• Proceedings of the Korea Concrete Institute Conference
• /
• 1998.10a
• /
• pp.281-286
• /
• 1998

The aim of this study is to compare the development of compressive strength of high-Flowing concrete with maturity and to investigate the applicability of strength prediction models of concrete. An experiment was attempted on the high-flowing concrete mixes using Ordinary portland cement, High belite cement, Blast furance slage cement and replaced Fly-ash of 30% by weight of Ordinary portland cement, the water-binder ratios of mixes being 0.35 and the curing temperatures being 30, 20, 10, 5$^{\circ}C$. Test results of mixes are statistically analyzed to infer the correlation coefficient between the maturity and the compressive strength of high-flowing concrete.

• Journal of Korean Association for Spatial Structures
• /
• v.20 no.4
• /
• pp.111-121
• /
• 2020

There has been increasing interest in UHPC (Ultra-High Performance Concrete) materials in recent years. Owing to the superior mechanical properties and durability, the UHPC has been widely used for the design of various types of structures. In this paper, machine learning based compressive strength prediction methods of the UHPC are proposed. Various regression-based machine learning models were built to train dataset. For train and validation, 110 data samples collected from the literatures were used. Because the proportion between the compressive strength and its composition is a highly nonlinear, more advanced regression models are demanded to obtain better results. The complex relationship between mixture proportion and concrete compressive strength can be predicted by using the selected regression method.

• Proceedings of the Korea Concrete Institute Conference
• /
• 1999.04a
• /
• pp.259-264
• /
• 1999

The aim of this study of to compare the development of compressive strength of high-strength concrete with maturity and investigate the applicability the strength prediction models. An experiment was attempted on the high-strength concrete mixes using portland cement replaced by silica fume of 10% by weight of cement, the water-binder ratios of mixes being 0.30 and 0.35, the curing temperatures being 30, 20, 10, 5$^{\circ}C$. Test results of mixes are statistically analyzed to infer the correlation coefficient between the maturity and the compressive strength of high-strength concrete. The constant of strength prediction equation were determined from test results, and the equation was adopted to predict the strength of slab(W80$\times$D100$\times$H20cm). The slab was cast in the laboratory from the same batch water-binder ratio of 0.30, and cores were cut from slab in order to estimate the actual strength. These values are used to compare with predicted value. The present study allows more realistic determination of early age compressive strength of high-strength concrete and can be efficiently used to control the quality in actual construction.

• Computers and Concrete
• /
• v.33 no.1
• /
• pp.55-75
• /
• 2024

The present study introduces an optimum performance soft computing model for predicting the compressive strength of high-performance concrete (HPC) by comparing models based on conventional (kernel-based, covariance function-based, and tree-based), advanced machine (least square support vector machine-LSSVM and minimax probability machine regressor-MPMR), and deep (artificial neural network-ANN) learning approaches using a common database for the first time. A compressive strength database, having results of 1030 concrete samples, has been compiled from the literature and preprocessed. For the purpose of training, testing, and validation of soft computing models, 803, 101, and 101 data points have been selected arbitrarily from preprocessed data points, i.e., 1005. Thirteen performance metrics, including three new metrics, i.e., a20-index, index of agreement, and index of scatter, have been implemented for each model. The performance comparison reveals that the SVM (kernel-based), ET (tree-based), MPMR (advanced), and ANN (deep) models have achieved higher performance in predicting the compressive strength of HPC. From the overall analysis of performance, accuracy, Taylor plot, accuracy metric, regression error characteristics curve, Anderson-Darling, Wilcoxon, Uncertainty, and reliability, it has been observed that model CS4 based on the ensemble tree has been recognized as an optimum performance model with higher performance, i.e., a correlation coefficient of 0.9352, root mean square error of 5.76 MPa, and mean absolute error of 4.1069 MPa. The present study also reveals that multicollinearity affects the prediction accuracy of Gaussian process regression, decision tree, multilinear regression, and adaptive boosting regressor models, novel research in compressive strength prediction of HPC. The cosine sensitivity analysis reveals that the prediction of compressive strength of HPC is highly affected by cement content, fine aggregate, coarse aggregate, and water content.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2000.04a
• /
• pp.287-290
• /
• 2000

Nowadays, strength control is performed by test of compressive strength of concrete which is taken in construction filed. But because it is possible to confirm only compressive strength of concrete by that way, it is difficult to performing strength control pr process plan, So, if we can predict compressive strength of concrete, we can decide when shores and forms can be removed safety, plan process efficiently. This study intends to propose basic data for strength control as determination the time of forwoak removal through investigating propriety of strength prediction using Freiesleben function.

• Structural Engineering and Mechanics
• /
• v.68 no.6
• /
• pp.691-700
• /
• 2018

Ground granulated blast furnace slag (GGBS) is a by product obtained from iron and steel industries, useful in the design and development of high quality cement paste/mortar and concrete. This paper investigates the applicability of relevance vector machine (RVM) based regression model to predict the compressive strength of various GGBS based concrete mixes. Compressive strength data for various GGBS based concrete mixes has been obtained by considering the effect of water binder ratio and steel fibres. RVM is a machine learning technique which employs Bayesian inference to obtain parsimonious solutions for regression and classification. The RVM is an extension of support vector machine which couples probabilistic classification and regression. RVM is established based on a Bayesian formulation of a linear model with an appropriate prior that results in a sparse representation. Compressive strength model has been developed by using MATLAB software for training and prediction. About 70% of the data has been used for development of RVM model and 30% of the data is used for validation. The predicted compressive strength for GGBS based concrete mixes is found to be in very good agreement with those of the corresponding experimental observations.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2006.05b
• /
• pp.145-148
• /
• 2006

Schmidt hammer and ultra-sonic method are commonly used for crushed sand concrete compressive strength test in a construction field. At present, various of equations for prediction of strength are present, which have been used in a construction field. The purpose of this study is to evaluate the correlation between prediction strength by presentation equations and destructive strength to test specimen, and find out which is a suitable equation for the construction site, In this study, a strength test was carried out destructive test by means of core sampling and traditional test. Non-destructive test was conducted Schmidt hammer and ultra-sonic method, the experimental parameter were concrete age, curing condition, test method and strength level. It is demonstrated that the correlation behavior of crushed sand concrete strength in this study good due to the perform analysis of correlation between core, destructive strength and non-destructive strength.

• Structural Engineering and Mechanics
• /
• v.58 no.6
• /
• pp.989-999
• /
• 2016

Moist curing of concrete is a time consuming procedure. It takes minimum 28 days of curing to obtain the characteristic strength of concrete. However, under certain situations such as shortage of time, weather conditions, on the spot changes in project and speedy construction, waiting for entire curing period becomes unaffordable. This situation demands early strength of concrete which can be met using accelerated curing methods. It becomes necessary to obtain early strength of concrete rather than waiting for entire period of curing which proves to be uneconomical. In India, accelerated curing methods are used to arrive upon the actual strength by resorting to the equations suggested by Bureau of Indian Standards' (BIS). However, it has been observed that the results obtained using above equations are exaggerated. In the present experimental investigations, the results of the accelerated compressive strength of the concrete are used to develop the regression models for predicting the short term and long term compressive strength of concrete. The proposed regression models show better agreement with the actual compressive strength than the existing model suggested by BIS specification.

• International Journal of Concrete Structures and Materials
• /
• v.7 no.4
• /
• pp.295-301
• /
• 2013

This paper deals with the interfacial effects of silica fume (SF) and styrene-butadiene rubber (SBR) on compressive strength of concrete. Analyzing the compressive strength results of 32 concrete mixes performed over two water-binder ratios (0.35, 0.45), four percentages replacement of SF (0, 5, 7.5, and 10 %) and four percentages of SBR (0, 5, 10, and 15 %) were investigated. The results of the experiments were showed that in 5 % of SBR, compressive strength rises slightly, but when the polymer/binder materials ratio increases, compressive strength of concrete decreases. A mathematical model based on Abrams' law has been proposed for evaluation strength of SF-SBR concretes. The proposed model provides the opportunity to predict the compressive strength based on time of curing in water (t), and water, SF and SBR to binder materials ratios that they are shown with (w/b), (s) and (p).This understanding model might serve as useful guides for commixture concrete admixtures containing of SF and SBR. The accuracy of the proposed model is investigated. Good agreements between them are observed.

• Smart Structures and Systems
• /
• v.14 no.5
• /
• pp.785-809
• /
• 2014

In this paper, an Adaptive nerou-based inference system (ANFIS) is being used for the prediction of shear strength of high strength concrete (HSC) beams without stirrups. The input parameters comprise of tensile reinforcement ratio, concrete compressive strength and shear span to depth ratio. Additionally, 122 experimental datasets were extracted from the literature review on the HSC beams with some comparable cross sectional dimensions and loading conditions. A comparative analysis has been carried out on the predicted shear strength of HSC beams without stirrups via the ANFIS method with those from the CEB-FIP Model Code (1990), AASHTO LRFD 1994 and CSA A23.3 - 94 codes of design. The shear strength prediction with ANFIS is discovered to be superior to CEB-FIP Model Code (1990), AASHTO LRFD 1994 and CSA A23.3 - 94. The predictions obtained from the ANFIS are harmonious with the test results not accounting for the shear span to depth ratio, tensile reinforcement ratio and concrete compressive strength; the data of the average, variance, correlation coefficient and coefficient of variation (CV) of the ratio between the shear strength predicted using the ANFIS method and the real shear strength are 0.995, 0.014, 0.969 and 11.97%, respectively. Taking a look at the CV index, the shear strength prediction shows better in nonlinear iterations such as the ANFIS for shear strength prediction of HSC beams without stirrups.