【摘要】：花朵授粉算法(flower pollination algorithm,FPA)是最近提出的一種新型群智能優(yōu)化算法,由于其較好地解決了全局搜索和局部搜索的平衡性問(wèn)題,且具有參數(shù)少,易實(shí)現(xiàn)等特點(diǎn),已得到廣泛應(yīng)用和研究,但現(xiàn)有研究對(duì)其參數(shù)的研究較少,同時(shí)該算法也存在演化后期收斂速度慢且易陷入局部極小等缺陷,使其應(yīng)用范圍受到制約。為了提升FPA算法的整體性能,對(duì)其控制步長(zhǎng)的縮放因子的取值進(jìn)行了修正;提出了把高斯變異和Powell法融入到花朵授粉算法中的混合算法GMPFPA(flower pollination algorithm combination with Gauss mutation and Powell search method)。改進(jìn)算法首先利用高斯變異對(duì)全局搜索進(jìn)行擾動(dòng),增強(qiáng)種群的多樣性,提高全局探測(cè)能力,然后引入局部尋優(yōu)能力強(qiáng)大的Powell法提升其局部開發(fā)能力。通過(guò)12個(gè)高維經(jīng)典測(cè)試函數(shù)對(duì)比實(shí)驗(yàn),驗(yàn)證了改進(jìn)算法的有效性和優(yōu)越性。
[Abstract]:Flower pollination algorithm (flower pollination algorithm,FPA) is a new group intelligence optimization algorithm proposed recently. Because it solves the balance problem of global search and local search well, it has the characteristics of few parameters and easy to realize. It has been widely used and studied, but there are few researches on its parameters. At the same time, the algorithm has some defects, such as slow convergence rate and easy to fall into local minimum in the late stage of evolution, which restricts its application scope. In order to improve the overall performance of the FPA algorithm, the scaling factor of its control step is modified, and a hybrid algorithm, GMPFPA (flower pollination algorithm combination with Gauss mutation and Powell search method)., which integrates Gao Si mutation and Powell method into the flower pollination algorithm is proposed. The improved algorithm first uses Gao Si mutation to disturb the global search, enhances the diversity of the population and improves the global detection ability. Then, the Powell method with strong local optimization ability is introduced to improve its local development ability. The effectiveness and superiority of the improved algorithm are verified by comparison of 12 high-dimensional classical test functions.
【作者單位】： 江西財(cái)經(jīng)大學(xué)信息管理學(xué)院;河池學(xué)院計(jì)算機(jī)與信息工程學(xué)院;
【基金】：國(guó)家自然科學(xué)基金No.F020204 廣西自然科學(xué)基金No.2013GXNSFBA019022 廣西高�？茖W(xué)技術(shù)研究項(xiàng)目Nos.KY2015LX332,KY2015LX334 江西省研究生創(chuàng)新項(xiàng)目No.YC2015-B054 河池學(xué)院計(jì)算機(jī)網(wǎng)絡(luò)與軟件新技術(shù)重點(diǎn)實(shí)驗(yàn)室資助項(xiàng)目No.2013-03;河池學(xué)院教改項(xiàng)目No.2014EB022;河池學(xué)院基金項(xiàng)目No.XJ2015QN003~~
【分類號(hào)】：TP18

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 鄧輝;王勇;;一種基于Powell法的人口遷移混合算法[J];廣西民族大學(xué)學(xué)報(bào)(自然科學(xué)版);2010年01期

2 葛艷;逄海萍;孟友新;江峰;;求解連續(xù)空間優(yōu)化問(wèn)題的Powell蟻群算法[J];哈爾濱工業(yè)大學(xué)學(xué)報(bào);2009年12期

3 錢曉山;陽(yáng)春華;徐麗莎;;Powell-DE算法在軟測(cè)量參數(shù)預(yù)估中的應(yīng)用[J];湖南大學(xué)學(xué)報(bào)(自然科學(xué)版);2013年12期

4 吳建輝;章兢;陳紅安;;融合Powell搜索法的粒子群優(yōu)化算法[J];控制與決策;2012年03期

5 張軍麗;周永權(quán);;一種用Powell方法局部?jī)?yōu)化的人工螢火蟲算法[J];模式識(shí)別與人工智能;2011年05期

6 夏桂梅;蘇長(zhǎng)慧;;基于Powell搜索法的混合微粒群算法[J];山西師范大學(xué)學(xué)報(bào)(自然科學(xué)版);2014年02期

7 霍軍周;李廣強(qiáng);滕弘飛;;用并行遺傳/Powell/蟻群混合算法求解衛(wèi)星艙布局問(wèn)題(英文)[J];大連理工大學(xué)學(xué)報(bào);2006年05期

8 胡斌祥;顧伯達(dá);;一維柔性監(jiān)控搜索技術(shù)及其對(duì)Powell型約束變尺度法的改進(jìn)[J];武漢工學(xué)院學(xué)報(bào);1989年01期

9 李辛,吳旺成;降維Powell方法[J];數(shù)值計(jì)算與計(jì)算機(jī)應(yīng)用;1984年02期

10 ;DETERMINATION OF VOLTAGE DEPENDENCE OF IONIZATION CROSS-SECTION USED IN ANALYTICAL ELECTRON MICROSCOPY[J];電子顯微學(xué)報(bào);1991年02期

相關(guān)重要報(bào)紙文章 前1條

1 ;Gray Powell撒謊?[N];電腦報(bào);2010年

，

本文編號(hào)：2450938