Analysis of Three-Phase Faults of Power Transformer using Artificial Neural Network | Original Article

ABSTRACT:

ABSTRACT

In this digital era, digital representation of electrical parameters makes the system operation more reliable and sensitive. A digital technique has been used here for analysing the faults. During fault detection, power transformers are prone to various harmonics and inrush current so we have to find a way that can differentiate the unwanted outages of power transformers. Differential protection is one of the most effective and sensitive method of transformer protection. It is based on the fact that during internal fault condition the current entering the electrical equipment is different from that leaving it. Differential relay is most suitable for protection of transformer and is capable of detecting very small magnitude of differential current. Inrush and fault currents are non-stationary and non-periodic signals containing both high frequency oscillations and localized impulses superimposed on the power frequency and its harmonics and transformer transient current signals during faults and inrush conditions deals with short duration. Therefore, discrete wavelet transform that can analyse these harmonic conditions effectively, is most suitable. To analyse the different fault conditions, the digital data obtained after Discrete Wavelet Transform, is fed to Artificial Neural Network. In the present paper we have to study the different operating conditions of the power transformer. Present study is focused on suitably analysing the Inrush condition and Internal faults.