A back-propagation neural network model is used to identify electrode types involved in partial discharge (tree, IEC (b), CIGRE method I) and to estimate the shapes of the cylindrical electrode voids, based on the specific charge-phase characteristics of the different electrode types.
|Number of pages||7|
|Journal||Electrical Engineering in Japan (English translation of Denki Gakkai Ronbunshi)|
|Publication status||Published - 1992|
ASJC Scopus subject areas
- Electrical and Electronic Engineering