Artificial neural network based implementation of Oommen´s curve

Author

Islam, Tarikul ; Khan, Md Firoz A. ; Khan, Shakeb A.

Author_Institution

Electr. Eng. Dept., Jamia Millia Islamia, New Delhi, India

fYear

2014

Firstpage

1

Lastpage

5

Abstract

An ANN based implementation of Oommen´s curve to study the online estimation of moisture in paper insulation of transformer using temperature and moisture in oil as input is presented. It is based on a multilayer feed forward network (MLP) with one hidden layer in addition to input and output layer. The implementation, analysis, results and applications of the scheme is discussed. The results confirm that the estimated output of the ANN follow the desired output of the Oommen´s curve very closely. It is found that the error remains within ±2% of full scale for temperature of 40°C to 100°C. The implementation has the potential to diagnose the incipient fault in real time based on estimation of moisture in paper insulation.

Keywords

fault diagnosis; feedforward neural nets; moisture; paper; power transformer insulation; Oommens curve; artificial neural network; incipient fault diagnosis; multilayer feed forward network; online estimation; paper insulation moisture; temperature 40 C to 100 C; transformer insulation; Artificial neural networks; Moisture; Oil insulation; Power transformer insulation; Training; Artificial Neural Networks (ANN); Oomen curve; power transformer;

fLanguage

English

Publisher

ieee

Conference_Titel

Power India International Conference (PIICON), 2014 6th IEEE

Print_ISBN

978-1-4799-6041-5

Type

conf

DOI

10.1109/34084POWERI.2014.7117613

Filename

7117613