摘要
针对标准粒子群优化算法存在易陷入局部最优点的缺点,提出了一种基于动态双种群的粒子群优化算法(DPSO).DPSO算法将种群划分成两个种群规模随进化过程不断变化的子种群,两个子种群分别采用不同的学习策略进行进化,并在进化过程中相互交换信息.该算法提高了全局寻优能力,有效地避免了早熟收敛的发生.将以DPSO算法为基础的排序算法和启发式分配算法(HA)相结合形成了解决柔性工作车间调度问题的新方法(DPSO-HA).通过对算例的研究和与其他方法的比较表明,该方法是有效可行的.
A dynamic double-population particle swarm optimization （DPSO） algorithm is presented to solve the problem that the standard PSO algorithm is easy to fall into a locally optimized point, where the population is divided into two sub-populations varying with their own evolutionary learning strategies and the information exchange between them. The algorithm thus improves its solvability for global optimization to avoid effectively the precocious convergence. Then, an ordering algorithm based on DPSO is integrated with the heuristic assignation （HA） algorithm to form a new algorithm DPSO-HA so as to solve the flexible job-shop scheduling problem （FJSP）. The new algorithm is applied to a set of benchmark problems as instances, and the simulation results show the effectiveness and feasibility of DPSO-HA algorithm for the flexible job-shop scheduling.
出处
《东北大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2007年第9期1238-1242,共5页
Journal of Northeastern University(Natural Science)
基金
国家自然科学基金资助项目(60274009)
关键词
双种群
粒子群优化
学习策略
DPSO-HA算法
柔性工作车间调度
double population
PSO（particle swarm optimization）
learning strategy
DPSO-HA algorithm
flexible job-shop scheduling
