Abstract: By introducing chaos state into the original Particle Swarm Optimization (PSO), this paper proposed a new algorithm-Chaos Particle Swarm Optimization (CPSO). The new algorithm makes good use of the ergodicity, stochastic property, and regularity of chaos. By judging the local convergence, when PSO gets into the local convergence, CPSO can start the chaos researching. The experimental results demonstrate that the new algorithm has the ability to avoid being trapped in local minima, and improves computational precision, convergence speed and the ability of global optimization.

Key words: chaos, optimization, particle swarm

摘要： 将混沌融入到传统粒子群提出了混沌粒子群算法。该方法利用了混沌运动的遍历性、随机性以及对初值的敏感性等特性，根据早熟判断机制，在基本粒子群算法陷入早熟时，进行群体的混沌搜索．数值仿真结果表明该方法能跳出局部最优，进一步提高了计算精度和收敛速度，以及全局寻优能力。

关键词: 混沌, 优化, 粒子群