基于DDE改进蝙蝠算法的动态火力分配方法  

Dynamic Fire Distribution Method Using Improved Bat Algorithm Based on DDE

作　　者：邱少明[1] 胡宏章 杜秀丽[1] 吕亚娜[1] QIU Shao-ming;HU Hong-zhang;DU Xiu-li;L Ya-na(Dalian University,Department of Information Engineering,Liaoning Dalian 116622,China)

机构地区：[1]大连大学信息工程学院

出　　处：《现代防御技术》2019年第6期61-67,87,共8页Modern Defence Technology

摘　　要：针对动态火力分配算法耗时长,而传统的蝙蝠算法寻优精度不高等问题,提出了一种基于动态差分改进的蝙蝠算法。该算法首先通过放宽部分约束条件加快生成初始解,然后将动态差分进化算法中的差分变异机制融入到蝙蝠算法中,再利用惩罚函数确保生成的解满足约束条件,最后利用蝙蝠种群进行解的迭代寻优。仿真结果表明,与蝙蝠算法、遗传算法、粒子群算法相比,改进的算法有较高的收敛精度和较快的收敛速率,且更适合应用在较大规模的火力分配问题中。Aiming at the long allocation of dynamic fire distribution algorithm,an improved bat algorithm based on dynamic differential evolution is proposed. Firstly,the algorithm speeds up the generation of initial solution by relaxing some constraints. Secondly,the differential mutation mechanism in the dynamic differential evolution algorithm is integrated into the bat algorithm. Then the penalty function is used to ensure that the generated solution satisfies the constraints. Finally,the bat population is used to perform iterative optimization. The simulation results show that the improved algorithm has faster convergence speed and higher convergence precision compared with the bat algorithm,genetic algorithm and particle swarm optimization algorithm. The advantage is distinct when the method is applicated in largescale firepower distribution problems.

关 键 词：动态火力分配 蝙蝠算法 约束优化问题 动态差分进化 整数规划 收敛 

分 类 号：TP391.9[自动化与计算机技术—计算机应用技术] E211[自动化与计算机技术—计算机科学与技术]