• 반도체디스플레이기술학회지
• /
• 제20권2호
• /
• pp.14-18
• /
• 2021

Electric Vehicle industry requires high technologies to stabilize apparatuses for the Coolant heater manufacturing. Vibrations of Leak Machine are one of the most critical factors for causing delivered of the defective product or poor inspection, which are the main reasons of the defects. In this study, the structure of the Leak Machine was analyzed through the experiment and the computer simulation to investigate the main reasons of the vibrations, and further to alter the design for the improved stability. And that design alterations were applied to the machine to identify the effects of those alterations. The result of the study shows that design alterations of the Leak Machine can effectively suppress about 97.8% of the vibrations, and further can improving the Inspection precision of the Coolant heater.

• 반도체디스플레이기술학회지
• /
• 제5권2호
• /
• pp.33-36
• /
• 2006

Many issues arose to use the Pb-free solder as adhesive materials in MEMS ICs and packaging. Then this study for easy and simple sealing method using adhesive materials was carried out to maintain hermetic characteristic in MEMS Package. In this study, Hermetic characteristic using negative PR (XP SU-8 3050 NO-2) as adhesive at the interface of Si test coupon/glass substrate and Si test coupon/LTCC substrate was examined. For experiment, the dispenser pressure was 4 MPa and the $200\;{\mu}m{\Phi}$ syringe nozzle was used. 3.0 mm/sec as speed of dispensing and 0.13 mm as the gap between Si test coupon and nozzle was selected to machine condition. 1 min at $65^{\circ}C$ and 15 min at $95^{\circ}C$ as Soft bake, $200\;mj/cm^2$ expose in 365 nm wavelength as UV expose, 1 min at $65^{\circ}C$ and 6 min at $95^{\circ}C$ as Post expose bake, 60 min at $150^{\circ}C$ as hard bake were selected to activation condition of negative PR. Hermetic sealing was achieved at the Si test coupon/ glass substrate and Si test coupon/LTCC substrate. The leak rate of Si test coupon/glass substrate was $5.9{\times}10^{-8}mbar-l/sec$, and there was no effect by adhesive method. The leak rate of Si test coupon/LTCC substrate was $4.9{\times}10^{-8}mbar-l/sec$, and there was no effect by dispensing cycle. Better leak rate value could be achieved to use modified substrate which prevent PR flow, to increase UV expose energy and to use system that controls gap automatically with vision.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2019년도 학술발표회
• /
• pp.160-160
• /
• 2019

Water is a limited source that needs to be properly managed and distributed to the ever-growing population of the world. Rapid urbanization and development have increased the overall water demand of the world drastically. However, there is loss of billions of liters of water every year due to leakages in water distribution systems. Such water loss means significant financial loss for the utilities as well. World bank estimates a loss of $14 billion annually from wasted water. To address these issues and for the development of efficient and reliable leakage management techniques, high efforts have been made by the researchers and engineers. Over the past decade, various techniques and technologies have been developed for leakage management and leak detection. These include ideas such as pressure management in water distribution networks, use of Advanced Metering Infrastructure, use of machine learning algorithms, etc. For leakage detection, techniques such as acoustic technique, and in recent yeats transient test-based techniques have become popular. Smart Water Grid uses two-way real time network monitoring by utilizing sensors and devices in the water distribution system. Hence, valuable real time data of the water distribution network can be collected. Best results and outcomes may be produced by proper utilization of the collected data in unison with advanced detection and management techniques. Long term reduction in Non Revenue Water can be achieved by detecting, localizing and repairing leakages as quickly and as efficiently as possible. However, there are still numerous challenges to be met and future research works to be conducted in this field.

• 한국융합학회논문지
• /
• 제13권3호
• /
• pp.33-41
• /
• 2022

본 논문에서는 다중 요인을 고려한 천연 가스 누출 정도 예측을 위해 관련 요인을 포함하는 기상청 자료와 천연가스 누출 자료를 통합하고, 요인 분석을 기반으로 중요 특성을 선택하는 머신러닝 기법을 제안한다. 제안된 기법은 3단계 절차로 구성되어 있다. 먼저, 통합 데이터 셋에 대해 선형 보간법을 수행하여 결측 데이터를 보완하는 전처리를 수행한다. 머신러닝 모델 학습 최적화를 위해 OrdinalEncoder(OE) 기반 정규화와 함께 요인 분석을 사용하여 필수 특징을 선택하며, 데이터 셋은 k-평균 클러스터링으로 레이블을 지정한다. 최종적으로 K-최근접 이웃, DT(Decision Tree), RF(Random Forest), NB(Naive Bayes)의 네 가지 알고리즘을 사용하여 가스 누출 수준을 예측한다. 제안된 방법은 정확도, AUC, 평균 표준 오차(MSE)로 평가되었으며, 테스트 결과 OE-F 전처리를 수행한 경우 기존 기법에 비해 성공적으로 개선되었음을 보였다. 또한 OE-F 기반 KNN(OE-F-KNN)은 95.20%의 정확도, 96.13%의 AUC, 0.031의 MSE로 비교 알고리즘 중 최고 성능을 보였다.