Skip to main navigation Skip to search Skip to main content

Estimating transformer oil parameters using artificial neural networks

  • American University of Sharjah
  • Abu Dhabi Transmission and Despatch Company

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

In this paper the correlation between dielectric strength, the water content and oil CO2/CO ratio with insulation resistance in oil-filled power transformers is studied using artificial neural networks. This correlation allows and improves the condition assessment of transformer insulation using the Megger test. This is because dielectric strength, water content and CO2/CO ratio are important parameters for determining the deterioration state of the transformer insulation. The neural network model is built using tests' data for nineteen power transformers. The data collected is the high voltage, medium voltage, and low voltage to ground insulation resistance, oil breakdown voltage, water content and oil CO2/CO ratio. The results propose an efficient model with a breakdown voltage, water content, and oil CO2/CO ratio prediction rates of 95%, 82.8%, and 87.3% respectively.

Original languageEnglish
Title of host publication2009 International Conference on Electric Power and Energy Conversion Systems, EPECS 2009
StatePublished - 2009
Externally publishedYes
Event2009 International Conference on Electric Power and Energy Conversion Systems, EPECS 2009 - Sharjah, United Arab Emirates
Duration: 10 Nov 200912 Nov 2009

Publication series

Name2009 International Conference on Electric Power and Energy Conversion Systems, EPECS 2009

Conference

Conference2009 International Conference on Electric Power and Energy Conversion Systems, EPECS 2009
Country/TerritoryUnited Arab Emirates
CitySharjah
Period10/11/0912/11/09

Keywords

  • Co2/co ratio
  • Condition assessment
  • Dielectric strength
  • Neural networks
  • Water content

Fingerprint

Dive into the research topics of 'Estimating transformer oil parameters using artificial neural networks'. Together they form a unique fingerprint.

Cite this