TY - GEN
T1 - Towards cost-effective maintenance of power transformer by accurately predicting its insulation condition
AU - Ghunem, Refat Atef
AU - Shaban, Khaled Bashir
AU - El-Hag, Ayman Hassan
AU - Assaleh, Khaled
PY - 2012
Y1 - 2012
N2 - Insulation resistance (IR) or Megger test has been commonly performed in both preventive and corrective maintenance activities to verify power transformers' insulation condition. Other insulation diagnosis tests such as oil breakdown voltage (BDV), water content and dissolved-gas-in-oil analysis have been conducted along with the IR test. In this paper, a prediction model is developed to correlate IR measurements of the power transformer with its oil quality parameters, the concentration of its total dissolved combustible gases (TDCG), and its carbon dioxide to carbon monoxide concentration (CO 2/CO) ratio. Four models, based on feed-forward artificial neural networks with back-propagation, are trained on collected data of real measurements. Accuracy levels of 96%, 84%, 88%, and 91% are obtained for BDV, water content, TDCG, and CO2/CO ratio respectively. Utilizing the proposed model can reduce maintenance costs by preventing and shortening transformers' outage times using inexpensive test, i.e. using IR test only.
AB - Insulation resistance (IR) or Megger test has been commonly performed in both preventive and corrective maintenance activities to verify power transformers' insulation condition. Other insulation diagnosis tests such as oil breakdown voltage (BDV), water content and dissolved-gas-in-oil analysis have been conducted along with the IR test. In this paper, a prediction model is developed to correlate IR measurements of the power transformer with its oil quality parameters, the concentration of its total dissolved combustible gases (TDCG), and its carbon dioxide to carbon monoxide concentration (CO 2/CO) ratio. Four models, based on feed-forward artificial neural networks with back-propagation, are trained on collected data of real measurements. Accuracy levels of 96%, 84%, 88%, and 91% are obtained for BDV, water content, TDCG, and CO2/CO ratio respectively. Utilizing the proposed model can reduce maintenance costs by preventing and shortening transformers' outage times using inexpensive test, i.e. using IR test only.
KW - artificial neural network (ANN)
KW - asset management
KW - dissolved-gas-in-oil analysis (DGA)
KW - preventive and corrective transformer maintenance
UR - https://www.scopus.com/pages/publications/84875618913
U2 - 10.1109/EPEC.2012.6474933
DO - 10.1109/EPEC.2012.6474933
M3 - Conference contribution
AN - SCOPUS:84875618913
SN - 9781467320801
T3 - 2012 IEEE Electrical Power and Energy Conference, EPEC 2012
SP - 111
EP - 116
BT - 2012 IEEE Electrical Power and Energy Conference, EPEC 2012
T2 - 2012 IEEE Electrical Power and Energy Conference, EPEC 2012
Y2 - 10 October 2012 through 12 October 2012
ER -