Based on PSO-BP network algorithm for fault diagnosis of power transformer

Abstract

Dissolved gas analysis is an effective method for the early detection of incipient fault in power transformers. To improve the capability of interpreting the result of dissolved gas analysis, a technology is proposed in this paper. The Particle Swarm Optimization (PSO) technique is used to integrate with Back Propagation (BP) neural networks, and using particle swarm to optimize the network's weights and biases, the fault of transformers is simulated and discussed. The results show that the accuracy of PSO-BP method is significantly higher than that of the conventional three-ratio method. So the Algorithm based on PSO-BP network model provides a more accurate, safe and reliable result for the fault diagnosis of transformers.