Título: Applying Associative Memories To Fault Location Identification
Autores: Alves da Silva, A. P.; Insfran, A. H. F.; Silveira, P. M. da; Lambert-Torres, G.
Resumo: Faults producing load disconnections or emergency situations have to be localized as soon as possible to start the electric network reconfiguration, restoring normal energy supply. This paper proposes the use of artificial neural networks (ANNs) of the associative memory type, to solve the fault localization problem. The main idea is to store measurement sets representing the normal behavior of the protection system into associative memories. Afterwards these memories are employed on-line for fault location estimarion from the protection system. Although the ANNs are trained with single contigencies only, their generalization capability allows a good performance for multiple contingencies.
Código DOI: 10.21528/CBRN1994-045
Artigo em PDF: CBRN1994-paper45.pdf
Arquivo BibTex: CBRN1994-paper45.bib