基于云模型的自学习进化算法  

Active Evolutionary Algorithm Based on Cloud Model

作　　者：赵志强[1] 缑锦[1] 陈维斌[1] 

机构地区：[1]华侨大学计算机科学与技术学院,福建厦门361021

出　　处：《北京交通大学学报》2009年第6期110-115,共6页JOURNAL OF BEIJING JIAOTONG UNIVERSITY

基　　金：国家自然科学基金资助项目(60573056);福建省自然科学基金资助项目(A0710013)

摘　　要：结合进化论和遗传理论的最新进展,提出基于学习算子的自学习进化算法;并将正态云模型引入进化过程中,提出云学习算子和基于云学习算子的自学习进化算法.最后的仿真实验表明,该算法具有精度高、收敛速度快等优点,能在很大程度上解决了现存进化算法的低效问题.A learn operator is proposed based on the analysis of the status in quo such as ignoring initiative of individual belonging to the current population and combined with the last word of evolutionism and genetics. The extension of the traditional evolutionary algorithms is made by adding this learn operator. The definition of active evolutionary algorithm is put forward. After imported the normal cloud in the procedure of evolutionary, the learn operator with cloud is defined and the active evolutionary algorithm based on cloud model is advanced. With some typical test functions, the results prove the high quality of the algorithm on precision, stability and convergence rate. It also indicated that this improved evolutionary can greatly overcome the shortcoming of low efficiency in traditional evolutionary algorithms.

关 键 词：云学习算子 学习算子 自学习进化算法 个体能动性 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]