In order to solve the problem that the traditional optimization parameters cannot be dynamically adjusted with the change of tool life in the milling process,resulting in the inability of the tool performance to be fully utilized,an adaptive optimization method of milling parameters was studied,and a dynamic milling parameter multi-objective optimization method based on the optimization gray wolf algorithm was proposed.The nonlinear mapping relationship between the milling parameters and the optimization target in the milling process was constructed by BP neural network;then the concept of tool life level was proposed,and the milling parameters within the life level were adaptively optimized by the particle swarm optimization gray wolf algorithm.The experimental results show that the method can provide the optimal milling parameter scheme during the entire tool life cycle according to the life decay degree of the tool,and carbon emissions is reduced while the use value of the tool is improved.