Transformer fault diagnosis based on improved artificial fish swarm optimization algorithm and BP network

Abstract

IEC three-ratio is an effective method for transformer fault diagnosis in the dissolved gas analysis (DGA). Considering the characteristic of three-ratio boundary is too absolute, fuzzy knowledge is utilized to preprocess. As the same time, for overcoming the deficiency of the back propagation (BP), an improved artificial fish swarm optimization (IAFSO) algorithm is used to optimize the weight and threshold of the BP. The global searching ability of the IAFSO approach is utilized to find the global optimization solution. It can overcome the slower convergence velocity and easily getting into local extremum of the BP neural network. So, aiming at the shortcoming of BP neural network and three-ratio, blurring the boundary of the gas ratio and the IAFSO algorithm is introduced to optimize the BP network. Then the IAFSO-IECBP method is proposed in this paper. Experimental results indicate that the proposed algorithm in this paper that both convergence velocity and veracity are all improved to some extent. Correctness and validity of this proposed method has also confirmed for transformer fault diagnosis.