scholarly journals Novel Analysis Methodology of Cavity Pressure Profiles in Injection-Molding Processes Using Interpretation of Machine Learning Model

Polymers ◽  
2021 ◽  
Vol 13 (19) ◽  
pp. 3297
Author(s):  
Jinsu Gim ◽  
Byungohk Rhee

The cavity pressure profile representing the effective molding condition in a cavity is closely related to part quality. Analysis of the effect of the cavity pressure profile on quality requires prior knowledge and understanding of the injection-molding process and polymer materials. In this work, an analysis methodology to examine the effect of the cavity pressure profile on part quality is proposed. The methodology uses the interpretation of a neural network as a metamodel representing the relationship between the cavity pressure profile and the part weight as a quality index. The process state points (PSPs) extracted from the cavity pressure profile were used as the input features of the model. The overall impact of the features on the part weight and the contribution of them on a specific sample clarify the influence of the cavity pressure profile on the part weight. The effect of the process parameters on the part weight and the PSPs supported the validity of the methodology. The influential features and impacts analyzed using this methodology can be employed to set the target points and bounds of the monitoring window, and the contribution of each feature can be used to optimize the injection-molding process.

2014 ◽  
Author(s):  
Catalin Fetecau ◽  
Felicia Stan ◽  
Laurentiu I. Sandu

This paper focuses on the in-mold monitoring of temperature and cavity pressure. The melt contact temperature and the cavity pressure along the flow path were directly measured using two pressure sensors and two temperature sensors fitted into the cavity of a spiral mold. Three melt temperatures and dies of different heights (1.0, 1.5 and 2 mm) were used to achieve a wide range of practically relevant shear rates. In order to analyze the extent to which the numerical simulation can predict the behavior of the molten polymer during the injection molding process, molding experiments were simulated using the Moldflow software and the simulation results were compared with the experimental data under the same injection molding conditions.


2020 ◽  
Vol 40 (10) ◽  
pp. 876-885
Author(s):  
Ming-Shyan Huang ◽  
Shih-Chih Nian

AbstractQuality consistency is essential in maximizing the productivity rate of the injection molding process and minimizing the production cost. The quality consistency problem is particularly acute in the case of injection molding processes performed using regrind resin, for which the rheological properties are less uniform and more unpredictable than those of virgin material. Accordingly, the present study proposes a two-stage approach for optimizing the injection molding process parameters in such a way as to achieve a consistent molding quality over repeated injection molding cycles. In the first stage, the values of the injection speed/pressure, velocity-to-pressure (V/P) switchover point, and packing pressure are individually determined based on an inspection of the cavity pressure profile and machine parameters provided by the injection molding machine controller. In the second stage, a robust parametric search method based on a first-order regression model is employed to determine the optimal combination of the process parameter settings. Using an Integrated Circuit (IC) tray fabricated from regrind resin for illustration purposes, the results confirm that the proposed method overcomes the problem of small variations in the melt quality and therefore provides an effective technique for improving the yield rate and quality of the continuous mass production.


1999 ◽  
Author(s):  
David C. Angstadt ◽  
John P. Coulter

Abstract Extensive research has been conducted in an attempt to develop reliable models or indicators for determining product quality based on process information. Relationships between part quality and process variables such as nozzle temperature, hydraulic pressure and cavity pressure have been established using methods such as statistical process control, regression analysis and artificial neural networks. Ideally, these models would be used to determine part quality without direct inspection. If a level of confidence equivalent to that obtained by traditional methods (e.g., SQC) could be achieved, “quality by inspection” could be eliminated. Two drawbacks to these models are that they are specific to the machine/mold/polymer (M/M/P) combination being studied and they require a significant amount of “up-front” process data for model formulation. A method for “normalizing” pressure data obtained from a range of machine/mold/polymer configurations to yield essentially one curve or attribute denoting acceptable part quality would greatly enhance the utility of P-t data in a manufacturing setting. The objective of the present research is to examine the effects on the temporal cavity pressure due to changes in the mold geometry and to investigate methods for obtaining generic pressure data for various geometries. Cavity pressure data was collected using geometric inserts fitted into a standard ASTM tensile specimen cavity. The pressure data was analyzed to determine the correlation between cavity pressure and part quality for three part geometries studied. A discussion of the utility of the pressure is presented and an attempt is made to find a geometry independent cavity pressure attribute for use in determining part quality.


2000 ◽  
Author(s):  
James T. Wang

Abstract In the co-injection molding process, two (or more) different polymers are injected into the cavity simultaneously or sequentially. Different properties of these two polymers and their distribution in the cavity greatly affect the applications of this molding process. The skin layer can use special polymers to provide good appearance and texture, strength, chemical resistance, EMI shielding and other functions. The core layer can use recycled or inexpensive materials. Together these can improve part quality and lower the cost. However, due to the dynamic interaction of two polymers in the manufacturing process and their difference in properties, process control becomes more complicated and process design becomes a challenge. The rules used for the traditional injection molding process design may not always be useful for co-injection molding any more. An integrated CAE software has been developed to simulate the co-injection molding process. In this study, the capability and usefulness of the CAE tool will be shown. The control of polymer distribution will be discussed. The effects of polymer properties and their distribution on part quality will also be studied.


2013 ◽  
Vol 135 (1) ◽  
Author(s):  
Eunyoung Chang ◽  
Seungwon Shin ◽  
Haseung Chung

Injection molding process is a widely used manufacturing technique to massively produce the components of mobile device with various sizes and complicated geometries. However, the final part quality, especially dimension or geometry, referring to the original design specifications is not often acceptable due to various reasons. This study aims at developing the numerical model to predict the final part quality and subsequently identifying the critical reasons for existing problems. moldflow and abaqus software have been simultaneously used to simulate the injection molding process and thermal deformation arising after ejection step from the mold. In order to validate the model, the deformation predicted by the developed model was compared with experimental results, and both results showed good agreement. We also carried out design of experiment (DOE) to investigate the effect of various processing parameters that affect the final deformation of injection molded product. The developed model and information derived from DOE are expected to provide useful resources to the initial stage of mobile device design.


2013 ◽  
Vol 535-536 ◽  
pp. 430-433
Author(s):  
Chul Woo Park ◽  
Seong Ho Seo

Injection molding process one of the most important methods to produce plastic parts with high efficiency and low cost. Today, Injection molded parts have been increased dramatically the demand for high strength and quality applications. In this study, truck brake pedal is made of Cast iron and plastic materials to replace the frame for the optimization process that minimizes the runner and the gate dimension will determine the size and shape. Runner and gate dimensions of change based on availability of the product. I will discuss the injection molding. This report investigates that the optimum injection molding condition for minimum of runner and gate position. The FEM Simulation CAE tool, MOLDFLOW, is used for the analysis of injection molding process.


Sign in / Sign up

Export Citation Format

Share Document