基于牛顿三次插值的自适应差分进化算法  

Adaptive differential evolution algorithm based on Newton cubic interpolation

作　　者：陈恩茂 徐志刚[2,3] 付源 CHEN En-mao;XU Zhi-gang;FU Yuan(School of Mechanical Engineering and Automation,Northeastern University,Shenyang 110819,China;Shenyang Institute of Automation,Chinese Academy of Sciences,Shenyang 110016,China;Institutes for Robotics and Intelligent Manufacturing,Chinese Academy of Sciences,Shenyang 110169,China;School of Mechanical and Transportation Engineering,Hunan University,Changsha 410082,China)

机构地区：[1]东北大学机械工程与自动化学院,辽宁沈阳110819 [2]中国科学院沈阳自动化研究所,辽宁沈阳110016 [3]中国科学院机器人与智能制造创新研究院,辽宁沈阳110169 [4]湖南大学机械与运载工程学院,湖南长沙410082

出　　处：《计算机工程与设计》2020年第8期2170-2176,共7页Computer Engineering and Design

基　　金：沈阳市双百工程基金项目(Z17-7-002)。

摘　　要：针对差分进化算法易早熟、对参数设置敏感的问题,提出一种基于牛顿三次插值的自适应差分进化算法。运用牛顿三次插值在最优个体附近进行局部搜索,提高算法的搜索速度;设计自适应论证策略评估是否在下一代中使用牛顿三次插值来避免算法早熟;缩放因子F和交叉概率CR均采用自适应学习策略不断更新,避免人为设置参数。采用CEC2013测试集上的28个基准函数进行测试,测试结果表明,对于大部分基准函数,该算法性能均优于其它改进DE算法。Aiming at the problems that the differential evolution algorithm is easy to premature and is sensitive to parameter setting,an adaptive differential evolution algorithm based on Newton cubic interpolation was proposed.Newton cubic interpolation was used to perform local search near the optimal individual,the search speed of the algorithm was improved.At the same time,an adaptive argumentation strategy was designed to evaluate whether Newton cubic interpolation was used in the next generation to avoid premature algorithm.Both the scaling factor F and the crossover probability CR were continuously updated using an adaptive learning strategy to avoid artificially setting parameters.The test was carried out using 28 benchmark functions on the CEC2013 test set.The results show that for most benchmark functions,the performance of the algorithm is better than that of other improved DE algorithms.

关 键 词：差分进化算法 牛顿三次插值 最优个体 局部搜索 自适应论证策略 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]