Finite Element Simulation Of Milling Process And Optimization Of Milling Parameters For Ti6Al4V Based On Deform-3D

Titanium alloy Ti6Al4 V is widely used in automobile,aviation and other important fields due to excellent mechanical properties,low density and good corrosion resistance.However,titanium alloy Ti6Al4 V has the characteristics of high temperature chemistry,small elastic modulus and low thermal conductivity,which makes the cutting process prone to problems such as high temperature,high energy consumption,too fast tool wear,and difficult to control the surface quality.It is a typical hard to process material.Therefore,in this study,a Gaussian process regression-Multiobjective particle swarm optimization(GPR-MOPSO)optimization model is proposed.With the help of DEFORM-3D finite element simulation technology,the data can be obtained to optimize the surface roughness and milling energy consumption per unit volume in titanium alloy milling process based on milling process parameters.The optimization model can provide an effective parameter control basis for maintaining quality stability and reducing energy consumption in milling process.Enchanted by the advantages of DEFORM-3D,such as reducing the cost of physical experiments,shortening the selection period of process parameters,this paper applies DEFORM-3D software to simulate the milling process of Ti6Al4 V and the finite element model of the process of milling titanium alloy with coated TiAlN cemented carbide tool is developed.In the simulation,the spindle speed,feed speed,milling width and milling depth are selected as milling parameters,and the surface roughness and energy consumption data of different parameter combinations are obtained.Compared with physical experiments,the validity of DEFORM-3D data acquisition is verified.Which provide reliable data source for the implementation of the multi-objective optimization model in the next step.In order to obtain a better surface roughness and reduce the energy consumption in the milling process,the Gaussian process regression model multi-objective particle swarm optimization model was constructed.Based on the data obtained from DEFORM-3D simulation,the prediction models of surface roughness and energy consumption were established by using Gaussian process regression,and the model of GPR-MOPSO optimization target was obtained.In order to improve the accuracy of the prediction model,the artificial bee colony optimization algorithm(ABC)was proposed to obtain the super parameters of GPR model.The MOPSO was used to optimize the GPR's optimization objective,and the Pareto solutions of machining parameters of titanium alloy Ti6Al4 V milling were obtained.The physical experiment of the Pareto solution was carried out to verify the validity of GPR-MOPSO model.