Melt index (MI) is the most important parameter in determining the polypropylene's grade. Since the lack of proper on-line instruments, its measurement interval and delay are both very long. This makes the quality control quite difficult.A neural network model based on PCA-GA-RBF was proposed to infer the MI of manufactured products from real process variables, where principle component analysis (PCA) was used to select the most relevant process features and to eliminate the correlations of the input variables, radial basis function (RBF) neural networks were used to characterize the nonlinearity and accuracy, and genetic algorithms (GA) was employed to optimize the parameters and structure of the RBF neural networks. The results show that the proposed method provides promising prediction reliability and accuracy.

Genetic algorithms,    , Radial basis function neural network,    ,  Principle component analysis,    ,  Melt index prediction