Plastic injection molding is widely used in the automotive, electronics, and other manufacturing industries. Since product quality is significantly affected by process variables such as temperature, pressure, speed, and cycle time, datadriven quality management has become increasingly important. However, conventional quality control methods mainly depend on operator experience and post-process inspection, making it difficult to detect defects and abnormal process conditions in real time. In addition, manufacturing datasets often suffer from severe class imbalance because defective samples are much fewer than normal samples. This study proposes an AI-based defect prediction and anomaly detection system using plastic injection molding process data. For defect prediction, XGBoost was selected as the supervised learning model, and SMOTE was applied to address class imbalance. Recall, F1-score, and PR-AUC were used as the main evaluation metrics instead of accuracy. SHAP analysis was also applied to identify important process variables affecting defect occurrence. For anomaly detection, Isolation Forest and AutoEncoder were used together. Isolation Forest was adopted for fast first-stage detection, while AutoEncoder was used to detect complex nonlinear abnormal patterns. The results indicate that the proposed system can support both defect prediction and process anomaly detection. In the supervised learning results, XGBoost showed the best performance on the CN7 dataset, achieving a recall of 1.000 and an F1-score of 0.800. However, all supervised models showed limited defect detection performance on the RG3 dataset, indicating the effect of severe class imbalance and dataset-specific characteristics. In anomaly detection, AutoEncoder achieved the highest F1-score among the compared models, while Isolation Forest demonstrated practical advantages for real-time application due to its computational efficiency. Therefore, the proposed AI-based system can contribute to smart quality management and data-driven decision-making in plastic injection molding processes.

Injection-molded products frequently exhibit localized surface defects such as weld lines, flow marks, scratches, bubbles, and burn marks due to variations in material flow, mold temperature, and cooling conditions. Conventional visual inspection is highly dependent on operator experience, while rule-based machine vision methods are limited under variations in lighting and surface texture. This study proposes a deep learning–based defect detection model using YOLOv8 combined with a novel Defect-Aware Augmentation technique designed to enhance robustness for small, local defect regions. The proposed augmentation pipeline includes geometric transformations, optical perturbations, local defect patch synthesis, and diffusion-based synthetic defect generation. Experiments were conducted on a custom dataset of 5,000 images (3,000 normal and 2,000 defective). Results show that the proposed model achieves significant improvements over baseline models, obtaining 95% precision, 90% recall, and 0.96 mAP@0.5, outperforming the default YOLOv8 model by 7%p in mAP. Ablation studies verify that defect-aware augmentation is the dominant factor contributing to the performance gain. The proposed system demonstrates high applicability for automated quality inspection in injectionmolding production lines.

In this study, the shape of the exterior, not the inside of the product, was modified. Various exterior shape change plans were compared and reviewed through injection molding analysis, and among them, the most effective shape for suppressing warpage deformation was derived. The shape of the product was modified to optimize the bending deformation of the cover located at the top of the automobile battery case. The analysis was conducted under a total of three conditions, each of shape A, which is a rectangular parallelepiped shape at the top of the product, and shape B, which is concave on the side of the product. As a result of the study, both shape A and shape B were reduced compared to the amount of bending deformation of the original shape. Among them, shape B2, which showed the largest reduction, decreased by 82.096% from the amount of bending deformation of the original shape.

High-entropy alloys (HEAs) have been reported to have better properties than conventional materials; however, they are more expensive due to the high cost of their main components. Therefore, research is needed to reduce manufacturing costs. In this study, CoCrFeMnNi HEAs were prepared using metal injection molding (MIM), which is a powder metallurgy process that involves less material waste than machining process. Although the MIM-processed samples were in the face-centered cubic (FCC) phase, porosity remained after sintering at 1200°C, 1250°C, and 1275°C. In this study, the hot isostatic pressing (HIP) process, which considers both temperature (1150°C) and pressure (150 MPa), was adopted to improve the quality of the MIM samples. Although the hardness of the HIP-treated samples decreased slightly and the Mn composition was significantly reduced, the process effectively eliminated many pores that remained after the 1275°C MIM process. The HIP process can improve the quality of the alloy.

The EV electric vehicle market is growing rapidly worldwide. Magnet fixing technology is important for mass production of driving motors, a key part of electric vehicles. The magnet fixing method was carried out by the PAM (Polyamide molding) method. This study conducted the injection of rotor core magnet PA of EV traction motor and is a study on the amount of rotor core deformation. In this study, the change in the outer diameter of the product after injection and the non-molding phenomenon were tested. An injection mold was made and the results and phenomena of product deformation types are discussed.

In this study, the change in the mold opening stroke of important functional parts according to the 20, 50, 80, and 100% increase in the injection speed of a hydraulic 150 ton hydraulic injection molding machine was studied to verify the accuracy of the injection speed and mold opening stroke and the reproducibility of the standard deviation. The null and alternative hypotheses were confirmed by conducting hypothesis verification according to the experimental condition change using the experimental design method.

High-entropy alloys (HEAs) are attracting attention because of their excellent properties and functions; however, they are relatively expensive compared with commercial alloys. Therefore, various efforts have been made to reduce the cost of raw materials. In this study, MIM is attempted using coarse equiatomic CoCrFeMnNi HEA powders. The mixing ratio (powder:binder) for HEA feedstock preparation is explored using torque rheometer. The block-shaped green parts are fabricated through a metal injection molding process using feedstock. The thermal debinding conditions are explored by thermogravimetric analysis, and solvent and thermal debinding are performed. It is densified under various sintering conditions considering the melting point of the HEA. The final product, which contains a small amount of non-FCC phase, is manufactured at a sintering temperature of 1250oC.

As the 4th industrial revolution emerges, the implementation of smart factories are essential in the manufacturing industry. However, 80% of small and medium-sized enterprises that have introduced smart factories remain at the basic level. In addition, in root industries such as injection molding, PLC and HMI software are used to implement functions that simply show operation data aggregated by facilities in real time. This has limitations for managers to make decisions related to product production other than viewing data. This study presents a method for upgrading the level of smart factories to suit the reality of small and medium-sized enterprises. By monitoring the data collected from the facility, it is possible to determine whether there is an abnormal situation by proposing an appropriate algorithm for meaningful decision-making, and an alarm sounds when the process is out of control. In this study, the function of HMI has been expanded to check the failure frequency rate, facility time operation rate, average time between failures, and average time between failures based on facility operation signals. For the injection molding industry, an HMI prototype including the extended function proposed in this study was implemented. This is expected to provide a foundation for SMEs that do not have sufficient IT capabilities to advance to the middle level of smart factories without making large investments.

사출성형공정은 열가소성 수지를 가열하여 유동상태로 만들어 금형의 공동부에 가압 주입한 후에 금형 내에서 냉각시키는 공정으로, 금형의 공동모양과 동일한 제품을 만드는 방법이다. 대량생산이 가능하고, 복잡한 모양이 가능한 공정으로, 수지온도, 금형온도, 사출속도, 압력 등 다양한 요소들이 제품의 품질에 영향을 미친다. 제조현장에서 수집되는 데이터는 양품과 관련된 데이터는 많은 반면, 불량품과 관련된 데이터는 적어서 데이터불균형이 심각하다. 이러한 데이터불균형을 효율적으로 해결하기 위하여 언더샘플링, 오버샘플링, 복합샘플링 등이 적용되고 있다. 본 연구에서는 랜덤오버샘플링(ROS), 소수 클래스 오버 샘플링(SMOTE), ADASTN 등의 소수클래스의 데이터를 다수클래스만큼 증폭시키는 오버샘플링 기법을 활용하고, 데이터마이닝 기법을 활용하여 품질예측을 하고자 한다.

In this paper, to improve the optical quality of aspherical plastic lenses for mobile use, the optimal molding conditions that can minimize the phase difference are derived using injection molding simulation, design of experiments, and machine learning. First, factors affecting the phase difference were derived using the design of the experiment method, and a data set was created using the derived factors, followed by the machine learning process. After predicting the model trained using the generated training data as test data and verifying it with the performance evaluation index, the model with the best predictive performance was the random forest model. Therefore, to derive the optimal molding conditions, random forests were used to predict 10,000 random pieces of data. As a result of applying the derived optimal molding conditions to the injection molding simulation, the phase difference of the lens could be reduced by 8.2%.

In this study, we used a numerical analysis program to study the molding conditions that affect the flow rate at the time of injection, using a spiral mold, which is mainly used for the evaluation of the flow rate of plastic resin. The mold temperature, melt temperature, and flow rate are composed of experimental factors. The three plastic forming factors were divided into five to six levels each. Since then, changes in the flow rate temperature were analyzed as the level of each forming factor increased. Experiments showed that all three forming factors increased the filling length of the spiral mold and the temperature of the flow front by a total of 34.53°C, melt temperatures increased the temperature of the flow front by a total of 34.53°C, the temperature increased by the flow rate was 23.5°C, and the temperature increased by the mold temperature was 1.99°C. It was shown that the melt temperature was the largest, followed by the flow rate and mold temperature. It was also possible to check the effect of plastic forming factors on the speed of the flow front.

Recently, the demand for reliability verification is increasing while designing and manufacturing molds using injection molding computer aided engineering(CAE). When performing flow analysis verification, a spiral mold is produced and compared with CAE. Because of the spiral shape, we needed a comparative evaluation with the flow distance of products with different forms. So, we compared the weight and flowed length using CAE. Variables are the change in the width of the spiral shape and the shape of the bar and plate. When the width of the spiral shape is 23mm rather than 15mm, the flow distance flows 30∼70mm more, with a maximum difference of 13%. As a result of comparing the spiral shape and the long square shape with the same width, the spiral shape had a flow distance of 60 to 105mm further, and a difference of up to 28% was found. As a result of comparing the plate shape and the spiral shape with a 15mm width product, the spiral shape has a flow distance of 310∼380mm further, and a difference of up to 82% is different.

Plastic products molded by injection molding have become an essential element of our lives. In addition, plastics can replace parts that used to be metal in the past. Plastic molded products used as a part of a mechanical system require high precision. At the same time, the appearance quality of molded products is also an important evaluation factor. The appearance quality of a molded product is affected by injection molding conditions, plastic material fluidity, and the condition of the mold surface. In this study, the cause of the short shot of the dog house, which functions to assemble the plastic tailgate parts for automobiles, was analyzed. In order to solve the short shot problem of the dog house, the root thickness of the dog house, injection molding conditions, and fluidity of plastic materials were experimented. Through the injection molding experiment, it was found that when the dog house root thickness was increased from 0.8mm to 1.2mm, the filling amount of the doghouse part increased by 43% in experiment mold. These results were verified by injection molding analysis.

In this study, in order of to reflect the mold deformation in the injection molding process to design of mold, the mold deformation was analyzed by performing flow and structural analysis. The 5 inch LGP(light guide plate) mold, platen and tie bar were modeled and applied to the analysis. The result of melt pressure from flow analysis was extracted for use as boundary conditions acting on the mold surface in the structural analysis. In order to evaluate the accuracy of simulation analysis results, injection molding was performed under the process conditions of simulation. As a results, the mold deformation during injection molding tends to be similar that of injection pressure, and it is confirmed that it shows the behavior and properties of melt resins. Compared with the simulation and experiment, the error of the maximum mold deformation in the injection phase was 4.20%.

A combination of Polycarbonate (PC) material and Polymethylmethacrylate (PMMA), fabricated using an injection molding machine, has been investigated to determine its advantages, as studied in Ref. 1). This paper aims to investigate the optimization of PMMA/PC blend for both tensile yield strength and impact strength. Furthermore, interaction effects of process conditions on mechanical properties including tensile yield strength and impact strength of PMMA/PC blend by injection molding process are interpreted in this study. Tensile and impact specimens are designed following ASTM, type V, and are fabricated by injection molding process. The processing conditions such as melt temperature, mold temperature, packing pressure, and cooling time are applied; each factor has three levels. As a result, in comparison with optimization of separated responses, mechanical properties of PMMA/PC are found to decrease when optimizing both tensile and impact strengths simultaneously. The melt temperature is found to be the most significant interaction parameter with the mold temperature and packing pressure. In addition, there is more interaction between the mold temperature and cooling time. This investigation provides a useful understanding of the control of injection molding processing of polymer blends in optical application.

In this study, the injection pressure of 31 MPa and clamping force of 1,000 kN toggle electric injection molding machine were used to measure the load transmitted to the frame during injection molding and to use it as the design basis data. In general, the toggle structure is composed of a movable plate, tie bars, crossheads, toggle links, toggle pins, base plates, etc and The material is spherical graphite cast iron(FCD 400). In this study, it was found that there was a 1.3% safety factor by calculating the clamping force in the structure of the five-point toggle link system. In addition, Expected static bottom load, Expected dynamic additional load, Maximum expected additional load, and Maximum weight load were measured using tensile measurements and presented as important basic design data of the assembly.