PCIM INDIA - BEST YOUNG RESEARCHER

Application of Artificial Neural Network for High Impedance Fault Detection in Power System

This paper presents a neural network-based method for the detection of high impedance faults (HIF), utilizing a Levenberg-Marquardt-trained artificial neural network as well as a realistic two-diode HIF model in MATLAB Simulink.

In combination with three-phase RMS voltages and currents as the only input parameters, a fault detection accuracy of 99.8% is reached. Insights in the modelling approach as well as training and simulation results are presented. The approach enables further innovation due to reliably detecting faults that remain invisible to conventional relays and fuses, in applications such as power system protection, transmission and distribution networks, and fire prevention. This paper showcases its capabilities on a simulated 220 kV transmission line with a high impedance fault at 10 km, detecting single-phase, two-phase, and three-phase faults at different resistance levels.

The provider of this whitepaper

pcim-news-platform-logo-firmenprofil (Mesago)

PCIM News Platform - MESAGO Messe Frankfurt GmbH

Rotebühlstr. 83-85
70178 Stuttgart
Deutschland

Phone : +49 711 61946-0

Contact form
PCIM India_Best Young Researcher_Application of Artificial Neural Network for High Impedance Fault Detection in Power System_Ms. Vaishnavi Petkar

Download free whitepaper