Electric power quality disturbance classification using self-adapting artificial neural networks

Abstract

The issue of power quality is now recognised as an essential feature of a successful electric power system. This is mainly due to the rapid increase of loads, which generate noise and, at the same time, are sensitive to the noise present in the supply system. As a result, power quality monitoring has become an important issue in modern power systems.This paper presents a technique for classifying electrical power quality disturbance events. The technique is based on a novel Self-Adapting Artificial Neural Network (SAANN), which has the unique capability of adapting to new disturbance features.In the proposed technique, distinctive feature vectors from disturbance events captured are extracted using Fast Fourier Transform (FFT) and Discrete Wavelet Transform (DWT). The feature vectors are then fed to two SAANN based classifiers, which classify the captured events into different categories of power quality disturbances. The proposed technique is tested using a number of disturbance events and results are presented.

A Self-Organizing Learning Array System for Power Quality Classification Based on Wavelet Transform

“…Ibrahim et al provided an excellent survey of the advanced AI techniques for PQ application [2]. The most interesting AI tools for PQ Manuscript problems include Expert Systems (ES) [3], Fuzzy Logic (FL) [4]- [7], Artificial Neural Networks (ANNs) [5], [8]- [10] and Genetic Algorithms (GA') [11]. Recent advances in wavelet transforms provide another powerful tool for PQ classification.…”

Classification of power quality events – A review

“…Extracted features are quite large in number which is able to increase the computation complexity. Some other significant techniques have been reported such as [125,126].…”

Power Quality: Overview and monitoring

“…Significant research has been conducted into developing appropriate methods for disturbance signal analysis, PQ assessment and PQ monitoring [9][10][11][12][13][14][15][16][17][18]. Basic techniques for analysing disturbance signals employ time domain representation where filters or DSP algorithms are implemented.…”

“…The importance of intelligent systems in a number of power system related applications has been recognised and is well documented [16][17][18]. Application of Artificial Neural Networks (ANNs) for PQ monitoring is showing promising results [11]. A neural network is a computational structure consisting of non-linear computing elements referred to as neurones, inspired by the performance of the biological neurone.…”