• Journal of Korean Society for Quality Management
• /
• v.51 no.2
• /
• pp.283-296
• /
• 2023

Purpose: The purpose of this study is to actually implement and verify whether welding defects can be detected in real time by utilizing deep learning AI solutions in the welding process of electric vehicle hairpin winding motors. Methods: AI's function and technological elements using synthetic neural network were applied to existing electric vehicle hairpin winding motor laser welding process by making special hardware for detecting electric vehicle hairpin motor laser welding defect. Results: As a result of the test applied to the welding process of the electric vehicle hairpin winding motor, it was confirmed that defects in the welding part were detected in real time. The accuracy of detection of welds was achieved at 0.99 based on mAP@95, and the accuracy of detection of defective parts was 1.18 based on FB-Score 1.5, which fell short of the target, so it will be supplemented by introducing additional lighting and camera settings and enhancement techniques in the future. Conclusion: This study is significant in that it improves the welding quality of hairpin winding motors of electric vehicles by applying domestic artificial intelligence solutions to laser welding operations of hairpin winding motors of electric vehicles. Defects of a manufacturing line can be corrected immediately through automatic welding inspection after laser welding of an electric vehicle hairpin winding motor, thus reducing waste throughput caused by welding failure in the final stage, reducing input costs and increasing product production.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.334-334
• /
• 2022

Improvement of old-fashioned rain gauge systems for automatic, timely, continuous, and accurate precipitation observation is highly essential for weather/climate prediction and natural hazards early warning, since the occurrence frequency and intensity of heavy and extreme precipitation events (especially floods) are recently getting more increase and severe worldwide due to climate change. Although rain gauge accuracy of 0.1 mm is recommended by the World Meteorological Organization (WMO), the traditional rain gauges in both weighting and tipping bucket types are often unable to meet that demand due to several existing technical limitations together with higher production and maintenance costs. Therefore, we aim to introduce a newly developed and cost-effective hybrid rain gauge system at 0.1 mm accuracy that combines advantages of weighting and tipping bucket types for continuous, automatic, and accurate precipitation observation, where the errors from long-term load cells and external environmental sources (e.g., winds) can be removed via an automatic drainage system and artificial intelligence-based data quality control procedure. Our rain gauge system consists of an instrument unit for measuring precipitation, a communication unit for transmitting and receiving measured precipitation signals, and a database unit for storing, processing, and analyzing precipitation data. This newly developed rain gauge was designed according to the weather instrument criteria, where precipitation amounts filled into the tipping bucket are measured considering the receiver's diameter, the maximum measurement of precipitation, drainage time, and the conductivity marking. Moreover, it is also designed to transmit the measured precipitation data stored in the PCB through RS232, RS485, and TCP/IP, together with connecting to the data logger to enable data collection and analysis based on user needs. Preliminary results from a comparison with an existing 1.0-mm tipping bucket rain gauge indicated that our developed rain gauge has an excellent performance in continuous precipitation observation with higher measurement accuracy, more correct precipitation days observed (120 days), and a lower error of roughly 27 mm occurred during the measurement period.

• The Journal of the Korea Contents Association
• /
• v.22 no.8
• /
• pp.274-287
• /
• 2022

Competition in the broadcasting market is intensifying as OTT services are spreading. And Korea is positioned as a competent international contents supply base. This can be helpful for the domestic contents production industry. However, it can result in being incorporated as a subcontractor in the global video industry. Therefore, it is necessary for Korean OTT operators to expand their market upto overseas and maintain competitiveness by linking content competitiveness to the sales expansion. This study was conducted to reduce the risk and encourage implementation through feasibility analysis of overseas business of domestic OTT operators. The North American market was selected as a region with high potential through in-depth interviews with experts and literatures review. And it was confirmed that the partnership with local platform is effective. Then, the sales and input costs were estimated, and business was evaluated using the net present value method. Totally 18 scenarios were created using multiple estimates for copyright cost, subscribers, and rate, which are highly uncertain. From the analyses, 8 scenarios were found to be acceptable. And copyright cost has the greatest impact on business success, followed by rates and subscribers.

• Journal of the Microelectronics and Packaging Society
• /
• v.29 no.4
• /
• pp.55-61
• /
• 2022

There is a major interest in diagnostic technology for multiple cancers worldwide. In order to reduce the difficulty of cancer diagnosis, a liquid biopsy technology based on a microfluidic device using trace amounts of biofluids such as blood is being studied. And optical biosensing, which measures the concentration of analytes through fluorescence imaging using biofluids, requires various strategies to improve sensitivity, and specialists and equipment are needed to carry out these strategies. This leads to an increase in diagnostic and production costs, and it is necessary to develop a technology to solve this problem. In this paper, we design and propose a fluorescent multi-cancer diagnostic sensing platform structure that implements passive self-separation technology and molecular recognition activation functions by fluid mixing, only with the geometry and microfluidic phenomena of microchannels based on self-driven flow by capillary force. In order to check the parameters affecting the performance of the plasma separation part of the designed sensor, the hydrodynamic diameter of the channel and the viscosity of the fluid were set as variables to confirm the formation of plasma separation flow through simulation. And finally, we propose an optimal sensor platform structure.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.12
• /
• pp.3330-3344
• /
• 2023

This paper proposes an antenna performance prediction model in the autonomous driving radar manufacturing process. Our research work is based upon a challenge dataset, Driving Radar Manufacturing Process Dataset, and a typical AutoML machine learning workflow engine, Pycaret open-source Python library. Note that the dataset contains the total 70 data-items, out of which 54 used as input features and 16 used as output features, and the dataset is properly built into resolving the multi-output regression problem. During the data regression analysis and preprocessing phase, we identified several input features having similar correlations and so detached some of those input features, which may become a serious cause of the multicollinearity problem that affect the overall model performance. In the training phase, we train each of output-feature regression models by using the AutoML approach. Next, we selected the top 5 models showing the higher performances in the AutoML result reports and applied the ensemble method so as for the selected models' performances to be improved. In performing the experimental performance evaluation of the regression prediction model, we particularly used two metrics, MAE and RMSE, and the results of which were 0.6928 and 1.2065, respectively. Additionally, we carried out a series of experiments to verify the proposed model's performance by comparing with other existing models' performances. In conclusion, we enhance accuracy for safer autonomous vehicles, reduces manufacturing costs through AutoML-Pycaret and machine learning ensembled model, and prevents the production of faulty radar systems, conserving resources. Ultimately, the proposed model holds significant promise not only for antenna performance but also for improving manufacturing quality and advancing radar systems in autonomous vehicles.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.369-377
• /
• 2023

In the industrial manufacturing sector, quality control is pivotal for minimizing defect rates; inadequate management can result in additional costs and production delays. This study underscores the significance of detecting texture defects in manufactured goods and proposes a more precise defect detection technique. While the DFR(Deep Feature Reconstruction) model adopted an approach based on feature map amalgamation and reconstruction, it had inherent limitations. Consequently, we incorporated a new loss function using statistical methodologies, integrated a skip connection structure, and conducted parameter tuning to overcome constraints. When this enhanced model was applied to the texture category of the MVTec-AD dataset, it recorded a 2.3% higher Defect Segmentation AUC compared to previous methods, and the overall defect detection performance was improved. These findings attest to the significant contribution of the proposed method in defect detection through the reconstruction of feature map combinations.

• Korean Circulation Journal
• /
• v.53 no.6
• /
• pp.351-366
• /
• 2023

Along with the development of immunosuppressive drugs, major advances on xenotransplantation were achieved by understanding the immunobiology of xenograft rejection. Most importantly, three predominant carbohydrate antigens on porcine endothelial cells were key elements provoking hyperacute rejection: α1,3-galactose, SDa blood group antigen, and N-glycolylneuraminic acid. Preformed antibodies binding to the porcine major xenoantigen causes complement activation and endothelial cell activation, leading to xenograft injury and intravascular thrombosis. Recent advances in genetic engineering enabled knock-outs of these major xenoantigens, thus producing xenografts with less hyperacute rejection rates. Another milestone in the history of xenotransplantation was the development of co-stimulation blockaded strategy. Unlike allotransplantation, xenotransplantation requires blockade of CD40-CD40L pathway to prevent T-cell dependent B-cell activation and antibody production. In 2010s, advanced genetic engineering of xenograft by inducing the expression of multiple human transgenes became available. So-called 'multi-gene' xenografts expressing human transgenes such as thrombomodulin and endothelial protein C receptor were introduced, which resulted in the reduction of thrombotic events and improvement of xenograft survival. Still, there are many limitations to clinical translation of cardiac xenotransplantation. Along with technical challenges, zoonotic infection and physiological discordances are major obstacles. Social barriers including healthcare costs also need to be addressed. Although there are several remaining obstacles to overcome, xenotransplantation would surely become the novel option for millions of patients with end-stage heart failure who have limited options to traditional therapeutics.

• 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.

• Nuclear Engineering and Technology
• /
• v.56 no.1
• /
• pp.301-308
• /
• 2024

Ceramic materials are being explored as alternatives to toxic lead sheets for radiation shielding due to their favorable properties like durability, thermal stability, and aesthetic appeal. However, crafting effective ceramics for radiation shielding entails complex processes, raising production costs. To investigate local viability, this study evaluated Malaysian ceramic tiles for shielding in diagnostic X-ray rooms. Different ceramics in terms of density and thickness were selected from local manufacturers. Energy Dispersive X-ray Fluorescence (EDXRF) and X-ray Fluorescence (XRF) characterized ceramic compositions, while Monte Carlo Particle and Heavy Ion Transport code System (MC PHITS) simulations determined Linear Attenuation Coefficient (LAC), Half-value Layer (HVL), Mass Attenuation Coefficient (MAC), and Mean Free Path (MFP) within the 40-150 kV energy range. Comparative analysis between MC PHITS simulations and real setups was conducted. The C3-S9 ceramic sample, known for homogeneous full-color structure, showcased superior shielding attributes, attributed to its high density and iron content. Notably, energy levels considerably impacted radiation penetration. Overall, C3-S9 demonstrated strong shielding performance, underlining Malaysia's potential ceramic tile resources for X-ray room radiation shielding.

• Composites Research
• /
• v.37 no.2
• /
• pp.115-125
• /
• 2024

As global issues and interest in the environment increase, the transition to eco-friendly materials is accelerating in the automobile industry. In the automotive industry, eco-friendly composite materials are mainly used in various interior and exterior components, reducing the reliance on traditional petroleum-based materials. In particular, natural fiber composites help reduce fuel consumption and greenhouse gas emissions by making vehicles lighter. Additionally, they boast superior thermal properties and durability compared to non-recyclable composite materials, making them suitable for automotive interior parts. Furthermore, reduced production costs and sustainability are key advantages of natural fiber composites. The eco-friendly composites market is expected to grow to $86.43 billion at a CAGR of 15.3% from 2022 to 2030, and the natural fiber composites market is predicted to grow at a CAGR of 5.3% from 2023 to 2028 to $424 million. In this review paper, we explore research trends in nextgeneration natural fiber composite materials for automobiles and their application in the actual automobile industry.