• 한국수소및신에너지학회논문집
• /
• 제22권1호
• /
• pp.69-76
• /
• 2011

PEMFC (polymer electrolyte membrane fuel cell) is device that generates electricity from hydrogen. It is one of the subjects related to renewable energy and various research has been conducted on the PEMFC. PEMFC has low operating temperature and high efficiency among fuel cells, and is given attention as means for automobile and domestic use. Analysis of flow field pattern in supplying hydrogen and oxygen is part of the research to increase PEMFC efficiency. In this study, separation plate currently used in PEMFC is transformed to wave shape and mass transfer characteristics in the channel is examined through numerical and experimental analysis. Wave shape separation plate yielded 18% increase of efficiency compared to separation plate used in normal channel. And improvements in mass transfer characteristics were verified.

• 한국수소및신에너지학회논문집
• /
• 제27권5호
• /
• pp.526-532
• /
• 2016

In this study, we synthesized a mediator immobilized biocatalyst([FCA/GOx]/PEI/CNT) by surface modification using ferrocene carboxylic acid(FCA), and evaluated its performance as anode catalyst for biofuel cell. Through the application of FCA on glucose oxidase (GOx), the free amine groups on the lysine residue of GOx surface reacted with carboxylic acid of FCA and make amide bond between GOx and FCA. As the result of that, the electron transfer of catalyst was increased up to 1.91 times($0.468mA{\cdot}cm^{-2}$) than the catalyst without surface modification (GOx/PEI/CNT), and high maxium power density of $1.79mA{\cdot}cm^{-2}$ was gained.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 추계학술대회 논문집
• /
• pp.415-418
• /
• 2005

In the semiconductor and optical industry, a new transport system which can replace the conventional transport systems is required. The transport systems are driven by the magnetic field and conveyer belts. The magnetic field may damage semiconductor and the contact force may scratch the optical lens. The ultrasonic wave driven system can solve these problems. In this semiconductor and optical industry, the non-contact system is required fur reducing the damages. The ultrasonic transportation is the solution of the problem. In this paper, the ultrasonic levitation system fur levitating object are proposed. The 3D vibration profiles of the beam are measured by Laser scanning Vibrometer fur verifying the vibration characteristics of the system and the amplitudes of the beam and the levitation heights of object are measured for evaluating the performance.

• 스마트미디어저널
• /
• 제8권3호
• /
• pp.31-40
• /
• 2019

To understand how a Convolutional Neural Network (CNN) model captures the features of a pattern to determine which class it belongs to, in this paper, we use Gradient-weighted Class Activation Mapping (Grad-CAM) to visualize and analyze how well a CNN model behave on the CNU weeds dataset. We apply this technique to Resnet model and figure out which features this model captures to determine a specific class, what makes the model get a correct/wrong classification, and how those wrong label images can cause a negative effect to a CNN model during the training process. In the experiment, Grad-CAM highlights the important regions of weeds, depending on the patterns learned by Resnet, such as the lobe and limb on 미국가막사리, or the entire leaf surface on 단풍잎돼지풀. Besides, Grad-CAM points out a CNN model can localize the object even though it is trained only for the classification problem.

• 한국압력기기공학회 논문집
• /
• 제19권2호
• /
• pp.93-101
• /
• 2023

In this study, a deep learning algorithm was used to diagnose electric potential signals obtained through CIPS and DCVG, used indirect inspection methods to confirm the soundness of buried pipes. The deep learning algorithm consisted of CNN(Convolutional Neural Network) model for diagnosing the electric potential signal and Grad CAM(Gradient-weighted Class Activation Mapping) for showing the flaw prediction point. The CNN model for diagnosing electric potential signals classifies input data as normal/abnormal according to the presence or absence of flaw in the buried pipe, and for abnormal data, Grad CAM generates a heat map that visualizes the flaw prediction part of the buried pipe. The CIPS/DCVG signal and piping layout obtained from the 3D finite element model were used as input data for learning the CNN. The trained CNN classified the normal/abnormal data with 93% accuracy, and the Grad-CAM predicted flaws point with an average error of 2m. As a result, it confirmed that the electric potential signal of buried pipe can be diagnosed using a CNN-based deep learning algorithm.

• 한국컴퓨터그래픽스학회논문지
• /
• 제25권5호
• /
• pp.11-20
• /
• 2019

딥러닝 기술의 발전으로 가상 현실이나 증강 현실 응용에서 사용하기 적절한 사용자 친화적 인터페이스에 관한 연구가 활발히 이뤄지고 있다. 본 논문은 사용자의 손을 이용한 인터페이스를 지원하기 위하여 손 끝 좌표를 추적하여 가상의 객체를 선택하거나, 공중에 글씨나 그림을 작성하는 행위가 가능하도록 딥러닝 기반 손 끝 객체 탐지 방법을 제안한다. 입력 영상에서 Grad-CAM으로 해당 손 끝 객체의 대략적인 부분을 잘라낸 후, 잘라낸 영상에 대하여 Atrous Convolution을 이용한 합성곱 신경망을 수행하여 손 끝의 위치를 찾는다. 본 방법은 객체의 주석 전처리 과정을 별도로 요구하지 않으면서 기존 객체 탐지 알고리즘 보다 간단하고 구현하기에 쉽다. 본 방법을 검증하기 위하여 Air-Writing 응용을 구현한 결과 평균 81%의 인식률과 76 ms 속도로 허공에서 지연 시간 없이 부드럽게 글씨 작성이 가능하여 실시간으로 활용 가능함을 알 수 있었다.

• 한국수소및신에너지학회논문집
• /
• 제25권1호
• /
• pp.28-38
• /
• 2014

The organic-inorganic composite membrane in polymer exchange membrane fuel cells (PEMFCs) have several fascinating technological advantages such as a proton conductivity, thermal stability and mechanical properties. As the inorganic filler, silicon carbide (SiC) fiber have been used in various fields due to its unique properties such as thermal stability, conductivity, and tensile strength. In this study, composite membrane was successfully fabricated by modified-silicon carbide fiber. Modified process, as a novel process in SiC, takes reaction by phosphoric acid after oxidation process (generated homogeniusly $SiO_2$ layer on SiC fiber). The mechanical property which was conducted by tensile test of the 5wt% modified-$SiO_2@SiCf$ composite membrane was better than that of Aquivion casting membrane as well as ion cxchange capacity(IEC) and proton conductivity. In addition, the single cell performance was observed that the 5wt% modified-$SiO_2@SiCf$ composite membrane was approximately $0.2A/cm^2$ higher than that of a Aquivion casting electrolyte membrane and electrochemical impedance was improved with the charge transfer resistance and membrane resistance.

• 한국정보통신학회논문지
• /
• 제22권12호
• /
• pp.1596-1603
• /
• 2018

화재에 대한 신속한 예측과 경고는 인명 및 재산피해를 최소화시킬 수 있는 필수적인 요소이다. 일반적으로 화재가 발생하면 연기와 화염이 함께 발생하기 때문에 화재 감지 시스템은 연기와 화염을 모두 감지할 필요가 있다. 그러나 대부분의 화재 감지 시스템은 화염 혹은 연기만 감지하며, 화재 감지를 위한 전처리 작업을 추가함에 따라 처리 속도가 느려지는 단점이 있다. 본 연구에서는 다중 레이블 분류(Multi-labeled Classification)를 지원하는 CNN 모델을 구성해서 화염과 연기를 동시에 예측하고, CNN의 특징을 기반으로 클래스에 대한 위치를 시각화하는 Grad-CAM을 이용해서 실시간으로 화재 상태를 모니터링 할 수 있는 화재 감지 시스템을 구현하였다. 또한, 13개의 화재 동영상을 사용해서 테스트한 결과, 화염과 연기에 대해 각각 98.73%와 95.77%의 정확도를 보였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1991년도 하계학술대회 논문집
• /
• pp.201-203
• /
• 1991

T. Kanal et al, were studied the superconducting properties in Bi system by mechanical grinding, in which the authors found that the samples ground degraded from the superconducting phases to nonsuperconducting phases. To obtain more information of the practical application in Bi system with high-Tc phase in this paper, these samples mechanically ground and the high-Tc phase properties of grinding powder samples were investigated.

• 한국수소및신에너지학회논문집
• /
• 제20권5호
• /
• pp.390-396
• /
• 2009

The flooding, especially in channel, is one of the critical issue to put proton exchange membrane fuel cell (PEMFC) to practical use. In this paper, channel flooding was investigated the pressure difference at cathode channel outlet. A ratio of pressure difference changes to 25, 50% as its variation rate. The pressure variable rate is reflected in dimensionless number FN. As a result, modified dimensionless number $FN^*$ correctly predicted the channel flooding. This study analyzes that a variety of pressure difference is how to affect flooding at the cathode of the PEMFC.