摘要
分析了粒子群优化算法的收敛性,指出它在满足收敛性的前提下种群多样性趋于减小,粒子将会因速度降低而失去继续搜索可行解的能力;提出混沌粒子群优化算法,该算法在满足收敛性的条件下利用混沌特性提高种群的多样性和粒子搜索的遍历性,将混沌状态引入到优化变量使粒子获得持续搜索的能力.实验结果表明混沌粒子群优化算法是有效的,与粒子群优化算法、遗传算法、模拟退火相比,特别是针对高维、多模态函数优化问题取得了明显改善.
The particle swarm optimization (PSO) algorithm is analyzed. Its premature convergence is due to the decrease of velocity of particles in search space that leads to a total implosion and ultimately fitness stagnation of the swarm. A chaotic particle swarm optimization (CPSO) algorithm is introduced to overcome the problem of premature convergence. CPSO uses the properties of ergodicity, stochastic property, and regularity of chaos to lead particles' exploration. This enable the swarm system to have the ability of "sustainable development". Simulation results show that CPSO prevents premature convergence effectively and is better than PSO, genetic algorithm and simulated annealing on some benchmark function optimization problems.
出处
《控制与决策》
EI
CSCD
北大核心
2006年第6期636-640,645,共6页
Control and Decision
基金
国家自然科学基金项目(60373095)
国家973计划项目(2100CCA00700)
教育部科学基金项目(KP0302)
关键词
粒子群优化算法
混沌
多模态函数优化问题
遗传算法
模拟退火算法
Particle swarm optimization
Chaos
Multi-modal function optimization problem
Genetic algorithms
Simulated annealing