Abstract: A new Particle Swarm Optimization（PSO） algorithm is proposed based on three aspects of improvement in standard PSO to solve the problems about premature convergence and low precision.The iteration formula of PSO based on the simple PSO which removes the velocity parameter is applied.Inertia weight，an important factor in PSO，is determined using a controlled chaotic variable to enhance the balance of global and local search of algorithm.The mutation operators are introduced to adjust individual and global optimal to improve the search performance of algorithm.The simulation experiments show that the proposed algorithm not only has great advantages of convergence property over standard PSO and some other modified PSO algorithms，but also effectively avoids being trapped in local minima.

Key words: Particle Swarm Optimization（PSO）, chaos, inertia weight, mutation

摘要： 为了克服粒子群算法早熟收敛和收敛精度不高的缺陷，提出了基于受控混沌映射的简化粒子群优化算法。该算法在采用去除了速度项的简化粒子群算法结构基础上，用受控混沌变量来描述惯性权值，并且对进化停滞的个体和全局极值进行变异操作。数值实验结果表明，新算法在收敛速度和收敛精度方面较已有方法有了明显提高，具有更强的摆脱局部极值的能力。

关键词: 粒子群优化算法, 混沌, 惯性权重, 变异