改进遗传算法的反无人机作战火力分配优化  

Optimization of fire assignment in anti-UAV combat with improved genetic algorithm

作　　者：秦长江[1] 黄亭飞 黄金才[1] QIN Changjiang;HUANG Tingfei;HUANG Jincai(College of Systems Engineering,National University of Defense Technology,Changsha 410073,China)

机构地区：[1]国防科技大学系统工程学院,湖南长沙410073

出　　处：《国防科技》2022年第1期85-92,共8页National Defense Technology

摘　　要：无人机作战与反无人机作战已成为现代战争一种非常重要的作战样式。如何快速针对来袭的多个无人机目标合理分配火力,提出最优的分配方案,是现代防空作战的重要课题。然而,当前军队尚缺少专门针对小型化无人机作战目标火力分配的研究,而传统意义上的火力分配模型已不能满足反无人机作战指挥决策的需求。采用基于深度强化学习的防控策略评估技术可动态性生成一个可行拦截方案。本文基于深度强化学习方法的初期决策,针对其无法满足火力分配决策所需的多种解决方案和决策结果不可控的问题,利用遗传算法的优势,建立了一个改进遗传算法的优化模型,有效解决了深度强化学习目标分配初期决策的结果优化问题,并通过仿真结果对比分析,验证了算法的可行性和有效性。此方法可以进一步应用于诸多易早熟收敛的小规模目标分配问题。UAV combat and anti-UAV combat have become very important combat styles.Quickly and reason‐ably allocating firepower to incoming UAV targets and the implementation of an optimal distribution scheme are im‐portant subjects in modern air defense combat.However,there is still a lack of research on firepower allocation for miniaturized UAV combat targets,and the traditional firepower allocation model no longer meets the requirements for anti-UAV combat command decision-making.Prevention and control strategy evaluation technology based on deep reinforcement learning is adopted to dynamically generate a feasible scheme.However,the initial decision of a deep reinforcement learning method cannot meet the multiple solutions needed for firepower allocation decisions and the decision result is not controllable.Therefore,we considered genetic algorithms to address this problem.We established an optimization model for an improved genetic algorithm that can effectively solve the optimization problem of early decisions based on deep reinforcement learning.Through comparison analysis,the simulation re‐sults verify the feasibility and validity of the algorithm.The proposed method can be further applied to the problem of the premature convergence of small target assignments.

关 键 词：改进遗传算法 反无人机作战 火力分配优化 

分 类 号：E919[军事]