摘要优化问题存在于现实生活中一般都是是非常复杂的，所有找到最好的解决方法变得不怎么可行。因此，一个明智的方法是寻找一个好的近似解，消耗较小的计算资源。若干个工程问题包含多个目标,同时需要解决，许多技术已经提出,模仿自然的，巧妙的方式探索单一和多目标优化的最优解问题。最早的自然激励技术是基因和其他进化启发式唤起达尔文进化原则。
本文以混合微粒群算法作为示例，它的计算模式是一种典型的群体智能，来进行多样性地来具体地探索群体智能。并且进行系统化工作对于优化效能评价有关智能微粒群算法。以智能优化的基本指标体系作为基础，组成一种智能微粒群优化动态效能评价模式体系，它能够综合评价算法整体优化性能和群体总体寻优动态，并分别对算法群体动态的聚合度、动态的最优值、动态的群体多样性和重心收敛度等评价模式进行了实例仿真和有效性验证。36237
毕业论文 关键字：微粒群优化算法，混沌粒子，群体智能
Performance simulation of Hybrid Particle Swarm Optimization for MATLAB
ABSTRACT
Real life optimization problems are often so complex that finding the best solution becomes computationally infeasible. Therefore, an intelligent approach is to search for a good approximate solution consuming lesser computational resources. Several engineering problems contain multiple objectives that need to be addressed simultaneously. Many techniques have been proposed that imitate nature’s own ingenious ways to explore optimal solutions for both single and multi-objective
optimization problems. Earliest of the nature inspired techniques are genetic and other evolutionary heuristics that evoke Darwinian evolution principles.
This dissertation presents the persity instance study of swarm intelligence through discussing a typical realization mode-particle swarm optimization(PSO).he systematical study on optimization efficiency evaluation of swarm intelligence is addressed firstly．Based on the basal evaluation index system in the field of intelligent optimization，a kind of evaluation model used to evaluate synthetically the general optimization performance and population dynamics of particle swarm optimization is proposed．This evaluation model including optimum value dynamics，population aggregation dynamics，population persity dynamics，as well as convergence dynamics of population center is simulated and validated by function optimization problems．
Keywords:
Particle swarm optimization algorithm,Chaotic particles,Swarm intelligence
目录
1    绪论    6
1.1    课题的目的和意义    6
1.2    算法的拓展与改进    7
1.2.1 研究背景    7
1.2.2 PSO算法的改进研究    7
1.3    发展趋势    9
1.4    本课题的基本内容    9
2    基本粒子群算法    12
2.1 粒子群算法概述    12
2.1.1 粒子群算法发展    12
2.1.2 粒子群算法简介    12
4.1.3 粒子群算法的特点    13
2.2 基本粒子群算法    14
2.3 粒子群算法的关键    17
2.3.1 粒子状态向量形式的确定    17
2.3.2 适应度函数的建立    17
2.3.3 粒子多样性的保证    18
2.3.4 粒子群算法的参数设置    18
3    混合粒子群算法    19
3．1 PSO早熟收敛判断    19
3．2基于基因换位算子改进策略    20
3．3多适应值函数机制    20 MATLAB混合微粒群算法的性能仿真:http://www.youerw.com/tongxin/lunwen_34588.html