• 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.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2002.05a
• /
• pp.545-550
• /
• 2002

Concrete is one of the essential structural materials in the construction. But, concrete consists of many materials and is affected by many factors such as properties of materials, site environmental situations, and skill of constructor. Therefore, concrete mixes depend on experiences of experts. However, it is more and more difficult to determine concrete mixes design by empirical means because more ingredients like mineral and chemical admixtures are included. Artificial Neural Networks(ANN) are a mimic models of human brain to solve a complex nonlinear problem. They are powerful pattern recognizers and classifiers, also their computing abilities have been proven in the fields of prediction, estimation and pattern recognition. Here, among them, the back propagation network and radial basis function network are used. Compositions of high-performance concrete mixes are eight components(water, cement, fine aggregate, coarse aggregate, fly ash, silica fume, superplasticizer and air-entrainer). Compressive strength and slump are measured. The results show that neural networks are proper tools to minimize the uncertainties of the design of concrete mixtures.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2004.05a
• /
• pp.738-741
• /
• 2004

This study is concerning on modeling to predict the flexural behaviors of FRP-confined concrete structural members. For compressive behaviors of confined concrete by FRP jackets, the hypoelasticity-based constitutive law of concrete has been presented under the basis of three-dimensional stress states. The strength enhancement of concrete wrapped by FRP jackets has been determined by the failure surface of concrete in tri-axial states, and its corresponding peak strain is computed by the strain enhancement factor. The behavior of FRP jackets has been modeled using the mechanics of orthotropic laminated composite materials in two-dimensional stress states. To be based on the three-dimensional constitutive laws, an algorithm for the prediction of flexural bending behaviors of FRP-confined concrete structural member has been presented.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.8 no.3
• /
• pp.169-176
• /
• 2004

The Mechanistic model, considering expansion stress, coefficient of diffusion etc. to time, is applied to predict the deterioration of concrete structures of the nuclear power plant(NPP) due to sulfate attack. Mix design for the test was three kinds of specified compressive strength 385, 280 and $210kgf/cm^2$ which are used to construct NPPs and cement was type I and V. The immersion test was performed with 10% $Na_2SO_4$ solution to cement type and strength for a year. The coefficient of diffusion on each concrete mix is calculated based on the results of immersion test, and it is used for predicting the sulfate attack of the concrete structures of NPP. The coefficient of diffusion of the target concrete ranged $0.5763{\sim}3.9002{\times}10^{-12}m^2/sec.$, and the sulfate attack rate of concrete structures of the NPP was predicted as 0.1~7.1 mm/year.

• Computers and Concrete
• /
• v.10 no.6
• /
• pp.557-573
• /
• 2012

This paper discusses the combined application of two different techniques, Neural Networks (NN) and Principal Component Analysis (PCA), for improved prediction of concrete properties. The combination of these approaches allowed the development of six neural networks models for predicting slump and compressive strength of concrete with mineral additives such as blast furnace slag, fly ash and silica fume. The Back-Propagation Multi-Layer Perceptron (BPMLP) with Bayesian regularization was used in all these models. They are produced to implement the complex nonlinear relationship between the inputs and the output of the network. They are also established through the incorporation of a huge experimental database on concrete organized in the form Mix-Property. Thus, the data comprising the concrete mixtures are much correlated to each others. The PCA is proposed for the compression and the elimination of the correlation between these data. After applying the PCA, the uncorrelated data were used to train the six models. The predictive results of these models were compared with the actual experimental trials. The results showed that the elimination of the correlation between the input parameters using PCA improved the predictive generalisation performance models with smaller architectures and dimensionality reduction. This study showed also that using the developed models for numerical investigations on the parameters affecting the properties of concrete is promising.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.11a
• /
• pp.57-58
• /
• 2022

Concrete mix design is used as essential data for the quality of concrete, analysis of structures, and stable use of sustainable structures. However, since most of the formulation design is established based on the experience of experts, there is a lack of data to base it on. are suffering Accordingly, in this study, the purpose of this study is to build a predictive model to use the concrete mixing factor as basic data for calculation using the DNN technique. As for the data set for DNN model learning, OPC and ternary concrete data were collected according to the presence or absence of admixture, respectively, and the model was separated for OPC and ternary concrete, and training was carried out. In addition, by varying the number of hidden layers of the DNN model, the prediction performance was evaluated according to the model structure. The higher the number of hidden layers in the model, the higher the predictive performance for the prediction of the mixing elements except for the compressive strength factor set as the output value, and the ternary concrete model showed higher performance than the OPC. This is expected because the data set used when training the model also affected the training.

• Structural Engineering and Mechanics
• /
• v.18 no.1
• /
• pp.21-40
• /
• 2004

In this paper, we modify the L-L model (Li et al. 2003) and extend the application of this model to concrete confined by both steel reinforcement and CFRP. Thirty-six concrete cylinders with a dimension of ${\varphi}30{\times}60$ cm were tested to verify the effectiveness of the proposed model. The experimental test results show that different types of steel reinforcement have a great effect on the compressive strength of concrete cylinders confined by steel reinforcement, but the different types of steel reinforcement have very little effect on concrete cylinders confined by both steel reinforcement and CFRP. Compared with the stress-strain curves of confined concrete cylinders, we can conclude that the proposed model can provide more effective prediction than others models.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2016.10a
• /
• pp.83-84
• /
• 2016

Surplus water inside a concrete other than moisture that is used for hydration of the cement affects the physical properties of the concrete (modulus of elasticity, compressive strength, drying shrinkage, and creep) by drying. Changes in temperature and humidity inside a concrete has correlation with the movement speed and reaction rate of deterioration factors such as carbon dioxide and chloride ions. In this study, comparison was performed between temperature and relative humidity inside the concrete and meteorological data for exposure environment through measurement at the site for two years. Surface temperature of the concrete (depth 1cm) was measured higher by 6℃ during the summers, while it was measured lower by 2℃ during the winters due to solar radiation, wind, and radiation cooling. As for relative humidity, change was large in the depth of 1cm, while more than 85% was maintained in the depth of 10cm.

• Computers and Concrete
• /
• v.15 no.4
• /
• pp.503-514
• /
• 2015

Fibre-added concretes are frequently used in large site applications such as slab and airports as well as in bearing system elements or prefabricated elements. It is very difficult to determine the mechanical properties of the fibre-added concretes by experimental methods in situ. The purpose of this study is to develop an artificial neural network (ANN) model in order to predict the compressive and bending strengths of hybrid fibre-added and non-added concretes. The strengths have been predicted by means of the data that has been obtained from destructive (DT) and non-destructive tests (NDT) on the samples. NDTs are ultrasonic pulse velocity (UPV) and Rebound Hammer Tests (RH). 105 pieces of cylinder samples with a dimension of $150{\times}300mm$, 105 pieces of bending samples with a dimension of $100{\times}100{\times}400mm$ have been manufactured. The first set has been manufactured without fibre addition, the second set with the addition of %0.5 polypropylene and %0.5 steel fibre in terms of volume, and the third set with the addition of %0.5 polypropylene, %1 steel fibre. The water/cement (w/c) ratio of samples parametrically varies between 0.3-0.9. The experimentally measured compressive and bending strengths have been compared with predicted results by use of ANN method.

• Computers and Concrete
• /
• v.21 no.5
• /
• pp.513-523
• /
• 2018

Time dependent strain due to creep is a significant factor in structural design. Multi-gene genetic programming (MGGP) and artificial neural network (ANN) are used to develop two models for prediction of creep compliance in concrete. The first model was developed by MGGP technique and the second model by hybridized MGGP-ANN. In the MGGP-ANN, the ANN is working in parallel with MGGP to predict errors in MGGP model. A total of 187 experimental data sets that contain 4242 data points are filtered from the NU-ITI database. These data are used in developing the MGGP and MGGP-ANN models. These models contain six input variables which are: average compressive strength at 28 days, relative humidity, volume to surface ratio, cement type, age at start of loading and age at the creep measurement. Practical equation based on MGGP was developed. A parametric study carried out with a group of hypothetical data generated among the range of data used to check the generalization ability of MGGP and MGGP-ANN models. To confirm validity of MGGP and MGGP-ANN models; two creep prediction code models (ACI209 and CEB), two empirical models (B3 and GL 2000) are used to compare their results with NU-ITI database.