Determining the Location and Type of Faults in Electrical Cables Using an Artificial Neural Network

Abstract

Detecting and locating faults in electrical cables has always been a challenge for power distribution systems. Over time, several methods have been developed to effectively manage these erroneous situations. This article develops a new approach to detecting, localizing, classifying, and predicting faults, especially in different types of short circuits in electrical cables, based on the artificial neural network method. The novelty of this approach lies in the ability of the method to predict the location and type of malfunction. The proposed method uses the Matlab and Simulink platform and includes four sequential stages.  A virtual machine is used to reduce the time and resources of the modeling process. The study shows the effectiveness of the method and its ability to successfully predict faults in real power supply systems.