• Computers and Concrete
• /
• v.10 no.2
• /
• pp.197-217
• /
• 2012

This research deals with the prediction of compressive strength of normal and high strength concrete using neural networks. The compressive strength was modeled as a function of eight variables: quantities of cement, fine aggregate, coarse aggregate, micro-silica, water and super-plasticizer, maximum size of coarse aggregate, fineness modulus of fine aggregate. Two networks, one using raw variables and another using grouped dimensionless variables were constructed, trained and tested using available experimental data, covering a large range of concrete compressive strengths. The neural network models were compared with regression models. The neural networks based model gave high prediction accuracy and the results demonstrated that the use of neural networks in assessing compressive strength of concrete is both practical and beneficial. The performance of model using the grouped dimensionless variables is better than the prediction using raw variables.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2006.05b
• /
• pp.549-552
• /
• 2006

Generally the ultra-high strength steel reinforced concrete has rich mix composition composed of high-strength type mineral admixtures and as a result of very low water-binder ratio(about under w/b=25%), it reveals ultra-high compressive strength(about over 100Mpa). Also, in order to obtain sufficient toughness after construction, we usually mix a large quantity steel fiber with ultra-high strength steel reinforced concrete therefore we must use proper mixer for workability. When we make the ultra-high strength steel reinforced concrete we need more long mixing time or much super-plasticizer than when we manufacture normal concrete. These bring about economical problems and performance deterioration. Therefore, in this study, in order to manufacture easily ultra-high strength steel reinforced concrete we develope a dedicated mixer for ultra-high strength steel reinforced concrete with high speed type. It carried out the examination for comparison between the dedicated and general type mixer, the analysis and counterplan of the point at issue when we manufacture ultra-high strength steel reinforced concrete by the dedicated mixer.

• Advances in concrete construction
• /
• v.6 no.1
• /
• pp.47-68
• /
• 2018

This article reports the utilization of fly ash (FA) waste product from industry and silpozz which is an agro-waste from agriculture as an environmental friendly material in construction industry. The evaluation of strength and durability study was observed using FA and silpozz as a partial replacement of Ordinary Portland Cement (OPC). The studied parameters are compressive strength, flexural strength, split tensile strength and bond strength as well as the durability study involves the acid soluble chloride (ASC), water soluble chloride (WSC), water absorption and sorptivity. Scanning electron microscopy (SEM) and XRD of selected samples are also done. It reveals from the test results that the deterioration factor (DF) in compressive strength is 4% at 365 days. The DF of split tensile strength and flexural strength is 0.96% and 0.6% at 90 days respectively. The minimum slip is 1mm and 1.1mm after 28 days of testing bond strength for NWC and SWC sample respectively. The percentage decrease in bond strength is 10.35% for 28 days SWC samples. The pre-cast blended concrete samples performed better to chloride diffusion. Modulus of elasticity of SWC samples are also studied.The water absorption and sorptivity tests are conducted after 28 days of curing.

• 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.15 no.2
• /
• pp.215-229
• /
• 2015

The emerging technology of self compacting concrete, fiber reinforcement together reduces vibration and substitute conventional reinforcement which help in improving the economic efficiency of the construction. The objective of this work is to find the regression model to determine the response surface of mix proportioning Steel Fiber Reinforced Self Compacting Concrete (SFSCC) using statistical investigation. A total of 30 mixtures were designed and analyzed based on Design of Experiment (DOE). The fresh properties of SCC and mechanical properties of concrete were studied using Response Surface Methodology (RSM). The results were analyzed by limited proportion of fly ash, fiber, volume combination ratio of two steel fibers with aspect ratio of 50/35: 60/30 and super plasticizer (SP) dosage. The center composite designs (CCD) have selected to produce the response in quadratic equation. The model responses included in the primary stage were flowing ability, filling ability, passing ability and segregation index whereas in harden stage of concrete, compressive strength, split tensile strength and flexural strength at 28 days were tested. In this paper, the regression model and the response surface plots have been discussed, and optimal results were found for all the responses.

• Advances in concrete construction
• /
• v.4 no.1
• /
• pp.49-69
• /
• 2016

This work investigates the mechanical properties of conventional concrete (CC) and self compacting concrete (SCC) using fine rubber and silpozz were accompanied by a comparative study between conventional rubberized concrete (CRC) and self compacting rubberized concrete (SCRC). Fine rubber (FR) from scrap tires has replaced the fine aggregate (FA) and Silpozz has been used as a replacement of cement at the proportions of 5, 10 and 15%. Silpozz as a partial replacement of cement in addition of superplasticiser (SP) increases the strength of concrete. Fresh concrete properties such as slump test, compaction factor test for CRC, whereas for SCRC slump flow, $T_{500}$, V-funnel, L-box, U-box, J-ring tests were conducted along with the hardened properties tests like compressive, split tensile and flexural strength test at 7, 28 and 90 days of curing. The durability and microstructural behavior for both CRC and SCRC were investigated. FR used in the present study is 4.75 mm passing with fineness modulus 4.74.M30 grade concrete is used with a mix proportion of 1:1.44:2.91 and w/c ratio as 0.43. The results indicate that as FR quantity increases, workability of both CRC and SCRC decreases. The results also show that the replacement of natural fine aggregate (NFA) with FR particles decreases the compressive strength with the increase of flexural strength observed upto 5% replacement of FR. Also replacement of cement with silpozz resulted enhancement of strength in SCRC.

• 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.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2008.11a
• /
• pp.919-922
• /
• 2008

This paper reports the physical and shrinkage properties of concrete using expansive additive(E) and three shrinkage reducing admixtures(SRA1, 2, 3) in order to reduce shrinkage of concrete. For the properties of fresh concrete, the use of SRA1, 2, 3 results in a increase in fluidity and decrease in the dosage of super plasticizer as much as 0.05$\sim$0.1%. And For the properties of hardened concrete, the use of SRA1, 2, 3 results in a decrease in compressive, tensile and flexural strength slightly. For drying shrinkage properties, the use of SRA3 is the most effective for reduction of shrinkage, and the next best way to reduce shrinkage is combination with expansive additive(E) and shrinkage reducing admixture(SRA) or the using of expansive additive(E).

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.20 no.5
• /
• pp.1-8
• /
• 2016

This paper presents an evaluation of engineering properties in TDFA(Tire Derived Fuel Ash)- based concrete in early age. Concrete containing 0.5 of w/b(water to binder) ratio and 20% of FA(Fly Ash) replacement ratio are prepared, and FA content are replaced with TDFA from 3% to 12% for evaluating the effect of TDFA on fresh and hardened concrete properties. With higher than 6% of TDFA replacement ratio, workability is significantly worsened but it is improved with more SP(Super plasticizer) and AE(Air Entrainer) agent. Concrete with 6~12% of TDFA shows reasonable strength development and better resistance to carbonation and chloride attack in spite of early-aged condition. However concrete with 6% TDFA shows poor resistance to freezing and thawing action due to insufficient air content. If air content and workability are obtained, replacement of TDFA to 12% can be used for concrete with FA.

• Composite Materials and Engineering
• /
• v.3 no.3
• /
• pp.201-220
• /
• 2021

In this study, potential of three machine learning techniques i.e., M5P, Support vector machines and Gaussian processes were evaluated to find the best algorithm for the prediction of flexural strength of concrete mix with steel fibre. The study comprises the comparison of results obtained from above-said techniques for given dataset. The dataset consists of 124 observations from past research studies and this dataset is randomly divided into two subsets namely training and testing datasets with (70-30)% proportion by weight. Cement, fine aggregates, coarse aggregates, water, super plasticizer/ high-range water reducer, steel fibre, fibre length and curing days were taken as input parameters whereas flexural strength of the concrete mix was taken as the output parameter. Performance of the techniques was checked by statistic evaluation parameters. Results show that the Gaussian process technique works better than other techniques with its minimum error bandwidth. Statistical analysis shows that the Gaussian process predicts better results with higher coefficient of correlation value (0.9138) and minimum mean absolute error (1.2954) and Root mean square error value (1.9672). Sensitivity analysis proves that steel fibre is the significant parameter among other parameters to predict the flexural strength of concrete mix. According to the shape of the fibre, the mixed type performs better for this data than the hooked shape of the steel fibre, which has a higher CC of 0.9649, which shows that the shape of fibers do effect the flexural strength of the concrete. However, the intricacy of the mixed fibres needs further investigations. For future mixes, the most favorable range for the increase in flexural strength of concrete mix found to be (1-3)%.