• Journal of Korean Association for Spatial Structures
• /
• v.23 no.2
• /
• pp.29-36
• /
• 2023

Reinforcement learning (RL) is widely applied to various engineering fields. Especially, RL has shown successful performance for control problems, such as vehicles, robotics, and active structural control system. However, little research on application of RL to optimal structural design has conducted to date. In this study, the possibility of application of RL to structural design of reinforced concrete (RC) beam was investigated. The example of RC beam structural design problem introduced in previous study was used for comparative study. Deep q-network (DQN) is a famous RL algorithm presenting good performance in the discrete action space and thus it was used in this study. The action of DQN agent is required to represent design variables of RC beam. However, the number of design variables of RC beam is too many to represent by the action of conventional DQN. To solve this problem, multi-agent DQN was used in this study. For more effective reinforcement learning process, DDQN (Double Q-Learning) that is an advanced version of a conventional DQN was employed. The multi-agent of DDQN was trained for optimal structural design of RC beam to satisfy American Concrete Institute (318) without any hand-labeled dataset. Five agents of DDQN provides actions for beam with, beam depth, main rebar size, number of main rebar, and shear stirrup size, respectively. Five agents of DDQN were trained for 10,000 episodes and the performance of the multi-agent of DDQN was evaluated with 100 test design cases. This study shows that the multi-agent DDQN algorithm can provide successfully structural design results of RC beam.

• Journal of the Korea Concrete Institute
• /
• v.22 no.3
• /
• pp.313-324
• /
• 2010

There are many problems in application of FRP reinforcing bars as shear reinforcement, since bending of FRP bars is not a feasible process on construction site. Even though FRP bars can be manufactured in bent shape, they have lower strength at bent location. However, there are no serious problems to use FRP bars as flexural reinforcement. Plates or slabs like bridge decks, in general, do not need shear reinforcements. These types of members with FRP flexural reinforcement have lower shear strength than those with conventional steel flexural reinforcement. However, reliable process or equation for shear strength estimation of FRP reinforced concrete without shear reinforcement are not established, yet. In this study, predicted shear strength obtained from available design equations and assessment equations are compared with 211 experimental results. The results showed that among the current design codes, the Architectural Institute of Japan (AIJ) and the Institution of Structural Engineers (ISE) provided the best estimation. ACI 440.1R-06 provided conservative results with degree of dispersion similar to that of ISE. In addition, regression analysis on the collected experimental results was conducted to develop regression models. As a result, a new reliable shear strength equation was proposed.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.18 no.2
• /
• pp.21-29
• /
• 2014

This paper evaluates the shear strength, behavior and failure mode of reinforced concrete beams with deformed GFRP reinforcing bar. Four concrete beam specimens were constructed and tested. It was carried out to observe failure behavior and load-deflection of simply supported concrete beams subjected to four-point monotonic loading. In order to eliminate of the uncertainty by the shear reinforcements, any stirrups were not used. Variables of the specimens were shear span-depth ratio, effective reinforcement ratio. The dimensions of specimen is 3,300 or $1,950mm{\times}200mm{\times}240mm$. Clear span and shear span were 2,900mm, 1,000mm respectively. Shear span-depth ratios were 6.5 and 2.5. Effective ratios of Longitudinal GFRP reinforcing bar were $1.126{\rho}_{fb}$, $2.250{\rho}_{fb}$, $3.375{\rho}_{fb}$ and $0.634{\rho}_{fb}$. All beam specimens were broken by diagonal-tension shear and the ACI 440.1R, CSA S806 and ISIS, which was used to design test beams, showed considerable deviation between prediction and test results of shear strengths.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.20 no.4
• /
• pp.144-152
• /
• 2016

This paper focuses on the experimental study for investigating the performance for lap splice of hooked or headed reinforcement in beam with different depths. In the experiment, seven specimens, with its variables as the lap length of headed or hooked bar, the existence of stirrups, etc., was manufactured. Bending test was conducted. Lap strengths by test were compared with the theoretical model based on KCI2012. The result showed that the cracks at failure mode occurred along the axial direction to a headed bar. The initial stiffness and the stiffness after initial crack were similar for all specimens. For HS series specimens without stirrups, a 25% increase in lap length was increased 11.8~18.1% maximum strengths. For HH series specimens without stirrups, a increase in lap length did not affect the maximum strengths because of the pryout failure of headed bar. For HS series specimens, the theoretical lap strengths based on KCI2012 considering the B grade lap and the reduction factor for stirrup were evaluated. They are smaller than the test strengths and can ensure the safety in terms of strength capacity. For HH series specimens, the stirrups in the lap zone are needed to prevent the pryout behaviour of headed bar.

• Korean Journal of Construction Engineering and Management
• /
• v.23 no.2
• /
• pp.95-101
• /
• 2022

This study attempts to identify the ways of reducing the floor impact sound, by applying six different types of the reinforced bar girders and stirrup arrangements to the Structure: (1) the longer-direction girder arrangements (2) the shorter-direction girder arrangements (3) the diagonal-direction arrangements (4) the longer-direction girder arrangements with stirrups (5) the shorter-direction girder arrangements with stirrups (6) the diagonal-direction arrangements with stirrups. In order to identify the most effective structural changes, each slab was tested with bang machines, measuring the level of the sound impact. The results showed that the longer-direction girder arrangements with stirrups were the most effective one. In addition, the effectiveness of slab was found to be remarkable, showing the level of minimum 1dB to maximum 5dB, where the slab was compared with the control models without girders and stirrups. In conclusion, it is suggested that the longer-direction girder arrangements with stirrups could possibly be applied to the Wall Structures to minimize the floor impact sound.