Abstract: Ant colony algorithm is a novel category of bionic parallel and intelligence system.It has many promising futures.However it has some shortcomings such as needing much time and easier occurring of stagnation behavior.This paper basis of converse ants algorithm use adapt adjust information element hangover coefficient，the ability of searching for global optimal solution can be improved.The algorithm can solve the traveling salesman problem，the results show that the ability of optimization and convergence speed have improved.

Key words: ant colony algorithm, traveling salesman problem, combinatorial optimization, converse ant algorithm

摘要： 蚁群算法是近几年优化领域中新出现的一种启发式仿生并行智能进化系统。它具有很多优良的性质，但同时也存在一些缺点，如运算过程中收敛速度慢，易出现停滞现象等。基于上述不足提出了一种自适应地调整挥发系数的逆向蚁群算法，在逆向蚁群算法的基础上自适应调整挥发系数ρ，提高了算法的性能，使算法比传统蚁群算法相比不仅更有利于全局寻优而且对其收敛速度有了很大地提高。将该算法用于旅行商问题，模拟计算结果显示该算法具有更强的全局最优解搜索能力，收敛速度上也有很大提高。

关键词: 蚁群算法, 旅行商问题, 组合优化, 逆向蚁群算法