论文部分内容阅读
集中式拦截联盟(CIC)形成是网络化防空导弹体系(NADMS)中的新问题,旨在确定目标、火力节点以及制导节点三者之间的最优匹配关系,以使得体系整体作战效能最大.根据问题背景,建立了CIC的约束优化问题模型,并选择收敛速度较快的粒子群优化(PSO)算法对模型进行求解.针对PSO的局部收敛问题,从认知心理学角度将人类特有的创造性思维(CT)引入粒子速度更新公式中,通过提升单个粒子的搜索能力来提高整个群体的寻优质量.基于CT过程经典的四阶段模型构建了算法框架,改进了PSO的速度更新公式.根据CIC问题特点,制定了编码策略及相关变量的离散化运算规则.实验结果证明了算法在CIC问题求解质量和收敛速度方面的优越性.
The formation of centralized interception alliance (CIC) is a new problem in Networked Air Defense Missile System (NADMS). The aim is to determine the optimal matching relationship among target, firepower node and guidance node so that the overall operational effectiveness of the system is maximized. According to the background of the problem, a CIC constrained optimization problem model is established, and a particle swarm optimization (PSO) algorithm with fast convergence is chosen to solve the model.For the problem of local convergence in PSO, from the perspective of cognitive psychology, (CT) is introduced into the particle velocity update formula to improve the search quality of a single particle to improve the quality of the entire population.An algorithm framework is built based on the classic four-phase model of CT process, and the speed update formula of PSO is improved.According to CIC Problem characteristics, and formulating the discretization algorithm of encoding strategy and related variables.The experimental results show the superiority of the algorithm in solving the quality and convergence speed of CIC.