• 한국도로학회논문집
• /
• 제19권6호
• /
• pp.57-66
• /
• 2017

PURPOSES : This study develops eco-friendly asphalt reinforcement materials applicable to bridge deck pavement. The main purpose is to ensure highly reliable quality applicable to structures and the possibility of practical application. The main target of the study is to develop materials that are environmentally friendly and capable of improving performance. METHODS : The application of double-reinforcement fiber improves the performance of the road pavement. 1. We use recycled film for application of sheet-typed reinforcement. 2. We use preprocessing fibers to reinforce the properties of composite pavement materials. RESULTS : The developed products may produce materials that fit the purpose of achieving stability and environmental friendliness. Sheet-typed reinforcements use more than 50% recycled resin. The most important type of damage to the asphalt layer is deflection (plastic deformation). These products have a very high deflection resistance of not less than 6,000 cycles/mm. In addition, all performance is excellent. Thus, it will be easier to access the field in the future. CONCLUSIONS : Fiber-reinforced asphalt pavement showed excellent performance. Sheet-typed reinforcements containing 50% recycling resin produced good performance in terms of functionality as well as environmental friendliness. Thus, enhancing the field applicability will enhance the usability of the reinforcements.

• Journal of Korean Biological Nursing Science
• /
• 제20권2호
• /
• pp.132-140
• /
• 2018

Purpose: This study has been carried out in order to develop and verify the effects of self-leadership reinforcement program for hospital nurses. Methods: The research design was a non-equivalent control group pre-posttest design. Participants were 64 individuals (32 in each group), all of whom were nurses working at a university hospital, with less than five years of job experience. Experimental group was provided with two hours of self-leadership reinforcement program, once per week, for four weeks. The questionnaire for pre and post test included general characteristics, transfer motivation for learning, self-leadership, communication ability, clinical nursing competency, organizational commitment, and turnover intentions. Results: There was a significant difference in self-leadership scores between experimental group and control group (F= 15.10, p<.001). There was also a significant difference between the experimental group and the control group in terms of transfer motivation for learning (t = -5.44 p<.001), communication ability (F = 15.29, p<.001), clinical nursing competency (F = 15.23, p<.001), and organizational commitment scores (F = 7.21, p=.009). Conclusion: The self-leadership reinforcement program developed in this study was effective in improving self-leadership, communication ability, clinical nursing competency, and organizational commitment. Thus, by implementing the program at clinical levels, it will be a basis for nursing personnel resource administration.

• 대한조선학회지
• /
• 제22권1호
• /
• pp.9-20
• /
• 1985

Generally the stiffened plate in the ship structure is subjected to not only axial load but shear load. With respect to those combined loads buckling analysis in necessary. In this paper, buckling strength is analyzed by using Finite Element Method when the stiffened plate with hole is under loading conditions mentioned above. To obtain the higher buckling strength, we need some reinforcement. The methods of reinforcement are attaching doubler around hole and stiffeners in the arbitrary directions For the sake of convenience those arbitrary directions were selected paralleled($0^{\circ}C$), vertical($90^{\circ}C$)and oblique($45^{\circ}C$) to the edge. Two kinds of method mentioned above are investigated, it is clarified that which of the two is more effective reinforcement. From the viewpoint of buckling strength, following conclusions were obtained. When external load direction is unknown, doubler reinforcement is more effective than those of parallel and vertical stiffener. And oblique stiffener reinforcement is more effective than that of doubler when external load direction is know.

• 로봇학회논문지
• /
• 제14권2호
• /
• pp.81-86
• /
• 2019

Robots are used in various industrial sites, but traditional methods of operating a robot are limited at some kind of tasks. In order for a robot to accomplish a task, it is needed to find and solve accurate formula between a robot and environment and that is complicated work. Accordingly, reinforcement learning of robots is actively studied to overcome this difficulties. This study describes the process and results of learning and solving which applied reinforcement learning. The mission that the robot is going to learn is bottle flipping. Bottle flipping is an activity that involves throwing a plastic bottle in an attempt to land it upright on its bottom. Complexity of movement of liquid in the bottle when it thrown in the air, makes this task difficult to solve in traditional ways. Reinforcement learning process makes it easier. After 3-DOF robotic arm being instructed how to throwing the bottle, the robot find the better motion that make successful with the task. Two reward functions are designed and compared the result of learning. Finite difference method is used to obtain policy gradient. This paper focuses on the process of designing an efficient reward function to improve bottle flipping motion.

• 품질경영학회지
• /
• 제51권4호
• /
• pp.573-588
• /
• 2023

Purpose: This study presents a research approach that utilizes deep reinforcement learning to construct optimal portfolios based on the business cycle for stocks and other assets. The objective is to develop effective investment strategies that adapt to the varying returns of assets in accordance with the business cycle. Methods: In this study, a diverse set of time series data, including stocks, is collected and utilized to train a deep reinforcement learning model. The proposed approach optimizes asset allocation based on the business cycle, particularly by gathering data for different states such as prosperity, recession, depression, and recovery and constructing portfolios optimized for each phase. Results: Experimental results confirm the effectiveness of the proposed deep reinforcement learning-based approach in constructing optimal portfolios tailored to the business cycle. The utility of optimizing portfolio investment strategies for each phase of the business cycle is demonstrated. Conclusion: This paper contributes to the construction of optimal portfolios based on the business cycle using a deep reinforcement learning approach, providing investors with effective investment strategies that simultaneously seek stability and profitability. As a result, investors can adopt stable and profitable investment strategies that adapt to business cycle volatility.

• 대한임베디드공학회논문지
• /
• 제19권3호
• /
• pp.131-139
• /
• 2024

Crew Transfer Vessels (CTVs) are primarily used for the maintenance of offshore wind farms. Despite being manually operated by professional captains and crew, collisions with other ships and marine structures still occur. To prevent this, the introduction of autonomous navigation systems to CTVs is necessary. In this study, research on the obstacle avoidance system of the autonomous navigation system for CTVs was conducted. In particular, research on obstacle avoidance simulation for CTVs using deep reinforcement learning was carried out, taking into account the currents and wind loads in offshore wind farms. For this purpose, 3 degrees of freedom ship maneuvering modeling for CTVs considering the currents and wind loads in offshore wind farms was performed, and a simulation environment for offshore wind farms was implemented to train and test the deep reinforcement learning agent. Specifically, this study conducted research on obstacle avoidance maneuvers using MATD3 within deep reinforcement learning, and as a result, it was confirmed that the model, which underwent training over 10,000 episodes, could successfully avoid both static and moving obstacles. This confirms the conclusion that the application of the methods proposed in this study can successfully facilitate obstacle avoidance for autonomous navigation CTVs within offshore wind farms.

• 한국지반공학회지:지반
• /
• 제12권3호
• /
• pp.49-62
• /
• 1996

인발시험은 보강토 구조물의 설계에 있어 보강재와 흙사이의 강도 정수를 결정하는데 사용된다. 그러나 이 시험의 해석시 보강재를 따라 발생하는 전단강도가 일정한 것으로 가정하는데 이는 인발시험중 흙과 보강재 사이의 점진성 전단으로 인해 흙과 보강재의 전단-변위 관계 계산시 오류가 발생하게 된다. 구과 보강재 사이의 shear stiffness계산시 점진성전단의 영향을 평가하기 위하여 유한요소법으로 인발시헙을 해석하였다. 흙과 보강재는 선형과 비선형거동으로 채석하였고 shear stiffnss는 일반적인 방법으로 계산하였는데 수정된 shear stiffness와는 많은 차이가 있었으며 그 차이로 인해 유한요소해석의 결과가 달라지게 된다. 본 논문에서는 유한요소해석결과와 시험치를 비교 분석하였으며 개선된 인발시험 해극방법에 대하여 논하였다.

• 한국지능시스템학회논문지
• /
• 제15권1호
• /
• pp.1-5
• /
• 2005

강화학습(Reinforcement-Learning)의 목적은 환경으로부터 주어지는 보상(reward)을 최대화하는 것이며, 강화학습 에이전트는 외부에 존재하는 환경과 시행착오를 통하여 상호작용하면서 학습한다 대표적인 강화학습 알고리즘인 Q-Learning은 시간 변화에 따른 적합도의 차이를 학습에 이용하는 TD-Learning의 한 종류로서 상태공간의 모든 상태-행동 쌍에 대한 평가 값을 반복 경험하여 최적의 전략을 얻는 방법이다. 본 논문에서는 강화학습을 적용하기 위한 예를 n-Queen 문제로 정하고, 문제풀이 알고리즘으로 Q-Learning을 사용하였다. n-Queen 문제를 해결하는 기존의 방법들과 제안한 방법을 비교 실험한 격과, 강화학습을 이용한 방법이 목표에 도달하기 위한 상태전이의 수를 줄여줌으로써 최적 해에 수련하는 속도가 더욱 빠름을 알 수 있었다.

• 대한치과기공학회지
• /
• 제42권2호
• /
• pp.91-98
• /
• 2020

Purpose: This study is to compare the flexural strength and modulus by inserting a mesh and stick type fiberglass reinforcement into resin specimens. Methods: Wax specimens (length 64 mm, width 39 mm, thickness 5 mm) are prepared according to ISO 20795-1:2013. Mesh type and stick type glass fiber reinforcements were prepared. The prepared wax specimens were used plaster and flask for investment. The flask was separated and the wax was removed. The heat curing resin was injected into the flask, and then a mesh type and stick type fiberglass reinforcement were inserted. The prepared resin specimen was cut into three equal parts (length 64 mm, width 10 mm, thickness 3.3 mm). The mesh type glass fiber reinforcement (MT group) and the stick type glass fiber reinforcement (ST group) were classified into two groups. The prepared specimen was measured using a universal testing machine (UTM). The data were analyzed by Mann-Whitney U test, and the significance level was set to 0.05. Results: In the flexural strength, the ST group was higher than the MT group, and there was a significant difference between the two groups (p<0.05). In the flexural modulus, the ST group was higher than the MT group, and there was a significant difference between the two groups (p<0.05). Conclusion: The stick-type glass fiber inreased the flexural strength than the mesh-type glass fiber reinforcement.

• 한국도로학회논문집
• /
• 제17권3호
• /
• pp.77-83
• /
• 2015

PURPOSES : In this study, a fracture-based finite element (FE) model is proposed to evaluate the fracture behavior of fiber-reinforced asphalt (FRA) concrete under various interface conditions. METHODS : A fracture-based FE model was developed to simulate a double-edge notched tension (DENT) test. A cohesive zone model (CZM) and linear viscoelastic model were implemented to model the fracture behavior and viscous behavior of the FRA concrete, respectively. Three models were developed to characterize the behavior of interfacial bonding between the fiber reinforcement and surrounding materials. In the first model, the fracture property of the asphalt concrete was modified to study the effect of fiber reinforcement. In the second model, spring elements were used to simulated the fiber reinforcement. In the third method, bar and spring elements, based on a nonlinear bond-slip model, were used to simulate the fiber reinforcement and interfacial bonding conditions. The performance of the FRA in resisting crack development under various interfacial conditions was evaluated. RESULTS : The elastic modulus of the fibers was not sensitive to the behavior of the FRA in the DENT test before crack initiation. After crack development, the fracture resistance of the FRA was found to have enhanced considerably as the elastic modulus of the fibers increased from 450 MPa to 900 MPa. When the adhesion between the fibers and asphalt concrete was sufficiently high, the fiber reinforcement was effective. It means that the interfacial bonding conditions affect the fracture resistance of the FRA significantly. CONCLUSIONS : The bar/spring element models were more effective in representing the local behavior of the fibers and interfacial bonding than the fracture energy approach. The reinforcement effect is more significant after crack initiation, as the fibers can be pulled out sufficiently. Both the elastic modulus of the fiber reinforcement and the interfacial bonding were significant in controlling crack development in the FRA.