• Journal of the Korea Concrete Institute
• /
• 제16권1호
• /
• pp.111-124
• /
• 2004

This research is a part of a research program to verify the seismic performance of circular reinforced concrete bridge columns with respect to longitudinal steel connection details under cyclic lateral load. A total of 21 column specimens were constructed and tested. Main variables in this test program were longitudinal steel connection details(continuous, lap-spliced, and mechanically connected), confinement steel ratio, and axial force ratio, etc. The test results of the columns with different longitudinal steel connection details showed different failure mode, strength degradation, and seismic performance. From the quasi-static test, it was found that the columns with all longitudinal reinforcement lap-spliced showed significantly reduced ductility. However, seismic performance of the columns with half of longitudinal reinforcement lap-spliced showed limited ductility but much more ductile behaviour than the columns with all longitudinal reinforcement lap-spliced. It was also found that the seismic performance, failure mode and strength degradation of columns with mechanical connected longitudinal reinforcement were similar to those of columns with continuous longitudinal reinforcement.

• Journal of the Earthquake Engineering Society of Korea
• /
• 제28권4호
• /
• pp.193-203
• /
• 2024

Existing reinforced concrete (RC) building frames constructed before the seismic design was applied have seismically deficient structural details, and buildings with such structural details show brittle behavior that is destroyed early due to low shear performance. Various reinforcement systems, such as fiber-reinforced polymer (FRP) jacketing systems, are being studied to reinforce the seismically deficient RC frames. Due to the step-by-step modeling and interpretation process, existing seismic performance assessment and reinforcement design of buildings consume an enormous amount of workforce and time. Various machine learning (ML) models were developed using input and output datasets for seismic loads and reinforcement details built through the finite element (FE) model developed in previous studies to overcome these shortcomings. To assess the performance of the seismic performance prediction models developed in this study, the mean squared error (MSE), R-square (R²), and residual of each model were compared. Overall, the applied ML was found to rapidly and effectively predict the seismic performance of buildings according to changes in load and reinforcement details without overfitting. In addition, the best-fit model for each seismic performance class was selected by analyzing the performance by class of the ML models.

• Proceedings of the Korea Concrete Institute Conference
• /
• 한국콘크리트학회 1997년도 가을 학술발표회 논문집
• /
• pp.561-568
• /
• 1997

Conventional confinement reinforcement for rectangular columns consist of closely spaced perimeter hoops, overlapping hoops, and crossties. One of the potential alternatives to conventional reinforcement is a welded reinforcement grid, prefabricated to required size and volumetric ratio of transverse reinforcement. An experimental investigation was carried out to investigate the strength and deformability of reinforced concrete columns confined with welded reinforcement grids. The comparisons of the envelopes of experimental force-displacement hysteric relationships for columns confined by welded grids with analytically generated force-displacement curves for columns confined with conventional ties. In general, inelastic deformability beyond the peak, as indicate by the slope of the cuvers, was similar to those indicated by columns with conventional ties. The superior performance of columns with welded grids may be attributed to the improved confinement characteristics of grids associated with increased rigidity of welded ties.

• Journal of the Semiconductor & Display Technology
• /
• 제16권3호
• /
• pp.127-130
• /
• 2017

In this research, we present a path planning method for an autonomous flight of unmanned aerial vehicles (UAVs) through reinforcement learning under simulated environment. We design the simulator for reinforcement learning of uav. Also we implement interface for compatibility of Deep Q-Network(DQN) and simulator. In this paper, we perform reinforcement learning through the simulator and DQN, and use Q-learning algorithm, which is a kind of reinforcement learning algorithms. Through experimentation, we verify performance of DQN-simulator. Finally, we evaluated the learning results and suggest path planning strategy using reinforcement learning.

• Journal of Korean Association for Spatial Structures
• /
• 제19권4호
• /
• pp.61-68
• /
• 2019

This paper discusses the influence of transverse reinforcement spacing and support width of concrete wide beam on shear performance. In order to evaluate the shear performance, a total of thirteen specimens were constructed and tested. The transverse reinforcement spacing, the number of legs and support width were considered as variables. From the test results, the shear strength equation of concrete wide beam is proposed for prediction of shear strength of concrete wide beam to consider the transverse reinforcement spacing and support width. It is shown that the proposed equation is able to predict shear strength reasonably well for concrete wide beam.

• Structural Engineering and Mechanics
• /
• 제67권1호
• /
• pp.93-104
• /
• 2018

The seismic behavior of reinforced concrete (RC) short columns with limited transverse reinforcement is investigated in this paper through an experimental program. The experimental program consists of four small-scale RC columns with an aspect ratio of 1.7, which are tested to the axial failure stage. The cracking patterns, hysteretic responses, strains in reinforcing bars, displacement decomposition and cumulative energy dissipation of the tested specimens are reported in detail in the paper. The effects of column axial load are investigated to determine how this variable might influence the performance of the short columns with limited transverse reinforcement. Brittle shear failure was observed in all tested specimens. Beneficial and detrimental effects on the shear strength and drift ratio at axial failure of the test specimens due to the column axial load are found in the experimental program, respectively.

• Journal of the Korea Society of Computer and Information
• /
• 제23권10호
• /
• pp.23-31
• /
• 2018

Recently, there have been many studies on machine learning. Among them, studies on reinforcement learning are actively worked. In this study, we propose a controller to control bicycle using DDPG (Deep Deterministic Policy Gradient) algorithm which is the latest deep reinforcement learning method. In this paper, we redefine the compensation function of bicycle dynamics and neural network to learn agents. When using the proposed method for data learning and control, it is possible to perform the function of not allowing the bicycle to fall over and reach the further given destination unlike the existing method. For the performance evaluation, we have experimented that the proposed algorithm works in various environments such as fixed speed, random, target point, and not determined. Finally, as a result, it is confirmed that the proposed algorithm shows better performance than the conventional neural network algorithms NAF and PPO.

• Journal of IKEEE
• /
• 제25권4호
• /
• pp.728-734
• /
• 2021

In recent years, there has been a strong interest in the end-to-end autonomous driving based on deep reinforcement learning. In this paper, we present a reward function of latent SAC deep reinforcement learning to improve the longitudinal driving performance of an agent vehicle. While the existing reward function significantly degrades the driving safety and efficiency, the proposed reward function is shown to maintain an appropriate headway distance while avoiding the front vehicle collision.

• Journal of the Korea institute for structural maintenance and inspection
• /
• 제21권2호
• /
• pp.60-68
• /
• 2017

This study was made to examine the motion characteristics according to the reinforcement of the reinforcement length and stiffener reinforcement for shear reinforcement to the foundation structure reinforced with shear reinforcement steel plate. Experimental study was made after specimen was installed on the ground as the same as in the practical site. Reinforcement lengths of the steel for shear reinforcement are divided into 1,000 mm, 1,200 mm and 1,400 mm in the specimen and as for reinforcement method of the stiffener, 4 stiffeners with interval of 100mm reinforced with the same materials as the shear reinforcement were manufactured for the experiment. Considering result of the experiment, it is expressed that no effect of the stiffener reinforcement was found and regarding the reinforcement length of shear reinforcement material the crossed point of the two converted lines of the value that the shear force is expressed in the bearing power in the expanded dangerous section and the value that the shear capacity receivable by the reinforcement materials in the dangerous section is proposed as effective reinforcement length.

• Proceedings of the KSR Conference
• /
• 한국철도학회 2011년도 정기총회 및 추계학술대회 논문집
• /
• pp.1143-1148
• /
• 2011

In this study, seismic structural reinforcement are carried out, based on the estimated seismic performance of underground box structures in urban railway, and displacement based design method was developed to enhance seismic performance of structures. New seismic reinforcement design method is proposed and compared with existing design methods. And presented an overview of the developed design methodology through a design example to verify the validity of that methods.