Compressive Strength Of High Performance Concrete Research Articles

A New Exponential Distribution to Model Concrete Compressive Strength Data

Concrete mixtures can be developed to deliver a broad spectrum of mechanical and durability properties to satisfy the configuration conditions of construction. One technique for evaluating the compressive strength of concrete is to suppose that it pursues a probabilistic model from which it is reliability estimated. In this paper, a new technique to generate probability distributions is considered and a new three-parameter exponential distribution as a new member of the new family is presented in detail. The proposed distribution is able to model the compressive strength of high-performance concrete rather than some other competitive models. The new distribution delivers decreasing, increasing, upside-down bathtub and bathtub-shaped hazard rates. The maximum likelihood estimation approach is used to estimate model parameters as well as the reliability function. The approximate confidence intervals of these quantities are also obtained. To assess the performance of the point and interval estimations, a simulation study was conducted. We demonstrate the performance of the offered new distribution by investigating one high-performance concrete compressive strength dataset. The numerical outcomes showed that the maximum likelihood method provides consistent and asymptotically unbiased estimators. The estimates of the unknown parameters as well as the reliability function perform well as sample size increases in terms of minimum mean square error. The confidence interval of the reliability function has an appropriate length utilizing the delta method. Moreover, the real data analysis indicated that the new distribution is more suitable when compared to some well-known and some recently proposed distributions to evaluate the reliability of concrete mixtures.

Investigation of Reinforced Concrete Column Containing Metakaolin and Fly Ash Cementitious Materials

Nowadays, high-performance concrete is employed in the building sector all over the world. For a strong and durable construction, high performance appears to be a better option. These specially designed types of concrete are made using both conventional and unique materials to fulfill a combination of performance requirements. The objective of this experiment is to investigate the behaviour of short and long columns made of high-performance concrete (HPC). In this study, HPC was manufactured by essential denominators such as cement, fine aggregate, coarse aggregate, water, and mineral admixtures such as metakaolin and fly ash at different replacement levels. The high-performance concrete (HPC) was designed with compressive strength (CS) of about 60 N/mm2. The mixture was developed under the guidelines in modified ACI 211.4R-93. All combinations have the same 0.30 water binder ratio (W/B) and are utilized to achieve improved workability with the addition of a superplasticizer for a chemical admixture, namely, CERAPLAST 300. Seven proportions are cast with 0%, 5%, 7.5%, and 10% replacement of cement with metakaolin and another set of specimens with 5%, 7.5%, and 10% replacement with metakaolin along with a constant 10% replacement of fly ash. For the investigation of strength properties, specimens (cube, prism, and cylinders) such as compressive strength (CS) (3, 7, 28, 56, and 90 days), flexural (FS) and tensile strength (STS) (28 days) and modulus of elasticity were cast (28 days). Totally 14 columns, 7 for short and long columns, were cast, each cured for 28 days. These specimens have been tested in the 1000 kN loading frame. All small columns were tested with concentrated compression, whereas long columns were investigated with little concentration and uniaxial bending. The compressive strength of HPC with 7.5 percent metakaolin and 10 percentage fly ash (MR6) is 59 MPa, 7.34% greater than the compressive strength of reference concrete.

A Study on Gel/Space Ratio Development in Binary Mixture Containing Portland Cement and Meta-Illite Calcined Clay/Rice Husk Ash.

Supplementary cementitious materials (SCMs) have been widely used to enhance both the microscopic and macroscopic properties of the Portland cement (PC)–SCM composite matrix. Few studies have been undertaken to establish the gel/space ratio of meta-illite calcined clay (MCC) and rice husk ash (RHA)-based high-performance concrete (HPC) mortar. This experimental paper describes a conventional degree of hydration (non-evaporable water) and porosity routes of establishing a link amid the gel/space ratio and compressive strength of a sieved mortar from Class 1 (50–75 MPa) HPC at an early age. Using the non-evaporable water method, this paper predicted the gel/space ratio of the hardened MCC/RHA-based HPC mortars and curved fitted into Powers’ exponent equation. The results from this study revealed that MCC or RHA additions (5–30% by weight of PC) to the PC-SCM matrix led to a moderate decline in the compressive strength of the low water-binder ratio (W/B) HPC mortar. The modification aimed at void volume (superabsorbent polymers, SAP, and air) applying Bolomey’s formula and Powers’ gel/space ratio developed a suitable fitting into the Powers’ model. This experimental procedure shows feasibility to predict the MCC and RHA outcome on the compressive strength of HPC.

A combination of deep learning and genetic algorithm for predicting the compressive strength of high‐performance concrete

AbstractThis article presented an efficient deep learning technique to predict the compressive strength of high‐performance concrete (HPC). This technique combined the convolutional neural network (CNN) and genetic algorithm (GA). Six CNN architectures were considered with different hyper‐parameters. GA was employed to determine the optimum number of filters in each convolutional layer of the CNN architectures. The resulted CNN architectures were then compared to each other to find the best architecture in terms of accuracy and capability of generalization. It was shown that all of the proposed CNN models are capable of predicting the HPC compressive strength with high accuracy. Finally, the best of the six considered models was validated through the 10‐fold cross‐validation method and compared to the previous studies on the same data set. Models were developed through a comprehensive data set consisting of 1030 HPC compressive strength test data. Comparing the proposed technique with previous studies showed that the proposed technique has a considerable advantage over previous methods and can be employed for reliable estimation of the mechanical properties of different engineering materials.

Computation of High-Performance Concrete Compressive Strength Using Standalone and Ensembled Machine Learning Techniques.

The current trend in modern research revolves around novel techniques that can predict the characteristics of materials without consuming time, effort, and experimental costs. The adaptation of machine learning techniques to compute the various properties of materials is gaining more attention. This study aims to use both standalone and ensemble machine learning techniques to forecast the 28-day compressive strength of high-performance concrete. One standalone technique (support vector regression (SVR)) and two ensemble techniques (AdaBoost and random forest) were applied for this purpose. To validate the performance of each technique, coefficient of determination (R2), statistical, and k-fold cross-validation checks were used. Additionally, the contribution of input parameters towards the prediction of results was determined by applying sensitivity analysis. It was proven that all the techniques employed showed improved performance in predicting the outcomes. The random forest model was the most accurate, with an R2 value of 0.93, compared to the support vector regression and AdaBoost models, with R2 values of 0.83 and 0.90, respectively. In addition, statistical and k-fold cross-validation checks validated the random forest model as the best performer based on lower error values. However, the prediction performance of the support vector regression and AdaBoost models was also within an acceptable range. This shows that novel machine learning techniques can be used to predict the mechanical properties of high-performance concrete.

Developing a boosted decision tree regression prediction model as a sustainable tool for compressive strength of environmentally friendly concrete.

One of the most significant parameters in concrete design is compressive strength. Time and money could be saved if the compressive strength of concrete is accurately measured. In this study, two machine learning models, namely, boosted decision tree regression (BDTR) and support vector machine (SVM), were developed to predict concrete compressive strength (CCS) using a complete dataset through the previous scientific studies. Eight concrete mixture parameters were used as the input dataset. Four statistical indices, namely the coefficient of determination (R2) and root mean square error (RMSE), mean absolute error (MAE), and RMSE-Standard Deviation Ratio (RSR), were used to illustrate the efficiency of the proposed models. The results show that the BDTR model outperformed SVM model with the overall result of R2=0.86 and RMSE=6.19 and MAE=4.91 and RSR=0.37, respectively. The results of this study suggest that the compressive strength of high-performance concrete (HPC) can be accurately calculated using the proposed BDTR model.

Incorporation of artificial neural network with principal component analysis and cross-validation technique to predict high-performance concrete compressive strength

Compressive strength is the most essential mechanical characterization for concrete due to its crucial role in stating the design standards. Therefore, early, and accurate evaluation of concrete compressive strength minimizes efforts, costs, and time. In this study, we investigate the ability of artificial neural network (ANN) incorporated with principal component analyses (PCA) and cross-validation (CV) techniques to forecast the high-performance concrete (HPC) compression strength. The obtained results from the ANN-CVPCA model showed a good agreement between predicted and actual values. The proposed model provides high accuracy prediction of HPC compressive strength. It also provided a higher correlation coefficient (0.96) and a lower value of mean absolute error (3.43mpa), root mean square error (4.64mpa) and normalized root mean square error (0.13). Moreover, a sensitivity analysis was carried out to identify the most influential parameters and the simulated results showed that the superplasticizer, blast furnace slag, and cement parameters respectively have great effects on the compressive strength of HPC. The performance of the ANN-CVPCA model compared with other models published in previous studies and achieved the desired superiority and more stable predictions due to the existence of PCA and CV which play a significant role in increasing the generalization ability as well as avoiding redundant data and reducing the uncertainty in modeling outcomes.

Investigation of Mechanical Properties, Durability and Microstructure of Low-Clinker High-Performance Concretes Incorporating Ground Granulated Blast Furnace Slag, Siliceous Fly Ash and Silica Fume

The main assumption of eco-efficient High-Performance Concrete (HPC) design is the reduction of Portland cement clinker content without negatively affecting the composite’s mechanical and durability properties. In this paper, three low-clinker HPC mixtures incorporating slag cement (CEM III/B as per EN 197-1) and Supplementary Cementitious Materials (SCMs)—Ground Granulated Blast Furnace Slag (GGBFS), Siliceous Fly Ash (SFA) and Silica Fume (SF)—were designed. The maximum amount of Portland cement clinker from CEM III/B varied from 64 to 116 kg in 1 m3 of concrete mix. The compressive strength of HPC at 2, 7, 14, 28, 56, 90 days, and 2 years after casting, as well as the modulus of elasticity on 2-year-old specimens, was tested. The depth of water penetration under pressure and internal frost resistance in freeze–thaw tests were evaluated after 56 days of curing. Additionally, the concrete pH value tests were performed. The microstructure of 2-year-old HPC specimens was analyzed using Scanning Electron Microscopy (SEM). The research proved that it is possible to obtain low-clinker High-Performance Concretes that reach compressive strength of 76–92 MPa after 28 days of curing, show high values of modulus of elasticity (49–52 GPa) as well as increased resistance to frost and water penetration under pressure.

Study on the Influence of fly ash, mineral powder and silicon powder on the performance of high-performance concrete

To study the effect of fly ash, mineral powder, and silica fume on the working performance and mechanical properties of C70 high-performance concrete by adding the same amount of fly ash, granulated blast furnace slag powder, and silica fume as a composite admixture to replace the amount of cement. Influencing the law, at the same time, the optimal dosage ratio of various admixtures is determined through the orthogonal experiment. The results show that: when adding 6% silica fume, it can improve the performance of high-performance concrete. When the amount is increased, the viscosity of the concrete increases and the fluidity decreases. Incorporating an appropriate amount of silica fume can greatly increase the compressive strength of concrete. When blended with fly ash in the proportion of 20%, the performance of high-performance concrete is better. When the same amount of fly ash replaces cement, fly ash reduces hydration and improves the cohesion of concrete, 7d, 28d the compressive strength of the cube increases significantly. Adding 10% mineral powder, mineral powder can affect the early compressive strength of highperformance concrete, extend the setting time of concrete, and improve the pumping capacity of concrete.

Prediction of compressive strength of High-Performance Concrete by Random Forest algorithm

The prediction results of the compressive strength of high-performance concrete (HPC) based on intelligent algorithms are seriously affected by the input variables. In this study, the Random Forest algorithm (RF) is introduced to optimize the number of input variables by evaluating the importance of influencing factors, and then predict the 28-day compressive strength through Random Forest Regression. The results show that this method is effective for the optimization of input variables, and when the parameters are set within a reasonable range, better prediction results can be obtained than non-variable optimization.

A hybrid data analytics approach for high-performance concrete compressive strength prediction

ABSTRACT Contrary to the popular belief cited in the literature, the proposed data analytics technique shows that multiple linear regression (MLR) can achieve as high a predictive power as some of the black box models when the necessary interventions are implemented pertaining to the regression diagnostic. Such an MLR model can be utilised to design an optimal concrete mix, as it provides the explicit and accurate relationships between the HPC components and the expected compressive strength. Moreover, the proposed study offers a decision support tool incorporating the Extreme Gradient Boosting (XGB) model to bridge the gap between black-box models and practitioners. The tool can be used to make faster, more data-driven, and accurate managerial decisions without having any expertise in the required fields, which would reduce a substantial amount of time, cost, and effort spent on measurement procedures of the compressive strength of HPC.

Non-Tuned Machine Learning Approach for Predicting the Compressive Strength of High-Performance Concrete.

Compressive strength is considered as one of the most important parameters in concrete design. Time and cost can be reduced if the compressive strength of concrete is accurately estimated. In this paper, a new prediction model for compressive strength of high-performance concrete (HPC) was developed using a non-tuned machine learning technique, namely, a regularized extreme learning machine (RELM). The RELM prediction model was developed using a comprehensive dataset obtained from previously published studies. The input variables of the model include cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregate, fine aggregate, and age of specimens. k-fold cross-validation was used to assess the prediction reliability of the developed RELM model. The prediction results of the RELM model were evaluated using various error measures and compared with that of the standard extreme learning machine (ELM) and other methods presented in the literature. The findings of this research indicate that the compressive strength of HPC can be accurately estimated using the proposed RELM model.

A Sensitivity and Robustness Analysis of GPR and ANN for High-Performance Concrete Compressive Strength Prediction Using a Monte Carlo Simulation

This study aims to analyze the sensitivity and robustness of two Artificial Intelligence (AI) techniques, namely Gaussian Process Regression (GPR) with five different kernels (Matern32, Matern52, Exponential, Squared Exponential, and Rational Quadratic) and an Artificial Neural Network (ANN) using a Monte Carlo simulation for prediction of High-Performance Concrete (HPC) compressive strength. To this purpose, 1030 samples were collected, including eight input parameters (contents of cement, blast furnace slag, fly ash, water, superplasticizer, coarse aggregates, fine aggregates, and concrete age) and an output parameter (the compressive strength) to generate the training and testing datasets. The proposed AI models were validated using several standard criteria, namely coefficient of determination (R2), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). To analyze the sensitivity and robustness of the models, Monte Carlo simulations were performed with 500 runs. The results showed that the GPR using the Matern32 kernel function outperforms others. In addition, the sensitivity analysis showed that the content of cement and the testing age of the HPC were the most sensitive and important factors for the prediction of HPC compressive strength. In short, this study might help in selecting suitable AI models and appropriate input parameters for accurate and quick estimation of the HPC compressive strength.

Mechanical Properties and Durability of High‐Performance Concretes Blended with Circulating Fluidized Bed Combustion Ash and Slag as Replacement for Ordinary Portland Cement

This study investigates the mechanical properties and durability of three families of high‐performance concrete (HPC), in which the first was blended with fly ash, the second with circulating fluidized bed combustion (CFBC) ash, and the third with CFBC slag. In addition to each of the three mineral additives, silica fume and a superplasticizer were also incorporated into the HPC. Hence, three families of HPC, containing 10%, 20%, and 30% mineral admixtures and 9% silica fume of the binder mass, respectively, were produced. The microstructure and hydration products of the HPC families were examined by scanning electron microscopy (SEM) and X‐ray diffraction (XRD) to explore the influence of fly ash, CFBC ash, and CFBC slag on the compressive strength and frost resistance of HPC. The experimental results show that the compressive strength of HPC could reach 60 MPa at 28 d age. When the fly ash content was 30%, the compressive strength of HPC was 70.2 MPa at 28 d age; after the freeze‐thaw cycle, the mass loss and strength loss of HPC were 0.63% and 8.9%, respectively. When the CFBC ash content was 20%, the compressive strength of HPC was 75 MPa at 28 d age. After the freeze‐thaw cycle, the mass loss and strength loss of HPC were 0.17% and 0.81%, respectively.

A mathematical model for strength prediction of HPC containing copper slag as a cementitious material

High-performance concrete (HPC) encompasses cement, copper slag, sand, coarse aggregate, superplasticizer, and water. The strength of HPC is determined by the specific surface area of supplementary cementitious materials. Hence it is interesting to investigate the effect of copper slag as a cement replacement on the strength of HPC. In this study, three-level of water-to-cement ratios (0.3, 0,4, and 0,5) were chosen. The various concrete mixtures are produced with increasing copper slag contents from 0 to 40 wt.% in steps of 10 wt.% as cement replacement. To obtain two levels of fineness, the copper slag was milled using a ball mill. The result shows that the strength of concrete containing copper slag for all water-to-cement ratio was lower than the control mixture at an early age (7 days). For the longer curing periods (28 days), the compressive strength of concrete was similar or slightly higher compared to the reference mixture at the replacement level up to 20% for two-level of fineness. A new model, according to Abrams Law, which is Abram-RET, is being proposed by the author to predict the compressive strength of high-performance concrete at 28 days, which gives a strong correlation with the experimental results.

A generalized method to predict the compressive strength of high-performance concrete by improved random forest algorithm

The prediction results of high-performance concrete compressive strength (HPCCS) based on machine learning methods are seriously influenced by input variables and model parameters. This study proposes a method with two stages to select proper variables, simplify parameter settings, and predict HPCCS. The appropriate variables are selected in the first stage by measuring their importance based on random forest, and then are optimized to predict HPCCS in the second stage. The results show that the proposed method was effective for input variable optimization, and could return better predictions than that without variable optimization, provided that the parameters are set within a reasonable range. Compared with previous models, the proposed method shows a strong generalization capacity for HPCCS prediction. We find that the prediction performance of the model is better when the input variables are expressed as absolute mass, and the model performers well when the actual compressive strength of HPC is high.

Monotonicity preserving SIRMs-connected fuzzy inference system for predicting HPC compressive strength

A harmony search-based single input rule modules (SIRMs)-connected FIS with monotonicity preserving property in predicting compressive strength for high-performance fly-ash concrete is proposed. The use of FIS with monotonicity preserving property in the prediction for concrete compressive strength is novel. The model considers the monotonic relationship between the input, i.e., water-binder ratio, and the output, i.e., compressive strength. Monotonicity index (MI) is then used to measure the fulfillment of monotonicity property of the model. The proposed model is evaluated using experimental data. Results show that the proposed model with MI gives better predictions for both training and testing data sets, compared with the model without MI. This indicates that the proposed method with MI is more suitable to be used in predicting compressive strength of high-performance fly-ash concrete. When compared to results from neural networks fitting tool, results from the proposed model for testing data set were found to be slightly better in terms of RMSE. The contributions of this paper are two-folds: (1) a new harmony search-based SIRMs-connected FIS with monotonicity preserving property in predicting high performance concrete (HPC) compressive strength is proposed; and (2) the suitability of monotonicity preserving property in predicting HPC compressive strength is investigated.

Prediction of High-Performance Concrete Strength Using a Hybrid Artificial Intelligence Approach

This study introduces an improved artificial intelligence (AI) approach called intelligence optimized support vector regression (IO-SVR) for estimating the compressive strength of high-performance concrete (HPC). The nonlinear functional mapping between the HPC materials and compressive strength is conducted using the AI approach. A dataset with 1,030 HPC experimental tests is used to train and validate the prediction model. Depending on the results of the experiments, the forecast outcomes of the IO-SVR model are of a much higher quality compared to the outcomes of other AI approaches. Additionally, because of the high-quality learning capabilities, the IO-SVR is highly recommended for calculating HPC strength.

Effect of rice husk ash and fly ash on the compressive strength of high performance concrete

The usage of industrial and agricultural wastes for building materials production plays an important role to improve the environment and economy by preserving nature materials and land resources, reducing land, water and air pollution as well as organizing and storing waste costs. This study mainly focuses on mathematical modeling dependence of the compressive strength of high performance concrete (HPC) at the ages of 3, 7 and 28 days on the amount of rice husk ash (RHA) and fly ash (FA), which are added to the concrete mixtures by using the Central composite rotatable design. The result of this study provides the second-order regression equation of objective function, the images of the surface expression and the corresponding contours of the objective function of the regression equation, as the optimal points of HPC compressive strength. These objective functions, which are the compressive strength values of HPC at the ages of 3, 7 and 28 days, depend on two input variables as: x1(amount of RHA) and x2(amount of FA). The Maple 13 program, solving the second-order regression equation, determines the optimum composition of the concrete mixture for obtaining high performance concrete and calculates the maximum value of the HPC compressive strength at the ages of 28 days. The results containMaxR28HPC= 76.716 MPa when RHA = 0.1251 and FA = 0.3119 by mass of Portland cement.

Comparison of artificial neural network and coupled simulated annealing based least square support vector regression models for prediction of compressive strength of high-performance concrete

High-performance concrete (HPC) is a complex composite material with highly nonlinear mechanical behaviors. Concrete compressive strength, as one of the most essential qualities of concrete, is also a highly nonlinear function of ingredients. In this paper, least square support vector regression (LSSVR) model based on coupled simulated annealing (CSA) has been successfully used to find the nonlinear relationship between the concrete compressive strength and eight input factors (the cement, the blast furnace slags, the fly ashes, the water, the superplasticizer, the coarse aggregates, the fine aggregates, Age of testing). To evaluate the performance of the CSA-LSSVR model, the results of the hybrid model were compared with those obtained by artificial neural network (ANN) model. A comparison study is made using the coefficient of determination R2 and Root Mean Squared Error (RMSE) as evaluation criteria. The accuracy, the computational time, the advantages and shortcomings of these modeling methods are also discussed. The training and testing results have shown that ANNs and CSA-LSSVR models have strong potential for predicting the compressive strength of HPC.