Analysis And Parameter Optimization Of Stamping Forming Process For 7A09 Aluminum Alloy Based On Pretreatment

7A09 aluminum alloy belongs to ultra-high-strength aluminum alloys,which can be widely used in lightweight design in the fields of automobile and aerospace,but its poor plastic deformation ability is still a key problem in stamping production.In this thesis,the pretreatment process of 7A09 aluminum alloy is studied to improve the plastic deformation ability of the material in the stamping process.Based on the improved BP neural network,the surrogate model between the process parameters and the forming quality is established.Finally,the improved intelligent optimization algorithm is used to find the best parameter combination,and the reliability of the optimization results is verified by experiment.The main work is as follows.The effect of different solution treatment schemes on the mechanical properties of 7A09 aluminum alloy is analyzed by uniaxial tensile test,and the stress-strain relationship of the material is obtained.The best solution treatment scheme is selected according to the plastic deformation ability of the material.The Hockett-Sherby constitutive equation of 7A09 aluminum alloy after solution treatment is established.Taking bulging part as the research object,combined with finite element analysis and stamping experiments,it is proved that the established finite element model can effectively predict the fracture behavior of the material.In order to improve the prediction accuracy of BP neural network for stamping forming,an improved BP neural network model based on the restricted Boltzmann machine model is proposed,and the learning efficiency of the neural network is improved by combining momentum factor and adaptive learning rate.Through the multi-dimensional nonlinear test function,the improved BP neural network model is compared with several common surrogate models,and the effectiveness of the improved BP neural network model is proved.Taking TRIP780 high-strength steel forming part as the research object,the training samples of neural network are obtained by Latin hypercube sampling.Based on the improved BP neural network model,a surrogate model between process parameters and forming quality is established.The optimal process parameters are obtained by particle swarm optimization algorithm,which effectively improved the quality of TRIP780 high-strength steel forming part.Taking the pretreated 7A09 aluminum alloy double C part as the research object,based on the established constitutive model and the improved BP neural network,the maximum thinning rate and the percentage of thickening area are selected as the forming quality indicators,and a multi-objective optimization model is established.In order to improve the reliability of multi-objective particle swarm optimization for process parameter optimization,the individual optimal selection mechanism and overflow particle elimination rule of multiobjective particle swarm optimization are improved based on the crowding operator.Dynamic inertia weight and dynamic mutation probability are introduced to improve the iterative efficiency.Finally,the improved multi-objective particle swarm algorithm is used to obtain the best combination of stamping process parameters for 7A09 aluminum alloy double C part.Combined with finite element simulation analysis and stamping experiment,the reliability of the optimization result is proved.