Artificial Neural Network Based Fault Detection and Classification in Power System

A continuous supply of electricity depends on the stability and dependability of power transmission infrastructure. If not identified and categorized right away, transmission line faults brought on by equipment malfunctions, environmental conditions, or short circuits can result in serious power outages. Traditional fault detection methods frequently depend on numerical and threshold-based approaches, which may not be accurate or quick enough in complicated fault situations. An Artificial Neural Network (ANN)-based method for fault detection and classification in high-voltage transmission lines is presented in this research in order to overcome these constraints. To simulate different kinds of symmetrical and unsymmetrical failures under diverse circumstances, a model based on MATLAB/Simulink is created. To classify faults, a Backpropagation Neural Network (BPNN) is trained using extracted and pre-processed voltage and current inputs. To effectively identify various defect kinds, a broad dataset is used to train the ANN model. To further improve accuracy and efficiency, future studies will investigate real-time hardware implementation and sophisticated deep learning techniques.