一种改进惯性权重的粒子群优化算法  

Particle Swarm Optimization Algorithm with Improved Inertia Weight

作　　者：薛文 XUE Wen(School of Electrical Engineering,Jilin Railway Technology College,Jilin 132299,China)

机构地区：[1]吉林铁道职业技术学院电气工程学院,吉林吉林132299

出　　处：《现代信息科技》2023年第20期88-91,共4页Modern Information Technology

摘　　要：针对粒子群算法易陷入局部最优解的问题,提出一种改进惯性权重的粒子群优化算法(CWPSO)。首先引入Sigmoid函数构造自适应的惯性权重策略;然后引入线性递减的惯性权重策略;最后通过群体适应度方差将自适应惯性权重策略和线性递减惯性权重策略动态结合,构造综合惯性权重策略,以提高算法全局搜索和局部搜索的能力。实验结果表明,CWPSO算法的寻优性能相较于对比算法有明显提升。Aiming at the problem that Particle Swarm Optimization is easy to fall into the local optimal solution,a CWPSO algorithm with improved inertia weight is proposed.Firstly,Sigmoid function is introduced to construct adaptive inertia weight strategy.Then the inertia weight strategy of linear decreasing is introduced.Finally,the adaptive inertia weight strategy and linear decreasing inertia weight strategy are dynamically combined by the variance of groupfitness to construct a comprehensive inertia weight strategy,so as to improve the global search and local search ability of the algorithm.The experimental results show that the optimization performance of CWPSO algorithm is obviously improved compared with the comparison algorithm.

关 键 词：粒子群算法 惯性权重 适应值 群体适应度方差 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]