Fault detection, classification and localization in HV power transmission lines using ANN

Abstract

Power transmission line is key equipment in secure and reliable power flow in each power system. To arise reliability and security of overhead power lines, different types of failures should be simulated to minimize their impact and to detect and resolve them as quickly as possible. The objective of this paper is to provide an accurate method for detection, classification and localization of faults occurring in power transmission lines using Artificial Neural Network (ANN). Power transmission system was modelled in DIgSILENT PowerFactory, simulating both normal and fault scenarios. Three types of faults were considered for simulation: single-phase-to-ground fault, two-phase short circuit, and three-phase short circuit. Each fault was simulated across the 110 kV power lines with a resolution of 5 %. In addition to the fault scenarios, normal scenario was carried out using a load flow analysis, where the system’s load was varied. Voltage and current data from these simulations were utilized to train and test the ANN model. Principal Component Analysis (PCA) was applied for dimensionality reduction, improving the efficiency and performance of the ANN model. The proposed model achieved an accuracy of 100 % in detecting fault types, a fault classification accuracy of 94 % for identifying the fault line, and a mean absolute error (MAE) of 1.15 in pinpointing the exact fault position. These results demonstrate the model's effectiveness in accurately identifying and localizing faults in power transmission lines, significantly contributing to the reliability and stability of power grid operations.