• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1381-1386
• /
• 2019

As traffic congestion in cities becomes more serious, intelligent traffic control is actively being researched. Reinforcement learning is the most actively used algorithm for traffic signal control, and recently Deep reinforcement learning has attracted attention of researchers. Extended versions of deep reinforcement learning have been emerged as deep reinforcement learning algorithm showed high performance in various fields. However, most of the existing traffic signal control were studied in a single intersection environment, and there is a limitation that the method at a single intersection does not consider the traffic conditions of the entire city. In this paper, we propose a cooperative traffic control at multi-intersection environment. The traffic signal control algorithm is based on a combination of extended versions of deep reinforcement learning and we considers traffic conditions of adjacent intersections. In the experiment, we compare the proposed algorithm with the existing deep reinforcement learning algorithm, and further demonstrate the high performance of our model with and without cooperative method.

• Journal of the Korean GEO-environmental Society
• /
• v.24 no.8
• /
• pp.5-11
• /
• 2023

Due to frequent occurrences of concentrated heavy rainfall caused by abnormal climate conditions in recent years, collapses of steep slopes have been occurring frequently due to surface erosion and increased pore water pressure. Various methods are being applied to prevent slope collapses, such as increasing the resistance to movement and reducing pore water pressure. Research on these methods has been consistently conducted as they provide an efficient response to slope collapses by satisfying both the conditions of resistance to movement and pore water pressure simultaneously. Therefore, in this study, we propose an upward slope reinforcement method by burying drainage materials with an upward slope inclination, instead of the conventional horizontal application. This approach aims to satisfy both slope reinforcement and drainage functions effectively, offering a comprehensive solution for slope stabilization. Furthermore, to determine the optimal burial angle that exhibits the most effective reinforcement and drainage effects of the proposed method, we investigated the reinforcement and drainage effects under conditions where the horizontal drainage materials were set at angles ranging from 0° to 60° in increments of 10° on a representative cross-section. Additionally, indoor model experiments were conducted under the conditions of 40°, which showed the most outstanding drainage effect, and 20°, which exhibited the highest safety factor, to validate the numerical analysis results. The results showed that the burial angle of 40° exhibits a relatively higher drainage effect as with the numerical analysis results, while the angle of 20° results in inadequate drainage and observed slope collapse.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.9 no.3
• /
• pp.338-347
• /
• 2021

This paper aims to evaluating the interlayer strength of 3D-printed concrete with interlayer reinforcement. According to lap splices, two reinforcement methods were considered. One method did not include lap splices of interlayer reinforcement, but the other method included lap splices with length of 40mm. In addition, two different curing conditions were applied: air curing conditions and water curing conditions. The compressive, splitting tensile, and flexural tensile strengths of 3D-printed concrete specimens were measured in three loading directions with different reinforcement methods and curing conditions. Splitting and flexural tensile strengths decreased considerably when tensile stresses acted over the interlayers of 3D-printed concrete specimens. However, the flexural tensile strength or interlayer bonding strength of the printed specimens increased significantly at the interlayers when the longitudinal interlayer reinforcement penetrated printed layers. Interlayer bonding strength of printed concrete decreased after air curing treatment was applied because interlayers of printed concrete with more pores formed by the air cu ring conditions are more vulnerable to the load.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.6
• /
• pp.3923-3930
• /
• 2014

In this study, the physical and dynamic characteristics of soil were analyzed by selecting 3 sections as research subjects among road and structure construction sections in the construction site of the Gwangyang ${\bigcirc}{\bigcirc}$ industry area, and conducted consolidation analysis and bearing capacity assessments through Midas-GTS according to the construction conditions of the structures and section conditions of reinforcement using stabilized soil. The effects of improving the settlement and bearing capacity according to the improved effects of the stability and sections of reinforcement using stabilized soil in applying the reinforcement method using stabilized soil were analyzed as a solution for improving the settlement and bearing capacity of soft clay for constructing roads and structures. The improvement effects of the settlement and bearing capacity were outstanding when the reinforcement method using stabilized soil to the soft clay was applied. After applying the reinforcement method using stabilized soil, the holdback effect of the consolidation settlement was excellent by decreasing the volume of the consolidation settlement from a minimum of 53% to a maximum of 82%. When the width of the reinforcement using stabilized soil was twice the width of the constructed structure, it was found that the holdback effect of the consolidation settlement ranged from 1% to 7% through the width of reinforcement using stabilized soil. In addition, when applying reinforcement more than 6m in width and 1m in depth using stabilized soil, it was found that the increase in the allowable bearing capacity was 2.3 to 3.3 times more than that before applying the reinforcement, which suggests that the increase in bearing capacity by applying the reinforcement method using stabilized soil was significant.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.3
• /
• pp.169-189
• /
• 2024

In the current work, a series of three-dimensional finite element analyses have been carried out to understand the behaviour of pre-existing single piles and pile groups to adjacent Shield TBM tunnelling by considering various reinforcement conditions. The numerical modelling has analysed the effect of the pile cutting, ground reinforcement and pile cap reinforcement. The analyses concentrate on the ground settlements, the pile head settlements, the axial pile forces and the shear stress transfer mechanism at the pile-soil interface. In all cases of the pile tips supported by weathered rock, the distributions of shear stresses presented a similar trend. Also, when the pile tips were cut, tensile forces or compressive forces were induced on the piles depending on the relative positions of the piles. Furthermore, when the pile tips are supported by weathered rock, approximately 70% of the load is supported by surface friction, and only the remaining 30% is supported by the pile tip. Furthermore the final settlement of the piles without reinforcement showed approximately 70% more settlement than the piles for which ground reinforcement is considered. It has been found that the ground settlements and the pile settlements are heavily affected by the pile cutting and reinforcement conditions. The behaviour of the single pile and group piles, depending on the pile cutting, conditions of ground and pile cap reinforcement, has been extensively examined and analysed by considering the key features in great details.

• Corrosion Science and Technology
• /
• v.6 no.6
• /
• pp.297-303
• /
• 2007

This paper discusses the chloride-induced corrosion of reinforcement in marine concrete structures focusing on the variability in the progress of deterioration. Through tests and analyses of reinforced concrete slabs taken out from existing open-pile structures that have been in service for 30 to 40 years, the following topics were particularly discussed: variation in chloride ion profiles of concrete, variation in corrosion properties of reinforcement embedded in concrete, and influence of the reinforcement corrosion on the load-carrying capacity of the concrete slabs. As a result, their variability was found to be very large even in one reinforced concrete slab with almost the same conditions. It was also discussed how to determine the calculation parameters for prediction of decreasing in load-carrying capacity of concrete members with chloride-induced corrosion of reinforcement.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.15 no.5
• /
• pp.145-151
• /
• 2016

We consider the position and thickness of reinforcement with respect to fatigue fracture of welded bogie frames and propose an appropriate reinforcement method for many cases. The bogie frame is usually designed in accordance with JIS and KS, and operates under harsh load conditions: dynamic loads generated while driving, various loads during operation, and large load differences between loading and unloading. Consequently, fatigue failure often occurs throughout the bogie frame. We modelled the reinforcing method using ANSYS software and reviewed stress in the vicinity of common fatigue failure sites through computer simulation, optimizing the position and thickness of reinforcement.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2003.05a
• /
• pp.585-590
• /
• 2003

It analyzed the reinforcement effect according to reinforced period for FREP. It found that reinforcement effect of P-Type that was reinforced during the usage decreased compared to I-Type that was reinforced before the usage. So when reinforcing a existing structure that is being used, it should consider the stress that is produced due to the fixed load. It evaluated bending and shear of RC reinforcing beam based on the test and analytical conditions of this study. It found that stress concentration was concentrated due to rapid change of bending rigidity in reinforced cutting part as a result of excessive reinforcement thickness of FREP. It resulted in rip-off failure. It means that it should evaluate the shear when designing reinforcement.

• Journal of Internet Computing and Services
• /
• v.25 no.4
• /
• pp.7-21
• /
• 2024

There are various machine learning techniques such as Reinforcement Learning, Deep Learning, Neural Network Learning, and so on. In recent, Large Language Models (LLMs) are popularly used for Generative AI based on Reinforcement Learning. It makes decisions with the most optimal rewards through the fine tuning process in a particular situation. Unfortunately, LLMs can not provide any explanation for how they reach the goal because the training is based on learning of black-box AI. Reinforcement Learning as black-box AI is based on graph-evolving structure for deriving enhanced solution through adjustment by human feedback or reinforced data. In this research, for mutually exclusive decision-making, Mutually Exclusive Learning (MEL) is proposed to provide explanations of the chosen goals that are achieved by a decision on both ends with specified conditions. In MEL, decision-making process is based on the tree-based structure that can provide processes of pruning branches that are used as explanations of how to achieve the goals. The goal can be reached by trade-off among mutually exclusive alternatives according to the specific contextual conditions. Therefore, the tree-based structure is adopted to provide feasible solutions with the explanations based on the pruning branches. The sequence of pruning processes can be used to provide the explanations of the inferences and ways to reach the goals, as Explainable AI (XAI). The learning process is based on the pruning branches according to the multi-dimensional contextual conditions. To deep-dive the search, they are composed of time window to determine the temporal perspective, depth of phases for lookahead and decision criteria to prune branches. The goal depends on the policy of the pruning branches, which can be dynamically changed by configured situation with the specific multi-dimensional contextual conditions at a particular moment. The explanation is represented by the chosen episode among the decision alternatives according to configured situations. In this research, MEL adopts the tree-based learning model to provide explanation for the goal derived with specific conditions. Therefore, as an example of mutually exclusive problems, employment process is proposed to demonstrate the decision-making process of how to reach the goal and explanation by the pruning branches. Finally, further study is discussed to verify the effectiveness of MEL with experiments.

• Journal of Welding and Joining
• /
• v.24 no.5
• /
• pp.29-36
• /
• 2006

In this study, an experimental method for the selection of optimal welding condition was proposed in the fillet weld which was done over the tack weld. This method used the response surface analysis in which the leg length and the reinforcement height were chosen as the quality variables of the weld bead profile. The overall desirability function, which was combined desirability function fur the two quality variables, was employed as the objective function for getting the optimal welding condition. In the experiments, the target values of the leg length and the reinforcement height are 6m and zero respectively for the horizontal fillet weld of 10mm thickness mild steel. The optimal welding conditions could predict the weld bead profile(leg length and reinforcement height) as 6.00mm and 0.19mm without tack weld and 6.00mm and 0.48mm with tack weld. from a series of welding test, it was revealed that a uniform weld bead can be obtained by adopting the optimal welding condition which was determined according to the method proposed.