Classification of Power Quality Disturbances using Mahalanobis Distance Classifier and Stockwell Transformation

Abstract

Detection and classification of PQ (Power Quality)
disturbances in distribution/transmission systems are very
important for protection of electricity network. Most of the
disturbances of power network are non-stationary and
momentary in nature, hence it requires advanced tools and
techniques for the analysis and classification of PQ disturbances.
This paper presents the detection and classification of PQ events
or disturbances employing Stockwell-Transformation, known as
S-Transformation, and Mahalanobis Distance (MD) based
approach. The proposed method exploits only four features
extracted through S-transformation of the voltage signal; then,
using these four features, classification is conducted by MD based
classifier. In this work, classification of several PQ disturbances,
such as, voltage sags, swells, harmonics, notch, flicker, transient
oscillation, momentary interruption, etc., are considered. The
simulation results demonstrate that the proposed method is very
effective and accurate in detecting and classifying PQ events.
Validation of the proposed approach has also been conducted
using real signal recorded in IEEE 1159.2 database. Moreover,
comparative classification performance of MD based classifier
with MED (minimum Euclidean distance) and LVQ (learning
vector quantization) reveals the superiority of the proposed
approach.