Neural Network was trained in order to classify the disturbances using the proposed method. From the satisfactory results obtained, the viability of the developed method can be seen.