摘要
针对粒子群算法早熟收敛和搜索精度低的问题,提出了基于混沌变异的小生境粒子群算法(NCPSO).该算法结合小生境技术并加入了淘汰机制,使算法具有良好的全局寻优能力.变尺度混沌变异具有精细的局部遍历搜索性能,使算法具有较高的搜索精度.实验结果表明,NCPSO算法可有效避免标准PSO算法的早熟收敛,具有寻优能力强、搜索精度高、稳定性好等优点,适合于工程应用中的复杂函数优化问题.
Niche chaotic mutation particle swarm optimization （NCPSO） is proposed to overcome the problem of the premature and low precision of the standard PSO. In this algorithm, niching methods and eliminating strategy are introduced to improve the global optimizing ability. Further, shrinking chaotic mutation, which behaves well in local searching, is introduced to improve the solution. Simulations show that NCPSO can avoid premature effectively and has powerful optimizing ability, good stability and higher optimizing precision.
出处
《控制与决策》
EI
CSCD
北大核心
2007年第1期117-120,共4页
Control and Decision
基金
国家自然科学基金项目(60572027)
四川省杰出青年基金项目(0326ZQ026-033)
关键词
混沌变异
小生境
粒子群优化算法
Chaotic mutation Niche, Particle swarm optimization algorithm
