• 한국멀티미디어학회논문지
• /
• 제23권12호
• /
• pp.1476-1485
• /
• 2020

Segmenting OCT retinal images into layers is important to diagnose and understand the progression of retinal diseases or identify potential symptoms. The task of manually identifying these layers is a difficult task that requires a lot of time and effort even for medical professionals, and therefore, various studies are being conducted to automate this using deep learning technologies. In this paper, we use cGAN-based neural network to automatically segmenting OCT retinal images into seven terrain-type regions defined by six layer boundaries. The network is composed of a Segnet-based generator model and a discriminator model. We also proposed a dynamic programming algorithm for refining the outputs of the network. We performed experiments using public OCT image data set and compared its performance with the Segnet-only version of the network. The experimental results show that the cGAN-based network outperforms Segnet-only version.

• KEPCO Journal on Electric Power and Energy
• /
• 제8권2호
• /
• pp.137-141
• /
• 2022

To inspect the power facility faults using artificial intelligence, it need that improve the accuracy of the diagnostic model are required. Data augmentation skill using generative adversarial network (GAN) is one of the best ways to improve deep learning performance. GAN model can create realistic-looking fake images using two competitive learning networks such as discriminator and generator. In this study, we intend to verify the effectiveness of virtual data generation technology by including the fake image of power facility generated through GAN in the deep learning training set. The GAN-based fake image was created for damage of LP insulator, and ResNet based normal and defect classification model was developed to verify the effect. Through this, we analyzed the model accuracy according to the ratio of normal and defective training data.

• 한국군사과학기술학회지
• /
• 제26권4호
• /
• pp.324-334
• /
• 2023

In this paper, the target simulator for RF signals was developed by using VST(Vector Signal Transceiver) and set by real-time signal processing SW programs. A function to process RF signals using FPGA(Field Programmable Gate Array) board was designed. The system functions capable of data processing, raw signals monitoring, target signals(simulated range, velocity) generating and RF environments data analyzing were implemented. And the characteristics of modulated signal were analyzed in RF environment. All function of programs for processing RF signal have options to store signal data and to manage the data. The validity of the signal simulation was confirmed through verification of simulated signal results.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1987년도 한국자동제어학술회의논문집; 한국과학기술대학, 충남; 16-17 Oct. 1987
• /
• pp.631-636
• /
• 1987

The design of ultrasonic transducer energy processing systems requires highly reliable command featuring mechanical frequency tracking and constant velocity control of the ultrasonic transducer with an acoustic load. This paper presents a new conceptional instantaneous current resultant control base high-frequency inverter using self turn-off devices driving an electrostrictive ultrasonic transducer system and its optimum control technique, which is implemented by feed-back of the ultrasonic transducer applied voltage and instantaneous velocity of the transducer vibrating system through a Phase-Locked-Loop control scheme. The feedback voltage corresponding to instantaneous velocity is averaged over a half-period with respect to constant amplitude/constant velocity control strategy. Described are the theory of this signal detection technique and the experimental set-up.

• 한국진공학회:학술대회논문집
• /
• 한국진공학회 2015년도 제49회 하계 정기학술대회 초록집
• /
• pp.139.2-139.2
• /
• 2015

In this study, We applied the magnetic field that has CW frequency and AM frequency to heating magnetic nano powder. For this experiment, We set up the devices flat-type magnetic field generator with CW frequency and AM frequency. We supplied the current to encircling coil by adjusting the power of generating of magnetic field device for AC voltage through Slidacs and using way of LC resonance circuit and SMPS(Switching Mode Power Supply). Above the encircling coil, We covered the circular flat insulator like glass. And we located the well plate containing the magnetic nano powder liquor above the circular flat insulator and exposed the magnetic field to this well plate. Using the flat-type magnetic field generator with CW and AM frequency and the magnetic field measurement sensor(Magnetic pick up coil or Hall sensor), We measured the strength of the magnetic field of circular flat insulator's surface in each position. The temperature of the magnetic nano powder in the well plate was quantitatively measured by the magnetic field strength through the Fluoroptic thermometer.

• 대한기계학회논문집B
• /
• 제37권12호
• /
• pp.1061-1068
• /
• 2013

본 연구에서는 선행연구에서 제시된 태양열원식 해수 담수기 모델에 디젤 발전기 폐열을 적용하였을 때 설계변수에 따른 담수량을 수치해석을 통하여 예측하고, 최적설계를 위한 자료를 제시하고자 하였다. 선행연구를 기초로 수학적 모델을 설정하였고, 폐열 회수관으로부터의 열교환량을 고려하였다. 해석의 결과를 선행연구의 결과와 비교 분석하여 해석의 타당성을 확보하였고, 타당성이 검증된 해석모델을 적용하여 여러 가지 설계 변수에 따른 담수량을 예측하였다. 결과적으로 선행연구와 전반적으로 일치한 해석결과를 확인하였고, 디젤 발전기 폐열을 적용하였을 때 담수량 향상정도를 확인하였다. 또한 수치해석을 통하여 최적의 효용단 수, 유리덮개 경사각 등을 결정하였다.

• 전력전자학회논문지
• /
• 제13권2호
• /
• pp.128-134
• /
• 2008

독립형 전원시스템에서 엔진을 이용한 발전시스템은 지금까지 에너지의 효율적인 측면보다는 설치 단가 및 신뢰성이 중요한 이슈가 되어왔으나, 최근 들어 신뢰성과 함께 에너지의 효율적 사용, 대기 환경 개선 및 발전 전력 품질 등이 점차 중요시 되어가고 있다. 가변속 엔진 발전 시스템의 경우 출력 전력에 대응하여 엔진 속도를 가변함으로써, 경부하시 획기적인 효율 개선이 가능하다. 또한 부하 전압, 주파수는 출력 인버터에 의해 제어되므로, 그 응답 속도가 빨라 고 품질의 전력을 전원에 공급할 수 있다. 특히 급격한 부하 증가 시 엔진 출력이 늘어나는 시간동안 부족한 전력을 슈퍼캐패시터로부터 공급받음으로써, 부하 급증 시에도 안정된 전력 공급이 가능하다. 본 논문에서는 소형 디젤 엔진과 슈퍼캐패시터를 이용한 가변속 엔진 발전 시스템의 개념을 설명하고, 가변속 운전의 필요성, 고정 운전속 대비 연비 절감 및 3상 4선식 인버터를 사용한 고품질의 전력 공급 등의 타당성을 모의 실험과 실험을 통하여 검증하도록 한다.

• Journal of electromagnetic engineering and science
• /
• 제18권1호
• /
• pp.63-69
• /
• 2018

This work demonstrates attenuation effects of plasma on waves propagating in the 26.5-40 GHz range. The effect is investigated via experiments measuring the transmission between two Ka-band horn antennas set 30 cm apart. A dielectric-barrier-discharge (DBD) plasma generator with a size of $200mm{\times}100mm{\times}70mm$ and consisting of 20 layers of electrodes is placed between the two antennas. The DBD generator is placed in a $400mm{\times}300mm{\times}400mm$ acrylic chamber so that the experiments can be performed for plasma generated under various conditions of gas and pressure, for instance, in air, Ar, and He environments at 0.001, 0.05, and 1 atm of pressure. Attenuation is calculated by the difference in the transmission level, with and without plasma, which is generated with a bias voltage of 20 kV in the 0.1-1.4 kHz range. Results show that the attenuation varies from 0.05 dB/m to 9.0 dB/m depending on the environment. Noble gas environments show higher levels of attenuation than air, and He is lossier than Ar. In all gas environments, attenuation increases as pressure increases. Finally, electromagnetic models of plasmas generated in various conditions are provided.

• Journal of Electrical Engineering and Technology
• /
• 제12권6호
• /
• pp.2099-2105
• /
• 2017

In a power system that has a high wind penetration, the output power fluctuation of a large-scale wind turbine generator (WTG) caused by the varying wind speed increases the maximum frequency deviation, which is an important metric to assess the quality of electricity, because of the reduced system inertia. This paper proposes a stable power-smoothing scheme of a doubly-fed induction generator (DFIG) that can suppress the maximum frequency deviation, particularly for a power system with a high wind penetration. To do this, the proposed scheme employs an additional control loop relying on the system frequency deviation that operates in combination with the maximum power point tracking control loop. To improve the power-smoothing capability while guaranteeing the stable operation of a DFIG, the gain of the additional loop is modified with the rotor speed and frequency deviation. The gain is set to be high if the rotor speed and/or frequency deviation is large. The simulation results based on the IEEE 14-bus system demonstrate that the proposed scheme significantly lessens the output power fluctuation of a WTG under various scenarios by modifying the gain with the rotor speed and frequency deviation, and thereby it can regulate the frequency deviation within a narrow range.

• 대한기계학회논문집B
• /
• 제27권11호
• /
• pp.1618-1629
• /
• 2003

The effects of the interaction between flow field and heat transfer caused by the longitudinal vortices are experimentally investigated using a five hole probe and a transient liquid crystal technique. The test facility consists of a wind tunnel with vortex generators protruding from a bottom surface and a mesh heater. In order to control the strength of the longitudinal vortices, the angle of attack of vortex generators used in the present experiment is 20$^{\circ}$, and the spacing between the vortex generators is 25mm. The height and cord length of the vortex generator is 20mm and 50mm, respectively. Three-component mean velocity measurements are made using a f-hole probe system, and the surface temperature distribution is measured by the hue capturing method using a transient liquid crystal technique. The transient liquid crystal technique in measuring heat transfer has become one of the most effective ways in determining the full surface distributions of heat transfer coefficients. The key point of this technique is to convert the inlet flow temperature into an exponential temperature profile using the mesh heater set up in the wind tunnel. The conclusions obtained in the present experiment are as follows: The two maximum heat transfer values exist over the whole domain, and as the longitudinal vortices move to the farther downstream region, these peak values show the decreasing trends. These trends are also observed in the experimental results of other researchers to have used the uniform heat flux method.