• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.17 no.5
• /
• pp.149-154
• /
• 2018

To improve the efficiency and lifetime of filters, we analyze the element distribution at the entrance and exit by using the flow inside a filter, confirming that the internal structure affects the filter efficiency. The flow in the pipe is predicted through computer simulations, and the filtration efficiency of each element is compared through experiments. The efficiency and lifetime of the filter are indirectly improved through the element distribution at the filter outlet according to the internal structure. Because pressure loss from the structure inevitably occurs, the efficiency and lifetime of filters against pressure loss must be considered.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.4
• /
• pp.109-116
• /
• 2019

The mechanical deformation of a battery separator causes internal short-circuiting of the cathode - anode, which directly affects the explosion/ignition of batteries. To increase the mechanical properties of the separator fabricated by electro-spinning, use of a thermal pressing method is inevitable. Therefore, this research aims to maximize the mechanical strength of a porous separator by finding the proper thermal press temperatures given to Electro-spun Polyacrylonitrile (PAN) nanofibers. The different thermal press temperatures $25^{\circ}C$, $50^{\circ}C$, $75^{\circ}C$, and $100^{\circ}C$ were applied to the electro-spun fiber at 30 MPa pressure for one hour. The higher the temperature, the higher the resultant tensile strength; however, a higher temperature also lowered the strain and porosity. Thus, the membrane thermal pressed at $50^{\circ}C$ showed the best mechanical properties and the second highest porosity. Using the data, $50^{\circ}C$ was judged as the best thermal pressing temperature in terms of performance.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.20 no.3
• /
• pp.1-7
• /
• 2021

With the advent of industry 4.0, big data and machine learning techniques are being widely adopted in the maintenance domain. Inverters are widely used in many engineering applications. However, overloading and complex operation conditions may lead to various failures in inverters. In this study, failure mode effect analysis was performed on inverters and voltages collected to investigate the over-voltage effect on capacitors. Several features were extracted from the collected sensor data, which indicated the health state of the inverter. Based on this correlation, the best features were selected for classification. Moreover, random forest classifiers were used to classify the healthy and faulty states of inverters. Different performance metrics were computed, and the classifiers' performance was evaluated in terms of various health features.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.21 no.7
• /
• pp.91-97
• /
• 2022

Pipes transport and supply fuel in various categories; however, corrosion occurs because of the external environment, impurities are mixed in the fuel, and substances leak to the outside, which can lead to serious accidents. Therefore, in this study, inspection equipment using a laser scanner was manufactured to classify conditions according to the degree of corrosion of the outer wall of the pipe, and the corrosion height and maximum value of the pipe were obtained from the surface information. Using the k-means method, it was classified into four states, and the standard of the average height and maximum height of corrosion for each state was derived.

• Journal of the Society of Disaster Information
• /
• v.19 no.2
• /
• pp.421-431
• /
• 2023

Purpose: The purpose of this study is to analyze the safety and disaster prevention effects of the Smart Safety System used to prevent safety accidents in construction machinery and demonstrate its safety. Method: Among construction machines, the behavioral patterns of workers according to the presence or absence of a smart safety system were analyzed for excavators with high risk and frequent accidents. Result: When the smart safety system was installed in the construction machine, the safety of workers from accidents caused by constriction and collision with the construction machine was secured. Conclusion: It is judged that the smart safety system installed in construction machinery can increase the effectiveness of disaster reduction and major disaster prevention related to construction machinery.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.329-330
• /
• 2020

본 논문에서는 Azure 클라우드 플랫폼의 가상서버 호스팅을 이용해 데이터 수집 환경을 구축하고, Azure에서 제공하는 자동화된 기계학습(Automated Machine Learning, AutoML)을 기반으로 데이터 분석 방법에 관한 연구를 수행했다. 가상 서버 호스팅 환경에 LAMP(Linux, Apache, MySQL, PHP)를 설치하여 데이터 수집환경을 구축했으며, 수집된 데이터를 Azure AutoML에 적용하여 자동화된 기계학습을 수행했다. Azure AutoML은 소모적이고 반복적인 기계학습 모델 개발을 자동화하는 프로세스로써 기계학습 솔루션 구현하는데 시간과 자원(Resource)를 절약할 수 있다. 특히, AutoML은 수집된 데이터를 분류와 회귀 및 예측하는데 있어서 학습점수(Training Score)를 기반으로 보유한 데이터에 가장 적합한 기계학습 모델의 순위를 제공한다. 이는 데이터 분석에 필요한 기계학습 모델을 개발하는데 있어서 개발 초기 단계부터 코드를 설계하지 않아도 되며, 전체 기계학습 시스템을 개발 및 구현하기 전에 모델의 구성과 시스템을 설계해볼 수 있기 때문에 매우 효율적으로 활용될 수 있다. 본 논문에서는 NPU(Neural Processing Unit) 학습에 필요한 데이터 수집 환경에 관한 연구를 수행했으며, Azure AutoML을 기반으로 데이터 분류와 회귀 등 가장 효율적인 알고리즘 선정에 관한 연구를 수행했다.

• Journal of Wind Energy
• /
• v.2 no.2
• /
• pp.30-37
• /
• 2011

A floating wind turbine dynamic simulation program, WindHydro, is newly developed taking into account wind inflow and incident wave. WindHydro consists of 5 modules, HDFloat for hydrodynamics, HDProp for hydrodynamic property calculation, HDMoor for mooring dynamics, AeroDyn for aerodynamics, DAFUL for multi-body dynamics with nonlinear elasticity, and interface program that connects each calculation module. A turbulent wind and regular wave load case is simulated for the 5-MW OC3-Hywind with a spar bouy platform and catenary mooring lines. The results are compared with the results of the FAST(developed by NREL). As a result, the overall system responses from WindHydro and FAST agree well although some differences in the generator responses are observed.

• Journal of Digital Convergence
• /
• v.18 no.6
• /
• pp.271-277
• /
• 2020

Machine translation refers to software that translates a source language into a target language, and has been actively researching Neural Machine Translation through rule-based and statistical-based machine translation. One of the important factors in the Neural Machine Translation is to extract high quality parallel corpus, which has not been easy to find high quality parallel corpus of Korean language pairs. Recently, the AI HUB of the National Information Society Agency(NIA) unveiled a high-quality 1.6 million sentences Korean-English parallel corpus. This paper attempts to verify the quality of each data through performance comparison with the data published by AI Hub and OpenSubtitles, the most popular Korean-English parallel corpus. As test data, objectivity was secured by using test set published by IWSLT, official test set for Korean-English machine translation. Experimental results show better performance than the existing papers tested with the same test set, and this shows the importance of high quality data.

• Journal of Periodontal and Implant Science
• /
• v.29 no.3
• /
• pp.593-607
• /
• 1999

치주인대세포는 치주인대의 유지와 개조에 있어서 중요한 역할을 담당하는 섬유아세포성 세포로서, 세포에 가해진 여러가지 조건에 따라 다양한 표현형의 변화를 나타내는 것으로 알려져 있다. 기계적 응력은 치주인대세포의 세포증 식과 밀접히 연관되어 있는 것으로 알려져 있으며, 이는 세포주기 조절인자들의 발현을 증가 시킴으로써 이루어질 것으로 생각되나 그 자세 한 작용기전은 알려져 있지 않다. 그러므로 이 연구의 목적은 기계적 응력이 사람 치주인대세 포의 세포증식과 세포주기 조절인자의 발현에 미치는 영향을 연구하기 위하여 사람 치주인대 세포에 기계적 응력을 가한 후 세포증식을 관찰하고 , 세포주기조절인자들인 p 53 , $p21^{WAF1/CIP1}$ cyclin-dependent kinases(cdks), cyclins 및 proliferating cell nuclear antigen(PCNA)의 단백질 발현 변화를 연구하였다. 본 연구에 사용한 사람 치주인 대세포는 교정치료를 목적으로 발거한 건전한 사람 소구치의 치주인대로부터 explantation culture하여 얻은 후 계대배양을 시행하여 제6 계대의 세포를 사용하였다. 배양한 사람 치주인 대세포를 55-mm Petriperm dish당 $1{\times}10^4$ 개를 분주하고, dish당 1kg의 기계적 응력을 가하면서 12일동안 세포배양을 시행하였다. 사람 치주인대세포의 세포증식은 기계적 응력을 가한 후 8-12일 사이에 현저히 증가하였으며, PCNA 단백질의 발현은 기계적 응력을 가한 후 6-10일 사이에 현저히 증가하였다. 또한 기계적 응력은 사람 치주 대세포의 cdk4, cdk6, cdk2 및 cyclin D1 단백질의 발현을 다소 증가 시켰으나, p53 및 $p21^{WAF1/CIP1}$ 단백질의 발현은 큰 변화가 없었다. 이상의 결과 서 기계적 응력은 사람 치주인대세포 의 p53 및 $p21^{WAF1/CIP1}$ 단백질 발현의 변화 없이 cdks 단백질 발현을 증가시킴으로써 세포증식을 증가시키는 것으로 생각된다.

• Korean Journal of Cognitive Science
• /
• v.12 no.4
• /
• pp.11-27
• /
• 2001

Machine translation (MT) quality assessment is an outstanding problem. In the present situation in which the quality of machine-translated products are far from the user\\`s satisfaction objective evaluation of MT system is a prerequisite to building mutual trust between the users and the vendors stimulating constructive competition among the developers and finally leading to improve the quality of MT systems. Especially there emerges a need for an intensive study on how to evaluate the quality of MT systems from both linguistic and data processing aspects and to secure a steady improvement of the translation quality. With due regard to such points we in this paper present a linguistic evaluation of English-to-Korean machine translation based on a test suite composed of 3.373 sentences that were classified into their linguistic phenomena and complexity levels and report the experimental results made from several commercial MT systems.