• Computers and Concrete
• /
• v.20 no.1
• /
• pp.31-38
• /
• 2017

In the present study an Artificial Neural Network (ANN) was used to predict the compressive strength of self-compacting concrete. The data developed experimentally for self-compacting concrete and the data sets of a total of 99 concrete samples were used in this work. ANN's are considered as nonlinear statistical data modeling tools where complex relationships between inputs and outputs are modeled or patterns are found. In the present ANN model, eight input parameters are used to predict the compressive strength of self-compacting of concrete. These include varying amounts of cement, coarse aggregate, fine aggregate, fly ash, fiber, water, super plasticizer (SP), viscosity modifying admixture (VMA) while the single output parameter is the compressive strength of concrete. The importance of different input parameters for predicting the strengths at various ages using neural network was discussed in the study. There is a perfect correlation between the experimental and prediction of the compressive strength of SCC based on ANN with very low root mean square errors. Also, the efficiency of ANN model is better compared to the multivariable regression analysis (MRA). Hence it can be concluded that the ANN model has more potential compared to MRA model in developing an optimum mix proportion for predicting the compressive strength of concrete without much loss of material and time.

• Computers and Concrete
• /
• v.22 no.4
• /
• pp.419-437
• /
• 2018

The compressive strength of self-compacting concrete (SCC) containing fly ash (FA) is highly related to its constituents. The principal purpose of this paper is to investigate the efficiency of hybrid fuzzy radial basis function neural network with biogeography-based optimization (FRBFNN-BBO) for predicting the compressive strength of SCC containing FA based on its mix design i.e., cement, fly ash, water, fine aggregate, coarse aggregate, superplasticizer, and age. In this regard, biogeography-based optimization (BBO) is applied for the optimal design of fuzzy radial basis function neural network (FRBFNN) and the proposed model, implemented in a MATLAB environment, is constructed, trained and tested using 338 available sets of data obtained from 24 different published literature sources. Moreover, the artificial neural network and three types of radial basis function neural network models are applied to compare the efficiency of the proposed model. The statistical analysis results strongly showed that the proposed FRBFNN-BBO model has good performance in desirable accuracy for predicting the compressive strength of SCC with fly ash.

• Computers and Concrete
• /
• v.34 no.4
• /
• pp.427-446
• /
• 2024

The I-shaped steel reinforced recycled aggregate concrete (SRRC) composite structure has the advantages of high bearing capacity and environmental protection, and the interfacial bond strength is an important theory. To this end, the I-shaped SRRC bond strength and its calculation based on artificial neural network (ANN) will be studied. Firstly, 39 push out tests of I-shaped SRRC were conducted, the load-slip curve has obvious regularity, which is divided into 4 segments by 3 regular points. Three bond strengths were defined based on these three rule points, and the approximate ranges of their values and the laws of influence of each factor on them were found. Secondly, the Elman ANN model used for the prediction of bond strength was established, and the parameters of Elman ANN predicting I-shaped SRRC bond strength were studied, and the effects of detailed parameters on the prediction results were revealed. Finally, the bond strength of SRRC was predicted using Elman and BP (back propagation) neural network models, both of which showed good prediction results. This study is a theoretical basis for the design and fine simulation of I-shaped SRRC composite structures.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2003.05a
• /
• pp.1017-1022
• /
• 2003

The hydraulic structures such as aqueduct tunnels and the drainage canal of the hydroelectric power plant in Japan are almost old. Therefore, the concrete surface of the aqueduct tunnel has received damage by wear-out and the crack, etc. This study was to develop repair mortar mixed a coal ash coarse powder by using two kinds of high early strength cements. As a result, the repair mortar was obtained by substituting the EF cement (maid in Japan) and the MT cement (maid in South Korea) at a rate of 60:40, and substituting the coal ash 30% and the mixing rate 35% of the artificial aggregate for natural fine aggregate.

• Computers and Concrete
• /
• v.30 no.6
• /
• pp.393-407
• /
• 2022

Due to the enormous cement content, pozzolanic materials, and the use of different aggregates, sustainable controlled low-strength material (CLSM) has a higher material cost than conventional concrete and sustainable construction issues. However, by selecting appropriate materials and formulations, as well as cement and aggregate content, whitethorn costs can be reduced while having a positive environmental impact. This research explores the desire to optimize plastic properties and 28-day unconfined compressive strength (UCS) of CLSM containing powder content from unprocessed-fly ash (u-FA) and recycled fine aggregate (RFA). The mixtures' input parameters consist of water-to-cementitious material ratio (W/CM), fly ash-to-cementitious materials (FA/CM), and paste volume percentage (PV%), while flowability, bleeding, segregation index, and 28-day UCS were the desired responses. The central composite design (CCD) notion was used to produce twenty CLSM mixes and was experimentally validated using MATLAB by an Artificial Neural Network (ANN). Variance analysis (ANOVA) was used for the determination of statistical models. Results revealed that the plastic properties of CLSM improve with the FA/CM rise when the strength declines for 28 days-with an increase in FA/CM, the diameter of the flowability and bleeding decreased. Meanwhile, the u-FA's rise strengthens the CLSM's segregation resistance and raises its strength over 28 days. Using calcareous powder as a substitute for cement has a detrimental effect on bleeding, and 28-day UCS increases segregation resistance. The response surface method (RSM) can establish high correlations between responses and the constituent materials of sustainable CLSM, and the optimal values of variables can be measured to achieve the desired response properties.

• Journal of the Korean Crystal Growth and Crystal Technology
• /
• v.17 no.6
• /
• pp.277-282
• /
• 2007

The artificial lightweight aggregate (ALA) was manufactured using coal bottom ashes produced from a thermoelectric power plant with clay and, the sintering temperature and batch composition dependence upon physical properties of ALA were studied. The bottom ash (BA) had 13wt% coarse particle (>4.75mm) and showed very irregular shape so should be crushed to fine particles to be formed with clay by extrusion process. Also the bottom ash contained a many unburned carbon which generates the gas by oxidation and lighten a aggregate during a sintering process. Plastic index of green bodies decreased with increasing bottom ash content but the extrusion forming process was possible for the green body containing BA up to 40wt% whose plastic index and plastic limit were around 10 and 22 respectively. The ALA containing $30{\sim}40wt%$ BA sintered at $1100{\sim}1200^{\circ}C$ showed a volume specific density of $1.3{\sim}1.5$ and water absorption of $13{\sim}15%$ and could be appled for high-rise building and super-long bridge.

• Journal of the Korean Recycled Construction Resources Institute
• /
• v.10 no.1
• /
• pp.48-55
• /
• 2022

This study uses the recovered water as mixing water and artificial lightweight aggregate pre-wetting water as part of a study to increase the recycling rate and reduce greenhouse gas of the ready-mixed concrete recovered during the concrete transport process, and cement fine powder of blast furnace slag(BFS) and fly ash(FA). The engineering characteristics of the three-component lightweight aggregate mortar used as a substitute were reviewed. For this purpose, the flow, dry unit mass, compressive strength, drying shrinkage, neutralization depth, and chloride ion penetration resistance of the three-component lightweight aggregate mortar were measured. When used together with the formulation, when 15 % of BFS and 5 % of FA were used, it was found to be positive in improving the compressive strength and durability of the mortar.

• Smart Structures and Systems
• /
• v.26 no.2
• /
• pp.241-251
• /
• 2020

Due to the undeniable importance of approximating the concrete compressive strength (CSC) in civil engineering, this paper focuses on presenting four novel optimizations of multi-layer perceptron (MLP) neural network, namely artificial bee colony (ABC-MLP), grasshopper optimization algorithm (GOA-MLP), shuffled frog leaping algorithm (SFLA-MLP), and salp swarm algorithm (SSA-MLP) for predicting this crucial parameter. The used dataset consists of 103 rows of information concerning seven influential parameters (cement, slag, water, fly ash, superplasticizer, fine aggregate, and coarse aggregate). In this work, the best-fitted complexity of each ensemble is determined by a population-based sensitivity analysis. The GOA distinguished its self by the least complexity (population size = 50) and emerged as the second time-effective optimizer. Referring to the prediction results, all tested algorithms are able to construct reliable networks. However, the SSA (Correlation = 0.9652 and Error = 1.3939) and GOA (Correlation = 0.9629 and Error = 1.3922) performed more accurately than ABC (Correlation = 0.7060 and Error = 4.0161) and SFLA (Correlation = 0.8890 and Error = 2.5480). Therefore, the SSA-MLP and GOA-MLP can be promising alternatives to laboratorial and traditional CSC evaluative methods.

• Computers and Concrete
• /
• v.24 no.2
• /
• pp.137-150
• /
• 2019

In this paper, surrogate models such as multivariate adaptive regression splines (MARS) and M5P model tree (M5P MT) methods have been investigated in order to propose a new formulation for the 28-days compressive strength of self-compacting concrete (SCC) incorporating metakaolin as a supplementary cementitious materials. A database comprising experimental data has been assembled from several published papers in the literature and the data have been used for training and testing. In particular, the data are arranged in a format of seven input parameters covering contents of cement, coarse aggregate to fine aggregate ratio, water, metakaolin, super plasticizer, largest maximum size and binder as well as one output parameter, which is the 28-days compressive strength. The efficiency of the proposed techniques has been demonstrated by means of certain statistical criteria. The findings have been compared to experimental results and their comparisons shows that the MARS and M5P MT approaches predict the compressive strength of SCC incorporating metakaolin with great precision. The performed sensitivity analysis to assign effective parameters on 28-days compressive strength indicates that cementitious binder content is the most effective variable in the mixture.

• 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.