一种求解约束优化问题的改进型免疫克隆算法  

AN IMPROVED IMMUNE CLONE ALGORITHM FOR SOLVING CONSTRAINED OPTIMISATION PROBLEM

作　　者：么焕民[1] 王杰楷[1] 梁宇[1] 

机构地区：[1]哈尔滨师范大学数学科学学院,黑龙江哈尔滨150025

出　　处：《计算机应用与软件》2014年第11期275-278,共4页Computer Applications and Software

基　　金：黑龙江省教育厅科技研究项目(12511155)

摘　　要：针对约束优化问题提出一种基于精英库机制的改进型免疫克隆优化算法ICOAEB(Immune clonal optimization algorithm based on elite bank)。该算法利用精英库机制动态存储迭代过程中父代优势个体,实现优秀个体的多代记忆,从而提高算法寻优能力;并利用灾变算子扰动算法运行过程从而摆脱迭代缓慢的状态,避免局部收敛。通过对五个约束优化函数的测试,实验结果表明ICOAEB的求解精度和稳定性较高,可以较好地解决约束优化问题。最后针对影响算法性能的两项重要参数选择问题给出了相关的实验及分析。We propose an improved immune clone optimisation algorithm which is based on elite bank mechanism（ ICOAEB） for constrained optimisation problem.This algorithm utilises the elite bank mechanism to dynamically store the superior individuals of father generation during the iteration process,implements the multi-generation memory of superior individuals,and thereby improves algorithm＇s optimisation ability.ICOAEB also uses the cataclysm operator to disturb the running process of the algorithm so as to get rid of the slow iteration state and to prevent local convergence of the algorithm.By testing five constrained optimisation functions,the experimental results show that the solution accuracy and stability of ICOAEB is higher,and it can well solve the constrained optimisation problem.Finally,correlated experiment results and analyses are given for the selection of two important parameters which can affect the performance of the algorithm.

关 键 词：约束优化 免疫克隆优化 精英库机制 灾变算子 局部收敛 参数选择 

分 类 号：TP3[自动化与计算机技术—计算机科学与技术]