Classification of Stockwell Transform Based Power Quality Disturbance with Support Vector Machine and Artificial Neural Networks

Abstract

The detection and classification of power quality events that disturb the voltage and/or current waveforms in the electrical power distribution networks is very important to generate electrical energy and to deliver this energy to the end-user equipment at an acceptable voltage. Various property extraction methods are used to determine the type of disturbances in the electrical signal. In this study, seven power distortions including voltage sag, voltage swell, voltage harmonics, voltage sag with harmonics, voltage swell with harmonics, flicker, transient signals and pure sine as a reference signal is used. Synthetic data are produced in MATLAB using parametric equations based on TS EN 50160 standard. Four kinds of feature extraction as frequency-amplitude, time-amplitude, geometric mean and standard deviation is made with Stockwell Transform (ST), which is one of the methods used for the feature extraction of the determined GKB. Detection of voltage distortions is interpreted through these properties. 640 simulation data is entered into the classifier by using Support Vector Machines (SVM) and Artificial Neural Networks (ANN) and their classification performance is compared.

Grid Arama Yoluyla Monotonik Olmayan Hiperparametre Planlama Sisteminin Yardımcı Öğrenimi

“…Advanced Adaptive Neural Networks (AANNs) are the latest developments for classification that have shown their effectiveness in solving different problems in various domains. For instance, AANNs are employed for pattern recognition (Jain et al, 2018) (Jain et al, 2019), object detection (Erol et al, 2018) (Rahman et al, 2020), images classification (Sharma et al, 2018) (Patel et al, 2019), medical diagnosis (Sarvamangala and Kulkarni, 2022) (Yu et al, 2021) (Houssein et al, 2021), etc (Demircan Keskin et al, 2022) (Güney et al, 2022) (Gemirter and Goularas, 2021). Recently, AANNs have gained more attention due to their applicability to large datasets in an efficient manner.…”