Condition assessment of power transformers using genetic-based neural networks

Genetic-based neural networks (GNNs) for the assessment of the condition of power transformers are presented. The GNNs automatically tune the network parameters, connection weights and bias terms of the neural networks, to yield the best model according to the proposed genetic algorithm. Due to the global search capabilities of the genetic algorithm and the highly nonlinear mapping nature of the neural networks, the GNNs can identify complicated relationships among the dissolved gas contents in the transformers insulation oil and hence the corresponding fault types. The proposed GNNs have been tested on the diagnostic records of the Taipower Company and compared with a fuzzy logic diagnosis system, artificial neural networks and a conventional method. The test results show that the proposed GNNs improve the diagnostic accuracy and the learning speed of the existing approaches.