【摘要】：植物花授粉算法是根據(jù)自然界中植物花朵授粉行為機理進行模擬而設計的一種新型啟發(fā)式優(yōu)化算法,算法的局部搜索和全局搜索過程分別模擬自花授粉和異花授粉行為,并通過隨機擾動來均衡算法局部搜索和全局搜索過程的比重分配。該算法具有結構簡單,魯棒性強,搜索能力強,容易實現(xiàn)等特點。目前,植物花授粉算法已被成功地應用到求解各種復雜的優(yōu)化問題中。但隨著研究的深入,研究者發(fā)現(xiàn)花授粉算法存在著后期尋優(yōu)精度不高,易陷入局部最優(yōu)等不足,限制了算法的應用范圍。本文針對目前植物花授粉算法所存在的不足之處進行了一些分析和改進,并將改進的算法應用于一些經典的優(yōu)化問題中,目的在于進一步完善植物花授粉算法的理論基礎,并拓展其應用范圍。本文的主要工作包括以下2個方面:(1)采用復數(shù)編碼的思想對植物花授粉算法的編碼方案進行改進,增加了花粉個體種群的多樣性,同時,擴展了算法的全局探測能力,避免算法過早地陷入局部最優(yōu),克服了后期尋優(yōu)精度不高的缺點,使得花授粉算法的整體性能更優(yōu)。(2)利用精英反向花授粉算法解決非線性方程問題,實驗結果表明,利用精英反向花授粉算法解非線性方程組在提高算法精確度的同時,加快了算法的收斂速度,避免算法出現(xiàn)早熟現(xiàn)象,具有高度的穩(wěn)定性。
[Abstract]:Plant flower pollination algorithm is a new heuristic optimization algorithm designed according to the mechanism of plant flower pollination behavior in nature. The local and global search processes of the algorithm simulate self-pollination and cross-pollination, respectively. Stochastic perturbation is used to equalize the proportion allocation of local search and global search process. The algorithm has the characteristics of simple structure, strong robustness, strong search ability and easy realization. At present, plant flower pollination algorithm has been successfully applied to solve various complex optimization problems. However, with the deepening of the research, researchers found that the anthesis pollination algorithm has some disadvantages, such as low precision in late stage optimization, easy to fall into local optimization and so on, which limits the application range of the algorithm. In this paper, we analyze and improve the shortcomings of the current plant flower pollination algorithm, and apply the improved algorithm to some classical optimization problems in order to further improve the theoretical basis of plant flower pollination algorithm. And expand its application range. The main work of this paper includes the following two aspects: (1) the idea of complex number coding is used to improve the coding scheme of plant flower pollination algorithm, which increases the diversity of individual pollen population, and extends the global detection ability of the algorithm. The algorithm can avoid falling into local optimization prematurely and overcome the disadvantage that the precision of late optimization is not high, which makes the whole performance of flower pollination algorithm better. (2) the elite reverse flowering pollination algorithm is used to solve the problem of nonlinear equation. The experimental results show that: The elite reverse pollination algorithm is used to solve the nonlinear equations, which not only improves the accuracy of the algorithm, but also accelerates the convergence speed of the algorithm, and avoids the precocity of the algorithm, so it has a high degree of stability.
【學位授予單位】：廣西民族大學
【學位級別】：碩士
【學位授予年份】：2017
【分類號】：TP18

【參考文獻】

相關期刊論文 前6條

1 肖輝輝;萬常選;段艷明;鐘青;;基于模擬退火的花朵授粉優(yōu)化算法[J];計算機應用;2015年04期

2 李超燕;賴紅輝;周建良;;基于極大熵和聲搜索算法的非線性方程組求解[J];計算機工程;2011年20期

3 陳得寶;李淮江;李崢;;復數(shù)編碼粒子群算法及在函數(shù)優(yōu)化中的應用[J];計算機工程與應用;2009年10期

4 王冬冬;周永權;;人工魚群算法在求解非線性方程組中的應用[J];計算機應用研究;2007年06期

5 王書亭;王戰(zhàn)江;;粒子群優(yōu)化算法求解非線性問題的應用研究[J];華中科技大學學報(自然科學版);2005年12期

6 鄭朝暉,張焱,裘聿皇;一種基于復數(shù)編碼的遺傳算法[J];控制理論與應用;2003年01期

，

本文編號：2438850