基于加权窗口特征的多目标火力集中分配和动态调整算法  

Multi-target Fire Concentration Allocation and Dynamic Adjustment Algorithm Based on Features of Weighted Window

作　　者：兰浩然 关佳兴 花园 LAN Haoran;GUAN Jiaxing;HUA Yuan(The 28th Research Institute of China Electronics Technology Group Corporation,Nanjing 210023,China)

机构地区：[1]中国电子科技集团公司第二十八研究所,南京210023

出　　处：《指挥信息系统与技术》2024年第2期51-56,共6页Command Information System and Technology

摘　　要：针对现有的火力打击规划方法在战前筹划时存在局部收敛性和全局优化能力差、缺乏对战中调整的临机处理和时效性考虑等问题,提出了基于加权窗口特征的火力集中分配和动态调整算法。首先,建立了基于加权窗口特征的分配模型以量化打击效益和资源代价,从而适应对不同作战需求的火力分配;然后,针对算法参数敏感和先验知识缺失的问题,提出了一种自适应参数的基于密度的聚类算法,可自适应寻优参数选择;最后,考虑到战中调整的实时性需求,提出了改进匈牙利算法以减少代价矩阵的迭代次数。试验表明,该算法能够有效解决战前规划和战中调整问题,且在大规模数据集上表现出比其他方法更加优越的性能,验证了该算法的有效性和灵活性。Aiming at problems of current fire strike planning methods about local convergence and poor global optimization ability in the pre-war planning,and lack of consideration on improvisation and timeliness during the adjustment in a battle,a fire concentration allocation and dynamic adjustment algorithm based on features of weighted window is proposed.Firstly,an allocation model based on features of weighted window is established to quantify the strike benefit and resource cost.Thus,the fire allocation can be adaptive to different operation requirements.Then,aiming at the problem of sensitivity to the algorithm parameters and absence of prior knowledge,an adaptive-parameter density-based clustering algorithm is presented to adaptively optimize parameter selection.Finally,considering the real-time requirement of adjustment in a battle,an improved Hungarian algorithm is proposed to reduce the iterations of the cost matrix.Experiments show that the algorithm can effectively solve problems during pre-war planning and adjustment in a battle.It has superior performance than other methods on large-scale data set,and the effectiveness and flexibility of the algorithm are verified.

关 键 词：武器目标分配(WTA) 火力打击规划 聚类 匈牙利算法 

分 类 号：TJ01[兵器科学与技术—兵器发射理论与技术] N945.25[自然科学总论—系统科学] E917[军事]