Support Vector Machines no suporte à detecção de faltas de alta impedância. Caso base: LT 500 kV Xingu / Tucuruí

The equipments of an electrical system is subject to several types failures, especially those present in the transmission that are built unsheltered way, thus being exposed bad weather, which invariably results wear and, therefore, equipment failure. Of these, lines (LT) most susceptible failure, due their large extensions. From this feature particular, construction LT dense tropical forest regions has led occurrence high impedance faults (FAI), difficult identify by current protection systems. In sense, identifying phenomenon quickly before it evolves more severe short circuits essential, protecting equipment, reducing operation and maintenance costs, environment from possible fires energy consequences outages. Therefore, getting 500 kV Xingu / Tucuruí as example, work aims analyze propose a strategy for FAI based on use supervised learning classifiers Support Vector Machines type.