人工蜂群算法的研究及其改进

发布时间：2018-06-20 07:03

本文选题：人工蜂群算法 + 差分进化算法　；参考：《延安大学》2017年硕士论文

【摘要】：随着应用和需求的不断扩展,非凸、非线性、高维、多变量和多目标等复杂优化问题大量涌现,对于这类问题的优化,传统优化算法已不再适用.群智能优化算法以其独特的寻优机制弥补了传统算法的不足,被广泛应用于解决各领域的复杂优化问题.常见的算法有遗传算法、粒子群算法、蚁群算法、人工鱼群算法等.Karaboga于2005年提出了人工蜂群算法,该算法具有简单易实现、控制参数少、鲁棒性强以及全局搜索能力较强等特点,因此得到了大量学者的关注,并在实际生活生产问题中得到广泛应用.本文首先简单介绍了最优化问题和最优化方法的发展历程,人工蜂群算法是一种新兴的群智能优化算法,自提出以来被大量学者关注并应用,但该算法还处于初级阶段,仍存在“早熟”收敛、局部搜索能力较弱和进化后期收敛速度较慢等缺点.本文在对算法的不足进行分析的基础上,提出了一种改进的人工蜂群算法.主要工作有:(1)深入剖析了标准人工蜂群算法的理论基础、基本原理、实现步骤等,并基于以上分析,总结出算法的优缺点;(2)针对算法的不足,本文主要从两方面对标准人工蜂群算法进行改进,一是采用反向学习的初始化方法,以增加解的多样性,二是引入受差分进化算法启发的搜索方程,以提高算法的开发能力;(3)通过仿真实验验证了改进后的算法具有更好的性能,优化能力更强.
[Abstract]:With the continuous expansion of application and demand, many complex optimization problems, such as non convex, nonlinear, high dimension, multivariable and multi-objective, are emerging. The traditional optimization algorithm is no longer applicable to the optimization of this kind of problem. The swarm intelligence optimization algorithm makes up for the shortcomings of the traditional algorithm with its unique optimization mechanism, and is widely used to solve the complexity of various fields. The common algorithms are genetic algorithm, particle swarm optimization, ant colony algorithm, artificial fish swarm algorithm and so on. In 2005,.Karaboga proposed artificial bee colony algorithm. This algorithm has the characteristics of simple and easy realization, low control parameters, strong robustness and strong global search ability, so a large number of scholars pay attention to it and live in real life. This paper first briefly introduces the development of optimization and optimization. Artificial bee colony algorithm is a new swarm intelligence optimization algorithm. Since it is put forward, a large number of scholars pay attention to it and apply it, but the algorithm is still in the primary stage, still has the convergence of "early maturing", and the local search ability is weak. In this paper, based on the analysis of the shortcomings of the algorithm, an improved artificial bee colony algorithm is proposed in this paper. The main work is as follows: (1) the theoretical basis, basic principle, and implementation steps of the standard artificial bee colony algorithm are analyzed in depth, and the advantages and disadvantages of the algorithm are summarized based on the above analysis; (2) the needles are summarized. For the deficiency of the algorithm, this paper mainly improves the standard artificial bee colony algorithm from two parties. First, the initialization method of reverse learning is adopted to increase the diversity of the solution. The two is to introduce the search equation inspired by the differential evolution algorithm to improve the development ability of the algorithm. (3) the improved algorithm has been proved to be better by simulation experiments. The performance, the optimization ability is stronger.
【学位授予单位】：延安大学
【学位级别】：硕士
【学位授予年份】：2017
【分类号】：TP18

【参考文献】