Classification of Power Quality Disturbances with S-Transform and Artificial Neural Networks Method

Karasu S., Sarac Z.

25th Signal Processing and Communications Applications Conference (SIU), Antalya, Turkey, 15 - 18 May 2017 identifier identifier


In this study, classification of 11 different Power Quality (PQ) disturbances with Artificial Neural Networks (ANN) has been done by using the attributes obtained with S-Transform. It was aimed to achieve accurate and high classification performance in noisy environment by using the least number of attributes representing PQ disturbances. The most suitable ones from the attributes were selected by Sequential Forward Selection (SFS) method. The performance of models with different hidden layer neuron numbers tested at different noise levels (40 dB, 30 dB and 20 dB) by using the selected attributes. In this study, it was found that for the most appropriate number of attributes and optimal model parameters, performance in noisy environment (20 dB) and overall performance were 99.0%.