摘要
传统子母弹反机场跑道封锁概率计算方法复杂、耗时长,不能实现毁伤效果侦察评估弹真实战场条件下的实时效能量化计算要求。为此,提出基于神经网络算法的子母弹反机场跑道封锁概率快速计算方法,该方法利用BP神经网络算法对原有计算模型进行拟合,获得可实现实时计算的封锁概率计算模型。仿真结果表明,该方法不仅可继承所学习的传统蒙特卡洛模型的优点,还可克服其准度、精度与耗时性之间的矛盾,评估所需时间从传统蒙特卡洛法的秒级缩短至毫秒级,实现战场毁伤效能实时计算要求,具备实用性和通用性。研究成果可为各类毁伤效果侦察弹对机场跑道封锁效能实时评估计算提供可行方法。
The traditional calculation method of the probability of airstrips blockaded by Cluster Munitions is complex and time-consuming,which can not meet the requirements of real-time effectiveness quantitative calculation of damage effect reconnaissance and evaluation missile under real battlefield conditions. Therefore,a fast calculation method for the blockade probability of cluster munitions against airport runways based on neural network algorithm is proposed. This method uses BP neural network algorithm to fit the original calculation model to obtain a blockade probability calculation model that can be calculated in real time. The simulation results show that this method can not only inherit the advantages of the traditional Monte Carlo model,but also overcome the contradiction between its accuracy,accuracy and time-consuming. The evaluation time is reduced from the second level of the traditional Monte Carlo method to the millisecond level,which meets the real-time calculation requirements of battlefield damage effectiveness,and has practicability and universality. The research results can provide a feasible method for real-time evaluation and calculation of the effectiveness of various damage effect reconnaissance bombs on airport runways.
作者
刘云辉
冯源
高月光
冯顺山
LIU Yunhui;FENG Yuan;GAO Yueguang;FENG Shunshan(State Key Laboratory of Explosion Science and Technology,Beijing University of Technology,Beijing 100081,China;China Academy of Ordnance Sciences,Beijing 100089,China)
出处
《火力与指挥控制》
CSCD
北大核心
2022年第9期159-162,169,共5页
Fire Control & Command Control
基金
国防科技创新团队奖基金资助项目(JCKY2019602D019)。
关键词
子母弹
封锁概率
神经网络
蒙特卡洛法
机场跑道
cluster ammunition
blocking probility
neural networks
Monte-Carlo method
runway
作者简介
刘云辉(1997-),男,江西吉安人,硕士研究生。研究方向:毁伤效能评估。
