基于模拟退火的自适应差分演化算法研究  

Research on Self-adaptive Differential Evolution Algorithm Based on Simulated Annealing

作　　者：苏清华[1,2] 胡中波[1] 张晓清[1] 

机构地区：[1]孝感学院数学系,孝感432000 [2]华中科技大学数学系,武汉430074

出　　处：《武汉理工大学学报》2009年第1期139-143,共5页Journal of Wuhan University of Technology

基　　金：国家自然科学基金(60572015);国家973重大基础研究专项(2004CCA02500)

摘　　要：基于模拟退火的自适应差分演化算法。通过模拟退火的更新策略来增强全局搜索能力,并提出了新的自适应技术来选择学习策略、确定算法的关键参数。数值实验及与同类算法的比较研究表明了该算法的有效性和优越性。According to the analysis for the two faults, this paper proposes a novel algorithm： self-adaptive differential evolution algorithm based on simulated annealing. With the aid of simulated annealing strategy, the proposed algorithm is able to improve the global search ability of conventional differential evolution algorithm. In the proposed algorithm, the choice of learning strategy and several critical control parameters are not required to be pre-specified. During evolution, the suitable learning strategy and parameters setting are gradually self-adapted according to the learning experience. Numerical experiments and comparative research expose the proposed algorithm as a competitive algorithm for the global optimization.

关 键 词：差分演化算法 模拟退火算法 自适应技术 

分 类 号：O231[理学—运筹学与控制论] TP18[理学—数学]