| 引用本文: | 刘若辰, 贾建, 赵梦玲, 焦李成.一种免疫记忆动态克隆策略算法[J].控制理论与应用,2007,24(5):777~784.[点击复制] |
| LIU Ruo-chen, JIA Jian, ZHAO Meng-ling, JIAO Li-cheng.An immune memory dynamic clonal strategy algorithm[J].Control Theory and Technology,2007,24(5):777~784.[点击复制] |
|
| 一种免疫记忆动态克隆策略算法 |
| An immune memory dynamic clonal strategy algorithm |
| 摘要点击 1738 全文点击 1814 投稿时间：2004-08-25 修订日期：2007-05-22 |
| 查看全文 查看/发表评论 下载PDF阅读器 |
| DOI编号 10.7641/j.issn.1000-8152.2007.5.016 |
| 2007,24(5):777-784 |
| 中文关键词 人工免疫系统 克隆选择理论 免疫记忆 货郎担问题 |
| 英文关键词 artificial immune system clonal selection theory immune memory traveling salesman problem |
| 基金项目 国家“863”计划资助项目(2006AA01Z107); 国家重点基础研究发展计划资助项目(2006CB705700). |
|
| 中文摘要 |
| 基于对克隆选择及免疫记忆动态过程的模拟, 本文提出了一种人工智能算法, 免疫记忆动态克隆策略算法,该算法模拟免疫系统的自我调节、记忆学习、自适应等机制, 实现全局优化计算与局部优化计算机制的有机的结合, 通过抗体与抗原的亲合度和抗体间亲合度的计算, 促进和抑制抗体的产生, 自适应地调节抗体群和记忆单元的克隆规模. 理论分析证明该算法以概率1收敛, 对多峰函数优化及货郎担问题的仿真试验表明, 算法有效, 而且具有全局搜索能力强, 种群多样性好及收敛速度快等特点. |
| 英文摘要 |
| Based on the clonal selection theory and immune memory mechanism in the natural immune system, a novel artificial immune system algorithm, immune memory dynamic clonal strategy algorithm(IMDCS) is proposed in this paper. By simulating the mechanisms of natural immune system such as self-adjusting, memory learning and adaptation, the algorithm realizes the global optimal computation combined with the local searching. According to the antibody-antibody affinity and antibody-antigen affinity, the algorithm can also allot adaptively the scales of the immune memory unit and antibody population. The IMDCS is proved theoretically to be convergent with probability 1. In the computer simulations of a 4 multimodal function problem and a two traveling salesman problem, it is shown that IMDCS has strong abilities in preserving high convergence rate, enhancing the diversity of the population and avoiding the premature convergence. |
|
|
|
|
|