Fault Forecast of the Transformer Using New Theory of Grey System

摘要

A transformer fault forecast system is presented in this paper, which not only take the non-equal-gap character of the predicting sequence into consideration, but also make improvements in the selection of initial conditions and the modification of background value. Experiments show that this method have comparatively higher accuracy than the other ecumenic non-equal-gap grey fault prediction model presented before. Based on those above a fault forecasting system of the transformer is introduced. The client can predict the short-term future characteristic quantities and the malfunction type likely to exist of the transformer, then a fault prediction of the transformer can be implemented.