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.
出处
《武汉理工大学学报》
CAS
CSCD
北大核心
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)
关键词
差分演化算法
模拟退火算法
自适应技术
differential evolution algorithm
simulated annealing algorithm
self-adaptation
