Optimization Of Injection Molding Process Parameters Of Shell Product

Injection molding is one of the widely used methods in plastic processing. The quality of injection molded parts is affected by the die structure, material properties, process parameters and environmental factors. In the actual production, because the molding process parameters on the quality of the products has a lot of nonlinear dynamic and uncertain factors, so through the optimization of the process parameters to improve the quality of injection molding products has always been a major difficulty in this field. According to the characteristics of injection molding process, the process parameters as the object of study, using CAE technology to injection molding process parameters optimization, there is very important significance to production to achieve the purpose of improve the quality of injection molding products.In this paper, a camera shell as the research object, mold temperature, melt temperature, injection time, injection pressure and cooling time as variables, product’s shrink mark index, volume shrinkage and warpage is used as the optimization index. Through the finite element software Moldflow, Taguchi experiment method, artificial neural network and genetic algorithm to optimize the product technical parameters. Improved the quality of the product and improved the production efficiency.This article first established in the ProE the three-dimensional model of molded parts, and finite element analysis model is established in the Moldflow. Gating system and cooling system is established and the reliability of the model was verified. Through the Moldflow numerical simulation the recommended process parameters. Got the plastic shrink mark index, volume shrinkage and the buckling deformation were2.965%,7.548%and0.4455mm. Then use the method of orthogonal experiment was carried out by orthogonal experiment design, and the results of the orthogonal experiment were analyzed by signal to noise ratio, the range analysis and variance analysis. After that three groups of the optimal process parameters combination are obtained. Results indicate that injection time and melt temperature on the effect of shrinkage mark index, volume shrinkage and warpage were significantly. The influence of injection pressure and mold temperature is slightly less. Cooling time has less effect on the index.For the multi-objective optimization problem of injection molded parts, set up the BP neural network model to describe the relationship between process parameters and quality index. The reliability and accuracy of the neural network model has been verified. And then use the genetic algorithm optimization neural network model. Under different weighting got four different sets of parameters optimization combination and the optimized parameters combination are simulated. By comparing the simulation values of recommended process parameters, optimum combination greatly improve the forming quality of injection molded part. The results show that: combined with the finite element analysis software Moldflow, the orthogonal test method, artificial neural network and genetic algorithm to optimize the product technical parameters is effective and feasible.