基于正态分布更新的质心粒子群优化算法  

Centroid particle swarm optimization algorithm based on normal distribution updating

作　　者：曹凯 高岳林 CAO Kai;GAO Yuein(School of Mathematics and Information Sciences,Beifang University of Nationalities,Yinchuan 750021,China;Ningxia Key Laboratory of Intelligent Information and Big Data Processing,Yinchuan 750021,China)

机构地区：[1]北方民族大学数学与信息科学学院,银川750021 [2]宁夏智能信息与大数据处理重点实验室,银川750021

出　　处：《黑龙江大学自然科学学报》2025年第1期20-26,共7页Journal of Natural Science of Heilongjiang University

基　　金：国家自然科学基金资助项目(11961001);宁夏自然科学基金资助项目(2021AAC03185);北方民族大学重大科研专项项目(ZDZX201901)。

摘　　要：为了解决粒子群优化算法容易陷入局部最优解以及求解精度较低等问题,提出了一种基于正态分布更新的质心粒子群优化算法(Normal distribution updating centroid particle swarm optimization algorithm,NUCPSO)。该方法首先对传统粒子群优化算法进行了改进,提出正态更新机制的粒子群优化算法,然后将“质心”粒子引入算法中,加强粒子搜索能力,增加种群多样性,使得算法的求解结果更接近真实值。通过12个标准测试函数的实验,表明基于正态更新的粒子群优化算法在全局搜索能力和算法精度上与其他2种算法相比都具有显著优势。In order to solve the problem that the particle swarm optimization algorithm is easy to fall into local optimal solution and the solution accuracy is low,a centroid particle swarm optimization algorithm based on normal distribution updating is proposed in this paper(Normal distribution updating centroid particle swarm optimization algorithm,NUCPSO).This method first improves the traditional Particle swarm optimization(PSO)algorithm and proposes a PSO algorithm with a normal updating mechanism.Then,the“centroid”particle is introduced into the algorithm to enhance the particles'searching ability and increase the population diversity,so that the solution results of the algorithm are closer to the true values.Through testing on 12 standard test functions,the experimental results of the PSO algorithm based on normal updating show that it has significant advantages in global searching ability and algorithm accuracy compared with the other two algorithms.

关 键 词：粒子群优化算法 质心粒子 正态更新机制 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]