Abstract: Particle swarm optimization is an effective random and holistic optimization algorithm，but the classical PSO algorithm easily plunges into local minimums.The paper proposes a new PSO algorithm which uses mutation and self-adjustable parameters.Via introducing the particle swarm evaluation，all the parameters of PSO algorithm can be dynamically adjusted by the evaluation of particle swarm’s holistic capability，then it can search fast in the prophase.At the same time the optimized result found in the particles mutated with the dynamic adjustable probability ensures the multiformity of particles，so it can prevent the algorithm plunging into the local minimums.The experimentative result of the three common testing functions shows the validity of the algorithm.

Key words: Particle Swarm Optimization（PSO）, swarm evaluation, mutation

摘要： 粒子群算法是一类有效的随机全局优化算法，但是经典PSO算法容易陷入局部最小值。提出了一种新的带变异自适应参数调整PSO算法，通过引入粒子群评价，根据粒子群的整体性能评价对PSO算法的所有参数动态调整，使前期能够快速搜索；同时对粒子本身找到的最优解以动态调整概率进行变异去保证粒子的多样性，防止后期陷入局部极小。对三个常用测试函数的数值仿真结果显示了该算法的有效性。

关键词: 粒子群（PSO）, 群评价, 变异