• 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.

• Proceedings of the Korea Concrete Institute Conference
• /
• 1999.04a
• /
• pp.463-468
• /
• 1999

The slurry wall of Inchon LNG receiving terminal tank will be planned the super flowing concrete having properties of high strength (required strength 520kg/$\textrm{cm}^2$), no-vibrating and massive structure in the underground. For the performance of this concrete, we investigate and select all materials, the optimum mix design and sensibility test in the laboratory. As test results, we choose portland blast-furnace slag cement and lime stone powder(L.S.P) as cementitious materials, W/C 41%(W/B 35.4%), S/a 50.8% and unit volume of coasre aggregate 0.30 as optimum mix design. Also test result of the fresh and hardened concrete are satisfied with specifications of slurry wall.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2018.05a
• /
• pp.130-131
• /
• 2018

The compressive strength of concrete is determined by various influencing factors. However, the conventional method for estimating the compressive strength of concrete has been suggested by considering only 1 to 3 specific influential factors as variables. In this study, nine influential factors (W/B ratio, Water, Cement, Aggregate(Coarse, Fine), Fly ash, Blast furnace slag, Curing temperature, and humidity) of papers opened for 10 years were collected at 4 conferences in order to know the various correlations among data and the tendency of data. The selected mixture and compressive strength data were learned using the Deep Learning Algorithm to derive an estimated function model. The purpose of this study is to investigate the effect of the number of hidden layers on the prediction performance in the process of estimating the compressive strength for an arbitrary combination.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.40 no.6
• /
• pp.104-113
• /
• 1998

The purpose of this experimental research is to produce the super-workable concrete using ordinary portland cement, blast-furnace slag lowder, and fly ash respectively, and investigate mechanical properties of super-workable concrete. For this purpose, after production of super-workable concrete for different unit weights of binder and percentages of fine aggregate, optimum mixing proportion of them was determined, and then mechanical properties of super-workable concrete such as static modulud of elasticity as well as compressive, tensile and flexural strength were tested and analyzed. Also, the mechanical performances of super-workable concrete were compared with those of high-strength concrete has an excellent mobility, compactability and segregation-resistance, but the strength of super-workable concrete is somewhat lower than that of high-strength concrete with equal mixing proportions of concrete.

• Proceedings of the Korea Concrete Institute Conference
• /
• 1997.04a
• /
• pp.177-185
• /
• 1997

The purpose of this study is to investigate the mechanical properties of super-workable concrete using O.P.C., blast-furnace slag, and fly ash respectively. For this purpose, after determining the optimum mix proportion of super-workable concrete according to unit weight of binder and percentage of fine aggregate respectively, mechanical properties of super-workable concrete such as compressive, tensile and flexural strength as well as elastic modules were tested and analyzed. Also, the mechanical performances of super-workable concrete were compared with those of high-strength concrete with equal mix proportion of concrete. As a result, super-workable concrete have an excellent mobility, placeability, and segregation-resistance, but the strength of super-workable concrete was shown to be somewhat lower than that of high-strength concrete with equal mix proportion of concrete.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2013.05a
• /
• pp.105-106
• /
• 2013

The construction of modern society, the use of high-strength concrete structures is becoming frequent. Admixture has been reported as a factor causing the explosion occurred. This study was experimental research on high strength concrete according to the kinds of admixture. Admixture of four different mix. fire resistance test results are outstanding when using blast furnace slag aggregate. When using silica fume spalling phenomena were most violent.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.54 no.2
• /
• pp.157-166
• /
• 2012

Most of the roads are paved with impermeable materials such as asphalt concrete and cement concrete, and in the event of heavy rainfall, rainwater directly flows into river through a drainage hole on the pavement surface. This large quantity of rainwater directly spilled into the river frequently leads to the flooding of urban streams, damaging lowlands and the lower reaches of a river. In recent years there has been a great deal of ongoing research concerning water permeability and drainage in pavements. Accordingly, in this research, a porous polymer concrete was developed for permeable pavement by using unsaturated polyester resin as a binder, recycled aggregate as coarse aggregate, fly ash and blast furnace slag as filler, and its physical and mechanical properties were investigated. Also, 3 types of permeable polymer block by optimum mix design were developed and rainfall runoff reduction effects by permeability pavement using permeable polymer block were analyzed based on hydraulic experimental model. The infiltration volume, infiltration ratio, runoff initial time and runoff volume in permeability pavement with permeable polymer block of $300{\times}300{\times}80$ mm were evaluated for 50, 100 and 200mm/hr rainfall intensity.

• Computers and Concrete
• /
• v.21 no.4
• /
• pp.463-470
• /
• 2018

In the present study, soft computing i.e., machine learning techniques and regression models algorithms have earned much importance for the prediction of the various parameters in different fields of science and engineering. This paper depicts that how regression models can be implemented for the prediction of compressive strength of concrete. Three models are taken into consideration for this; they are Gaussian Process for Regression (GPR), Multi Adaptive Regression Spline (MARS) and Minimax Probability Machine Regression (MPMR). Contents of cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate and age in days have been taken as inputs and compressive strength as output for GPR, MARS and MPMR models. A comparatively large set of data including 1030 normalized previously published results which were obtained from experiments were utilized. Here, a comparison is made between the results obtained from all the above mentioned models and the model which provides the best fit is established. The experimental results manifest that proposed models are robust for determination of compressive strength of concrete.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2013.11a
• /
• pp.68-71
• /
• 2013

Reactive Powder Concrete (RPC) is an ultra high strength and high ductility cement-based composite material and has shown some promise as a new generation concrete in construction field. It is characterized by a silica fume-cement mixture with very low water-binder (w/b) ratio and very dense microstructure, which is formed using various powders such as cement, silica fume and very fine quartz sand (0.15~0.4mm) instead of ordinary coarse aggregate. However, the unit weight of cement in RPC is as high as 900~1,000 kg/㎥ due to the use of very fine sand instead of coarse aggregate, and a large volume of relatively expensive silica fume as a high reactivity pozzolan is also used, which is not produced in Korea and thus must be imported. Since the density of RPC has a heavy weight at 2.5~3.0 g/㎤. In this study, the modified RPC was made by the combination of ternary pozzolanic materials such as blast furnace slag and fly ash, silica fume in order to economically and practically feasible for Korea's situation. The fire resistance and structural behavior of the modified RPC exposed to high temperature were investigated.

• Smart Structures and Systems
• /
• v.30 no.2
• /
• pp.195-207
• /
• 2022

Computational drawbacks associated with regular predictive models have motivated engineers to use hybrid techniques in dealing with complex engineering tasks like simulating the compressive strength of concrete (CSC). This study evaluates the efficiency of tree potential metaheuristic schemes, namely shuffled complex evolution (SCE), multi-verse optimizer (MVO), and beetle antennae search (BAS) for optimizing the performance of a multi-layer perceptron (MLP) system. The models are fed by the information of 1030 concrete specimens (where the amount of cement, blast furnace slag (BFS), fly ash (FA1), water, superplasticizer (SP), coarse aggregate (CA), and fine aggregate (FA2) are taken as independent factors). The results of the ensembles are compared to unreinforced MLP to examine improvements resulted from the incorporation of the SCE, MVO, and BAS. It was shown that these algorithms can considerably enhance the training and prediction accuracy of the MLP. Overall, the proposed models are capable of presenting an early, inexpensive, and reliable prediction of the CSC. Due to the higher accuracy of the BAS-based model, a predictive formula is extracted from this algorithm.