Abstract: It costs large quantity of time and tends to be trapped into local optimizing computation by using traditional ant colony algorithm of combinational optimization in the process of computing.Besides，it also causes much useless redundant iterated codes and leads to low efficiency.In order to solve these problems，an adaptive algorithm of combinatorial optimization is proposed in this paper.Through the ways of changing the iteration of pheromones，analyzing the selection of parameters and increasing the partial update modes of pheromones，the overall computing efficiency and convergence rate is enhanced and the scope of optimization is expanded.What’s more，it decreases the useless iterated codes and occurrence of stagnation the simulation experiment of the combinatorial optimization on Traveling Salesman Problem proves the feasibility and validity of this algorithm.