Open AccessDetection and classification of complex power quality disturbances using S‐transform amplitude matrix–based decision tree for different noise levels
Author(s) -
Puliyadi Kubendran Arun Kumar,
Loganathan Ashok Kumar
Publication year - 2017
Publication title -
international transactions on electrical energy systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.428
H-Index - 42
ISSN - 2050-7038
DOI - 10.1002/etep.2286
Subject(s) - noise (video) , decision tree , s transform , computer science , power (physics) , noise power , control theory (sociology) , mathematics , pattern recognition (psychology) , electronic engineering , artificial intelligence , engineering , physics , discrete wavelet transform , wavelet transform , quantum mechanics , image (mathematics) , control (management) , wavelet
Summary This paper presents a simple and effective method for detection of complex power quality disturbances using S‐transform amplitude matrix. In this work, classification of complex power quality disturbances has been implemented using a rule‐based decision tree for different noise levels, such as with no noise, 30‐dB noise, and 45‐dB noise. The S‐transform is distinct, which provides a frequency‐dependent resolution with direct relationship to the Fourier spectrum. The features obtained from S‐transform amplitude matrix are dissimilar, clear, and immune to noise. According to a rule‐based decision tree, 7 types of single power disturbance and 16 types of complex power disturbance are well identified in this work. The proposed work is simulated using MATLAB simulation, and the various results are found, which detect the single and complex power quality disturbances; and it proves that the proposed method is effective and unaffected against noise.