Development of detection and classification stages for a new distance protection approach based on cumulants and neural networks

This paper presents the use of Higher Order Statistics (HOS) and Artificial Neural Networks (ANNs) for distance relaying purposes. The main objective is to design a distance relay prototype. In the current paper, the results of fault detection and classifications using such tools are presented. Preliminary results of fault location are also presented. It can be noticed the reliability as well as high speed in detecting faults. These results are very promising as the method combines a large number of samples of HOS with different features and the capability of ANNs to discriminate different patterns. Furthermore this new distance protection approach under development is based on voltage signals only which represent an innovation in distance relaying.