免疫算法

The Immune Algorithm

本文在分析标准遗传算法的优越性与存在不足的基础上 ,借鉴生命科学中免疫的概念与理论 ,提出了一种新的算法———免疫算法 .该算法的核心在于免疫算子的构造 ,而免疫算子又是通过接种疫苗和免疫选择两个步骤来完成的 .理论证明免疫算法是收敛的 ,并结合TSP问题 ,提出了免疫疫苗的选取与免疫算子的构造方法 .最后 ,用免疫算法对 75城市的TSP问题进行了仿真计算 ,并将其计算过程与标准遗传算法进行了对比 ,结果表明该算法对减轻遗传算法后期的波动现象具有明显的效果 ,同时使收敛的速度有较大的提高 .

Based on analyses of GA′s properties,a novel algorithm,the immune algorithm—IA ,is proposed with analogies to the concept and the theory of immunity in biotic science.The core of the algorithm lies on constructing the immune operator that is realized by vaccination and immune selection.IA is approved theoretically con vergent.The strategies and the methods of selecting and constructing a vaccine for TSP are given in this paper.A simulation test of 75-city TSP is done with IA,and its computational process is compared with that of canonical genetic algo rithms.The results show that IA can evidently alleviate the undulate phenomenon at the end of the evolutionary process,therefore increases the convergent speed.