计算机技术与发展2026，Vol.36Issue(1)：64-72,87,10.DOI:10.20165/j.cnki.ISSN1673-629X.2025.0208
多策略改进的无速度粒子群优化算法
A Multi-strategy Improved Particle Swarm Optimization without Velocity
孙博文 1王友才 2何立新 3陈焱焱2
作者信息
- 1. 中国科学院 合肥物质科学研究院,安徽 合肥 230031||合肥大学 人工智能与大数据学院,安徽 合肥 230601
- 2. 中国科学院 合肥物质科学研究院,安徽 合肥 230031
- 3. 合肥大学 人工智能与大数据学院,安徽 合肥 230601
- 折叠
摘要
Abstract
To solve the standard particle swarm optimization tendency to fall into local optima,a multi-strategy improved velocity-free particle swarm optimization is proposed.Firstly,a one-dimensional infinite folding iterative chaotic map is introduced to initialize the population,ensuring a more uniform distribution of the population in the solution space,increasing the diversity of the initial population,and improving the convergence speed and accuracy of the algorithm.Secondly,discarding the particle velocity component improves con-vergence speed.Finally,a fitness-based competitive selection mechanism is designed to guide directional migration and diffusion of high-quality particle information,promote the overall evolution of the population to a better region,avoid premature convergence,and establish an adaptive step size adjustment model based on Weibull distribution to effectively balance the global search and local development capabilities.The improved algorithm is tested on 14 standard test functions and CEC2019,and compared with multiple swarm intelligence algorithms.It is showed MPSOWV has significant advantages in optimization performance and convergence precision.Further application to practical engineering problems demonstrates its superiority in handling real-world challenges.关键词
粒子群优化算法/无速度/混沌映射/竞争选择/自适应威布尔飞行Key words
particle swarm optimization/velocity-free/chaotic mapping/competitive selection/adaptive Weibull flight分类
信息技术与安全科学引用本文复制引用
孙博文,王友才,何立新,陈焱焱..多策略改进的无速度粒子群优化算法[J].计算机技术与发展,2026,36(1):64-72,87,10.
