A neural network based method for leakage current prediction of polymeric insulators

A neural network based method for leakage current prediction of polymeric insulators

This letter describes a neural network approach to the prediction of the leakage current (LC) on silicone rubber insulators exposed to salt-fog. The validity of the approach was examined by testing several insulators in a salt-fog chamber. Feed-forward back propagation was found as the best method a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on power delivery 2006-01, Vol.21 (1), p.506-507
Hauptverfasser: Jahromi, A.N., El-Hag, A.H., Jayaram, S.H., Cherney, E.A., Sanaye-Pasand, M., Mohseni, H.
Format: Artikel
Sprache:eng
Schlagworte:
Aging
Applied sciences
Back propagation
Chambers
Degradation
Electric, optical and optoelectronic circuits
Electrical engineering. Electrical power engineering
Electronics
Errors
Exact sciences and technology
Feedforward systems
Insulation life
Insulator testing
Insulators
Leakage current
neural network
Neural networks
Plastic insulation
polymeric insulator
Polymers
Rubber
salt-fog test
Silicone rubber
Training
Various equipment and components
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This letter describes a neural network approach to the prediction of the leakage current (LC) on silicone rubber insulators exposed to salt-fog. The validity of the approach was examined by testing several insulators in a salt-fog chamber. Feed-forward back propagation was found as the best method among several training methods evaluated for the prediction of the LC. The predicted LC with this method has less than 12% error for the tested cases.
ISSN:0885-8977
1937-4208
DOI:10.1109/TPWRD.2005.858805