改进差分进化算法求解武器目标分配问题

针对武器目标分配问题求解收敛速度慢、搜索效率低、寻优精度差的问题, 提出一种基于改进差分进化算法的武器目标分配方法。首先, 建立多约束条件下武器目标分配优化模型, 将动态武器目标分配问题离散为静态武器目标分配问题处理。其次, 采用随机邻域变异策略平衡差分进化算法全局探索和局部开发能力, 采用基于历史存档的自适应参数整定方法, 根据“精英”信息动态更新算法参数。最后, 通过与5种变种差分进化算法的对比实验, 验证了所提方法寻优精度高、收敛速度快、鲁棒性强的优点。

Improved differential evolution algorithm for solving weapon-target assignment problem

To solve the problems of the slow convergence rate and the low search efficiency in solving weapon-target assignment(WTA),an improved differential evolution(DE)algorithm is proposed.Firstly,the WTA model is established under the multi-constraint condition,and the dynamic WTA(DWTA)problem is discretized into the static WTA(SWTA)problem.Secondly,the exploration and exploitation capabilities of DE algorithm gorithm are slightly balanced by the random neighborhood-based mutation strategy,and the adaptive parameter setting method based on historical archive is adopted to dynamically update parameters based on“elite”information.Finally,through the comparative experiments with five kinds of variant DE algorithms,the present algorithm is proved to have a high searching accuracy,a fast convergence speed and a strong robustness.