为了更准确预测导弹贮存可靠性,提出基于全局逼近BP网络和局部逼近RBF网络对导弹贮存可靠性进行预测,给出了预测的基本步骤,分别基于BP网络和RBF网络对某型舰舰导弹的贮存可靠性进行了预测,结果表明:这两种网络都能够解决导弹贮存可靠性预测的问题,预测误差均满足要求;RBF网络预测精度略高于BP网络,具有更好的函数逼近能力。RBF网络更适用于导弹贮存可靠性的预测。

To get better effect of missile storage reliability forecasting, the paper put forward a method based on neural network, and discussed steps of forecasting based on back propagation network and radial basis function network. At last, the storage reliability of one type ship-to-ship missile was forecasted based on BP network and RBF network. The result was suggested that both of the BP and RBF are suitable for Missile storage reliability forecasting, and the precision of the train goal is better by using RBF network. RBF network is more suitable for resolving this forecast problem.