Open AccessPartial discharge classifier based on wavelet theory
Author(s) -
Yun Yang,
Xiaoxiao Zhao,
Yanjie Zhang
Publication year - 2020
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/768/6/062084
Subject(s) - fractal , wavelet , classifier (uml) , pattern recognition (psychology) , computer science , artificial intelligence , algorithm , mathematics , mathematical analysis
The excursion of fractal parameters is the main obstacle to the application of classifiers trained by fractal-parameter-based features. In order to solve this problem, the characteristics of fractal parameters are studied based on partial discharge ultra-high-frequency signals mathematical models. One solution to this problem based on symlets wavelet has been put forward. And the result of implementation to signals with different signal-to-noise-ratio shows that it’s a promising approach to expand the applicability of the classifier.