基于BP神经网络的潜地导弹落点参数计算方法

Calculation Method of Impact Point Parameter Based on BP Neural Network for Submarine-Launched Ballistic Missile

针对潜地导弹采用传统数值积分迭代法求取落点参数计算量大,不能满足潜艇水下机动发射要求的问题,利用BP神经网路,设计了潜地导弹落点参数快速计算方法。首先介绍了六自由度弹道运动微分方程及其传统计算方法,并分析了采用BP神经网络计算落点参数的可行性,然后通过输入输出变量的选择、样本的设计、BP神经网络的结构设计等,建立了BP神经网络计算落点参数模型,最后在Matlab平台完成仿真计算。仿真计算结果表明:基于BP神经网络的潜地导弹落点参数计算方法具有较高的计算精度和较快的计算速度,可为实现潜地导弹水下机动发射提供技术支持。

In view of the problem of large amount calculation based on traditional numerical integration to calculate impact point parameter,the traditional calculation method can not meet the requirement of submarine underwater mobile launch for submarine-launched ballistic missile.The BP neural network was used to establish the fast calculation method of impact point parameter.It introduced that the trajectory differential equation with six degrees of freedom and the traditional calculation method.The calculation feasibility based on BP neural network was analyzed.Then,the calculation model based on BP neural network was established by the selection of input and output variables,the sample design and the structure design.The simulation calculation was completed on Matlab platform.The simulation results indicate that the calculation method of impact point parameter based on BP neural network has high accuracy and fast calculation speed.The calculation method can provide technical support to submarine underwater mobile launch of submarine-launched ballistic missile.