In order to realize the parameter selection of CNC real-time task in collaborative design mode,a task pa- rameter selection method on the basis of multi-objective optimization is proposed.In this method,a multi-objective optimization model is established according to real-time task model,performance objective as well as system con- straint,and the model is solved by means of an extended non-dominated sorting genetic algorithm with co-evolution operator and elite team retention mechanism,thus the speed of searching optimal task parameters in large-scale de- cision space improves,which promotes the overall performance of CNC system to achieve the optimum.Finally,the parameter selection strategy of CNC real-time task is summarized according to simulation results and the superiority of the proposed method in practical application is proved through a comparison with the traditional task parameter selection approach.