本文關(guān)鍵詞：新型灰狼優(yōu)化算法在函數(shù)優(yōu)化中的應(yīng)用　出處：《蘭州理工大學(xué)學(xué)報(bào)》2016年03期 　論文類(lèi)型：期刊論文

  更多相關(guān)文章： 灰狼優(yōu)化算法 函數(shù)優(yōu)化 群智能 混沌

【摘要】：針對(duì)灰狼優(yōu)化算法在求解連續(xù)函數(shù)優(yōu)化問(wèn)題時(shí)精度不高、易出現(xiàn)早熟收斂等缺陷,提出一種改進(jìn)的灰狼優(yōu)化算法.該算法在初始種群個(gè)體時(shí)采用混沌序列方法,為算法全局搜索的多樣性奠定基礎(chǔ).根據(jù)個(gè)體適應(yīng)度值將種群分為兩個(gè)子種群,分別執(zhí)行不同的搜索方式,以平衡算法的開(kāi)采能力和勘探能力.選取幾個(gè)標(biāo)準(zhǔn)測(cè)試函數(shù)對(duì)算法性能進(jìn)行測(cè)試,測(cè)試結(jié)果表明,與其他群智能優(yōu)化算法相比,該算法在求解精度和收斂速度方面均具有較強(qiáng)的競(jìng)爭(zhēng)力.
[Abstract]:Aiming at the shortcomings of grey wolf optimization algorithm in solving continuous function optimization problems, such as low precision and premature convergence, an improved grey wolf optimization algorithm is proposed, which uses chaotic sequence method in the initial population. According to the individual fitness value, the population is divided into two sub-populations, each of which performs different search methods. In order to balance the mining ability and exploration ability of the algorithm, several standard test functions are selected to test the performance of the algorithm. The test results show that the algorithm is compared with other swarm intelligence optimization algorithm. The algorithm is competitive in solving accuracy and convergence speed.
【作者單位】： 貴州民族大學(xué)人文科技學(xué)院;貴州財(cái)經(jīng)大學(xué)信息學(xué)院;
【基金】：貴州省科學(xué)技術(shù)基金(黔科合J字[2007]2204號(hào))
【分類(lèi)號(hào)】：TP18
【正文快照】： 工程應(yīng)用領(lǐng)域中的許多問(wèn)題可以轉(zhuǎn)化為求解一個(gè)連續(xù)函數(shù)優(yōu)化問(wèn)題,可描述為min f(x)s.t.li≤xi≤ui,i=1,2,…,d(1)式中:f(x)為目標(biāo)函數(shù),x=(x1,x2,…,xd)為d維決策變量,li和ui分別為變量xi的上界和下界.由于問(wèn)題(1)的復(fù)雜性,傳統(tǒng)優(yōu)化方法難以對(duì)其進(jìn)行有效的求解.群體智能優(yōu)化算法

【相似文獻(xiàn)】

相關(guān)期刊論文 前10條

1 任偉建;李瑩瑩;李文成;;基于函數(shù)優(yōu)化的生物智能進(jìn)化算法綜述[J];自動(dòng)化技術(shù)與應(yīng)用;2012年05期

2 陳明杰;黃佰川;張e，

本文編號(hào)：1363000