• Proceedings of the Korea Water Resources Association Conference
• /
• 2022.05a
• /
• pp.183-183
• /
• 2022

최근 몇 년 동안 기후변화에 대응하기 위한 탄소중립 혹은 저탄소 운영의 중요성이 강조되어왔다. 상수도 관망은 직접적인 탄소 배출 시설물은 아니지만, 상수도 관망의 운영 그리고 구성요소의 제조부터 폐기까지의 전 생애주기 동안 막대한 양의 에너지를 사용하는데, 이러한 에너지의사용이 탄소 배출에 간접적인 영향을 주는 것으로 알려져 있다. 특히 수자원공사에 따르면, '17년 기준 수도사업 관련 전기 사용에 따른 간접 배출이 70만tCO2eq에 이르는 것으로 보고되고 있어, 에너지의 효율적인 운영 및 자산관리 체계의 필요성이 커지고 있는 실정이다. 상수도 관망의 에너지 효율에 영향을 주는 요인은 크게 구성요소의 노후와 누수로 구분할 수 있다. 본 연구에서는 상수도 관망 관로 별 노후와 누수 여부를 판단하여 교체 전략을 수립할 수 있는 자산관리 모형을 제안하고 관로별 에너지 효율을 시각화하여 전반적인 자산관리에 근거를 제시하고자 한다. 모형은 최적화 기법을 통한 관로별 기능적 노후도 산정 및 누수 탐지, 관만 내 누수 지역화, 에너지 효율 시각화 등 총 3개의 모듈로 구성되어 있다. 제안한 모형은 고도의 차이가 큰 국내 D시 가상 관망에 적용하였다. 해당 관망에 다양한 관로의 노후 및 누수 상황을 가정하여 가상의 데이터를 생성하고 이를 토대로 관로별 기능적 노후와 누수 조건을 고려하여 해당 모형을 검증한다. 또한, 노후와 누수에 따른 가상 상황별 관로의 자산관리 의사결정 예시를 제공하여 향후 모형의 활용에 대한 가이드 라인을 제시한다. 마지막으로 관망 내 설치된 감압밸브를 터빈으로 전환하여 관망 운영 단계에서 무의미하게 소산되는 열에너지를 회수하는 방안을 검증하였다. 최적화 기법을 통해 비용 대비 최적 터빈 설치 지역을 선정하였고 향후 터빈 설치에 고려해야 할 사항을 정리한다. 본 연구에서의 결과는 향후 종합적인 저탄소형 상수도 관망을 위한 초석을 제공할 것으로 기대한다.

• Annual Conference of KIPS
• /
• 2022.05a
• /
• pp.520-523
• /
• 2022

일본 우주항공연구개발기구(Japan Aerospace Exploration Agency, JAXA)는 2007년부터 2017년까지 달 탐사선 셀레네(Selenological and Engineering Explorer, SelEnE)가 관측한 데이터를 수집하고, 연구했다. JAXA는 지구 상층 대기에 존재하는 산소가 자기장의 꼬리 부분에 실려 달로 이동한다는 사실을 발견했다. 하지만 이 연구는 아직 진행 중이며 달의 산화 과정 규명에 추가 연구가 필요하다. 본 논문에서는 생성적 적대 신경망(Generative Adversarial Networks, GAN)으로 달 분화구의 영구 그림자 영역을 제거하고, 물과 얼음을 발견하여 선행 연구의 완성도를 향상하고자 한다. 실험에 사용할 모델은 CIPS(Conditionally Independent Pixel Synthesis)다. CIPS는 실제 같은 영상을 고해상도로 합성한다. 합성할 데이터의 최적인 가중치 초기화 및 파라미터 갱신 방법, 활성 함수 조합은 실험을 통해 확인한다. 필요에 따라 앙상블 학습을 할 수도 있다. 성능평가는 FID(Frechet Inception Distance), 정밀도, 재현율을 사용한다. 제안한 방법은 진행 중인 연구의 시간과 비용을 절약하고, 인과관계를 더욱 명확히 밝히는 데 도움 될 수 있다고 사료된다.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.11a
• /
• pp.351-356
• /
• 2022

Among the path planning methods used to generate the ship's path, the graph search-based method is widely used because it has the advantage of its completeness, optimality. In order to apply the graph-based search method to the berthing path plan, the deviation from the path must be minimized. Path following suitability should be considered essential, since path deviation during berthing can lead to collisions with berthing facilities. However, existing studies of graph search-based berthing path planning are dangerous for application to real-world navigation environments because they produce results with a course change just before berthing. Therefore, in this paper, we develop a cost function suitable for path following, and propose a 3D A* algorithm that applies it. In addition, in order to evaluate the suitability for the actual operating environment, the results of the path generation of the algorithm are compared with the trajectory of the data collected by manned operations.

• Journal of Practical Agriculture & Fisheries Research
• /
• v.19 no.1
• /
• pp.109-117
• /
• 2017

In the production of organic Panax ginseng, the morphological changes were confirmed by providing general water and microbubble water, respectively. Analysis of seedling ginseng treated with general water and bubbles water revealed that many seedlings were formed in the seedling treated with bubble water, and about 15% weight increase occurred in the growing period. The growth rate of stem, leaf, and root was about 15% higher than that of all. Taken together, the growth of seedling cultivation using bubble water was about 15% overall. In order to process ginseng, the dried ginseng was higher in dry weight than the general water seedling seedlings grown in bubble water. This suggests that more processed products will be produced per unit weight at the time of producing the processed products at the farm, which can directly increase the farm income.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.137-147
• /
• 2023

LiDAR is used in autonomous driving and various industrial fields to measure the size and distance of an object. In addition, the sensor also provides intensity images based on the amount of reflected light. This has a positive effect on sensor data processing by providing information on the shape of the object. LiDAR guarantees higher performance as the resolution increases but at an increased cost. These conditions also apply to LiDAR intensity images. Expensive equipment is essential to acquire high-resolution LiDAR intensity images. This study developed artificial intelligence to improve low-resolution LiDAR intensity images into high-resolution ones. Therefore, this study performed parameter analysis for the optimal super-resolution neural network model. The super-resolution algorithm was trained and verified using 2,500 LiDAR intensity images. As a result, the resolution of the intensity images were improved. These results can be applied to the autonomous driving field and help improve driving environment recognition and obstacle detection performance

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.44 no.1
• /
• pp.117-124
• /
• 2024

The objective of Value Engineering (VE) is to derive the optimal value at the most efficient life cycle cost, comprising three stages: Pre-Study, Study, and Post-Study. In this study, we propose a method for information collection and analysis during planned site visit surveys in the preparation stage of VE. The 3D spatial model, created using a drone, facilitated observation and analysis of the study area from various angles, both from the center and the outside. Additionally, through the utilization of drones, we conducted on-site investigations of the research area's 3D spatial model, enabling a macroscopic perspective previously only feasible through a microscopic viewpoint during planned site visits in the pre-study phase. Furthermore, the utilization of actual spatial data obtained from observations allowed for real-time information verification during Design VE workshops, enhancing the efficiency and reliability of the VE project.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.93-104
• /
• 2024

Demand response is a strategy that encourages customers to adjust their consumption patterns at times of peak demand with the aim to improve the reliability of the power grid and minimize expenses. The integration of renewable energy sources into smart grids poses significant challenges due to their intermittent and unpredictable nature. Demand response strategies, coupled with reinforcement learning techniques, have emerged as promising approaches to address these challenges and optimize grid operations where traditional methods fail to meet such kind of complex requirements. This research focuses on investigating the application of reinforcement learning algorithms in demand response for renewable energy integration. The objectives include optimizing demand-side flexibility, improving renewable energy utilization, and enhancing grid stability. The results emphasize the effectiveness of demand response strategies based on reinforcement learning in enhancing grid flexibility and facilitating the integration of renewable energy.

• Composites Research
• /
• v.37 no.3
• /
• pp.226-231
• /
• 2024

Coal ash has been used as a sand replacement in the construction industry. Due to the use of bituminous coal as a result of anthracite depletion, and quicklime as an air purifier in the desulfurization process, pop-out defects have recently occurred in concrete using coal ash, severely limiting the recycling of coal ash into concrete. In this study, the components that cause the pop-out problem of the coal ash filled concrete were identified and a pretreatment method to fully expand the expansive components in advance was proposed as a solution to this problem. By treating water twice for 10 min, allowing the CaO mixed in the coal ash to fully expand, the problems of pop-out and reduced compressive strength of the concrete were overcome. The cost and time efficient water treatment method proposed in this study is expected to promote the recycling of coal ash into concrete.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.23-32
• /
• 2024

Large-scale fires and their consequential damages are becoming increasingly common, but confidence in fire detection systems is waning. Recently, widely-used chemical fire detectors frequently generate lots of false alarms, while video-based deep learning fire detection is hampered by its time-consuming and expensive nature. To tackle these issues, this study proposes a fire detection model utilizing an autoencoder approach. The objective is to minimize false alarms while achieving swift and precise fire detection. The proposed model, employing an autoencoder methodology, can exclusively learn from normal data without the need for fire-related data, thus enhancing its adaptability to diverse environments. By amalgamating data from five distinct sensors, it facilitates rapid and accurate fire detection. Through experiments with various hyperparameter combinations, the proposed model demonstrated that out of 14 scenarios, only one encountered false alarm issues. Experimental results underscore its potential to curtail fire-related losses and bolster the reliability of fire detection systems.

• Journal of the Korean Institute of Gas
• /
• v.24 no.2
• /
• pp.1-8
• /
• 2020

Centrifugal pump is a facility that transfers energy to fluid through centrifugal force, which is usually generated by rotating the impeller at high speed, and is a major process facility used in many LNG production bases such as vaporization seawater pump, industrial water and fire extinguishing pump using seawater. to be. Currently, pumps in LNG plant sites are subject to operating conditions that vary depending on the amount of supply desired by the customer for a long period of time. Pumps in particular occupy a large part of the consumption strategy at the plant site, and if the optimum operation condition is not available, it can incur enormous energy loss in long term plant operation. In order to solve this problem, it is necessary to identify the performance deterioration factor through the flow analysis and the result analysis according to the fluctuations of the pump's operating conditions and to determine the optimal operation efficiency. In order to evaluate operation efficiency through experimental techniques, considerable time and cost are incurred, such as on-site operating conditions and manufacturing of experimental equipment. If the performance of the pump is not suitable for the site, and the performance of the pump needs to be reduced, a method of changing the rotation speed or using a special liquid containing high viscosity or solids is used. Especially, in order to prevent disruptions in the operation of LNG production bases, a technology is required to satisfy the required performance conditions by processing the existing impeller of the pump within a short time. Therefore, in this study, the rotation difference of the pump was applied to the ANSYS CFX program by applying the modified 3D modeling shape. In addition, the results obtained from the flow analysis and the curve fitting toolbox of the MATLAB program were analyzed numerically to verify the outer diameter correction theory.