• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.6
• /
• pp.36-42
• /
• 2021

With recent developments in the Fourth Industrial Revolution, the manufacturing industry has changed rapidly. Through key aspects of Fourth Industrial Revolution super-connections and super-intelligence, machine learning will be able to make fault predictions during the foam-making process. Polyol and isocyanate are components in polyurethane foam. There has been a lot of research that could affect the characteristics of the products, depending on the specific mixture ratio and temperature. Based on these characteristics, this study collects data from each factor during the foam-making process and applies them to machine learning in order to predict faults. The algorithms used in machine learning are the decision tree, kNN, and an ensemble algorithm, and these algorithms learn from 5,147 cases. Based on 1,000 pieces of data for validation, the learning results show up to 98.5% accuracy using the ensemble algorithm. Therefore, the results confirm the faults of currently produced parts by collecting real-time data from each factor during the foam-making process. Furthermore, control of each of the factors may improve the fault rate.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.74-79
• /
• 2022

In this study, the plasma corrosion resistance and the change in the number of contamination particles generated using the plasma etching process and cleaning process of coating parts for semiconductor plasma etching equipment were investigated. As the coating method, atmospheric plasma spray (APS) was used, and the powder materials were Y₂O₃ and Y₃Al₅O₁₂ (YAG). There was a clear difference in the densities of the coatings due to the difference in solubility due to the melting point of the powdered material. As a plasma environment, a mixed gas of CF₄, O₂, and Ar was used, and the etching process was performed at 200 W for 60 min. After the plasma etching process, a fluorinated film was formed on the surface, and it was confirmed that the plasma resistance was lowered and contaminant particles were generated. We performed a surface cleaning process using piranha solution(H₂SO₄(3):H₂O₂(1)) to remove the defect-causing surface fluorinated film. APS-Y₂O₃ and APS-YAG coatings commonly increased the number of defects (pores, cracks) on the coating surface by plasma etching and cleaning processes. As a result, it was confirmed that the generation of contamination particles increased and the breakdown voltage decreased. In particular, in the case of APS-YAG under the same cleaning process conditions, some of the fluorinated film remained and surface defects increased, which accelerated the increase in the number of contamination particles after cleaning. These results suggest that contaminating particles and the breakdown voltage that causes defects in semiconductor devices can be controlled through the optimization of the APS coating process and cleaning process.

• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.345-349
• /
• 2023

In this paper, we propose a study on the development of deep learning structure for defective pixel detection of next-generation smart LED display board using imaging device. In this research, a technique utilizing imaging devices and deep learning is introduced to automatically detect defects in outdoor LED billboards. Through this approach, the effective management of LED billboards and the resolution of various errors and issues are aimed. The research process consists of three stages. Firstly, the planarized image data of the billboard is processed through calibration to completely remove the background and undergo necessary preprocessing to generate a training dataset. Secondly, the generated dataset is employed to train an object recognition network. This network is composed of a Backbone and a Head. The Backbone employs CSP-Darknet to extract feature maps, while the Head utilizes extracted feature maps as the basis for object detection. Throughout this process, the network is adjusted to align the Confidence score and Intersection over Union (IoU) error, sustaining continuous learning. In the third stage, the created model is employed to automatically detect defective pixels on actual outdoor LED billboards. The proposed method, applied in this paper, yielded results from accredited measurement experiments that achieved 100% detection of defective pixels on real LED billboards. This confirms the improved efficiency in managing and maintaining LED billboards. Such research findings are anticipated to bring about a revolutionary advancement in the management of LED billboards.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.5
• /
• pp.199-206
• /
• 2023

The current software becomes the huge size of source codes. Therefore it is increasing the importance and necessity of static analysis for high-quality product. With static analysis of the code, it needs to identify the defect and complexity of the code. Through visualizing these problems, we make it guild for developers and stakeholders to understand these problems in the source codes. Our previous visualization research focused only on the process of storing information of the results of static analysis into the Database tables, querying the calculations for quality indicators (CK Metrics, Coupling, Number of function calls, Bad-smell), and then finally visualizing the extracted information. This approach has some limitations in that it takes a lot of time and space to analyze a code using information extracted from it through static analysis. That is since the tables are not normalized, it may occur to spend space and time when the tables(classes, functions, attributes, Etc.) are joined to extract information inside the code. To solve these problems, we propose a regularized design of the database tables, an extraction mechanism for quality metric indicators inside the code, and then a visualization with the extracted quality indicators on the code. Through this mechanism, we expect that the code visualization process will be optimized and that developers will be able to guide the modules that need refactoring. In the future, we will conduct learning of some parts of this process.

• Industry Promotion Research
• /
• v.9 no.1
• /
• pp.21-29
• /
• 2024

In the rapidly advancing information society, electronic devices, including smartphones and tablets, are increasingly digitized and equipped with high-performance features such as flexible displays. This study focused on optimizing the manufacturing process for Transparent Conductive Films (TCF) by using the cost-effective conductive polymer PEDOT and transparent substrate PET as alternatives to expensive materials in flexible display technology. The variables considered are production speed (m/min), coating maximum temperature (℃), and PEDOT supply speed (rpm), with surface resistivity (Ω/□) as the response parameter, using Response Surface Methodology (RSM). Optimization results indicate the ideal conditions for production: a speed of 22.16 m/min, coating temperature of 125.28℃, and PEDOT supply at 522.79 rpm. Statistical analysis validates the reliability of the results (F value: 18.37, P-value: < 0.0001, R²: 0.9430). Under optimal conditions, the predicted surface resistivity is 145.75 Ω/□, closely aligned with the experimental value of 142.97 Ω/□. Applying these findings to mass production processes is expected to enhance production yields and decrease defect rates compared to current practices. This research provides valuable insights for the advancement of flexible display manufacturing.

• Journal of IKEEE
• /
• v.28 no.3
• /
• pp.474-478
• /
• 2024

In this paper, we proposes a deep learning network for quality inspection in a multi-camera inline inspection system for pharmaceutical containers. The proposed deep learning network is specifically designed for pharmaceutical containers by using data produced in real manufacturing environments, leading to more accurate quality inspection. Additionally, the use of an inline-capable deep learning network allows for an increase in inspection speed. The development of the deep learning network for quality inspection in the multi-camera inline inspection system consists of three steps. First, a dataset of approximately 10,000 images is constructed from the production site using one line camera for foreign substance inspection and three area cameras for dimensional inspection. Second, the pharmaceutical container data is preprocessed by designating regions of interest (ROI) in areas where defects are likely to occur, tailored for foreign substance and dimensional inspections. Third, the preprocessed data is used to train the deep learning network. The network improves inference speed by reducing the number of channels and eliminating the use of linear layers, while accuracy is enhanced by applying PReLU and residual learning. This results in the creation of four deep learning modules tailored to the dataset built from the four cameras. The performance of the proposed deep learning network for quality inspection in the multi-camera inline inspection system for pharmaceutical containers was evaluated through experiments conducted by a certified testing agency. The results show that the deep learning modules achieved a classification accuracy of 99.4%, exceeding the world-class level of 95%, and an average classification speed of 0.947 seconds, which is superior to the world-class level of 1 second. Therefore, the effectiveness of the proposed deep learning network for quality inspection in a multi-camera inline inspection system for pharmaceutical containers has been demonstrated.

• Journal of IKEEE
• /
• v.28 no.3
• /
• pp.469-473
• /
• 2024

In this paper proposes a study on the development of a multi-camera inline inspection system using machine vision for quality inspection of pharmaceutical containers. The proposed technique captures the pharmaceutical containers from multiple angles using several cameras, allowing for more accurate quality assessment. Based on the captured data, the system inspects the dimensions and defects of the containers and, upon detecting defects, notifies the user and automatically removes the defective containers, thereby enhancing inspection efficiency. The development of the multi-camera inline inspection system using machine vision is divided into four stages. First, the design and production of a control unit that fixes or rotates the containers via suction. Second, the design and production of the main system body that moves, captures, and ejects defective products. Third, the design and development of control logic for the embedded board that controls the entire system. Finally, the design and development of a user interface (GUI) that detects defects in the pharmaceutical containers using image processing of the captured images. The system's performance was evaluated through experiments conducted by a certified testing agency. The results showed that the dimensional measurement error range of the pharmaceutical containers was between -0.30 to 0.28 mm (outer diameter) and -0.11 to 0.57 mm (overall length), which is superior to the global standard of 1 mm. The system's operational stability was measured at 100%, demonstrating its reliability. Therefore, the efficacy of the proposed multi-camera inline inspection system using machine vision for the quality inspection of pharmaceutical containers has been validated.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.25 no.2
• /
• pp.51-55
• /
• 2015

The present research is focused on the effect of porous graphite what is influenced on the 4H-SiC crystal growth by PVT method. We expect that it produces more C-rich and a change of temperature gradient for polytype stability of 4H-SiC crystal as adding the porous graphite in the growth cell. The SiC seeds and high purity SiC source materials were placed on opposite side in a sealed graphite crucible which was surrounded by graphite insulator. The growth temperature was around $2100{\sim}2300^{\circ}C$ and the growth pressure was 10~30 Torr of an argon pressure with 5~15 % nitrogen. 2 inch $4^{\circ}$ off-axis 4H-SiC with C-face (000-1) was used as a seed material. The porous graphite plate was inserted on SiC powder source to produce a more C-rich for polytype stability of 4H-SiC crystal and uniform radial temperature gradient. While in case of the conventional crucible, various polytypes such as 6H-, 15R-SiC were observed on SiC wafers, only 4H-SiC polytype was observed on SiC wafers prepared in porous graphite inserted crucible. The defect level such as MP and EP density of SiC crystal grown in the conventional crucible was observed to be higher than that of porous graphite inserted crucible. The better crystal quality of SiC grown using porous graphite plate was also confirmed by rocking curve measurement and Raman spectra analysis.

• Journal of the Korea Concrete Institute
• /
• v.21 no.3
• /
• pp.367-375
• /
• 2009

Recently, more focus is shift to imbalances in aggregate market supply and demand and an exhaustion of natural resources. In this situation, Electric arc furnace oxidizing slag (EAF slag) has high application possibility as aggregate for concrete due to similar property with general aggregate. However, it is inherent the problem which causes pop-out by free-CaO contained in slag In this study, we've got the plan to assure the chemical stability of EAF slag, and then experimentally tested the mechanical performance and durability for the fine aggregate used EAF slag. On this test result, we suggest the application plan. At the result of this study, it shows that EAF slag would reduce the surface defect such as pop-out due to natural aging for the fixed hour and adjustment the grain size of EAF slag. And mechanical performance and durability according to the replacement rate of concrete service, were revealed more than equal or equal compare to general aggregate. Hereafter, quality control must precede not to impede the beauty of concrete surface as assure the safety for aging and processing. And, to establish the environmental resource recycling system for by-products of steel, it should be made development of various application and guideline of quality control for the EAF slag aggregate. Moreover, it must be constantly studied all kind of engineering performance and durability for related to this study.

• Korean Journal of Materials Research
• /
• v.22 no.12
• /
• pp.675-681
• /
• 2012

We aimed to examine the co-doping effects of 1/6 mol% $Mn_3O_4$ and 1/4 mol% $Cr_2O_3$ (Mn:Cr = 1:1) on the reaction, microstructure, and electrical properties, such as the bulk defects and grain boundary properties, of ZnO-$Bi_2O_3-Sb_2O_3$ (ZBS; Sb/Bi = 0.5, 1.0, and 2.0) varistors. The sintering and electrical properties of Mn,Cr-doped ZBS, ZBS(MnCr) varistors were controlled using the Sb/Bi ratio. Pyrochlore ($Zn_2Bi_3Sb_3O_{14}$), ${\alpha}$-spinel ($Zn_7Sb_2O_{12}$), and ${\delta}-Bi_2O_3$ (also ${\beta}-Bi_2O_3$ at Sb/Bi ${\leq}$ 1.0) were detected for all of the systems. Mn and Cr are involved in the development of each phase. Pyrochlore was decomposed and promoted densification at lower temperature on heating in Sb/Bi = 1.0 system by Mn rather than Cr doping. A more homogeneous microstructure was obtained in all systems affected by ${\alpha}$-spinel. In ZBS(MnCr), the varistor characteristics were improved dramatically (non-linear coefficient, ${\alpha}$ = 40~78), and seemed to form ${V_o}^{\cdot}$(0.33 eV) as a dominant defect. From impedance and modulus spectroscopy, the grain boundaries can be seen to have divided into two types, i.e. one is tentatively assigned to ZnO/$Bi_2O_3$ (Mn,Cr)/ZnO (0.64~1.1 eV) and the other is assigned to the ZnO/ZnO (1.0~1.3 eV) homojunction.