A hybrid Computing Intelligence Approach for the Stator Insulation Residual Life Predicting of Large Generator

A hybrid computing intelligence approach was used in the study of an engineering diagnosis problem in this paper. Aimed at the problems of small samples and multi-collinearity of variables in complicated data modeling, RBF neural network was embedded into the regression framework of partial least square (PLS) method. The PLS method was used to extract variable components from sample data and the dimension of input variables was then reduced. Moreover, RBF neural network was used to fit the non-linearity between input and output variables in projection space, and the disadvantages of traditional modeling method were overcome. Finally, this modeling method was applied to the prediction of residual breakdown voltage of the large generator stator insulation. The test results show that the hybrid model has better prediction ability than traditional modeling method