Reinforcement learning (RL) is successfully applied to various engineering fields. RL is generally used for structural control cases to develop the control algorithms. On the other hand, a machine learning (ML) is adopted in various research to make automated structural design model for reinforced concrete (RC) beam members. In this case, ML models are developed to produce results that are as similar to those of training data as possible. The ML model developed in this way is difficult to produce better results than the training data. However, in reinforcement learning, an agent learns to make decisions by interacting with an environment. Therefore, the RL agent can find better design solution than the training data. In the structural design process (environment), the action of RL agent represent design variables of RC beam. Because the number of design variables of RC beam section is many, multi-agent DQN (Deep Q-Network) was used in this study to effectively find the optimal design solution. Among various versions of DQN, Double Q-Learning (DDQN) that not only improves accuracy in estimating the action-values but also improves the policy learned was used in this study. American Concrete Institute (318) was selected as the design codes for optimal structural design of RC beam and it was used to train the RL model without any hand-labeled dataset. Six agents of DDQN provides actions for beam with, beam depth, bottom rebar size, number of bottom rebar, top rebar size, and shear stirrup size, respectively. Six agents of DDQN were trained for 5,000 episodes and the performance of the multi-agent of DDQN was evaluated with 100 test design cases that is not used for training. Based on this study, it can be seen that the multi-agent RL algorithm can provide successfully structural design results of doubly reinforced beam.

Vertical takeoff and landing (VTOL) drones are increasingly recognized as an important solution for last-mile delivery in the food and beverage sector, owing to their rapid deployment capabilities and high operational flexibility. In particular, growing interest in drone delivery services has been observed among fast food and coffee franchises, where rapid delivery is essential due to the time-sensitive nature of food and beverage items intended for immediate consumption. Despite this trend, there remains a lack of research on the structural modeling of flight routes for VTOL drones operating under automatic flight conditions, and on the implementation of first-come-first-served (FCFS) delivery services utilizing predefined flight routes. Accordingly, this study comprehensively describes the operations for food and beverage delivery services using VTOL drones. In particular, it addressed the use of multiple drones to conduct FCFS-type multi-point delivery services along fixed routes suitable for automatic flight.

Fault detection in electromechanical systems plays a significant role in product quality and manufacturing efficiency during the transition to smart manufacturing. Because collecting a sufficient number of datasets under faulty conditions of the system is challenging in practical industrial sites, unsupervised fault detection methods are mainly used. Although fault datasets accumulate during machine operation, it is not straightforward to utilize the information it contains for fault detection after the deep learning model has been trained in an unsupervised manner. However, the information in fault datasets is expected to significantly contribute to fault detection. In this regard, this study aims to validate the effectiveness of the transition from unsupervised to supervised learning as fault datasets gradually accumulate through continuous machine operation. We also focus on experimentally analyzing how changes in the learning paradigm of the deep learning model and the output representation affect fault detection performance. The results demonstrate that, with a small number of fault datasets, a supervised model with continuous outputs as a regression problem showed better fault detection performance than the original model with one-hot encoded outputs (as a classification problem).

이 논문은 S대학교 ‘사고와 글쓰기’ 교과에서 AI 자동 피드백 프로그 램 키위(KEEwi)를 활용한 수업 사례를 분석하고 그것이 지닌 효과와 한 계에 관해 탐색할 것을 목적으로 한다. 먼저 2장에서는 AI 자동 피드백 프로그램의 동향과 원리를 살펴보고 3장에서는 키위 프로그램을 활용한 수업 운영과 구체적 사례에 관해 설명하였다. 4장에서는 설문조사 분석 을 통한 학습자들의 프로그램 만족도와 교육 효과 및 한계에 관해 논의 하였다. 그 결과 이 프로그램은 즉각적이고 반복적인 피드백을 통해 학 습자의 학습 능률을 향상시킬 뿐 아니라 수업에 대한 흥미를 유발하여 글쓰기 역량을 강화하는 데 긍정적인 영향을 끼치는 것으로 드러났다. 또한 교수자에게는 글쓰기 교육의 보조 도구이자 협력자로 기능하며 학 습자 중심의 피드백 환경을 조성하는 데 기여하는 것으로 파악된다. 그 러나 키위 엔진은 완전한 대체 도구가 아니며 자체적인 오류와 문제를 가지고 있어 절대적인 평가 지표로 활용하는 것에는 한계가 있음이 확인 되었다. 이러한 연구는 대학 글쓰기 교양수업에서 AI 자동 피드백 프로 그램이 학습자와 교수자에게 끼치는 영향과 그 한계를 파악하는 데 도움 이 되리라 생각한다.

지진이라는 재해는 인류가 직면하고 있는 재해 중 가장 파괴적인 자연재해 중 하나로 인명, 자연을 포함한 인프라, 경제에도 지대한 영향을 끼질 수 있다. 세계적으로도 최근 수년간 환태평양 조산대를 기점으로 지진의 빈도가 꾸준히 증가해왔으며 강도 또한 상승해져왔다. 규모가 7 가량을 넘는 지진부터는 인류가 대처하기 힘들만큼 많은 에너지가 발생되며 특히나 우리나라와 밀접히 인접해 있는 일본의 경우 난카이 대지진과 같은 이슈가 발생하여 그 경계의식이 높아진 실정이다. 따라서 이에대한 지진 에너지를 효과적으로 흡수하고 분살시킬 수 있는 댐퍼장치들이 많이 발명되었고 여기에 적용되는 많은 압축 소재들이 개발되고 있다. 현재까지는 많은 댐퍼 장치가 고무를 압축재료로 사용하고 있으며 이를 대체하기 위해 폴리우레탄이라는 고분자 재료가 개발되었지만 낮은 하중에도 쉽게 변형이 발생하는 한계가 발생하는 문제가 있다. 따라서 본 연구에서는 폴리케톤이라는 물질을 재료적 성능 평가를 통해 제안한다. 폴리 케톤은 합성될 때 일산화탄소를 매개로 하기 때문에 탄소저감에도 효과적인 물질이다. 이러한 폴리케톤을 폴리우레탄과 반복 압축 실 험을 통해 비교하였으며 시편의 길이, 선행압축의 유무 등의 변수를 적용하여 실험을 진행하였다. 이후 힘-변형 그래프, 최대 압축성능, 에너지 소산 능력, 초기회복력 등의 성능을 확인하였다. 실험 결과 모든 결과가 폴리케톤이 폴리우레탄보다 우수한 성능을 나타냈으며 내진 구조용 압축소재로서의 적용 가능성을 입증하였다.

본 연구는 다시마 양식을 위한 통합 자동화 시스템을 개발하고, 이를 통해 생산성, 비용 효율성, 환경적 지속 가능성을 모두 개선하는 데 중점을 두고 있다. 기존의 노동 집약적 수확 방식과 넓은 공간을 필요로 하는 수평 건조 방식은 비효율적이며, 환경적 부작 용을 초래했다. 이에 본 연구는 자동화된 수확 시스템, 해상-육상 연계 운송 시스템, 그리고 수직 건조 시스템을 통합적으로 개발하여 양 식업의 생산성을 극대화하고 자원 사용을 최적화하였다. 자동화된 수확 시스템은 작업 속도를 약 35% 향상시켰으며, 작업의 일관성을 유지하여 품질 오차율을 2% 이하로 줄이는 성과를 보였다. 해상-육상 연계 운송 시스템은 모듈형 컨테이너를 활용하여 운송 중 손상률 을 기존 15%에서 5%로 감소시켰고, 운송 시간을 평균 6시간에서 4시간으로 단축하였다. 또한, 수직 건조시스템은 고밀도 적재와 자연 대류 방식을 도입하여 건조 시간을 기존 48시간에서 28시간으로 40% 단축하였으며, 에너지 소비를 25% 감소시켰다. 이러한 시스템은 데이터 기반으로 설계 및 검증되었으며, 통합적으로 양식업의 경제성 향상과 환경적 부담 감소를 동시에 실현하였다. 본 연구의 결과는 다른 해조류 양식에도 적용 가능하며 지속 가능한 해양 자원 관리에 기여할 것으로 기대된다.

Automated structural design methods for reinforced concrete (RC) beam members have been widely studied with various techniques to date. Recently, artificial intelligence has been actively applied to various engineering fields. In this study, machine learning (ML) is adopted to make automated structural design model for RC beam members. Among various machine learning methods, a supervised learning was selected. When a supervised learning is applied to development of ML-based prediction model, datasets for training and test are required. Therefore, the datasets for rectangular and t-shaped RC beams was constructed by commercial structural design software of MIDAS. Five supervised learning algorithms, such as Decision Tree (DT), Random Forest (RF), K-Nearest Neighbor (KNN), Artificial Neural Networks (ANN), eXtreme Gradient Boosting (XGBoost) were used to develop the automated structural design model. Design moment (Mu), design shear force (Vu), beam length, uniform load (wu) were used for inputs of structural design model. Width and height of the designed section, diameter of top and bottom bars, number of top and bottom bars, diameter of stirrup bar were selected for outputs of structural design model. Performance evaluation of the developed structural design models was conducted using metrics sush as root mean square error (RMSE), mean square error (MSE), mean absolute error (MAE), and coefficient of determination (R2). This study presented that random forest provides the best structural design results for both rectangular and t-shaped RC beams.

The demand for automated diagnostic facilities has increased due to the rise in high-risk infectious diseases. However, small and medium-sized centers struggle to implement full automation because of limited resources. An integrated molecular diagnostics automation system addresses this issue by integrating small-scale automated facilities for each diagnostic process. Nonetheless, determining the optimal number of facilities and human resources remains challenging. This study proposes a methodology combining discrete event simulation and a genetic algorithm to optimize job-shop facility layout in the integrated molecular diagnostics automation system. A discrete event simulation model incorporates the number of facilities, processing times, and batch sizes for each step of the molecular diagnostics process. Genetic algorithm operations, such as tournament, crossover, and mutation, are applied to derive the optimal strategy for facility layout. The proposed methodology derives optimal facility layouts for various scenarios, minimizing costs while achieving the target production volume. This methodology can serve as a decision support tool when introducing job-shop production in the integrated molecular diagnostics automation system

In general, optimized pavement thickness design abilities and reliable construction procedures have been considered being crucial element for expressway in South Korea till millenium. However, after 2005, a proper management efforts on existing expressway became recognized as an important factor after 2,005. One of good example is rising attention of HPMS(Highway Pavement Management System). In HPMS, the crucial component is: surveying the existing expressway surface condition with reasonable, reliable and efficient procedure. Becasue of this reason, application of various advanced and sophisticated technologies on HPMS area were considered since 2010. During this time, many advanced technologies such as AI(Artificial Intelligence) techniques and corresponding physical equipment were considered to be applied. Through application of AI technologies in HPMS business area, two major outcomes can be achieved: first one is an automated pavement surface monitoring work system for maximized efficiency and second thing is saving current HPMS management budget through faster and more reasonable surveying results. In this paper, the feasibility of AI technology on actual pavement surface monitoring and analysis procedure was considered. As a result, AI based pavement surface monitoring and analysis approach succesfully provided reasonable results compared to the conventional human effort analysis approach. This findings provide a promising signal that more AI based technologies can successfully applied in HPMS business area in the next future. Morevoer, the achievement of automated HPMS can also be possible in the near future.

오일펜스는 해상에 유출된 기름의 확산을 차단하기 위해 신속하게 설치되는 방제자재이다. 본 연구에서는 소형경비정과 소형 방제정에 간편하게 적재하고 운용할 수 있는 자동팽창식 폴딩 오일펜스를 개발하였다. 폴딩 오일펜스는 별도의 공기 주입 없이 스프링에 의해 자동으로 팽창되며, 내부 구조체 상부의 부력체에 의해 삼각형 형태로 안정된 기립 상태를 유지한다. 또한 국내 오일펜스 A형 형식 승인 규격(수면상 20~30 cm, 수면하 30~40 cm)을 충족하는 것으 확인하였고, 조파수조 및 실해역 실험을 통해 기능 구현을 검증하였다. 핵 심 부품인 인장스프링에 대해 10,000회 피로시험과 염수침지시험을 수행한 결과, 성능에 이상이 없음을 확인하였다. 본 장비의 개발은 해 양오염사고의 초동방제 대응능력을 향상시키고, 국내외 해양방제산업의 발전에 기여할 것으로 기대된다.

Fishways, particularly installed at the estuary, have a purpose to encourage fluent migration for migratory fishes, as well as amphidromous and even freshwater species. Not choosing the laborious traditional method of using traps, we assessed the efficiency of the two fishways installed at the west and east barrage of the Nakdong River estuarine barrage respectively, by analyzing the videos recorded through automatic monitoring system. We randomly selected 30 videos monthly at each fishways and identified what kind of fishes were using the fishways and categorised their behaviour such as size, time and whether they passed the monitoring system or not. As a result, a total 8 families 14 species were recorded by monitoring system, with the most dominance of Erythroculter erythropterus (Relative Abundance: 59.5%), followed by Micropterus salmoides (R.A: 19.9%) and Mugil cephalus (R.A: 9.9%). The monitoring system can capture passing fishes during night but the number of appearances of fish species at each hour of a day indicated significant diurnal activities (p<0.05). When fishes pass the monitoring system, approximately 70% of them passed through the monitoring device, while 17% of them showed fallback movement. Our finding indicates that species-specific characteristics of each fish are well represented through video monitoring method. In order to maximise advantages of using video monitoring, it is necessary to consider the installation point properly so that the monitoring system does not interfere with the movement of fish. Also, the utilisation of AI technology in the future is also necessary.