【摘要】 研究了药房智能存取系统拣选路径的动态规划问题,提出了该问题的数学模型,并设计了一种新的自适应混合粒子群遗传算法(Adaptive hybrid particle swarm algorithm)。该算法在粒子群遗传混合算法的基础上引入了动态调整和自适应进化的策略。在算法前期粒子群搜索阶段,建立了惯性权重系数、认知系数与收缩因子之间的联动关系,随着惯性权重的动态变化,认知系数与收缩因子也适时进行调整,提高了搜索效率和搜索精度。在算法的后期,采用了遗传算法的自适应交叉和变异的进化过程,对陷入局部最优的粒子群进行打散,使得每次迭代中都能最大限度的获取路径信息,使种群的搜索朝向解空间的不同区域发展。经过对某大型医院智能存取系统的路径规划仿真实验,验证了提出的算法相对于其他算法在求解速度和求解精度上都有较大的提高。更多还原

【Abstract】 Dealing with a dynamic routing planning problem of the intelligent access system used in pharmacy,the mathematical formulations were proposed and an hybrid algorithm for this problem was designed.The designed algorithm incorporated the genetic algorithm and particle swarm algorithm and recommended dynamic adjustment and self-adaptive evolution strategies.The previous of the particle algorithm,with dynamic changing of the inertia weight,other parameters also made adjustments to improve search efficiency and search accuracy.In the latter part of the genetic algorithm,with selfadaptive parameter adjustment strategy,the amount of routing information could be maximized according to each iteration,and the search could be driven towards diverse regions of the solution space.The performance of the proposed algorithm was tested on some intelligent access system instances.It proves to be more effective and efficient than other algorithm.更多还原