改进粒子群算法在二维排样中的研究与应用  

Research and application of an improved particle swarm algorithm in two-dimensional layout

作　　者：董辉[1] 陈建军[1] 

机构地区：[1]浙江工业大学信息工程学院,浙江杭州310023

出　　处：《浙江工业大学学报》2016年第4期388-391,共4页Journal of Zhejiang University of Technology

摘　　要：针对服装行业二维不规则样片优化排样问题,提出了一种改进的粒子群优化排样方法.该算法在传统的粒子群优化算法中先引入小生境的思想,将种群划分成多个子群,各子群运用粒子群算法单独进化,取出各子群进化后的最好粒子,又可形成新群体,新群体运用混合蛙跳算法进化,使子群的最好粒子进一步更新,种群的多样性进一步增强,全局寻优的能力进一步提升.该算法概念简单,易于实现,具有较好的能力去搜索全局最优解和较快的收敛速度.实验结果表明该算法是有效的.An improved particle swarm algorithm is proposed to solve the optimization of twodimensional irregular layout problem in the garment industry.In this algorithm,the niche technology is introduced to the traditional particle swarm optimization algorithm while the population is divided into multiple sub-swarms and each sub-swarm is evolved by particle swarm algorithm independently.Then the best particles in the sub-swarms are reformed into a new group and the new group can be evolved by shuffled frog leaping algorithm.This algorithm can update the best particles of sub-swarms,enhance the diversity of the population and promote the global optimization capability further.The algorithm is simple in concept and is easy to be implemented.It has better ability to search the global optimal solution and faster convergence speed.Experimental results show that the algorithm is effective.

关 键 词：小生境 粒子群 混合蛙跳 排样 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]