Characterization of high impedance faults using the Stockwell transform and artificial neural networks

• Grant number: 21/08949-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: November 01, 2021
• End date: October 31, 2022
• Field of knowledge: Engineering - Electrical Engineering - Power Systems
• Principal Investigator: José Carlos de Melo Vieira Júnior
• Grantee: Marco Antônio Sartorato Nozela
• Host Institution: Escola de Engenharia de São Carlos (EESC). Universidade de São Paulo (USP). São Carlos , SP, Brazil

Abstract

High Impedance Faults (HIFs) are a type of disturbance in distribution systems (DSs) that occur when an energized conductor comes in contact with a poorly conductive surface. HIFs can cause damage to property and equipment, in addition to the electrocution of living beings and ignition of fires. The small amplitude of HIFs currents makes it difficult to detect them by conventional protection methods, such as fuses and overcurrent relays. Furthermore, its random and non-linear nature poses a challenge to reliably distinguishing it from other events, such as capacitor bank switching and transformer energizing. Therefore, the HIFs attract the interest of companies and researchers around the world, however, there is still no fully efficient solution for detecting this disturbance. In this context, this work intends to contribute to this area by characterizing the HIFs through the behavior of the associated signals in the frequency domain, prioritizing the high-frequency band. For this, the calculation of the Stockwell Transform will be used to obtain and analyze the harmonic spectrum of voltage and current signals recorded in simulated DSs, during the occurrence of HIFs. After studying the high-frequency characteristics of the event, it is intended to develop an Artificial Neural Network to recognize new patterns and meaningful characteristics of the HIFs. Thus, this project aims to contribute to the development of new HIF computational representation models and methods of protection against HIFs in DSs. (AU)