Method for optimizing injection molding process based on RBF (Radial Basis Function) neural network

Abstract

The invention provides a method for optimizing injection molding process based on RBF (Radial Basis Function) neural network. The method comprises the following steps: building a CAE (Computer Aided Engineering) analysis model and first injection molding parameters of an injection molding product; carrying out injection molding parameter optimization on the first injection molding parameters for at least one time to acquire first optimized injection molding parameters; carrying out orthogonal test design on the first injection molding parameters to acquire orthogonal test data; training the RBF neural network by using a part of or whole orthogonal test data to acquire trained RBF neural network; acquiring final optimized injection molding parameters by using the trained RBF neural network.According to the method for optimizing the injection molding process based on the RBF neural network disclosed by the invention, the acquisition efficiency of the final optimized parameters can be improved, an optimizing effect is good, the acquired final optimized injection molding parameters are more accurate, and an injection molding requirement can be met.

Description

technical field [0001] The invention relates to the field of injection molding technology, in particular to a method for optimizing injection molding technology based on RBF neural network. Background technique [0002] In injection molding, the final injection quality of the product is closely related to the mold structure, pouring method, injection molding process and material properties. The mold structure mainly affects the molding quality items such as appearance and shape, and the parameters and methods that can be adjusted are limited. It is mainly reflected in improving the appearance quality by modifying the molding surface of the mold and adjusting the waterway. The key factor that determines the quality of product injection molding is the pouring method. In the pouring method, the gate position and the number of gates are the core factors that affect the final injection molding quality. The gate form can adjust and compensate for the negative effects caused by imp...

AI Technical Summary

Problems solved by technology

[0003] However, only relying on CAE-assisted analysis still relies on the analyst's own experience to a high degree. According to experience, most of the injection molding defects of the product can be properly solved in the stage of mold trial and machine adjustment, but the biggest problem with experience mold trial is for the time of mold trial. Defects that are difficult to eliminate often require repeated mold trials. It is difficult to find the best molding process parameters, which is likely to cause large production waste and delay the mold production period. How to further improve the efficiency of mold design and the optimization effect of injection molding process? Poorness is an urgent problem to be solved

Images