量子粒子群混合优化算法求解约束优化问题  

Hybrid Algorithm Based on Quantum Particle Swarm Optimization for Saving Constrained Optimization Problems

作　　者：陈义雄[1,2] 梁昔明[1,3] 黄亚飞[1] 龙文[4] 

机构地区：[1]中南大学信息科学与工程学院,长沙410083 [2]湘潭钢铁公司培训中心,湘潭411104 [3]北京建筑大学理学院,北京100044 [4]贵州省经济系统仿真重点实验室贵州财经大学,贵阳550004

出　　处：《小型微型计算机系统》2015年第2期296-300,共5页Journal of Chinese Computer Systems

基　　金：北京自然科学基金项目(4122022)资助;北京市属高等学校人才强教计划项目(201107123)资助;贵州省科学技术基金项目(黔科合J字[2013]2082号)资助;贵州省高校优秀科技创新人才支持计划项目(黔教合KY字[2013]140)资助

摘　　要：针对标准粒子群优化算法和量子行为粒子群优化算法的特性,将两种算法融合在一起,提出一种量子粒子群混合优化算法用于求解约束优化问题.此算法充分发挥了标准粒子群优化算法中通过个体与群体之间的相互学习,加强粒子间的信息交互,更新粒子的搜索速度;又兼顾了在量子行为粒子群优化算法中以概率密度函数的方式进行全局搜索,促使粒子跳出局部极值点,有效避免了粒子的早熟收敛.仿真结果表明:改进的混合优化算法,有效提高了算法的全局搜索能力和收敛速度,对处理约束优化问题具有一定的研究价值.Hybrid optimization algorithm is proposed for solving constrained optimization problems in this paper, according to charac- teristics of the standard particle swarm optimization algorithm and quantum-behaved particle swarm optimization algorithm, and com- bined with the two algorithms. This algorithm makes full use of the standard particle group algorithm through individual and group learning with each other, strengthen information interaction between particles, and updated search speed of the characteristics of parti- cles ; and with the global searching characteristic of the probability density function in the quantum behaved particle swarm optimiza- tion, and causing the particles to jump out of local optimum, and effectively avoids the premature convergence of the particles. Simula- tion result shows that the improved hybrid algorithm effectively improved the global search ability and convergence speed of the algo- rithm, and with certain research value for handle constrained optimization problems.

关 键 词：粒子群优化 量子 早熟 约束优化 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]