• Nuclear Engineering and Technology
• /
• v.40 no.1
• /
• pp.87-92
• /
• 2008

Tokamak reactor system analysis code was developed at KAERI (Korea Atomic Energy Research Institute) and is used here for the conceptual development of a DEMO reactor. In the system analysis code, prospects of the development of plasma physics and the relevant technology are included in a simple mathematical model, i.e., the overall plant power balance equation and the plasma power balance equation. This system analysis code provides satisfactory results for developing the concept of a DEMO reactor and for identifying the necessary R&D areas, both in the physics and technology areas for the realization of the concept. With this system analysis code, the performance of a DEMO reactor with a limited extension of the plasma physics and technology adopted in the ITER design. The main requirements for the DEMO reactor were selected as: 1) demonstrate tritium self-sufficiency, 2) generate net electricity, and 3) achieve a steady-state operation. It was shown that to access an operational region for higher performance, the main restrictions are presented by the divertor heat load and the steady-state operation requirements.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.11
• /
• pp.4426-4442
• /
• 2020

Since scene segmentation is becoming a hot topic in the field of autonomous driving and medical image analysis, researchers are actively trying new methods to improve segmentation accuracy. At present, the main issues in image semantic segmentation are intra-class inconsistency and inter-class indistinction. From our analysis, the lack of global information as well as macroscopic discrimination on the object are the two main reasons. In this paper, we propose a Densely connected residual Attention network (DA-Res2Net) which consists of a dense residual network and channel attention guidance module to deal with these problems and improve the accuracy of image segmentation. Specifically, in order to make the extracted features equipped with stronger multi-scale characteristics, a densely connected residual network is proposed as a feature extractor. Furthermore, to improve the representativeness of each channel feature, we design a Channel-Attention-Guide module to make the model focusing on the high-level semantic features and low-level location features simultaneously. Experimental results show that the method achieves significant performance on various datasets. Compared to other state-of-the-art methods, the proposed method reaches the mean IOU accuracy of 83.2% on PASCAL VOC 2012 and 79.7% on Cityscapes dataset, respectively.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.06a
• /
• pp.1305-1307
• /
• 2022

자동차 부품의 결함은 시스템 전체의 성능 저하 및 인적 물적 손실이 발생할 수 있으므로 생산라인에서의 불량 검출은 매우 중요하다. 따라서 정확하고 균일한 결과의 불량 검출을 위해 딥러닝 기반의 고장 진단 시스템이 다양하게 연구되고 있다. 하지만 제조현장에서는 정상 샘플보다 비정상 샘플의 발생 빈도가 현저히 낮다. 이는 학습 데이터의 클래스 불균형 문제로 이어지게 되고, 이러한 불균형 문제는 고장을 판별하는 분류 모델의 성능에 영향을 끼치게 된다. 이에 본 연구에서는 모터의 동작음으로부터 불량 모터를 판별하는 불량 검출 시스템 설계를 위한 데이터 불균형 해결 방법을 제안한다. 자동차 사이드 미러 모터의 동작음을 학습 및 테스트를 위한 데이터 셋으로 사용하였으며 손실함수 계산 시 학습 데이터 셋의 클래스별 샘플 수 가 반영되는 label-distribution-aware margin(LDAM) loss 와 Inception, ResNet, DenseNet 신경망 모델의 비교 분석을 통해 불균형 데이터를 처리할 수 있는 가능성을 보여주었다.

• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.92-99
• /
• 2023

Autonomous vehicles should recognize and respond to the specified speed to drive in compliance with regulations. To recognize the specified speed, the most representative method is to read the numbers of the signs by recognizing the speed signs in the front camera image. This study proposes a method that utilizes YOLO-Labeling-Labeling-EfficientNet. The sign box is first recognized with YOLO, and the numeric digit is extracted according to the pixel value from the recognized box through two labeling stages. After that, the number of each digit is recognized using EfficientNet (CNN) learned with the virtual environment dataset produced directly. In addition, we estimated the depth of information from the height value of the recognized sign through regression analysis. We verified the proposed algorithm using the virtual racing environment and GTSRB, and proved its real-time performance and efficient recognition performance.

• Nuclear Engineering and Technology
• /
• v.52 no.4
• /
• pp.827-834
• /
• 2020

Damage of tungsten due to helium ions of a PF device was studied. The tungsten was analyzed by SEM and AFM after irradiation. SEM revealed fine bubbles of helium atoms with diameters of a few nanometers, which join and form larger bubbles and blisters on the surface of tungsten. This observation confirmed the results of molecular dynamics simulation. SEM analysis after etching of the irradiated surface indicated cavities with depth range of 35-85 nm. The average fluence of helium ion of the PF device was calculated about 5.2 × 10¹⁵ cm^-2 per shot, using Lee code. Energy spectrum of helium ions was estimated using a Thomson parabola spectrometer as a function of dN/dE ∝ E^-2.8 in the energy range of 10-200 keV. The characteristics of helium ion beam was imported to SRIM code. SRIM revealed that the maximum DPA and maximum helium concentration occur in the depth range of 20-50 nm. SRIM also showed that at depth of 30 nm, all of the tungsten atoms are displaced after 20 shots, while at depth of higher than 85 nm the destruction is insignificant. There is a close match between SRIM results and the measured depths of cavities in SEM images of tungsten after etching.

• Nuclear Engineering and Technology
• /
• v.54 no.10
• /
• pp.3717-3723
• /
• 2022

For the first time, two-dimensional temporal behavior of the edge localized mode (ELM) filament is measured in the edge tokamak plasma with a multi-channel electrical probe array (MCEP). MCEP, which has 16 floating probes (4 × 4), is mounted at the far scrape-off layer (SOL) region in the KSTAR. An electron temperature and an ion flux are measured by sideband method (SBM), which can achieve two-dimensional measurements with high time resolution. Furthermore, temporal evolutions of the electron temperature and the ion flux are obtained during the ELM occurrence. In the H-mode period, short spikes from ELM bursts are observed in measured plasma parameters, and the trend is similar to that of typical Hα signal. Interestingly, when blob-like ELM filaments crash the probe, the heat flux is significantly higher in a local region of the probe array. The results show that our probe array using the SBM can measure the ELM behavior and the plasma parameters without the effect of the stray current caused by the huge device. This study can provide valuable data needed to understand the interaction between the SOL plasma and the plasma facing components (PFCs).

• Nuclear Engineering and Technology
• /
• v.55 no.8
• /
• pp.2966-2976
• /
• 2023

A tritium breeder is a lithium-based material capable of producing tritium. Many researchers designing nuclear-fusion energy are studying tritium production using pebbles, which are solid-type breeders. The sphericity and size of the pebbles are critical in obtaining pebbles with good tritium-breeding efficiency. Furthermore, tritium-release efficiency can be increased by using pebbles with appropriate porosities. Promising raw materials for tritium-breeding materials include Li₄SiO₄ and Li₂TiO₃. Li₄SiO₄ has a higher lithium density than Li₂TiO₃ and exhibits excellent tritium-breeding efficiency. However, it has the disadvantage of being easily decomposed during the Li₄SiO₄-green-pebble sintering process because of its low structural stability at high temperatures and high lithium density. In this study, we attempted to determine the optimal conditions for manufacturing Li₄SiO₄ pebbles using the droplet-freeze-drying method. The optimal Li₄SiO₄ slurry conditions and sintering temperatures were determined. The optimal Li₄SiO₄ slurry-fabrication conditions were 3 wt% polyvinyl alcohol and 75 wt% Li₄SiO₄ based on the deionized-water weight content. The sintering temperature at which Li₄SiO₄ did not decompose and exhibited the optimum porosity of 10.8% was 900 ℃.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1283-1297
• /
• 2023

Mid-wave infrared (MWIR) imagery, due to its ability to capture the temperature of land cover and objects, serves as a crucial data source in various fields including environmental monitoring and defense. The KOMPSAT-3A satellite acquires MWIR imagery with high spatial resolution compared to other satellites. However, the limited spatial resolution of MWIR imagery, in comparison to electro-optical (EO) imagery, constrains the optimal utilization of the KOMPSAT-3A data. This study aims to create a highly visible MWIR fusion image by leveraging the edge information from the KOMPSAT-3A panchromatic (PAN) image. Preprocessing is implemented to mitigate the relative geometric errors between the PAN and MWIR images. Subsequently, we employ a pre-trained pixel difference network (PiDiNet), a deep learning-based edge information extraction technique, to extract the boundaries of objects from the preprocessed PAN images. The MWIR fusion imagery is then generated by emphasizing the brightness value corresponding to the edge information of the PAN image. To evaluate the proposed method, the MWIR fusion images were generated in three different sites. As a result, the boundaries of terrain and objects in the MWIR fusion images were emphasized to provide detailed thermal information of the interest area. Especially, the MWIR fusion image provided the thermal information of objects such as airplanes and ships which are hard to detect in the original MWIR images. This study demonstrated that the proposed method could generate a single image that combines visible details from an EO image and thermal information from an MWIR image, which contributes to increasing the usage of MWIR imagery.

• Nuclear Engineering and Technology
• /
• v.56 no.4
• /
• pp.1501-1512
• /
• 2024

Plasma disruption in tokamak experiments is a challenging issue that causes damage to the device. Reliable prediction methods are needed, but the lack of full understanding of plasma disruption limits the effectiveness of physics-driven methods. Data-driven methods based on supervised learning are commonly used, and they rely on labelled training data. However, manual labelling of disruption precursors is a time-consuming and challenging task, as some precursors are difficult to accurately identify. The mainstream labelling methods assume that the precursor onset occurs at a fixed time before disruption, which leads to mislabeled samples and suboptimal prediction performance. In this paper, we present disruption prediction methods based on anomaly detection to address these issues, demonstrating good prediction performance on J-TEXT and EAST. By evaluating precursor onset times using different anomaly detection algorithms, it is found that labelling methods can be improved since the onset times of different shots are not necessarily the same. The study optimizes precursor labelling using the onset times inferred by the anomaly detection predictor and test the optimized labels on supervised learning disruption predictors. The results on J-TEXT and EAST show that the models trained on the optimized labels outperform those trained on fixed onset time labels.

• The Journal of Korean Institute of Information Technology
• /
• v.16 no.11
• /
• pp.105-113
• /
• 2018

In this paper, we proposed a method for effective classification of eye, nose, and mouth of human face. Most recent image classification uses Convolutional Neural Network(CNN). However, the features extracted by CNN are not sufficient and the classification effect is not too high. We proposed a new algorithm to improve the classification effect. The proposed method can be roughly divided into three parts. First, the Haar feature extraction algorithm is used to construct the eye, nose, and mouth dataset of face. The second, the model extracts CNN features of image using AlexNet. Finally, Haar-CNN features are extracted by performing convolution after Haar feature extraction. After that, CNN features and Haar-CNN features are fused and classify images using softmax. Recognition rate using mixed features could be increased about 4% than CNN feature. Experiments have demonstrated the performance of the proposed algorithm.