Injection molding process parameter optimization method for transparent complex multi-cavity plastic part

Abstract

The invention discloses an injection molding process parameter optimization method for a transparent complex multi-cavity plastic part. The method comprises the steps that firstly, orthogonal test design is conducted based on a CAE simulation result, and main factors influencing buckling deformation are screened out; secondly, nonlinear function relationships between main factors of Kriging modelmapping and an optimization target are established based on different correlation functions, and the Kriging model with the highest precision is selected as a relationship model reflecting a design variable and buckling deformation; different optimization algorithms are adopted for optimization respectively, optimal injection molding process parameter combinations are obtained respectively, and the optimal injection molding process parameter with the minimum error is selected as the process parameter combination with the minimum buckling deformation. According to the optimization method, buckling deformation of the transparent complex multi-cavity plastic part can be effectively reduced, and the optimization method is particularly suitable for optimizing injection molding process parameters of the transparent complex multi-cavity plastic part on the basis of a one-mold multi-cavity technology for forming a plurality of different plastic part products through one mold.

Description

technical field [0001] The invention relates to an injection molding process parameter optimization method, in particular to a Kriging model-based injection molding process parameter optimization method for molding a plurality of different kinds of transparent and complex multi-cavity plastic products, and belongs to the technical field of injection molding processing. Background technique [0002] Injection molding is a multi-parameter, strongly coupled, complex nonlinear system whose input is the performance parameters of polymer materials, mold design parameters, and molding process parameters, and whose output is the utilization rate of polymer materials, injection molding efficiency, and molded product quality. evolutionary process. Compared with ordinary plastic products, transparent plastic products will be affected by birefringence, residual stress, and haze, and have high requirements for product quality. Product attributes, mold structure and injection molding pro...

AI Technical Summary

Problems solved by technology

In the prior art, researchers mostly use polynomial response surface model and neural network model to establish the functional relationship between process parameters and warpage deformation. The polynomial response surface model has the advantage of being easy to construct, but its accuracy is low, while the neural network model although It has high fitting accuracy for nonlinear problems, but requires a large number of sample points to ensure accuracy

Through sample training, the Kriging surrogate model can obtain high fitting accuracy. However, the key to the construction of the Kriging model is the determination of relevant model parameters. Existing studies mostly use the maximum likelihood estimation method to determine the relevant model parameters, which makes the initial value It becomes very difficult to choose

Images