The design of high speed and ultra high speed grinding process determines the integrity and machining efficiency of the workpiece surface.Multi-objective optimization method provides a variety of choices for the design of process parameters by fixing the objective models and the constraint decision variables.This paper's main contents and achievements are as follows:(1)The basic theory of multi-objective optimization algorithm is discussed.This paper makes studies on gamultiobj function which is based on NSGA-?,such as the crowding distance,density estimation,constraint handling and main flow and so on.(2)In order to make decision-makers meet optimization results,The optimization algorithm,kernel principal component analysis and hybrid population inversion algorithm is applied to Inversion for critical decision variable and the inversion of decision variables to meet the needs of decision maker parameter design.(3)The optimization algorithm,kernel principal component analysis and hybrid population inversion(gamultiobj-KPCA-MPGA)algorithm are proposed.The fusion algorithm is applied to the actual grinding process parameters inversion,and compared with other inversion methods to verify the superiority of the method.(4)In order to facilitate the decision maker to obtain the inversion results,we use the assembly language of C#,MATLAB and database to develop the multi-objective optimization software.The feasibility and reliability of the software are verified by the experimental samples obtained by the high speed grinding,and able to preferably solve multi-objective optimization problems. |