粒子群优化算法的改进与分析

Improvement and Analysis of Particle Swarm Optimization

介绍了基本粒子群优化算法及其原理,针对其易陷入局部极值和后期收敛速度慢的缺点,研究了基于惯性权重因子的改进粒子群优化算法。通过测试函数对固定惯性权重和时变惯性权重参数的选择进行了系统的实验,并且分析了种群规模与学习因子参数对粒子群算法优化性能的影响。

The basic particle swarm optimization algorithms and its principle have been introduced, the particle swarm optimization has poor accelerate speed and can be easy to be caught into local optima, so the particle swam optimization cased the weight inner is researched. Make the experiment on the fixing inertia weight and changed inertia weight by testing function, and analyze an impact of population size and the factor studying over particle swarm algorithm optimization function.