摘要
基于微粒群算法进化思想提出的二阶微粒群算法,从理论上分析此算法可以提高其性能及在实际生活中的应用.首先运用递归方程分析微粒运动轨迹的位置和速度,推导出微粒的轨迹与速度收敛条件,然后选取两组参数用MATLAB仿真验证其合理性.最后利用4个测试函数与标准微粒群算法进行比较.实验结果表明,二阶微粒群算法能够更快更好地收敛于全局最优.
The second-order particle swarm optimization is presented based on particle swarm optimization evolutionary thought. From the theoretical analysis, it can improve the performance and its application in the real life. Firstly, this paper analyzes the position and velocity of the particle trajectory, and it concludes the trajectory of the particles and the speed of convergence condition. Then, two groups of parameters are given by MATLAB simulation to verify the results of the analysis and it is reasonable. Finally, it is compared with the standard parti- cle swarm optimization with four test function. The experimental results show that the second-order particle swarm optimization cart converge to global optimal of better and faster.
作者
展之婵
陈京荣
伊亚平
郑荣基
Zhan Zhi-chan Chen Jing-rong Yi Ya-ping Zheng Rong-ji(School of Mathematics and Physics Lanzhou Jiaotong University, Lanzhou Gansu 73007)
出处
《河西学院学报》
2017年第5期11-17,共7页
Journal of Hexi University
基金
国家自然科学基金项目(项目编号:61463026,61463027)
关键词
标准二阶微粒群算法
递归方程
收敛条件
仿真
Second-order particle swarm optimization
Recursive equation
Convergence condition
Simulation
