基于GA-BP神经网络的防空导弹实时目标分配方法  

Target Assignment Method of Air Defense Missile Based on GA-BP Neural Network

作　　者：孙栋一 蒲宇亭 章建榜 SUN Dongyi;PU Yuting;ZHANG Jianbang(Unit 95010 of PLA,Shantou 515000,Guangdong,China)

机构地区：[1]中国人民解放军95010部队,广东汕头515000

出　　处：《空天防御》2025年第1期62-70,共9页Air & Space Defense

摘　　要：针对现代防空作战中作战环境高动态变化的状况,防空导弹武器系统需要实时在线解决目标分配的问题,为此本文提出了一种基于遗传算法(Genetic Algorithm, GA)优化+BP(Back Propagation)神经网络学习的防空导弹实时目标分配方法。首先,综合考虑防空导弹武器数量及毁伤概率等要素,以毁伤效能最大为优化目标,建立防空导弹目标分配问题优化模型;其次,构建基于GA-BP神经网络的防空导弹目标分配框架,利用遗传算法求解加BP神经网络预测,实现当前防空导弹对威胁目标的准确高效分配;最后,利用优化后的神经网络进行仿真分析,以验证所提方法的有效性和实用性。Given the great dynamic change in the modern air defense combat environment,the air defense missile weapon system requires real-time online target allocation.In this study,a real-time target allocation method for air defense missiles based on a genetic algorithm(GA)optimized back propagation(BP)neural network was proposed.Firstly,the optimization model of the air defense missile target allocation problem was established by employing the number of air defense missile weapons and damage probability,and the maximum damage effectiveness was set as the optimization goal.Then,the air defense missile target allocation framework based on the GA-BP neural network was constructed.The optimal weights and thresholds of the BP neural network were acquired using a genetic algorithm to optimize the BP neural network.The accurate and efficient allocation of threat targets to the current air defense missile was achieved from neural network prediction.Finally,the optimized neural network was applied for simulation analysis,allowing real-time target allocation under the battlefield situation,and verifying the effectiveness and practicability of the proposed method.

关 键 词：防空导弹 遗传算法 BP神经网络 目标分配 辅助决策 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]