用神经网络组合预测法估算反舰导弹研制费用  

Estimating the Development Expenses of Anti-Ship Missiles by a Joint Forecasting Methed of Artificial Neural Network

作　　者：张金春[1] 翟景春[1] 姜晨[1] 

机构地区：[1]海军航空工程学院,山东烟台264001

出　　处：《系统工程与电子技术》2002年第9期111-113,共3页Systems Engineering and Electronics

摘　　要：运用BP神经网络组合预测法对反舰导弹研制费用进行估算。首先分别利用神经网络和回归分析方法对导弹研制费用进行估算 ,然后利用BP网络对所得结果进行组合预测。计算实例表明 ,使用BP神经网络组合预测方法所得的预测结果比单一使用神经网络或回归分析方法所得结果总体误差要小 ,因而该方法是可行的、有效的。A joint forecasting methed of artificial neural network (ANN) is used to estimate the development expenses of anti-ship missiles. Firstly ANN and regressive analysis are separately employed to estimate the development expenses of anti-ship missiles, then the BP neural network is utilized to forecast the expenses based on the first two estimating results. The result shows that the overall forecasting error of this joint forecasting method is smaller than that of either ANN or regressive analysis. So the joint forecasting method is effective and feasible.

关 键 词：反舰导弹 神经网络 回归分析 组合预测 研制费用 

分 类 号：TJ761.14[兵器科学与技术—武器系统与运用工程]