Open AccessEvaluating RMS based continuous S-Transform with deep learning for detecting and classifying voltage sag and swell
Author(s) -
Kamarulazhar Daud,
Syazreena Sarohe,
Wan Salha Saidon,
Saodah Omar,
Nurlida Ismail,
Nazirah Mohamat Kasim
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1045/1/012041
Subject(s) - voltage sag , extreme learning machine , swell , support vector machine , decision tree , artificial intelligence , root mean square , artificial neural network , pattern recognition (psychology) , voltage , computer science , point (geometry) , power quality , power (physics) , control theory (sociology) , mathematics , engineering , physics , control (management) , electrical engineering , thermodynamics , quantum mechanics , geometry
Voltage sag and swell can cause serious problems like instability, short lifetime, and data errors in power quality. The objective of this paper is to present the detection and classification of voltage sag and swell. S-Transform is used as a base to detect the triggering point of disturbances using Root Mean Square (RMS) method. This paper also presents the type of sags and swells by applying the features into Extreme Learning Machine (ELM) neural network approach in MATLAB. In addition, ELM method is compared with Support Vector Machine (SVM) and Decision Tree method to observe the best classification between these three methods. The accuracy of the classifications was displayed in percentages. It was verified that the detection using RMS and classification using ELM are possible because the results are clearly showing the advantages of the RMS in detecting and ELM for classifying the power quality problems.