• 산업경영시스템학회지
• /
• 제45권4호
• /
• 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.

• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2004년도 학술대회 논문집
• /
• pp.69-72
• /
• 2004

In this paper, we measured the electrical and optical characteristics of an electrodeless fluorescent lamp system as product of the inside and outside of the country and compared the measured data. Output current wave of domestic 150 W is unstable than it's of Endura 150 W. But the former of spend time after discharging and output current value is small than the latter. And optical characteristics(brightness, flux, color rendering index, efficiency) value of the former is a little small than the latter. In conclusion, if we improve a little more quality then we must secure the superiority in competition.

• 한국조명전기설비학회:학술대회논문집
• /
• 한국조명전기설비학회 2004년도 학술대회 논문집
• /
• pp.21-24
• /
• 2004

In this paper, we measured the optical characteristics of the electrodeless fluorescent lamp system as product of the inside and outside of the country and compared the measured data. Power consumption wave of domestic 150 W is unstable than it's of Endura 150 W. Optical characteristics(luminance, luminous flux, color rendering index, efficiency, CIE chromaticity coordinate) value of the former is a little small than the latter. In conclusion, if we improve a little more quality then we must secure the superiority in competition.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 추계학술대회 논문집 전기물성,응용부문
• /
• pp.157-160
• /
• 2004

In this paper, we measured the electrical and optical characteristics of an electrodeless fluorescent lamp system as product from the inside and outside of the country and compared the measured data. Output current wave of domestic 85W is unstable than it's of QL 85 W and the former of spend time after discharging and output current value is larger than the latter. Moreover optical characteristics(brightness, flux, efficiency) value of the former is small than the latter but color rendering index is equivalent. In conclusion, if we improve a little more quality then we must secure the superiority in competition.

• 한국산학기술학회논문지
• /
• 제13권4호
• /
• pp.1648-1653
• /
• 2012

일반적으로 후반부 공정에서의 불량은 전 제조공정에서 누적되어 온 부가가치의 손실로써 거의 완성품 가격에 해당하는 품질비용을 유발하게 되고 제조공정의 효율성에 악영향을 미치게 된다. 본 연구에서는 품질 변동성이 존재하는 후반부 제조공정을 대상으로 고객이 요구한 납기와 품질수준을 동시에 반영하는 작업투입 알고리즘을 제안한다. 본 연구에서 제안한 알고리즘의 성능을 평가하기 위하여 평균납기지연을 최소화하는 것을 목적으로 기존에 널리 사용되고 있는 대안들과의 성능 비교를 실시하여 그 우수성을 확인한다. 또한 고객이 요구한 품질요구수준에 따른 공정능력 관점에서도 본 연구에서 제시한 알고리즘이 뛰어난 성능을 보이는 것을 입증하였다.

• 전자공학회논문지CI
• /
• 제41권2호
• /
• pp.9-22
• /
• 2004

본 논문에서는 NP-Complete 부류에 속하는 다중 디스크 데이터 배치 문제를 해결하기 위한 병렬 유전자 알고리즘을 제안한다. 이 문제는 디스크 입출력 처리의 병렬성이 극대화되도록 Binary Cartesian Product File의 데이터 블록들을 디스크어레이에 배치하는 방식을 찾는 것이다. 이 문제를 해결하기 위하여 제안되었던 DAGA 방식은 순차 유전자 알고리즘(Genetic Algorithm)으로서, 이전에 제안되었던 다른 방식에 비해 디스크 수에 대한 제약을 없애면서도 우수한 결과를 제공함을 보여 주었으나 시뮬레이션 시간이 너무 커서 큰 용량의 데이터 구성에 대한 시뮬레이션을 어렵게 하는 문제점이 있었다. 본 논문에서는 DAGA의 시뮬레이션 시간 단축을 위한 방식으로서, 2차원 토러스(2-Dimension Torus) 기반 병렬 유전자 알고리즘(ParaDAGA)을 제안한다. ParaDAGA는 분산 객체 모형을 기반으로 설계되었으며, 단일 프로세서 시스템에서 구현된 병렬처리 컴퓨터 시뮬레이터에서 수행되도록 구현하였다. 시뮬레이션 연구를 통하여, ParaDAGA의 시뮬레이션 변수 값이 결과에 주는 영향을 분석하였고, ParaDAGA 방식이 DAGA 방식에 비해 우수한 결과를 제공할 수 있는지를 실험하였다. 실험 결과는 ParaDAGA 방식이 순차 알고리즘인 DAGA보다 알고리즘 수행 시간 뿐 아니라, 찾아낸 결과도 우수함을 보여준다.

• 품질경영학회지
• /
• 제52권1호
• /
• 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.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2003년도 ICCAS
• /
• pp.1295-1299
• /
• 2003

The Mass Flow Controller(MFC) has become crucial in semiconductor manufacturing equipments. It is an important element because the quality and the yield of a semiconductor process are decided by the accurate flow control of gas. Therefore, the demand for the high speed and the highly accurate control of MFCs has been requested. It is hard to find an article of the control algorithm applied to MFCs. But, it is known that commercially available MFCs have PID control algorithms. Particularly, when the system detects the flow by way of heat transfer, MFC control problem contains the time delay and the nonlinearity. In this presentation, MFC control algorithm with the superior performance to the conventional PID algorithm is discussed and the superiority is demonstrated through the experiment. Fuzzy controller was utilized in order to compensate the nonlinearity and the time delay, and the performance is compared with that of a product currently available in the market. The control system, in this presentation, consists of a personal computer, the data acquisition board and the control algorithm carried out by LabWindows/CVI program on the PC. In addition, the method of estimating an actual flow from sensor output containing the time delay and the nonlinearity is presented. In conclusion, according to the result of the experiment, the proposed algorithm shows better accuracy and is faster than the conventional controller.

• Human Ecology Research
• /
• 제54권1호
• /
• pp.27-43
• /
• 2016

This study initiates from the question of whether current advertising regulations are appropriate to be applied to the market. It confirms the relationship between misleading online advertisements of weight-loss food and consumer damages. This study argues that it is necessary to enforce monitoring and regulating (strengthening monitoring) for situations where misleading advertisements are exposed in the market with subsequent consumer damages. However, deregulation is needed for advertisements exposed in the name of misleading advertisements but with no consumer damages. In conclusion, the regulations of current weight loss foods are properly established $vis-{\grave{a}}-vis$ the market situation. However, misleading advertisements are prevalent for all regulated types: Type I (product quality and effect), Type II (endorsement and warranty), Type III (ways to use and safety), Type IV (comparison and superiority), and Type V (company information). Promotion targeting businesses, market monitoring and control are necessary to ensure that advertising regulations (which have existed only as an institution) can be appropriately applied. It is also confirmed that 'comparison advertising' (applicable to Type IV where consumer damages were not shown compared to other regulations) does not have an actual effect as a consumer protection regulation that should be considered in regulation revisions. Consumers also did not recognize Type III and V in the purchasing stage while consumer damages were demonstrated; consequently, this implies that consumers need to check and become attentive to these types.

• 한국의류학회지
• /
• 제44권3호
• /
• pp.427-440
• /
• 2020

This study developed a vest prototype capable of monitoring body temperature using textile electrodes to prevent the sudden death of babies as well as to determine the quality of developed products by evaluating usability with commercial products. Based on the results of the 7th Size Korea Project, a basic pattern for a vest prototype was drafted by applying the average size of two-year-old Korean babies. Two prototypes were the detachable (VEST I) and integrated textile electrodes vest type (VEST II), which followed the same design. The materials were 100% cotton single jersey (SJ) and double jersey (DJ). Six experts evaluated the usability of the developed vests (VEST I & VEST II) and commercial product (VEST M). The single-layer woven textile electrode appeared to have a slightly higher conductivity than the double-layer one. There was no statistical difference in the body temperature sensing function between VEST I and VEST II. Finally, the superiority of the VEST I was verified through a comparison with commercial products (VEST M). The usability test suggested that a wearable smart clothing system of the integrated conductive textile could be further commercialized for bio-monitor applications in Ubiquitous-health care.