Optimization of HV electrode systems by neural networks using a new learning method

P. K. Mukherjee, C. Trinitis, H. Steinbigler

Research output: Contribution to journalArticlepeer-review

17 Scopus citations

Abstract

To avoid a large number of iterations, optimization of electrode shapes has been done by artificial neural networks (NN). Two practical examples have been considered, an axisymmetric single-phase GIS bus termination and an axisymmetric transformer shield ring. The shape of the electrodes has been taken as quarter-ellipse or half-ellipse because an ellipse has more flexibility a than circle. For NN, the socalled resilient propagation algorithm, learning faster than the standard back-propagation algorithm, has been employed. The training sets as well as the test sets of NN have been prepared by charge simulation method.

Original languageEnglish
Pages (from-to)737-742
Number of pages6
JournalIEEE Transactions on Dielectrics and Electrical Insulation
Volume3
Issue number6
DOIs
StatePublished - 1996
Externally publishedYes

Fingerprint

Dive into the research topics of 'Optimization of HV electrode systems by neural networks using a new learning method'. Together they form a unique fingerprint.

Cite this