基于遗传算法的智能蚁群算法优化设计  

Design of Intelligent Ant Colony Optimization Based on Genetic Algorithm

作　　者：胡明[1] 蔡传军 童绪军 HU Ming;CAI Chuanjun;TONG Xujun(Anhui Medical College,Hefei 230001,China)

机构地区：[1]安徽医学高等专科学校,合肥230001

出　　处：《景德镇学院学报》2023年第6期16-20,共5页Journal of JingDeZhen University

基　　金：安徽省教学改革项目(2021jyxm0747);安徽省高校优秀青年骨干教师国内访问研修项目(gxgnfx2022116);安徽省虚拟仿真实训基地项目(2022xnfzjd012)。

摘　　要：为提升蚁群算法的寻优求解能力,文章使用Logistic函数对遗传算法进行了优化。在优化后的遗传算法中,对蚁群进行了交叉和变异操作,以实现蚁群算法的智能优化。为验证改进算法的性能,选择了100个城市进行寻优测试。实验结果表明,在采用遗传算法优化后,该方法使种群平均适应度得到了较好的提升。在寻优求解过程中,蚁群算法中蚂蚁信息素的分布密集浓度明显增加,具备较好的收敛性。同时,在相同迭代次数下,该方法获得的寻优路径也最短,具有较为显著的应用效果。To improve the optimization and solving ability of Ant Colony Algorithm,this article uses Logistic function to optimize Genetic Algorithm,and uses the optimized Genetic Algorithm to perform crossover and mutation operations on the ant colony during optimization,achieving intelligent optimization of Ant Colony Algorithm.To verify the performance of the improved algorithm,100 cities were selected as experimental subjects for problem optimization testing.The experimental results show that after using Genetic Algorithm optimization,the method has a good improvement in the average fitness of its population.In the optimization solution,the Ant Colony Algorithm has a significant increase in dense concentration of ant pheromone distribution,and has good convergence.At the same iterations,the optimization path obtained by this method is the shortest,which has a significant application effect.

关 键 词：遗传算法 蚁群算法 交叉变异 遗传算子 

分 类 号：TB4724[一般工业技术—工业设计]