基于集成改进蚁群算法的作战环推荐方法  

Operation loop recommendation method based on integrated improved ant colony algorithm

作　　者：李杰[1] 谭跃进[1] LI Jie;TAN Yuejin(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：《系统工程与电子技术》2024年第6期2002-2012,共11页Systems Engineering and Electronics

基　　金：国家自然科学基金(71971213)资助课题。

摘　　要：作战环推荐是依靠优化算法从作战网络中为指挥员推荐最优的作战环,以对目标形成高质量打击。未来作战中的作战环推荐面临体系规模大、决策节奏快的特点。对此,提出了一种集成改进的蚁群算法,能够实现高效、高质的作战环推荐优化求解。首先,将作战环推荐问题转换为一种基于多仓库路径规划的数学模型。然后,针对原始蚁群算法前期收敛速度慢、算法参数对结果影响大和容易陷入局部最优的问题分别提出了3种改进策略:基于边权重信息的信息素初始化、基于差分进化的蚁群算法参数自适应优化和基于遗传算子的全局搜索能力提升,并进行了集成改进。最后,在案例分析中对集成改进蚁群算法进行了分析和对比,验证了所提算法在不需要大幅提高耗时的情况下,优化结果要优于未集成改进的蚁群算法,且相比于原始蚁群算法提升效果显著。Operation loop recommendation(OLR)is based on the optimization algorithm to recommend the optimal operation loop from the combat network for the commander,in order to strike the target with high quality.The OLR in the future operations is faced with the characteristics of large scale and fast decision-making pace.In this regard,an integrated improved ant colony(AC)algorithm is proposed,which can realize efficient and high-quality optimization solution on OLR.Firstly,the OLR problem is transformed into a mathematical model based on multi-warehouse path planning.Secondly,to solve the problems of the original AC algorithm,such as slow convergence speed in the early stage,the algorithm parameters have great influence on the results,and easy to fall into the local optimization,three improvement strategies are proposed and integrated:pheromone initialization based on edge weight information,adaptive optimization of AC algorithm parameters based on differential evolution,and improvement of global search ability based on genetic operator.Finally,the case study analyzes and compares the integrated improved AC algorithm,verifies that the optimization result of the proposed algorithm is better than that of the unintegrated improved AC algorithm without significantly increasement of the time consumption,and the effect is significantly improved compared with the original AC algorithm.

关 键 词：作战环推荐 多仓库路径规划 智能优化 蚁群算法 集成改进 

分 类 号：N936[自然科学总论]