An automatic fault diagnosis solution for electrical power systems

This work proposes a software tool for fault diagnosis in power systems. The solution was developed to monitoring real-time SCADA data of the transmission and generation network of a Brazilian electric utility in order to assist operators of control centres to analyse the occurrence and to decide the best procedures to re-establish the service in order to enhance the service reliability and reduce the power restoration time. The fault diagnosis system is formulated as an optimization problem and solved through two stages: event classification at equipment level. The developed approach also identifies the malfunctioned protective devices as well the missing and false alarms. Possible fault scenarios were considered in part of a real Brazilian power system to validate the methodology.