A new transformer differential protection based on Principal Component Analysis

In this paper, a new algorithm for the differential protection of a power transformer based on the Principal Component Analysis is presented. The algorithm involves the pattern recognition from differential current data. Its purpose is to discriminate between energization and over-excitation conditions and transformer short-circuits. The performance of the algorithm was analysed simulating several scenarios of a test three-phase power system using the PSCAD/EMTDC program for different operation conditions. The obtained results show that the proposed algorithm can be implemented as a base for a transformer differential protection.