摘要：随着量子技术、信息技术、生物技术等尖端技术的飞速发展，自然计算科学与其它科学不断的交叉和演化。产生了一批赞新的、生命力强、功能强大的计算分支，如混合粒子群算法、遗传算法、量子计算等。自然计算的分支---粒子群优化算法，自从1995年Kennedy和Eberhart博士提出了粒子群优化算法（Particle Swarm Optimization，PSO），就受到了国内外研究者的关注，并被广泛地应用于多个不同的领域。粒子群优化算法也存在着一些缺陷，即粒子群优化本身的参数的设置存在的问题、容易陷入局部极值点从而导致得不到全局最优解、缺乏速度的动态调节。因此找到一种既能提高算法的收敛速度又能提高算法搜索精度的算法是非常重要的。混合粒子群算法将混合寻优机制引入后既保证了收敛速度，又降低了陷于局部最优的风险。本文主要研究如何改进混合粒子群算法使其具有既保证了收敛速度，又降低了陷于局部最优的风险的性能。22203
毕业论文关键词： 粒子群优化算法；SelPSO；BreedPSO；SimuAPSO；PSO
The performance of hybrid particle swarm algorithm simulation research
Abstract: As quantum technology， information technology， the rapid development of cutting-edge technologies such as biotechnology， natural computing science and other scientific crossover and evolution. Produce a new batch of praise， vitality is strong， powerful computing branches， such as hybrid particle swarm optimization (pso) algorithm， genetic algorithm， quantum computing， etc. Branch of the natural computation - Particle Swarm Optimization algorithm， since 1995， Kennedy and Eberhart Particle Swarm Optimization algorithm was presented to Dr (Particle Swarm Optimization， PSO)， has been the attention of the researchers at home and abroad， and have been widely used in many different fields. Particle swarm optimization algorithm also has some defects， the particle swarm optimization parameter setting of existing problems， easy to fall into local extreme value point and lead to can not get the global optimal solution， the lack of speed and dynamic adjustment. So find a way to both can improve the convergence speed of the algorithm and can improve search precision of the algorithm is very important. Hybrid particle swarm optimization (pso) after introducing hybrid optimization mechanism is to ensure the convergence speed， and reduce the risk in a local optimum. This paper mainly studies how to improve the hybrid particle swarm algorithm has not only ensure the convergence speed， and reduce the risk of into local optimum performance.
Keywords: Particle Swarm Optimization；SelPSO；BreedPSO；SimuAPSO；PSO
目录
摘要 i
Abstract i
目录 vi
1 绪论 1
1.1 自然计算 1
1.1.1 自然计算的研究背景 2
1.1.2 自然计算的应用 2
1.1.3 自然计算发展趋势 3
1.2 粒子群算法 4
1.2.1 基本粒子群算法的一般步骤 5
1.2.2 基本粒子算法流程图 6
2 混合粒子群算法 7
2.1 基于自然选择的算法SELPSO 7
2.1.1 基于SelPSO算法原理 7
2.1.2 SelPSO算法的流程 7
2.2 基于杂交的算法BREEDPSO 8
2.2.1 基于BreedPSO算法原理 8
2.2.2 BreedPSO算法的流程 9 混合粒子群算法的性能仿真研究+源代码:http://www.youerw.com/tongxin/lunwen_14726.html