基于自识别交叉算子和自适应变异算子的遗传算法研究  

A Genetic Algorithm Based on Self-identify Crossover and Adaptive Mutation Operators

作　　者：孙秀娟[1] 刘希玉[2] 李丽丽[1] 

机构地区：[1]山东师范大学信息科学与工程学院,山东济南250014 [2]山东师范大学管理学院,山东济南250014

出　　处：《信息技术与信息化》2008年第1期55-57,共3页Information Technology and Informatization

基　　金："泰山学者"建设工程专项经费资助;山东省自然科学基金重大项目(编号:Z2004G02);山东省中青年科学家奖励基金资助项目(编号:03BS003);山东教育厅科技计划项目(编号:J05G01)

摘　　要：为有效地解决遗传算法收敛速度和局部最优解的矛盾,本文提出了一种具有自识别交叉算子和基于海明距离的动态变异算子的遗传算法。自识别交叉算子保证父代的优良模式遗传到下一代,加快了算法的收敛速度;而动态变异算子扩大了搜索范围,增强了算法跳离局部最优解的能力。实验证明,两种改进算子的有效结合保证算法能以较快速度收敛于全局最优解。In order to solve the conflict between algorithm convergence and the best local answer effectively, the paper puts forward an improved genetic algorithm with a self - identify crossover operator and a mutation operator based on Haiming Distance. The crossover operator speeds up the convergence rate by giving fine pattern heredity of the father generation to next generation, Dynamic mutation operator can expand searching scope and enhance the capability of the algorithm to avoid approaching the best local solution. The experimental result indicates that the algorithm with the effective combination of both improved operators can converge to the best answer at higher speed.

关 键 词：遗传算法 自识别交叉算子 自适应变异算子 海明距离 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]