• Nuclear Engineering and Technology
• /
• 제55권6호
• /
• pp.2088-2095
• /
• 2023

The safety of nuclear installations is largely determined by the tightness of fuel elements cladding. As the Fukushima nuclear accident showed, the main task in case of loss of power supply is to ensure reliable removal of residual heat release from spent fuel pool (SFP) with irradiated fuel assemblies (IFAs). The paper presents the results of calculated-experimental studies and thermal-hydraulic modeling of temperature storage modes of IFAs in SFP. Experimental studies of SFP's temperature regime and calculated evaluation of residual heat removal due to the thermal conductivity of building structures surrounding the SFP were performed. To ensure the safe operation of research reactors, it's necessary to know the IFA's residual heat power (RHP) in the reactor and SFP, which is determined depending on the operating time of fuel assemblies (FAs) and the IFAs calculated holding time. The FAs operating time depends on the reactor energy output. The IFAs calculated holding time is determined by the fuel burnup, U-235 mass in the fuel, and reactor utilization factor. The IFAs fuel burnup was calculated using the MCU-PTR program. Also presented are the RHP's calculation results using some of the empirical dependencies. The concept of a passive heat removal system (PHRS) based on thermosyphon's operating principle was proposed.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 추계학술발표대회
• /
• pp.700-703
• /
• 2021

Infrared cameras are widely used in recent research for automatic monitoring the abnormal behaviors of the pig. However, when deployed in real pig farms, infrared cameras always get polluted due to the harsh environment of pig farms which negatively affects the performance of pig monitoring. In this paper, we propose a real-time noise-robust infrared camera-based pig automatic monitoring system to improve the robustness of pigs' automatic monitoring in real pig farms. The proposed system first uses a preprocessor with a U-Net architecture that was trained as a GAN generator to transform the noisy images into clean images, then uses a YOLOv5-based detector to detect pigs. The experimental results show that with adding the preprocessing step, the average pig detection precision improved greatly from 0.639 to 0.759.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권7호
• /
• pp.1794-1806
• /
• 2023

This study presents a method for capturing photographs of users as input and converting them into 2D character animation sprites using a generative adversarial network-based artificial intelligence network. Traditionally, 2D character animations have been created by manually creating an entire sequence of sprite images, which incurs high development costs. To address this issue, this study proposes a technique that combines motion videos and sample 2D images. In the 2D sprite generation process that uses the proposed technique, a sequence of images is extracted from real-life images captured by the user, and these are combined with character images from within the game. Our research aims to leverage cutting-edge deep learning-based image manipulation techniques, such as the GAN-based motion transfer network (impersonator) and background noise removal (U² -Net), to generate a sequence of animation sprites from a single image. The proposed technique enables the creation of diverse animations and motions just one image. By utilizing these advancements, we focus on enhancing productivity in the game and animation industry through improved efficiency and streamlined production processes. By employing state-of-the-art techniques, our research enables the generation of 2D sprite images with various motions, offering significant potential for boosting productivity and creativity in the industry.

• Nuclear Engineering and Technology
• /
• 제55권7호
• /
• pp.2483-2488
• /
• 2023

Differential die-away analysis (DDAA) technology is a special nuclear material (SNM) active detection analysis technology. Be a nuclear material shielded or not, the technology can reveal the existence of nuclear materials by inducing fission from an external pulsed neutron source. In this paper, a detection model based on DDAA analysis technology was established by geant4 Monte Carlo simulation software, and the optimal sensitivity of the detection system is achieved by optimizing different configurations. After the geant4 simulation and optimization, a prototype was established, and experimental research was carried out. The result shows that the prototype can detect 200 g of ²³⁵U in a steel cylinder shield that's of 1.5 cm in inner diameter, 10 cm in thickness and 280 kg in weight.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2022년도 제66차 하계학술대회논문집 30권2호
• /
• pp.49-52
• /
• 2022

건물 외벽에 발생하는 균열은 시설물 구조 안전에 영향을 미치며 그 크기에 따라 위험도가 달라진다. 이에 따라 전문검사관의 현장 점검을 통해 발생 균열 두께를 정밀하게 측정할 필요가 있고 최근에는 이러한 현장 안전점검에 인공지능을 도입하려는 추세다. 그러나 기존의 균열 데이터셋은 주로 콘크리트에만 한정되어 다양한 외벽에 강인한 모델을 구축하기 어렵고 균열 두께를 측정하기 위해 정확한 마스크(Mask) 정보가 필요하나 이를 만족하는 데이터셋이 부재하다. 본 논문에서는 다양한 외벽에 강인한 균열 구획화 모델을 목적으로 2,744장의 이미지를 촬영하고 매직 완드 기법으로 라벨링을 진행해 데이터셋을 구축 후, 이를 바탕으로 딥러닝 기반 균열 구획화 모델을 개발했다. UNet-ResNet50을 최종모델로 선정 및 개발 결과, 테스트 데이터셋에 대해 81.22%의 class IoU 성능을 보였다. 본 연구의 기술을 바탕으로 균열 두께를 측정하여 건축물 안전점검에 활용될 수 있기를 기대한다.

• 무역학회지
• /
• 제46권4호
• /
• pp.131-148
• /
• 2021

This study examines how corporate social responsibility (CSR) affects corporate tax avoidance behavior. Using a sample of publicly listed U.S. firms, we find that legal CSR-which is required by law-reduces the level of corporate tax avoidance because this type of CSR reduces information asymmetry between investors and corporate management in such a way that investors are less likely to perceive tax avoidance behavior as a risk. On the other hand, we find that the relationship between normative CSR-which is a voluntary type of CSR behavior-and tax avoidance is not statistically significant. Instead, our additional analysis reveals that normative CSR increases the level of corporate tax avoidance conditional on reporting quality. This study provides meaningful implications to the academic literature and to practitioners. Not only does this study highlight the fact that not all CSR are alike, it highlights that it is important to provide transparent CSR information in order to allow stakeholders to estimate the net effects of firms' CSR activities and tax payment.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.611-614
• /
• 2023

갈비뼈 병변 진단 과정은 방사선 전문의가 CT 스캐너를 통해 생성된 2 차원 CT 이미지들을 해석하며 진행된다. 병변의 위치를 파악하고 정확한 진단을 내리기 위해 수백장의 2차원 CT 이미지들이 세밀하게 검토되며 갈비뼈를 분류한다. 본 연구는 이런 노동 집약적 작업의 문제점을 개선시키기 위해 Biaxial Rib Segmentation(BARS)을 제안한다. BARS 는 흉부 CT 볼륨의 관상면과 수평면으로 구성된 2 차원 이미지들을 U-Net 모델에 학습한다. 모델이 산출한 세그멘테이션 마스크들의 조합은 서로 다른 평면의 공간 정보를 보완하며 3 차원 갈비뼈 볼륨을 재건한다. BARS 의 성능은 DSC, Recall, Precision 지표를 사용해 평가하며, DSC 90.29%, Recall 89.74%, Precision 90.72%를 보인다. 향후에는 이를 기반으로 순차적 갈비뼈 레이블링 연구를 진행할 계획이다.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2024년도 제69차 동계학술대회논문집 32권1호
• /
• pp.45-46
• /
• 2024

본 논문에서는 Self-Attention 기반 딥러닝 기법인 Dense Prediction Transformer(DPT) 모델을 MVTec Anomaly Detection(MVTec AD) 데이터셋에 적용하여 실제 산업 제품 이미지 내 이상 부분을 분할하는 연구를 진행하였다. DPT 모델의 적용을 통해 기존 Convolutional Neural Network(CNN) 기반 이상 탐지기법의 한계점인 지역적 Feature 추출 및 고정된 수용영역으로 인한 문제를 개선하였으며, 실제 산업 제품 데이터에서의 이상 분할 시 기존 주력 기법인 U-Net의 구조를 적용한 최고 성능의 모델보다 1.14%만큼의 성능 향상을 보임에 따라 Self-Attention 기반 딥러닝 기법의 적용이 산업 제품 이상 분할에 효과적임을 입증하였다.

• Nuclear Engineering and Technology
• /
• 제56권2호
• /
• pp.426-436
• /
• 2024

Nuclear security has been emphasized to ensure the safety of the environment and humans, as well as to protect nuclear materials and facilities from malicious attacks. With increasing utilization of nuclear energy and emerging potential threats, there has been a renewed focus on nuclear security. Korea has made efforts to enhance the regulatory oversight processes, both for general and specific legislative systems. While Korea has demonstrated effective nuclear security activities, continuous efforts are necessary to maintain a high level of security and to improve regulatory efficiency in alignment with international standards. In this study, the comprehensive regulatory oversight framework for the security of Korean nuclear facilities has been investigated. For reference, the U.S. regulatory oversight frameworks for nuclear facilities, with a focus on nuclear security, and the motivations of changes in regulatory oversight framework have been identified. By comparing these regulatory programs and frameworks, insights and considerations for enhancing nuclear security regulations have been identified. A comprehensive security inspection program tailored for the Korean regulatory oversight framework has been proposed, and has been preliminarily applied to hypothetical conditions for further discussion.

• Nuclear Engineering and Technology
• /
• 제56권3호
• /
• pp.1022-1028
• /
• 2024

A neutronics study of a supercritical CO₂-cooled fast reactor core for nuclear propulsion has been performed in this work. The thermal power of the reactor core is 30 MWth and a ceramic UO₂ fuel can be used to achieve a 20-year lifetime without refueling. In order to make a compact core with inherent safety features, the drum-type reactivity control system and folding-type shutdown system are adopted. In addition, we suggest a cold shutdown system using gadolinium as a spectral shift absorber (SSA) against flooding. Although there is a penalty of U-235 enrichment for the core embedded with the cold shutdown system, it effectively mitigates the increment of reactivity at the flooding of seawater. In this study, the neutronics analyses have been performed by using the continuous energy Monte Carlo Serpent 2 code with the evaluated nuclear data file ENDF/B-VII.1 Library. The supercritical CO₂-cooled fast reactor core is characterized in view of important safety parameters such as the reactivity worth of reactivity control systems, fuel temperature coefficient (FTC), coolant temperature coefficient (CTC), and coolant temperature-density coefficient (CTDC). We can say that the suggested core has inherent safety features and enough flexibility for load-following operation.