基于改进差分进化算法的动态防空资源分配优化  

Dynamic Air Defense Resource Allocation Optimization Based on Improved Differential Evolution Algorithm

作　　者：罗天羽 邢立宁 王锐[1] 王凌[3] 石建迈[1] 孙昕 Luo Tianyu;Xing Lining;Wang Rui;Wang Ling;Shi Jianmai;Sun Xin(College of Systems Engineering,National University of Defense Science and Technology,Changsha 410073,China;College of Electronic Engineering,Xi'an University of Electronic Science and Technology,Xi'an 710071,China;Department of Automation,Tsinghua University,Beijing 100084,China)

机构地区：[1]国防科技大学系统工程学院,湖南长沙410073 [2]西安电子科技大学电子工程学院,陕西西安710071 [3]清华大学自动化系,北京100084

出　　处：《系统仿真学报》2024年第6期1285-1297,共13页Journal of System Simulation

基　　金：国家自然科学基金重点项目(62036006);陕西省重点科技创新团队项目(2023-CX-TD-07);陕西省重点研发计划(2024GHZDXM-48)。

摘　　要：面对动态防空资源分配问题中存在的空袭目标突现和雷达、发射车等资源受干扰现象,在综合考虑雷达、发射车和导弹等武器装备性能的基础上,基于目标集、资源集建立了最小化目标总拦截价值与生存概率的混合整数决策模型。提出了一种新的改进差分进化算法进行求解,采用反向学习策略生成初始解,确保初始种群的质量,设计了一种快速修复与重构的启发式规则作用于多阶段,以提升算法的搜索能力。仿真实验验证了该算法具有求解时间和求解精度上的优越性。该研究能使武器系统在动态事件的随机影响下,保持高效的作战能力和决策效果。Based on the integrated performance of weapon equipments such as radars,launchers and missiles,a mixed-integer decision model that minimizes the total target intercept value and the probability of survival based on Target-Set,Resource-Set is developed.A new improved differential evolutionary algorithm has been introduced to solve the problem,and the initial solutions is generated by using the reverse learning strategies to ensure the quality of the initial populations.An inspiration rule for the fast repair and reconstruction is designed to work at multi-stage to improve the search capability of the algorithm.The simulation experiment results show the algorithm's superiority in search time and search accuracy,which can maintain the efficient combat capabilities and decision-making under the random influence of dynamic events.

关 键 词：防空作战 动态防空资源分配 反向学习 改进差分进化算法 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术]