Data Mining for Distribution System Fault Classification
This document has been relocated to http://scholarsmine.mst.edu/ele_comeng_facwork/1520
There were 15 downloads as of 28 Jun 2016.
Abstract
Digital relaying equipment at substations allow for large amounts of data storage that can be triggered by predetermined system conditions. Some of this information retrieved from relays at several locations in a local utility's service territory has been mined for determining trends and relationships. Data mining aims to make sense of the retrieved data by revealing meaningful relationships. This paper discusses some useful data mining techniques that are applied to data recorded by overcurrent relays at several substations. The purpose is to classify faults, verify relay settings and determine fault induced trip per substations. High accuracy is obtained.
