Ammunition storage reliability forecasting based on radial basis function neural network

Abstract

In order to forecast ammunition storage reliability better, the paper researched a forecasting method based on neural network which is with the ability of actualizing multi-nonlinear mapping from input to output, and discussed steps of forecasting based on radial basis function (RBF) network. The storage reliability of one new-style ammunition is forecasted based on RBF network. The results show that RBF is suitable for ammunition storage reliability forecasting, and the precision of the train goal is better by using RBF network than by using BP network. RBF network is more suitable for dealing with this problem.