Bundling of Power Quality Indices as Method for Correlating Load Susceptibility and Disturbances Superposition

Abstract

This paper presents a neuro-fuzzy approach to

power quality assessment. Electrical equipment susceptibility to

disturbances varies from type to type. Additionally, not only

one physical phenomenon (e.g. harmonics) can cause

equipment malfunctioning or damage, but more likely a

superposition of some different disturbances. The authors

propose an automated neuro-fuzzy approach to power quality

indicia bundling which is correlated to equipment susceptibility.

Whereby distortion power is seen as one of the power quality

indices.

The neuro-fuzzy analyzer matches logically different indices

and gives as output one value describing the possible thread to

electrical equipment. A reduction of data amount to be analysed

by a system engineer is aimed.