基于改进遗传算法的优化研究  

Research on Optimization of Genetic Algorithm

作　　者：罗江英[1] 陆韬[1] 

机构地区：[1]丽水学院计算机与信息工程学院,浙江丽水323000

出　　处：《西安文理学院学报（自然科学版）》2008年第2期40-42,共3页Journal of Xi’an University(Natural Science Edition)

摘　　要：遗传算法本身固有的并行处理性和开放性,使得它在优化识别方面的效率非常之高,而且受到越来越广泛的研究.然而,遗传算法自身也有一些缺点.遗传算法在寻优过程中易出现"早熟",设计变量增多时效率较低以及结构分析时间长.论文分析了遗传算法的常见缺陷,并通过采用小生境技术、基于多父体变量级别的杂交以及小生境技术的改进策略,遗传算法的优化性能(优化效率和质量)得到了大大的提高.The genetic algorithm＇s parallel processing and openness makes it highly efficient in the optimized recognition, moreover receives more and more extensive research. However, it also has some shortcomings. On the one hand, in the process of seeking the superior seeds, it may be easy to appear precociously, and with the increase of the design variable, the effectiveness is fairly lower, more time is spent. Through the improved strategy based on the niche technical and the multi-father body variable rank hybrid, the genetic algorithm optimized performance （optimized efficiency and quality） is greatly improved.

关 键 词：遗传算法 缺陷 改进 策略 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]