Correction of current transformer distorted secondary currents due to saturation using artificial neural networks

Current transformer saturation can cause protective relay misoperation or e ven prevent tripping, This paper presents the use of artificial neural netw orks (ANN) to correct current transformer (CT) secondary waveform distortio ns. The ANN is trained to achieve the inverse transfer function of iron-cor e toroidal CTs which are widely used in protective systems. The ANN provide s a good estimate of the true (primary) current of a saturated transformer. The neural network is developed using MATLAB (R) and trained using data fr om EMTP simulations and data generated from actual CTs, In order to handle large dynamic ranges of fault currents, a technique of employing two sets o f network coefficients is used. Different sets of network coefficients deal with different fault current ranges, The algorithm for running the network was implemented on an Analog De,ices ADSP-2101 digital signal processor. T he calculating speed and accuracy proved to be satisfactory in real-time ap plication.