Data mining of power transformer database using self-organising maps

Abstract

Data mining is part of a large area of recent research in artificial intelligence and information processing and management otherwise known as knowledge discovery in databases (KDD). The main aim here is to identify new information or knowledge from a database in which the dimensionality or amount of data is so large that it is beyond human comprehension. The self-organising map (SOM) is used to analyse a power transformer database from one of the electric energy providers in Japan. Furthermore, the regression aspect of SOM is also tested. Regression is achieved by searching for the Best Matching Unit (BMU) using the known vector components. Some attempts have also been made in using SOM to predict transformer oil temperature changes. Conventionally, oil temperature changes in a power distribution transformer, are predicted using explicit numerical calculations. This paper applies the self-organising maps to the prediction of oil temperature changes.