Simplified artificial neural network structure with the current transformer saturation detector provides a good estimate of primary currents

This paper presents use of artificial neural networks (ANN) to correct current transformer (CT) secondary currents distortions caused by the CT saturation. The ANN is trained to achieve the inverse transfer function of iron-core toroidal CTs, which are widely used in protective systems. The ANN has been designed as a simplified structure to minimize use of memory when implemented in protective devices. To properly estimate primary currents for a saturated transformer, a current transformer saturation detector has been added to the ANN. The ANN is developed using the MATLAB/sup TM/ program and trained using data generated from actual CTs. The ANN calculating speed and accuracy are satisfactory in real-time applications, and provides good estimates of primary currents.