Research Article

Power Transformer Differential Protection Based on Neural Network Principal Component Analysis, Harmonic Restraint and Park's Plots

Table 1

(a) Performance of NNPCA and FFBPNN having topology of 12-11-1

Neural network topologyTraining errorMax. epochInrushFault
PAPA

NNPCA0.00011000−1.00.00.961.0
FFBPNN0.00011000−1.00.00.961.0

P: predicted, A: actual.
(b) Accuracy in classification (%)

Trained transformer ratingsTested transformer ratings
315 MVA200 MVA160 MVA
FFBPNNNNPCAFFBPNNNNPCAFFBPNNNNPCA

315 MVA99.3210094.5910098.64100
200 MVA94.5910099.3210098.64100
160 MVA94.5910096.32100100100