Abstract: The enactment of the parameters of an ant system is determined by experience and experiment.This leads to heavy work load and makes the optimal combination of the parameters difficult to obtain.On the basis of the ant algorithm and the result of the experiment，the effect by changing the parameters of α、β、ρ is discussed，and an improved scheme is proposed.Then both of the improved scheme and the ant algorithm are applied to the function optimization problem，and a comparison is made in the simulation.

摘要： 蚁群算法的参数设置一直是依靠经验和实验来确定，造成实验工作量大且难以得到最优的参数组合，影响了算法的使用。从基本蚂蚁算法出发，结合实验结果，讨论了α、β及ρ的变化对实验结果的影响，提出了相应的参数改进方案。并将经此方案修正的蚂蚁算法与基本蚂蚁算法同时运用于经典函数优化问题中，对仿真结果进行了对比。