Study On Thin Plate Machining Based Ongrey Correlation Theory And Genetic Algorithm

Due to its poor rigidity and high material removal,thin-walled parts are prone to deformation,instability and chattering during processing,which seriously affect the quality of the product.In addition,the lack of experience and theory is difficult in actual production.The development of reasonable process parameters can not give full play to the superior performance of the machine tool.In this paper,the layer cutting test of aluminum alloy sheet parts is taken as the carrier,and the deformation law and surface quality of the parts are deeply explored.The influence of milling factors on the processing quality is analyzed and the corresponding optimization scheme is proposed.The specific research work is as follows:Firstly,based on the principle of metal cutting,the milling force and residual stress which affect the processing quality of thin-walled parts are analyzed in detail.The stability in milling process is analyzed,and the natural mode and vibration mode distribution of the end milling cutter are obtained.The steady-state response of the end milling cutter under the excitation force is obtained by the harmonic response analysis.Secondly,the orthogonal milling experiment of thin plate was set up with the decision variables of axial depth,radial depth,feed per tooth and spindle speed.The data of deformation error and surface roughness of workpiece were obtained.Through the regression function of MATLAB,a prediction model between decision variables and surface roughness is constructed,and its validity is verified by variance analysis.Then,taking the maximum deformation and surface roughness of workpiece as the characteristic target,the grey correlation theory is used to analyze the correlation degree between the decision variables and the characteristic target.The results show that the feed per tooth has the greatest influence on the deformation,followed by the axial depth of cut,the radial depth of cut and the spindle speed.The feed per tooth and the radial depth of cut have the greatest influence on the surface roughness,and the axial cutting has the greatest influence on the surface roughness.Deep impact is minimal.Finally,with the ideal value of processing quality as reference sequence,the correlation coefficient matrix between each decision variable and the characteristic target is obtained,and the superiority level of each variable is optimized.Finally,by setting constraints on decision variables and selecting optimization targets,the overall model of thin-layer stratified milling parameters optimization is constructed.The genetic algorithm is combined with the artificial neural network to minimize the nonlinear deformation of the machining deformation.The NSGAII algorithm with elite strategy is used to optimize the multi-objectives composed of surface roughness and material removal rate,and the two are not dominated.The Pareto frontier solution set has been verified that the surface quality of the workpiece obtained by the optimized parameters is greatly improved compared with the previous processing efficiency,which can provide decision support for actual production.