Multi-object optimization and decision algorithm of numerical control processing parameters

In order to improve the quality and production efficiency of NC turning of gasoline engine piston, a multi-objective optimization method based on non-dominated sorting differential evolution algorithm and a decision-making method based on weighted relative distance are proposed. Taking the surface roughness and material removal rate as the optimization parameters, a multi-objective optimization model was established. In view of the limited accuracy of the empirical formula of surface roughness and the unadaptability of different production equipment and process, the fitting method of learning factor adaptive neural network is proposed. The non-dominated sorting differential evolution algorithm is used to solve the multi-objective optimization model, and the Pareto frontier solution set is obtained. A decision-making method based on weighted relative distance is proposed, and the optimal production plan is obtained. After verification, compared with the current production plan, the surface roughness of the optimized workpiece is reduced by more than twice, and the material removal rate is increased by 57.98%. The above data fully prove the effectiveness of the optimization plan.