• Journal of Korean Society for Quality Management
• /
• v.51 no.1
• /
• pp.55-65
• /
• 2023

Purpose: The purpose of this study is to propose an optimization process to improve product yield in the process using process data. Recently, research for low-cost and high-efficiency production in the manufacturing process using machine learning or deep learning has continued. Therefore, this study derives major variables that affect product defects in the manufacturing process using eXplainable Artificial Intelligence(XAI) method. After that, the optimal range of the variables is presented to propose a methodology for improving product yield. Methods: This study is conducted using the injection molding machine AI dataset released on the Korea AI Manufacturing Platform(KAMP) organized by KAIST. Using the XAI-based SHAP method, major variables affecting product defects are extracted from each process data. XGBoost and LightGBM were used as learning algorithms, 5-6 variables are extracted as the main process variables for the injection process. Subsequently, the optimal control range of each process variable is presented using the ICE method. Finally, the product yield improvement methodology of this study is proposed through a validation process using Test Data. Results: The results of this study are as follows. In the injection process data, it was confirmed that XGBoost had an improvement defect rate of 0.21% and LightGBM had an improvement defect rate of 0.29%, which were improved by 0.79%p and 0.71%p, respectively, compared to the existing defect rate of 1.00%. Conclusion: This study is a case study. A research methodology was proposed in the injection process, and it was confirmed that the product yield was improved through verification.

• Journal of Powder Materials
• /
• v.22 no.1
• /
• pp.1-5
• /
• 2015

Powder injection molding is an important manufacturing technology to mass produce superalloy components with complex shape. Injection molding step is particularly important for realizing a desired shape, which requires much time and efforts finding the optimum process condition. Therefore computer aided engineering can be very useful to find proper injection molding conditions. In this study, we have conducted a finite element method based simulation for the spiral mold test of superalloy feedstock and compared the results with experimental ones. Sensitivity analysis with both of simulation and experiment reveals that the melt temperature of superalloy feedstock is the most important factor for the full filling of mold cavity. The FEM based simulation matches well the experimental results. This study contributes to the optimization of superalloy powder injection molding process.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.20 no.5
• /
• pp.659-665
• /
• 2011

Recently, the plastic resin such as PC, ABS are widely used in IT market. Especially, in most cases the keypads mounted on the mobile phone are the dual-injection-plated type. Environmental regulation is based on the quality of injection-molded products and the minimum process steps are required to avoid the plating defects. Various parameters to produce the injection-molded plastic products make it difficult to obtain the desired stability. However, the past experience and the use of CAE analysis make it possible to predict the problems occurred in injection molding process. Especially, the problems of the weld lines such as runner balancing, bending, deformation and forming defects can be solved systematically and minimized by CAE analysis. Through this study, the non-uniform volumetric shrinkage and the difference in temperature distribution induce the deformation and the high value of stress causes the problems such as crack.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2002.02a
• /
• pp.103-108
• /
• 2002

The gas injection molding technique(GIT) is a special injection molding process and has been an established and acknowledged process technique for many years. GIT has proved successful in cases where warpage has to be minimized, sink marks avoided and material input reduced. The classic field of application for GIT, however, is the production of thick-walled, rod shaped parts or hollow articles. Through this application, the handle part for automobile is molded and this part is consequently used as a insert for the additional injection molding process encapsulated with PVC.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.1
• /
• pp.1-6
• /
• 2021

In this study, we investigate the injection molding of f-theta lens, an important element of the laser scanning unit of laser printers and scanning systems. The f-theta lens is an aspherical plastic lens that must be molded with a precision of seconds. An injection molding method is often used for mass producing aspherical plastic lenses at a low cost. In the injection molding process, costs related to forming and injection are included. Therefore, in this study, to determine the shrinkage and deformation of injection molded f-theta lens, we predict the pressure and temperature distributions. Further, based on the analysis of the predictions, we maximize the design efficiency and verify the cost and development period reduction.

• Journal of computational fluids engineering
• /
• v.18 no.3
• /
• pp.20-25
• /
• 2013

In various manufacturing industries, an in-mold decoration (IMD) process for plastic objects is widely utilized because a film forming and an injection molding processes run simultaneously. In the present study, the deformation of polymer film and filling of resin in the IMD process were numerically investigated to evaluate the quality of the plastic object formed by the IMD process, which consists of thermoforming and injection molding processes. To obtain the initial shape of the polymer film during the injection molding process, the deformation of the polymer film in the thermoforming process was pre-formed using the vacuum conditions to attach the film to a cavity. Since the properties and deformation of polymer film are greatly affected by the behavior of polymer resin being injected into a mold cavity, numerical simulations for the injection molding and film forming were performed with one-way coupling method. The results showed that the injected resin could lead to the tearing of the polymer film in local regions near the corners. In order to verify the proposed numerical methodology, the numerical results of the deformation patterns printed on the initial polymer film were compared with the experimental data. The proposed methodology to couple film forming analysis with injection molding analysis can be used to predict the deformation of film in IMD process.

• Design & Manufacturing
• /
• v.17 no.4
• /
• pp.72-78
• /
• 2023

Injection molding is a process widely used in various industries because of its high production speed and ease of mass production during the plastic manufacturing process, and the product is molded by injecting molten plastic into the mold at high speed and pressure. Since process conditions such as resin and mold temperature mutually affect the process and the quality of the molded product, it is difficult to accurately predict quality through mathematical or statistical methods. Recently, studies to predict the quality of injection molded products by applying artificial neural networks, which are known to be very useful for analyzing nonlinear types of problems, are actively underway. In this study, structural optimization of neural networks was conducted by applying multi-task learning techniques according to the characteristics of the input and output parameters of the artificial neural network. A structure reflecting the characteristics of each process step was applied to the input parameters, and a structure reflecting the quality characteristics of the injection molded part was applied to the output parameters using multi-tasking learning. Building an artificial neural network to predict the three qualities (mass, diameter, height) of injection-molded product under six process conditions (melt temperature, mold temperature, injection speed, packing pressure, pacing time, cooling time) and comparing its performance with the existing neural network, we observed enhancements in prediction accuracy for mass, diameter, and height by approximately 69.38%, 24.87%, and 39.87%, respectively.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.17 no.6
• /
• pp.1465-1477
• /
• 1993

Powder Injection Molding(PM) is an advanced and complicated technology for manufacturing ceramic or metal products making use of a conventional injection molding process, which is generally used for plastic products. Among many technologies involved in the successful PIM, injection molding process is one of the key steps to form a desired shape out of powder/binder mixtures. Thus, it is of great importance to have a numerical tool to predict the powder injection molding filling process. In this regard, a finite element analysis system has been developed for numerical simulations of filling process of powder injection molding. Powder/polymer mixtures during the filling pro cess of injection molding can be rheologically characterized as Non-Newtonian fluids with a so called yield phenomena and have a peculiar feature of apparent slip phenomena on the wall boundaries surrounding mold cavity. Therefore, in the present study, a physical modeling of the filling process of powder/polymer mixtures was developed to take into account both the yield stress and slip phenomena and a finite element formulation was developed accordingly. The numerical analysis scheme for filling simulation is accomplished by combining a finite element method with control volume technique to simulate the movement of flow front and a finite difference method to calculate the temperature distribution. The present study presents the modeling, numerical scheme and some numerical analysis results showing the effect of the yield stress and slip phenomena.

• Journal of the Korean Society of Manufacturing Technology Engineers
• /
• v.21 no.4
• /
• pp.593-600
• /
• 2012

Thixomolding of Mg-alloy is a semi-solid injection molding process utilizing thixotropic phenomenon. Using this process, higher strength, thinner wall section and tighter tolerance without porosity are obtained. It has been applied for production of near-net-shape magnesium component. To design optimal thixomolding process of Mg-alloy part, molding conditions such as slurry temperature, mold temperature and injection time should be determined properly. Selection of these parameters has been dependent upon engineers' experience and intuitiveness. In this paper, to improve mechanical properties of the thixomolded product, optimal selection of process variables such as injection velocity, barrel temperature and die temperature in the process has been studied through microstructural analysis and Taguchi method. Performance of the process is verified through experiments.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.13 no.4
• /
• pp.21-27
• /
• 2014

The injection molding process has several advantages enabling it to produce large quantities of molded plastic products using a repetitive process. In recent years, it has been necessary to develop an injection molding process with micro/nano-sized patterns for application to the semiconductor industry and to the bio/nano manufacturing industry. In this study, we apply gas pressure to the inside of a mold and consider the gas dissolution phenomenon for a resin filling into a micro pattern with a line structure. Using numerical analysis, we calculate the filling ratio with respect to time for various internal gas pressures and various aspect ratios of the micro-patterns.