The effects of three cutting parameters, such as feed rate, cutting speed and axial depth of cut, on the surface roughness of the workpiece and the vibration amplitude of the tool were studied experimentally.The end milling test for 6061 aluminum workpiecewas carried out by BBD response surface method, and the experimental results were analyzed by mathematical modeling. A multiobjective optimization method based on genetic algorithm was proposed to reduce the surface roughness and tool vibration amplitude. A radial basis neural network model for predicting surface roughness and tool vibration was established and its accuracy was verified by experiments.