Application of improved Elman neural network based on fuzzy input for fault diagnosis in oil-filled power transformers

摘要

Dissolved Gas Analysis (DGA) is a popular method to detect and diagnose different types of faults occurring in power transformers. In this paper, a improved Elman neural network is uesed to resolve the online fault diagnosis problems for oil-filled power transformer. Because of the uncertainty factors of the transformer faults, a method using fuzzy math theory to deal with the data of the neural network input is also proposed. The fault diagnosis structure of neural network based on improved three-ratio method is given. In addition, to improve the convergence speed, Recursive Prediction Error algorithm is used in training network Through on-line monitoring the concentrations of the dissolved gases, the proposed diagnostic system can offer a way to interpret the incipient faults. The simulation diagnosis demonstrates the effectiveness and veracity of the proposed algorithm.