• Structural Engineering and Mechanics
• /
• v.57 no.4
• /
• pp.657-680
• /
• 2016

Reinforced concrete (RC) deep beams are structural members that predominantly fail in shear. Therefore, determining the shear strength of these types of beams is very important. The strut-and-tie method is commonly used to design deep beams, and this method has been adopted in many building codes (ACI318-14, Eurocode 2-2004, CSA A23.3-2004). In this study, the efficiency of artificial neural networks (ANNs) in predicting the shear strength of RC deep beams is investigated as a different approach to the strut-and-tie method. An ANN model was developed using experimental data for 214 normal and high-strength concrete deep beams from an existing literature database. Seven different input parameters affecting the shear strength of the RC deep beams were selected to create the ANN structure. Each parameter was arranged as an input vector and a corresponding output vector that includes the shear strength of the RC deep beam. The ANN model was trained and tested using a multi-layered back-propagation method. The most convenient ANN algorithm was determined as trainGDX. Additionally, the results in the existing literature and the accuracy of the strut-and-tie model in ACI318-14 in predicting the shear strength of the RC deep beams were investigated using the same test data. The study shows that the ANN model provides acceptable predictions of the ultimate shear strength of RC deep beams (maximum $R^2{\approx}0.97$). Additionally, the ANN model is shown to provide more accurate predictions of the shear capacity than all the other computed methods in this study. The ACI318-14-STM method was very conservative, as expected. Moreover, the study shows that the proposed ANN model predicts the shear strengths of RC deep beams better than does the strut-and-tie model approaches.

• Structural Engineering and Mechanics
• /
• v.45 no.3
• /
• pp.323-336
• /
• 2013

With the ongoing development in the computer science areas of artificial intelligence and computational intelligence, researchers are able to apply them successfully in the construction industry. Given the complexities indeep beam behaviour and the difficulties in accurate evaluation of its deflection, the current study has employed the Adaptive Network-based Fuzzy Inference System (ANFIS) as one of the modelling tools to predict deflection for high strength self compacting concrete (HSSCC) deep beams. In this study, about 3668measured data on eight HSSCC deep beams are considered. Effective input data and the corresponding deflection as output data were recorded at all loading stages up to failure load for all tested deep beams. The results of ANFIS modelling and the classical linear regression were compared and concluded that the ANFIS results are highly accurate, precise and satisfactory.

• 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.

• Earthquakes and Structures
• /
• v.12 no.1
• /
• pp.23-34
• /
• 2017

Composite steel plate deep beam (CDB) is proposed as a lateral resisting member, which is constructed by steel plate and reinforced concrete (RC) panel, and it is connected with building frame through high-strength bolts. To investigate the seismic performance of the CDB, tests of two 1/3 scaled specimens with different length-to-height ratio were carried out under cyclic loads. The failure modes, load-carrying capacity, hysteretic behavior, ductility and energy dissipation were obtained and analyzed. In addition, the nonlinear finite element (FE) models of the specimens were established and verified by the test results. Besides, parametric analyses were performed to study the effect of length-to-height ratio, height-to-thickness ratio, material type and arrangement of RC panel. The experimental and numerical results showed that: the CDBs lost their load-carrying capacity because of the large out-of plane deformation and yield of the tension field formed on the steel plate. By increasing the length-to-height ratio of steel plate, the load-carrying capacity, elastic stiffness, ductility and energy dissipation capacity of the specimens were significantly enhanced. The ultimate loading capacity increased with increasing the length-to-height ratio of steel plate and yield strength of steel plate; and such capacity increased with decreasing of height-to-thickness ratio of steel plate and gap. Finally, a unified formula is proposed to calculate their ultimate loading capacity, and fitting formula on such indexes are provided for designation of the CDB.

• International Journal of Concrete Structures and Materials
• /
• v.7 no.2
• /
• pp.127-133
• /
• 2013

After reviewing the background and motivations for using modern computational methods for the design of reinforced concrete structures, an algorithm making use of the object oriented programming language Python and professionally developed finite element software is presented for the sizing and placement of the reinforcement in RC structures. The developed method is then used to design the reinforcement of a deep beam. To validate the design, two identical deep beam specimens were manufactured with the obtained steel, and then tested in the laboratory. It was found that the experimental results corroborated those predicted with the finite element design method.

• Magazine of the Korea Concrete Institute
• /
• v.5 no.2
• /
• pp.151-161
• /
• 1993

본 논문은 전단철근을 갖지 않는 비교적 짧은 지간의 철근콘크리트 보에서 전단특성을 규명하고 균열전단강도와 극한전단강도를 예측하기 위한 것으로 총30개의 보를 4 series로 나누어 실험을 수행하였다. 실험의 변수는 콘크리트의 강도, 전단지간-유효높이의 비, 인장철근량등이며, 실험과정을 통해 파괴형상, 처짐, 전단강도등을 측정하였다. 실험결과로부터 콘크리트의 강도가 커지고 철근량이 많아질수록, 그리고 전단지간이 짧아질수록 철근콘크리트 보의 균열 및 극한전단강도가 증가됨을 밝혔다. 또한, 실험성과를 회귀분석하여 균열전단강도와 극한전단강도 추정식을 제안하였다. 제안된 추정식에 의한 계산값과 실험성과를 비교 검토하여 그 상관성을 확인하였다.

• Journal of Welding and Joining
• /
• v.15 no.2
• /
• pp.54-63
• /
• 1997

For the purpose of establishing laser welding condition (laser power, welding speed and beam focus) and of evaluating tailored blanks for two kinds of thin steel sheets SPCC and SK5M using in the thin plate structure such as automobile, train, and so on, investigated their $CO^2$ laser weldability under various initial welding conditions. SPCC thin sheet showed good weldability under some welding conditions. But, high carbon steel sheet SK5M needed heat treatment after welding to obtain ductility of the welded joint. And next, tailored blank was tested through deep drawing to evaluate reliability of their obtained laser welding conditions. The forming depths by tailored blank were SPCC+SPCC=22-25mm and SK5M+SK5M=13-25mm.

• Structural Engineering and Mechanics
• /
• v.77 no.2
• /
• pp.273-291
• /
• 2021

The strut-and-tie method (STM) has been widely accepted and used as a rational approach for the design of disturbed regions ('D' regions) of reinforced concrete members such as in corbels and deep beams, where traditional flexure theory does not apply. This paper evaluates the applicability of the equilibrium based STM in strength predictions of deep beams (with rectangular and circular cross-section) and corbels using the available experiments in literature. STM is found to give fairly good results for corbel and deep beams. The failure modes of these deep members are also studied, and an optimum amount of distribution reinforcement is suggested to eliminate the premature diagonal splitting failure. A comparison with existing empirical and semi empirical methods also show that STM gives more reliable results. The nonlinear finite element analysis (NLFEA) of 50 deep beams and 20 corbels could capture the complete behaviour of deep members including crack pattern, failure load and failure load accurately.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2008.03a
• /
• pp.1260-1268
• /
• 2008

In case of deep excavation analysis, the theory of beam on elasto-plastic geo-material (elasto-plastic theory) can not consider the inclined ground layers appropriately. It is frequently assumed that the soil layers are parallel to the surface. However, the soil layers are generally inclined and even asymmetric. The common modelling of the asymmetric half section of the excavation system using the elasto-plastic theory, can lead differences from the real behaviour of ground, which has critical significance in case of deep excavation in urban area. In this study, an attempt to find appropriate modelling methods was made by carrying out a comparative study between the FEM and the elasto-plastic analyses. It is shown that in case of the upward-inclined soil profile the elasto-plastic theory may underestimate the performance of retaining structures.

• International Journal of Concrete Structures and Materials
• /
• v.1 no.1
• /
• pp.63-73
• /
• 2007

Optimum multi-layered feed-forward neural network (NN) models using a resilient back-propagation algorithm and early stopping technique are built to predict the shear capacity of reinforced concrete deep and slender beams. The input layer neurons represent geometrical and material properties of reinforced concrete beams and the output layer produces the beam shear capacity. Training, validation and testing of the developed neural network have been achieved using 50%, 25%, and 25%, respectively, of a comprehensive database compiled from 631 deep and 549 slender beam specimens. The predictions obtained from the developed neural network models are in much better agreement with test results than those determined from shear provisions of different codes, such as KBCS, ACI 318-05, and EC2. The mean and standard deviation of the ratio between predicted using the neural network models and measured shear capacities are 1.02 and 0.18, respectively, for deep beams, and 1.04 and 0.17, respectively, for slender beams. In addition, the influence of different parameters on the shear capacity of reinforced concrete beams predicted by the developed neural network shows consistent agreement with those experimentally observed.