Fuzzy based methodologies comparison for high‐impedance fault diagnosis in radial distribution feeders

Abstract

This study presents a comparison of two developed intelligent systems that carries out, in an integrated manner, failure diagnosis on electric power distribution feeders. These procedures aim to identify and classify critical situations, as highimpedance faults, which can potentially damage the system components and cause power supply interruptions to consumers. The intelligent systems combine the wavelet transform, Dempster-Shafer evidence theory, voting scheme, fuzzy inference system and artificial neural networks. Results show the efficiency, reliability, and robustness of the proposed methodology, allowing its real-time application.

A novel discrete wavelet transform‐based graphical language classifier for identification of high‐impedance fault in distribution power system

“…Nevertheless, all these works, presents the identification and location of conventional fault without considering the HIF. On the other hand, the authors in and present the identification and location of HIF in power system but fail to test the robustness of the classifier for all other conventional faults and switching transients. In this case, the accuracy of identification of HIF in the system lies in the range of 70% to 100% by methods like DWT, Morphological fault detector and combination of WT with other various classifiers namely Fuzzy‐ARTMAP, Boosted decision tree, Finite element method and Extreme learning machine.…”

HIF detection in distribution networks based on Kullback–Leibler divergence

“…An undetected HIF may persist on the distribution feeder for a long time, resulting in power loss. Also, the resultant arc may cause fire hazard and electric shock, posing a serious threat to human life and network equipment [9–11].…”

A Ergonomia Aplicada Ao Projeto De Equipamentos Nucleares: Uma Proposta De Redesign De Um Telemedidor

“…Immersing in this universe, Artificial Intelligence (AI) can be listed as a precursor for the development of tools that modernize the electrical system and has gained more and more space in the energy market, being used as one of the methodology with the highest number of positive results, due to the National Interconnected System (NIS) that is fully controlled through AI. Among the AI's, they emphasize Artificial Neural Networks (ANN's) (MAGALHÃES et al, 2016;TONELLI-NETO, 2017), the fuzzy logic (RIZOL et al, 2011;DECANINI et al, 2012), the genetic algorithms (WEN and CHANG, 1997), tabu search (CHANG and WEN, 1998) Petri nets (LO et al, 1997), and more recently the Artificial Immune System (AIS) (DASGUPTA, 1998;DE CASTRO, 2001), which has great prominence in the literature because of its excellent results in the detection and classification of disturbances in EPS. These methodologies are the basis of the self-recovery capacity, which among other ISSN 1809-3957 resources, guarantee the continuity of service to users with quality and for the longest possible time.…”