• Journal of the Korea Computer Graphics Society
• /
• v.29 no.1
• /
• pp.23-29
• /
• 2023

In this paper, we introduce a method to obtain high-quality results at a low cost for simulating musculoskeletal characters based on data from the reference motion through motion capture on two-legged walking through reinforcement learning. We reset the motion data of the reference motion to allow the character model to perform, and then train the corresponding motion to be learned through reinforcement learning. We combine motion imitation of the reference model with minimal metabolic energy for the muscles to learn to allow the musculoskeletal model to perform two-legged walking in the desired direction. In this way, the musculoskeletal model can learn at a lower cost than conventional manually designed controllers and perform high-quality bipedal walking.

• The Journal of Korea Robotics Society
• /
• v.12 no.3
• /
• pp.297-305
• /
• 2017

As the development of autonomous vehicles becomes realistic, many automobile manufacturers and components producers aim to develop 'completely autonomous driving'. ADAS (Advanced Driver Assistance Systems) which has been applied in automobile recently, supports the driver in controlling lane maintenance, speed and direction in a single lane based on limited road environment. Although technologies of obstacles avoidance on the obstacle environment have been developed, they concentrates on simple obstacle avoidances, not considering the control of the actual vehicle in the real situation which makes drivers feel unsafe from the sudden change of the wheel and the speed of the vehicle. In order to develop the 'completely autonomous driving' automobile which perceives the surrounding environment by itself and operates, ability of the vehicle should be enhanced in a way human driver does. In this sense, this paper intends to establish a strategy with which autonomous vehicles behave human-friendly based on vehicle dynamics through the reinforcement learning that is based on Q-learning, a type of machine learning. The obstacle avoidance reinforcement learning proceeded in 5 simulations. The reward rule has been set in the experiment so that the car can learn by itself with recurring events, allowing the experiment to have the similar environment to the one when humans drive. Driving Simulator has been used to verify results of the reinforcement learning. The ultimate goal of this study is to enable autonomous vehicles avoid obstacles in a human-friendly way when obstacles appear in their sight, using controlling methods that have previously been learned in various conditions through the reinforcement learning.

• The Journal of the Convergence on Culture Technology
• /
• v.5 no.4
• /
• pp.439-444
• /
• 2019

In this paper, the seismic performance evaluation of the subway lines 1~4 conducted from April 2010 to October 2013 for the existing structures that were not seismically designed based on the seismic design criteria of urban railways was studied. The detailed design of seismic reinforcement for the facilities requiring seismic reinforcement was summarized through the detailed design of the seismic reinforcement construction conducted from March to December 2018. As a result of the evaluation, 53.2km (total project cost of 322 billion won) of 141.5km of Lines 1~4 were considered to require seismic reinforcement, and finally, the company aims to secure a 100% earthquake-proof rate to withstand earthquake-scale 6.5 by 2020. This paper can be used as basic research data to evaluate and reinforce seismic performance of urban railways in the future.

• Journal of the Korean Geosynthetics Society
• /
• v.18 no.1
• /
• pp.55-65
• /
• 2019

This paper describes results of experimental and numerical analyses, in order to analyze a reinforcement effect of concrete mat on open cut restoration of underground cavity. The plate loading tests were conducted to evaluate a reinforcement effect of concrete mat, at reinforcement depths from the ground surface of 10 cm, 20 cm, and 30 cm. The result showed that the reduction ratio of stress (earth pressure) was about 60% at all reinforcement depth. The reinforcement effect considering ground surface settlement and reduction ratio of stress based on laboratory tests and numerical analysis was significant, at reinforcement depths from the ground surface of 10 cm~20 cm. LFWD test results showed that subgrade modulus was the largest when concrete mat was installed 20 cm below ground surface. Therefore, it is effective to reinforce concrete mat within 20 cm from the surface, when the underground cavity due to damage of underground utilities was formed in the height direction to the bottom of the pavement layer.

• Journal of Korea Foundry Society
• /
• v.17 no.1
• /
• pp.93-99
• /
• 1997

A possibility of production of aluminium matrix composites by using the lost foam process was investigated. Silicon carbide particles, graphite particles, and stainless steel wires were used as reinforcement materials. The reinforcement materials were introduced to the polystyrene to form patterns via injection molding process. The results obtained from this experiment can be summarized as follows. In Al/SiCp system, the particles with the radius of $100{\mu}m$ and over were entrapped in the matrix in the case of upward freezing of which solidification direction was opposite to floating direction of the particles. And few particles were entrapped in the matrix in downward freezing. In Al/graphite system, almost no particles were entrapped in the matrix except the area chill attatched. When the thickness of polystyrene slice was 4mm in Al/stainless steel wire system, the floating tendency of fibers was observed to increase as the distance from the ingate was increased.

• Journal of the Korea Concrete Institute
• /
• v.15 no.1
• /
• pp.69-77
• /
• 2003

One directional and biaxial tension tests of 13 reinforced concrete panels were conducted to derive a constitutive law of concrete. Based on the test results, a model equation is derived for the stress-strain relationship of concrete in tension. Main test variables are reinforcement ratio and the load ratio applied in two directions. In addition a failure envelope of concrete in tension-tension region is suggested based on the initial crack occurrence. Test results show that the concrete carries substantial tensile stress even after cracking occurrence. However, the application of this proposed stress-strain relationship for concrete is limited to the case where the direction of reinforcement coincides with the direction of the applied principal stresses.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.4
• /
• pp.241-248
• /
• 2022

Shear Reinforcement of Dual Anchorage(SRD) is used to reinforce the safety of reinforced concrete structures at construction sites. Welding is used to make shear reinforcement, and welding plays an important role in determining productivity and competitiveness of products. Therefore, a weld bead detection inspection is required. In this paper, we suggest an algorithm for inspecting welding beads using image data of welding beads. First, the proposed algorithm calculates a brightness value in a vertical direction in an image, and then divides a welding bead in a vertical direction by finding a position corresponding to a 50% height point of the brightness value distribution in the image. The welding bead area is also divided in the same way for the horizontal direction, and then the segmentation image is analyzed if there is a welding bead. The proposed algorithm reduced the amount of computation by performing analysis after specifying the region of interest. In addition, accuracy could be improved by using all brightness values in the vertical and horizontal directions using the difference of brightness between the base metal and the welding bead region in the SRD image. The experiment compared the analysis results using five algorithms, such as K-mean and K-neighborhood, as a method to detect if there is a welding bead, and the experimental result proved that the proposed algorithm was the most accurate.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.13 no.1
• /
• pp.94-99
• /
• 2004

The global stiffnesses and vibration characteristics of vehicle structures are mainly influenced by local stiffnesses of the joint structures consisted of complicated thin-walled panels. In this paper, the parametric study for the stiffnesses of the center pillar-roof rail joint of vehicle structure is performed through the linear static analysis. The analysis result shows that the reinforcement panel much affects the joint stiffness of out-plane direction (i.e., z-direction). And also, the flange radius and width of the joint structure much affect the Joint stiffness of out-plane direction. The study shows that vehicle joint stiffnesses can be effectively determined in designing vehicle structure through the parametric study.

• KCI Concrete Journal
• /
• v.11 no.3
• /
• pp.53-64
• /
• 1999

A theory is proposed to predict the response of the load-deformation relationship of the reinforced concrete structures under the service state after cracking. The crack direction and concrete strains through the loading history before failure can be estimated by this theory based on the rotating crack model, which considers equilibrium, compatibility conditions, and average stress-strain relationship. The proposed crack direction and deformation show good agreement with test results under service state. The behavior of a variety of concrete structures, such as shear walls, deep beams and the web of box girders, can be predicted by this proposed theory under service state.

• Journal of Biosystems Engineering
• /
• v.28 no.2
• /
• pp.127-136
• /
• 2003

The top-to-bottom compression strength of corrugated board box is the most important mode of loading during it's no, and it depends largely on the edgewise compression strength of the corrugated board in the cross-machine direction and to a considerable extent on the flexural stiffness in both principal directions (CD; cross-machine direction, MD; machine direction) of the corrugated board. Corrugated board is a sandwich structure with an orthotropic property. The purpose of this study was to elucidate the principal design parameters for board combination of corrugated board from the viewpoint of bending strength through the finite element analysis [FEA] fur the various corrugated board. In general, the flexural stiffness [FS] in the MD was 2-3 times larger than that in the CD, and the effect of liner for the FS of corrugated board was much bigger than that of corrugating medium. The flexural stiffness index [FSI] was high when the stiffness of liner was in the order of inner, outer, and middle liner in double-wall corrugated board [DW], and the effect of the stiffness arrangement or itself reinforcement of corrugating medium on the FSI was not high. In single-wall corrugated board [SW] with DW. the variation of FSI with itself stiffness reinforcement of liner was much bigger than that with stiffness arrangement of liner. The highest FSI was at the ratio of about 2:1:2 for basis weight distribution of outer, middle, and inner liner if the stiffness of liner and total basis weight of corrugated board were equal in DW Secondarily. basis weight was in the order of inner, outer, and middle liner. However, the variation of FSI with basis weight distribution between liner and corrugating medium was much bigger than that with itself basis weight distribution ratio of liner and corrugating medium respectively in both DW and SW. md the FSI was high as more total basis weight was divided into liner. These phenomena fur board combination of corrugated board based on the FEA were well verified by experimental investigation.