Detecção de Faltas de Alta Impedância Baseada em Boosting de Árvores de Decisão

The occurrence of high impedance faults is an event that difficult to detect in distribution lines and may cause various hazards the population. With conductor falling ground, fault current does not sensibilize protection systems can several accidents. Frequently, this type confused with other line events, further delaying detection. present work aims insert simulated data events common network, them using a boosting decision trees, XGBoost classifier. obtained results demonstrate accuracy 97.67% classification model.