Open AccessEnhancing Data Applied in the Research of Partial Discharge Systematic Diagnosis
Author(s) -
Yi Yang,
Demeng Bai,
Meng Li,
Huiling Dou
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1982/1/012158
Subject(s) - partial discharge , sample (material) , computer science , set (abstract data type) , artificial neural network , ultra high frequency , artificial intelligence , gaussian , data set , data mining , noise (video) , pattern recognition (psychology) , algorithm , engineering , image (mathematics) , electrical engineering , telecommunications , voltage , chemistry , physics , chromatography , quantum mechanics , programming language
The existing problems in the current partial discharge PRPS sample enhancement method have been summarized in this artcle, and a GIS UHF partial discharge data enhancement method has been proposed which is based on noise coupling, Gaussian blur and so on. It solves the problem of unable to collect a large number of defect maps and form a sample set due to the lack of GIS partial discharge cases, which limits the application of intelligent algorithms such as deep neural networks. This partial discharge PRPS sample enhancement method has been proved through application that it can effectively enhance the partial discharge sample set, make the samples evenly distributed, and meet the training needs of intelligent algorithms such as deep neural networks. The intelligent diagnosis algorithm trained using the enhanced sample set has a high diagnostic accuracy rate of 95%, which has practical application value.