Method for multi-objective quality comprehensive evaluation optimization of injection molding technology

Abstract

The invention relates to the technical field of injection molding and especially relates to a method for multi-objective quality comprehensive evaluation optimization of an injection molding technology. The method comprises the steps that response data of each quality index is obtained through combination of an orthogonal experiment method and mold flow analysis software Moldflow; then, by a variation coefficient method, the weight of each quality index in comprehensive evaluation quality is determined; secondly, a technique for order preference by similarity to an ideal solution is used to compute a relative similarity degree between each sample point and an ideal sample point; experimental sequence sequencing is conducted, wherein the priority is higher with the larger relative similarity degree; and then, a relative similarity mean and a range of each factor level are computed, and an influence tendency picture of the relative similarity means and factor levels is drawn, so factor main effects can be obtained. In this way, an optimal technological parameter combination with consideration of multi-objective quality can be obtained.

Description

technical field [0001] The present invention relates to the field of optimization of injection molding process parameters of electronic connectors, and specifically relates to how to find the best combination of molding process parameters while taking into account multi-objective quality from among numerous quality index influencing factors. method. Background technique [0002] Injection molding is a relatively mature technology among many molding technologies, but with the rapid development of the current electronic industry, higher requirements are put forward for the quality and performance of products. The strict requirements of high quality, high performance and high precision have seriously affected the rapid development of the electronics industry. [0003] Injection molding is a highly complex non-linear, variable, non-isothermal, non-steady-state molding process. Factors affecting molding quality mainly include: material, plastic part structure, mold structure an...

AI Technical Summary

Problems solved by technology

The learning speed of the BP neural network is slow, and it is difficult to solve the contradiction between the network scale and the instance scale of the application problem. There is no unified theoretical guidance for the selection of the network structure, which is generally determined by experience, and sometimes with the improvement of training ability, Predictive ability is reduced

Images