• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.45 no.4
• /
• pp.233-239
• /
• 2022

The injection molding process is a process in which thermoplastic resin is heated and made into a fluid state, injected under pressure into the cavity of a mold, and then cooled in the mold to produce a product identical to the shape of the cavity of the mold. It is a process that enables mass production and complex shapes, and various factors such as resin temperature, mold temperature, injection speed, and pressure affect product quality. In the data collected at the manufacturing site, there is a lot of data related to good products, but there is little data related to defective products, resulting in serious data imbalance. In order to efficiently solve this data imbalance, undersampling, oversampling, and composite sampling are usally applied. In this study, oversampling techniques such as random oversampling (ROS), minority class oversampling (SMOTE), ADASYN(Adaptive Synthetic Sampling), etc., which amplify data of the minority class by the majority class, and complex sampling using both undersampling and oversampling, are applied. For composite sampling, SMOTE+ENN and SMOTE+Tomek were used. Artificial neural network techniques is used to predict product quality. Especially, MLP and RNN are applied as artificial neural network techniques, and optimization of various parameters for MLP and RNN is required. In this study, we proposed an SA technique that optimizes the choice of the sampling method, the ratio of minority classes for sampling method, the batch size and the number of hidden layer units for parameters of MLP and RNN. The existing sampling methods and the proposed SA method were compared using accuracy, precision, recall, and F1 Score to prove the superiority of the proposed method.

• Journal of Korean Society for Quality Management
• /
• v.52 no.1
• /
• pp.43-56
• /
• 2024

Purpose: The injection molding process, crucial for plastic shaping, encounters difficulties in sustaining product quality when replacing injection machines. Variations in machine types and outputs between different production lines or factories increase the risk of quality deterioration. In response, the study aims to develop a system that optimally adjusts conditions during the replacement of injection machines linked to molds. Methods: Utilizing a dataset of 12 injection process variables and 52 corresponding sensor variables, a predictive model is crafted using Decision Tree, Random Forest, and XGBoost. Model evaluation is conducted using an 80% training data and a 20% test data split. The dependent variable, classified into five characteristics based on temperature and pressure, guides the prediction model. Bayesian optimization, integrated into the selected model, determines optimal values for process variables during the replacement of injection machines. The iterative convergence of sensor prediction values to the optimum range is visually confirmed, aligning them with the target range. Experimental results validate the proposed approach. Results: Post-experiment analysis indicates the superiority of the XGBoost model across all five characteristics, achieving a combined high performance of 0.81 and a Mean Absolute Error (MAE) of 0.77. The study introduces a method for optimizing initial conditions in the injection process during machine replacement, utilizing Bayesian optimization. This streamlined approach reduces both time and costs, thereby enhancing process efficiency. Conclusion: This research contributes practical insights to the optimization literature, offering valuable guidance for industries seeking streamlined and cost-effective methods for machine replacement in injection molding.

• Elastomers and Composites
• /
• v.47 no.4
• /
• pp.336-340
• /
• 2012

Residual stress in the injection molded part is originated from thermal shrinkage and shear stress during injection molding process. There are many measurement methods of residual stress in the plastic part. Residual stress in opaque products can be measured by chemical cracking test. This method enables the solvent and specimen to react and to cause cracks. Cracks developed according to the level of residual stress. Thus the stresses in plastic part can be quantitatively measured by counting the number of cracks or measuring the size of cracks. Relationship between stress and number of cracks in a plastic specimen has been investigated in this study. Bergen jig was used to give a strain in the specimens those were molded using PC/PBT and PC/ABS. Solvent for the chemical cracking test was prepared using tetrahydrofuran and methyl alcol with the ratio of 1 to 3. Stresses in the specimen can be calculated by strains those were imposed by Bergen jig. Cracks were developed for stress higher than certain level. The number of cracks increased by second order function for stress.

• Design & Manufacturing
• /
• v.13 no.2
• /
• pp.30-36
• /
• 2019

Traditional cell culture(2-dimensional) is the method that provide a nutrient and environment on a flat surface to cultivate cells into a single layer. Since the cell characteristics of 2D culture method is different from the characteristics of the cells cultured in the body, attempts to cultivate the cells in an environment similar to the body environment are actively proceeding in the industry, academy, and research institutes. In this study, we will develop a technology to fabricate micro-structures capable of culturing cells on surfaces with various curvatures, surface shapes, and characteristics. In order to fabricate the hemispheric plastic structure(thickness $50{\mu}m$), plastic preform mold (hereinafter as "preform mold") corresponding to the hemisphere was first prepared by injection molding in order to fabricate a two - layer structure to be combined with a flat plastic film. Then, thermoplastic polymer dissolved in an organic solvent was solidified on a preform mold. As a preliminary study, we proposed injection molding conditions that can minimize X/Y/Z axis deflection value. The effects of the following conditions on the preform mold were analyzed through injection molding CAE, [(1) coolant inlet temperature, (2) injection time, (3) packing pressure, (4) volume-pressure (V/P). As a result, the injection molding process conditions (cooling water inlet temperature, injection time, holding pressure condition (V / P conversion point and holding pressure size)) which can minimize the deformation amount of the preform mold were derived through CAE without applying the experimental design method. Also, the derived injection molding process conditions were applied during actual injection molding and the degree of deformation of the formed preform mold was compared with the analysis results. It is expected that plastic film having various shapes in addition to hemispherical shape using the preform mold produced through this study will be useful for the molding preform molding technology and cast molding technology.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.37 no.1
• /
• pp.113-119
• /
• 2013

Despite rapid changes in the structure of industry, manufacturing remains a key industry for economic progress, promotion of trade, increased employment, and the creation of new industries. Production technologies are essential for strengthening the competitiveness of small- and medium-sized manufacturing industries. However, it is very difficult to standardize and systematically propagate production technology from an experienced worker to an inexperienced worker because these technologies are generally improved by the skilled people in a workshop. In this study, we introduce a Web-based platform system consisting of a knowledge authoring tool, technology database, semantic database, and Web portal service for sharing production technologies for the exterior housing parts of mobile products. By investigating various cellular phone designs, reference form factors for three types of mobile phone housings were designed based on the standard features. In addition, several manufacturing technologies and considerable information such as reference mold designs and molding conditions optimized using CAE and recent R&D outputs are stored in this system.

• Journal of the Microelectronics and Packaging Society
• /
• v.30 no.2
• /
• pp.1-12
• /
• 2023

In the current era of the global mobile smart device revolution, electronic devices are required in all spaces that people interact with. The establishment of the internet of things (IoT) among smart devices has been recognized as a crucial objective to advance towards creating a comfortable and sustainable future society. In-mold electronic (IME) processes have gained significant industrial significance due to their ability to utilize conventional high-volume methods, which involve printing functional inks on 2D substrates, thermoforming them into 3D shapes, and injection-molded, manufacturing low-cost, lightweight, and functional components or devices. In this article, we provide an overview of IME and its latest advances in application. We review biomimetic nanomaterials for constructing self-supporting biosensor electronic materials on the body, energy storage devices, self-powered devices, and bio-monitoring technology from the perspective of in-mold electronic devices. We anticipate that IME device technology will play a critical role in establishing a human-machine interface (HMI) by converging with the rapidly growing flexible printed electronics technology, which is an integral component of the fourth industrial revolution.