Application of neural-network modules to electric power system fault section estimation

This paper presents a neural system intended to aid the control center operator in the task of fault section estimation. Its analysis is based on information about the operation of protection devices and circuit breakers. In order to allow the diagnosis task, the protection system philosophy of busbars, transmission lines, and transformers are modeled with the use of two types of neural networks: the general regression neural network and the multilayer perceptron neural network. The tool described in this paper can be applied to real bulk power systems and is able to deal with topological changes without having to retrain the neural networks.

I. Introduction

Progress in the areas of communication and digital technology has increased the amount of information available at supervisory control and data-acquisition (SCADA) systems. Although that information is very useful, during events that cause outages, the operator may be overwhelmed by the excessive number of simultaneously operated alarms, which increases the time necessary for identifying the main outage cause and to start the restoration process. Besides factors, such as stress and inexperience, can affect the operator's performance; thus, the availability of a tool to support the real-time decision-making process is welcome.