基于混沌理论和自适应惯性权重的PSO算法优化

Optimization of PSO Algorithm Based on Chaotic Theory and Adaptive Inertia Weight

针对粒子群算法固定惯性权重和早熟收敛的缺陷,提出一种动态自适应惯性权重调整策略,有效增强了算法的全局和局部寻优能力;并针对早熟问题,采用混沌映射方法增加种群多样性,同时利用负梯度方向调整群体极值,极大降低了算法陷入局部极值的概率.通过在多个常用测试函数上与其他算法比较,证明了所提改进粒子群算法的正确性和有效性.

In view of both fixed inertia weight and premature convergence obvious flaws of particle swarm optimization（PSO）algorithm,a dynamic adaptive adjustment strategy for inertia weight was proposed on the basis of a detailed analysis of the relationship among the inertia weight,population size,particle fitness and search space dimension,which effectively enhances the global and local optimization abilities of the algorithm.For the problem of premature,the chaotic mapping method was used to increase the diversity of the population,while the group extreme was adjusted in the direction of negative gradient,which greatly reduces the probability of fall into the local extreme.The correctness and effectiveness of the proposed PSO algorithm were verified to improve by some common used test functions compared with those by other algorithms.