• Smart Structures and Systems
• /
• v.30 no.2
• /
• pp.209-219
• /
• 2022

The determination for bearing capacity of precast nodular piles is conventionally time-consuming and high-cost by using numerous experiments and empirical methods. This study proposes an intelligent method to evaluate the bearing capacity and shaft resistance of the nodular piles with high efficiency based on long short-term memory (LSTM) approach. A series of field tests are first designed to measure the axial force, shaft resistance and displacement of the combined nodular piles under different loadings, in comparison with the single pre-stressed high-strength concrete piles. The test results confirm that the combined nodular piles could provide larger ultimate bearing capacity (more than 100%) than the single pre-stressed high-strength concrete piles. Both the LSTM-based method and empirical methods are used to calculate the shift resistance of the combined nodular piles. The results show that the LSTM-based method has a high-precision estimation on shaft resistance, not only for the ultimate load but also for the working load.

• Computers and Concrete
• /
• v.19 no.2
• /
• pp.217-226
• /
• 2017

This paper summarizes the results of experimental research, and artificial intelligence methods focused on determination of compressive strength of lightweight cement mortar with silica fume and fly ash after sulfate attack. The artificial neural network and the support vector machine were selected as artificial intelligence methods. Lightweight cement mortar mixtures containing silica fume and fly ash were prepared in this study. After specimens were cured in $20{\pm}2^{\circ}C$ waters for 28 days, the specimens were cured in different sulfate concentrations (0%, 1% $MgSO_4^{-2}$, 2% $MgSO_4^{-2}$, and 4% $MgSO_4^{-2}$ for 28, 60, 90, 120, 150, 180, 210 and 365 days. At the end of these curing periods, the compressive strengths of lightweight cement mortars were tested. The input variables for the artificial neural network and the support vector machine were selected as the amount of cement, the amount of fly ash, the amount of silica fumes, the amount of aggregates, the sulfate percentage, and the curing time. The compressive strength of the lightweight cement mortar was the output variable. The model results were compared with the experimental results. The best prediction results were obtained from the artificial neural network model with the Powell-Beale conjugate gradient backpropagation training algorithm.

• Structural Engineering and Mechanics
• /
• v.54 no.4
• /
• pp.741-754
• /
• 2015

This study evaluates prediction models for three EDPs (engineering demand parameters) using data from three symmetrical structures with RC walls designed according to the currently enforced Romanian seismic design code P100-1/2013. The three analyzed EDPs are: the maximum interstorey drift, the maximum top displacement and the maximum shear force at the base of the RC walls. The strong ground motions used in this study consist of three pairs of recordings from the Vrancea intermediate-depth earthquakes of 1977, 1986 and 1990, as well as two other pairs of recordings from significant earthquakes in Turkey and Greece (Erzincan and Aigion). The five pairs of recordings are rotated in a clockwise direction and the values of the EDPs are recorded. Finally, the relation between various IMs (intensity measures) of the strong ground motion records and the EDPs is studied and two prediction models for EDPs are also evaluated using the analysis of residuals.

• Computers and Concrete
• /
• v.10 no.5
• /
• pp.523-539
• /
• 2012

Silica fume has long been used as a mineral admixture to improve the durability and produce high strength and high performance concrete. And in marine and coastal environments, penetration of chloride ions is one of the main mechanisms causing concrete reinforcement corrosion. In this paper, we proposed a numerical procedure to predict the chloride diffusion in a hydrating silica fume blended concrete. This numerical procedure includes two parts: a hydration model and a chloride diffusion model. The hydration model starts with mix proportions of silica fume blended concrete and considers Portland cement hydration and silica fume reaction respectively. By using the hydration model, the evolution of properties of silica fume blended concrete is predicted as a function of curing age and these properties are adopted as input parameters for the chloride penetration model. Furthermore, based on the modeling of physicochemical processes of diffusion of chloride ion into concrete, the chloride distribution in silica fume blended concrete is evaluated. The prediction results agree well with experiment results of chloride ion concentrations in the hydrating concrete incorporating silica fume.

• Journal of the Korea Concrete Institute
• /
• v.13 no.2
• /
• pp.130-138
• /
• 2001

This paper presents on the shear behavior prediction of reinforced concrete beams using Transformation Angle Truss Model (TATM). The TATM can evaluate the stress-strain relationships for cracked concrete by transforming stresses and strains for principal plane into those over the crack surfaces. This proposed analytical method simplifies the Fixed Angle Softened Truss Model (FA-STM) and removes the limitation of applicability of the FA-STM. The shear.strength and strain of reinforced concrete beams are predicted by using the TATM. For the verification of proposed method, experimental results of reinforced concrete beams were compared with theoretical results by the TATM, FA-STM and Rotating Angle Softened Truss Model (RA-STM).

• Journal of the Korea Concrete Institute
• /
• v.12 no.1
• /
• pp.101-112
• /
• 2000

In many structures, the masonry infill panels have been used for architectural reasons and their influence on the structure is often ignored by engineers. However, it has been recognized that the presence of masonry infills may debates. Recently, the pushover analysis technique is used for the prediction of the inelastic behaviors of structures in the seismic evaluation of existing buildings. However, the reliability of this analysis method has not been fully checked with the test results, particularly in the case of masonry-infilled frames. The objective of this study is to verify the correlation between the experimental and analytical reponses of a high-rise masonry-infilled reinforced concrete frame using DRAIN-2DX program and the test results performed previously. It is concluded from this comparison that the strength and stiffness of members can be predicted with quite high reliability while the ductility capacity of members can not be described reasonably.

• Structural Engineering and Mechanics
• /
• v.52 no.1
• /
• pp.97-113
• /
• 2014

In the present work appropriate concrete material models have been proposed to predict drying shrinkage and specific creep of High-performance concrete (HPC) using Artificial Neural Network (ANN). The ANN models are trained, tested and validated using 106 different experimental measured set of data collected from different literatures. The developed models consist of 12 input parameters which include quantities of ingredients namely ordinary Portland cement, fly ash, silica fume, ground granulated blast-furnace slag, water, and other aggregate to cement ratio, volume to surface area ratio, compressive strength at age of loading, relative humidity, age of drying commencement and age of concrete. The Feed-forward backpropagation networks with Levenberg-Marquardt training function are chosen for proposed ANN models and same implemented on MATLAB platform. The results shows that the proposed ANN models are more rational as well as computationally more efficient to predict time-dependent properties of drying shrinkage and specific creep of HPC with high level accuracy.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.1
• /
• pp.9-18
• /
• 2023

Predicting the compressive strength of high-performance concrete (HPC) is challenging because of the use of additional cementitious materials; thus, the development of improved predictive models is essential. The purpose of this study was to develop an HPC compressive-strength prediction model using an ensemble machine-learning method of combined bagging and stacking techniques. The result is a new ensemble technique that integrates the existing ensemble methods of bagging and stacking to solve the problems of a single machine-learning model and improve the prediction performance of the model. The nonlinear regression, support vector machine, artificial neural network, and Gaussian process regression approaches were used as single machine-learning methods and bagging and stacking techniques as ensemble machine-learning methods. As a result, the model of the proposed method showed improved accuracy results compared with single machine-learning models, an individual bagging technique model, and a stacking technique model. This was confirmed through a comparison of four representative performance indicators, verifying the effectiveness of the method.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.46 no.6
• /
• pp.37-45
• /
• 2004

In this study, twelve different glass fiber reinforced polymer concrete composite panel specimens with various rib heights and tensile side and reinforced side thickness were produced, and the flexural tests were conducted to figure out the effect of The height and thickness influencing on the flexural properties of composite panel. Test results of the study are presented. Especially, a prediction equation of the ultimate moment based on the strength design method agrees well with the test results, and it is thought to be useful for the corresponding design of cross-section according to various spans as the glass fiber reinforced polymer concrete composite panel is applied for a permanent mold.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2005.05a
• /
• pp.375-378
• /
• 2005

In the mechanism of beam shear failure, beam action and arch action always exist simultaneously. According to a/d ratio, the proportion and contribution between these two actions to shear capacity are merely changed. Moreover, the current codes recommendations are founded on the experimental results with normal strength concrete, the applicable range of $f'_{c}$ must be extended. Based on this mechanism and new requirement, an analytical equation is proposed for shear capacity prediction of reinforced concrete beams without stirrups. To reflect contribution change of two actions, stress variation in longitudinal reinforcement along the span is considered with Jenq and Shah Model. Dowel action and shear friction are also taken into account. Size effect is included to derive more precise equation. It is shown that the proposed equation is more accurate than other empirical equations and codes. So, it can be possible that wide range of a/d ratio is considered by one equation.