Power quality disturbances classification using complex wavelet phasor space reconstruction and fully connected feed forward neural network

Power quality disturbances (PQD) degrades the of power. Detection these PQDs in real time using smart systems connected to power grid is a challenge due integration energy generation units and electronic devices. Deep learning methods have shown advantages for PQD classification accurately. events are non-stationary occur at discrete events. Pre-processing signal dual tree complex wavelet transform localizing according time-frequency-phase information improves accuracy.Phase space reconstruction sub bands 2D data use fully feed forward neural network accuracy. In this work, combination DTCWT-PSR FC-FFNN used classify different PSDs accurately.The proposed algorithm evaluated its performance considering configurations most optimum structure developed. The accuracy demonstrated be 99.71% suitable activity with reduced complexity.