Fault identification in an AC-DC transmission system using neural networks

Abstract

The possibility of using neural networks to identify faults that may have occurred in an AC-DC power system is explored. Based on the ability of these networks to distinguish reliably between different types of fault, appropriate control measures can be taken to improve the dynamic performance of the AC-DC power system. Three different neural network architectures to distinguish between different types of fault on the AC-DC system are proposed, and a comparison between them is made.<>