| GH4169 superalloy has been widely used in the manufacture of aero-engine blades due to its good material properties.However,due to its high plasticity and low thermal conductivity,it is difficult to guarantee the surface roughness and shape precision of the blades after machining.Multi-axis CNC belt grinding is a kind of flexible machining method,which can achieve a high surface integrity in the complex surface machining,so it is often used in the field of aero-engine blade precision processing.However,it is difficult to ensure the synergy of the accuracy of the blade surface roughness and shape at the same time.According to the above problem,this paper presents a GH4169 superalloy blade multi-axis CNC abrasive belt grinding process optimization and its experimental study.Through the experiment and modeling simulation match method,author explored the rule of multi-axis CNC abrasive belt grinding,and through the neural network algorithm,predicted the stability domain of the after grinding.The synergy of shape and property optimization model of nickel-based superalloy blade is established.The main research contents are as follows:(1)Study On Process Model And Parameter Optimization Of CNC Belt Grinding For Superalloy Blade.Firstly,based on the theory of surface forming and material removal in belt grinding,the process analysis of blade surface roughness and material removal rate after multi-axis synchronous CNC belt grinding was carried out,and the process parameter model was established.Then,based on nickel-based superalloy material,a typical belt grinding experimental platform was built to explore the relationship between process parameters,surface roughness and material removal rate.Finally,the grinding process parameters were optimized based on grey correlation theory.(2)Prediction Of Surface Roughness And Material Removal Rate In Belt Grinding Of Superalloy Materials.Firstly,the central training method of radial basis neural network was improved.The experimental data in Chapter 2 were used as training set and test set,and the grinding parameters were used as input to predict the surface roughness and material removal rate after grinding.Then,the prediction model of surface roughness and material removal rate suitable for nickel-based superalloy after belt grinding was obtained.Finally,the errors between the results of the two traditional prediction models and the experiment are compared respectively,and the results show that the improved RBF neural network has the best prediction accuracy,the maximum error of roughness is 9.5%,and the maximum error of material removal rate is 7%.(3)Study On Synergy Of Shape And Property Of Superalloy Blade Belt Grinding.Firstly,according to the machining requirements of GH4169 superalloy blades,a formality synergy model based on banker algorithm was proposed.Then,the banker algorithm is improved by discretization and priority setting.On the basis of the third chapter,the grinding process parameters were optimized and simulated by MATLAB and CNC abrasive belt grinding software.The simulation results show that this method can effectively carry out the collaborative optimization of shape.(4)Experimental Verification And Analysis Of Multi-axis CNC Grinding Process Optimization Of Superalloy Blades.Firstly,CNC belt grinding test platform for a certain type of aero-powered GH4169 superalloy blade was established.Then,the surface roughness and shape accuracy of the machined blades were measured,and the results were compared and analyzed.Finally,the effectiveness of the synergistic optimization method for blade shape was verified. |
PDF Full Text Request