文献类型：期刊文献

中文题名：战场兵力调度模型的仿真分析与研究

英文题名：Based on Improved Particle Swarm Optimization Algorithm of Battlefield Forces Scheduling Model

作者：李亚红[1];冯炳灿[2];冯东华[1,3]

第一作者：李亚红

机构：[1]南阳理工学院计算机与信息工程学院;[2]新乡学院设备处;[3]武汉理工大学计算机科学与技术学院

第一机构：南阳理工学院计算机与信息工程学院,河南南阳473004

年份：2016

卷号：0

期号：1

起止页码：4-7

中文期刊名：计算机仿真

外文期刊名：Computer Simulation

收录：CSTPCD;;北大核心:【北大核心2014】；CSCD:【CSCD_E2015_2016】；

基金：河南省教育厅自然科学计划研究项目(2010C520007)

语种：中文

中文关键词：兵力调度;粒子群优化算法;免疫克隆算法;全局搜索

外文关键词：Force scheduling; Particle swarm optimization algorithm;Immune clone algorithm;Global search

摘要：在战场兵力调度过程中,由于无法对战场上有大量的不确定因素以及参数进行全部标定,没有对调度任务进行排序,在调度过程中会产生一定的盲目性,导致当前以粒子群算法为基础的战场兵力调度模型在寻求最优调度时,无法迅速找到唯一的调度方案。提出一种改进的粒子群优化算法对战场兵力调度进行建模,将免疫克隆原理运用于战场兵力调度模型中,将克隆原理中的抗体作为粒子群算法中的粒子,对粒子按照亲和度的高低进行排列然后实施克隆选择、抑制和变异,有效提高了战场兵力调度粒子群算法的种群多样性和全局最优解搜索能力。以空战为例对战场进行仿真,仿真结果表明,改进的粒子群算法在很大程度上减少了寻找战略部署且标函数全局最优解所需的迭代次数,缩短了兵力的部署时间,取得了理想的兵力调度效果。
Battlefield forces in the traditional scheduling process, because there are a lot of uncertain factors on the battlefield and the number of parameters to consider more range is wide, will produce certain blindness in the process of scheduling, the battlefield of the current based on particle swarm optimization （pso） forces scheduling model for seeking the optimal scheduling, unable to quickly find the scheduling scheme. Therefore, an improved par- ticle swarm optimization algorithm was carried out on the field force scheduling modeling, immune clone principle ap- plied in the battlefield of forces in the scheduling model, the principle of clone antibody as particle in the particle swarm algorithm, carried out in accordance with the affinity of arrangement of the particles and then implementation of clonal selection, restrain and mutation, effectively improve the field force scheduling the species diversity of particle swarm optimization （pso） algorithm and the global optimal solution search ability. In air combat, for example on the battlefield simulation, simulation results show that the improved particle swarm algorithm in strategic deployment target function is largely reduced the required number of iterations, the global optimal solution greatly shortens the time of force deployment of ideal strength scheduling results have been achieved.