APPLICATION OF ANN AND GA FOR TRANSFORMER WINDING/ INSULATION FAULTS

This report presents an application of Artificial Neural Network and Genetic
Algorithm for transformer winding/insulation faults diagnosed using Dissolved Gas
in Oil Analysis. A back propagation training method is applied in neural network to
detect the faults without cellulose involvement. While, heuristic method of Genetic
Algorithm is used to locate the optimal values to enhance the accuracy of fault
detection. The dissolved gas in oil analysis is chosen to diagnosis the transformer
faults in this project as the method is known to be an early fault detection method and
enables to carry out during online operation of the transformer. Besides, the condition
of the transformer could be monitored continuously by time to time. The project
outcome is analyzed using Neural Network and Genetic Algorithm MATLAB
Toolbox. Comparison between the real fault and predicted fault is made as to observe
the accuracy rate of the system. As transformer faults detection concentrated more in
conventional method such the stability of the voltage and current of the transformer.
Therefore, hopefully the transformer winding and insulation faults could be studied
from new point ofview and method.