一种求解约束优化问题的自适应差分进化算法  

An Adaptive Differential Evolution Algorithm for Constrained Optimization Problems

作　　者：閤大海[1] 李元香[1] 龚文引[2] 何国良[1] 

机构地区：[1]武汉大学软件工程国家重点实验室,武汉大学计算机学院,湖北武汉430072 [2]中国地质大学(武汉)计算机学院,湖北武汉430074

出　　处：《电子学报》2016年第10期2535-2542,共8页Acta Electronica Sinica

基　　金：国家重大仪器专项(No.2011YQ170065.4);国家自然科学基金(No.61573324)

摘　　要：自适应算子选择方式已被用于差分进化算法求解全局优化问题及多目标优化问题,然而在求解约束优化时难于为自适应算子选择方式找到一种方式来恰当分配信用.为此,本文提出了一种基于混合种群的自适应适应值方式来对约束优化问题中变异策略进行信用分配并采用概率匹配方法自适应选择差分变异策略,同时对算法变异缩放因子与交叉率进行自适应设置提高算法的成功率.实验结果表明算法在求解约束优化问题相比于CODEA/OED,ATMES,εBBO-dm,COMDE以及εDE算法有较高的收敛精度及收敛速度,同时验证了自适应方式的有效性.该算法可用于预报、质量控制、会计过程等科学和工程应用领域.The adaptive operator selection method is used to solve the global optimization problem and multi-objective optim ization problem of differential evolution algorithm. However,it is difficult to find a way to properly allocate credit for the adaptive operator selection in solving the constrained optim ization problem. In order to realize the adaptive strategy selection in differential evolution,we present a com bined population based adaptive fitness m ethod to achieve the credit assignm ent of m utate strategies for constrained optim ization problem s and use probability m atching m ethod to select the m utate strategy adaptively. And we also set the m utation scaling factor and the crossover rate adaptively to im prove the success rate of the algorithm. Experim ental results showthat the algorithm has higher accuracy and convergence speed com paring to CODEA / OED,ATMES,εBBO-dm,COMDE and εDE. We also test and verify the effectiveness of the adaptive method. The algorithm can be used in forecasting,quality control,accounting process,and other scientific and engineering applications.

关 键 词：约束优化 差分进化算法 自适应 信用分配 概率匹配 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]