Prediction Of Compressive Strength Research Articles

Prediction of compressive strength of geopolymer concrete using a hybrid ensemble of grey wolf optimized machine learning estimators

Geopolymer concrete (GPC) has the potential to replace conventional concrete. But, the mixed proportion of GPC poses several difficulties due to various contributing factors. The design of a reliable prediction model becomes challenging because of the non-linear relationship between the proportion of GPC mix and compressive strength (CS). This study implements a hybrid ensemble machine learning model (HEML) from grey wolf optimized conventional machine learning (CML) models to predict the CS of GPC. An experimental database of 1123 records was compiled from different published research work. The database was used to train and test three optimized CML models namely random forest regressor (RFR), Neural network (NN), and Multivariate regression spline (MARS). Utilizing a meta-learner XGBoost algorithm, the CML models' predicted outputs were trained to develop HEML. Statistical parameters notably R2, Adjusted R2, RMSE, MAE, MAPE, VAF, index, and the Shapiro-Wilk statistical test were used to compare the HEML and CML models' predicted outputs. The HEML model showed better performance in both the training and testing phase than the CML models. Two sensitivity analysis methods were adopted to analyze the impact of various parameters on the compressive strength of geopolymer concrete based on the model with the highest prediction accuracy.

Predictive strength model of cement-treated fine-grained soils using key parameters: Consideration of the total water/cement and soil/cement ratios

Soil stabilization techniques have been widely used to improve the mechanical and engineering properties of soft ground, such as strength, compressibility, and permeability. Recently, dredged soils that have high water content, high compressibility, and low strength have been mixed with cement and used as filling and landfill materials. The water and cement contents and soil types (clay or silt) in these soil–cement mixtures can be determined according to the purpose of use. To this end, the design of these mixtures requires the accurate prediction of the unconfined compressive strength (qu). Therefore, this paper proposes a predictive model for qu of cement-treated fine-grained soils (CTFSs) for ground improvement and stabilization of dredged soils. Ordinary Portland cement and two types of fine-grained soils (clay and silt) were used as the basic materials in the experiment. Unconfined compression tests were performed in a wide range of experiment conditions: water content (wt: 40–170 %), cement content (c: 5–25 %), and curing time (t: 3–90 d), and the results were correlated by two key parameters, wt/c (total water content/cement ratio) and s/c (soil/cement ratio). The results demonstrated that wt/c and s/c were strongly correlated with the qu development of CTFSs depending on the curing period. Therefore, we established a predictive model for qu by combining the power and exponential functions for (s/c)X and (wt/c)Y. The X and Y values of proposed model could equally be applied for different curing periods for soils of different types with different characteristics. In addition, the proposed model could predict long-term qu by using the time coefficient (ct) normalized by the curing period of 7 d. The mean absolute percentage error and coefficient of determination of the proposed model were lower and higher, respectively, than those of the reported data. Overall, the proposed predictive model is a promising tool for predicting the qu of CTFSs, for instance, for ground improvement and cement-treated dredged soils.

Statistical analysis on mechanical behaviour of ternary blended high strength concrete

The growing demand for high strength concrete [HSC] in the construction industry increases the usage of cement, resulting in environmental issues. Recent studies are showing that the utilization of cementitious materials in concrete can effectively reduce the volume of cement. In the present study, ternary blended combinations were prepared using cement, silica fume, and fly ash to attain the HSC. Here, cement was partially replaced by silica fume [2.5, 5, 7.5, and 10%] and fly ash [5, 10, and 15%], respectively. Mini slump cone test was conducted to identify the compatibility of cement paste with polycarboxylate ether [PCE] based superplasticizer. The packing density of aggregates was calculated to reduce the voids and improve the particle distribution in HSC. An experimental investigation was carried out, and the ultimate compressive strength was obtained as 71.55 MPa at 28 days of curing. Multi linear regression analysis was conducted to simulate the mix design for aiding the prediction of compressive strength of the HSC.

Unconfined compressive strength prediction of recycled cement-treated base mixes using soft computing techniques

ABSTRACT The study evaluates the viability of using Full-depth reclamation (FDR) as an eco-friendly approach for constructing roads. The research employs chemical stabilizers in reclaimed asphalt pavement (RAP) material to create a cement-treated base (CTB) layer. The study uses artificial neural network (ANN) models to predict the 7-days unconfined compressive strength (UCS) of RAP material-based CTB mixes. The Levenberg-Marquardt backpropagation-based ANN (LM-BP-ANN) and Scaled Conjugate Gradient backpropagation-based ANN (SCG-BP-ANN) models are used to forecast the UCS values. The models are assessed based on regression coefficient (R) and mean squared error (MSE), and the LM-BP-ANN model outperforms the SCG-BP-ANN model with an R value of 0.99556 and MSE of 0.0305. The findings suggest that the proposed models have the potential to forecast UCS values of recycled cement-treated base mixes.

Behavior of concrete-filled cold-formed steel built-up section stub columns

This paper presents a test campaign concerning the behavior of concrete-filled cold-formed steel built-up section stub columns. The test program consisted of five types of cold-formed steel built-up sections infilled with concrete of three different grades (C40, C80 and C120). A pair of identical open sections were built-up to form a closed section by discrete self-tapping screws and connected using steel strips where necessary. A total of 42 stub columns, including 32 concrete-filled specimens and 10 hollow counterparts, was axially compressed between fixed-ends. Details of material properties tests and stub column tests are described in this paper. The stub column compressive strengths, full range axial load-shortening histories as well as load–strain responses and failure modes are presented and discussed. The test strengths were compared with the design predictions by the current American Specification ACI318, despite that this design rule was originally developed for concrete-filled steel columns with conventional tubular sections rather than built-up sections. The comparison demonstrated that the American Specification ACI318 provides generally unconservative and unreliable compressive strength predictions for the concrete-filled cold-formed steel built-up section stub columns. Necessary improvements shall be made in order to yield accurate compressive strength predictions.

Delayed Strength Development of Composite Cementitious with Calcium Silicate Slag

Using pulverized calcium silicate slag (CSS) to replace part of Portland cement (PC) as composite cementitious material is the most energy-saving and clean treatment method. The main objective of this study was to investigate the delayed strength development of the CSS-PC composite cementitious. The compressive strength of the composite cementitious with 10% to 40% CSS was tested, the delayed strength was calculated, and the delayed age was analyzed. Results showed that the delayed strength and delayed age increased with the increase in the substitution rate of CSS, which was determined by the ratio of C2S and C3S. Moreover, a compressive strength prediction model of CSS-PC composite cementitious was established based on the “core-shell” hydration model. The calculated value was compared with the specification value of each country to analyze whether the compressive strength of CSS-PC composite cementitious meets the engineering requirements.

Experimental study and machine learning prediction on compressive strength of spontaneous-combustion coal gangue aggregate concrete

Spontaneous-combustion coal gangue aggregate (SCGA) has low physical properties and strong water absorption capacity. Previous studies are mostly based on the principle of equal mix proportion, which makes the slump of spontaneous-combustion coal gangue aggregate concrete (SCGAC) lower than that of natural aggregate concrete (NAC). This study obtained the compressive strength of SCGAC at different curing ages under the premise of similar concrete workability, and quantified the effect of SCGA content on the compressive strength of concrete; the meso-structure of SCGAC was obtained by SEM test to reveal the deterioration mechanism of SCGAC compressive performance; based on five independent machine learning (ML) algorithms and three ensemble ML algorithms, SCGAC compressive strength prediction models were proposed, and the prediction performance of each model was evaluated to quantify the importance of each influencing factor on the concrete compressive strength. The results show that by using pre-soaked SCGA and refining the concrete mix proportion, fresh concrete with different SCGA replacement ratios can exhibit similar slump values (70–75 mm); due to the weak interfacial transition zones (ITZs) between cement mortar and SCGA, and the inferior properties of SCGA, the compressive strengths of concrete with 100% replacement ratio at 7 d, 14 d, 28 d and 90 d were reduced by 15.3%, 16.7%, 22.0% and 21.6% respectively compared with NAC; the predictive ability of the ensemble ML models was higher than that of the independent ML models, and the XGB model had the best predictive ability; based on the feature importance analysis of SHAP value, it was found that SCGA density, aggregate-cement ratio and SCGA water absorption were the most important factors affecting the compressive strength of SCGAC.

Application of Group Method of Data Handling via a Modified Levenberg-Marquardt Algorithm in the Prediction of Compressive Strength of Oilwell Cement with Reinforced Fly Ash Based on Experimental Data

SummaryThe experimental design of well cement with durable compressive strength (CS) is challenging and time-consuming. The current research predicts CS using the enhanced group method of data handling via a modified Levenberg-Marquardt algorithm (GMDH-LM) with experimental data. Class F fly ash (CFFA) is used as a supplementary material to cement at various proportions. Experimental tests of CS, thermogravimetric (TG) analysis, rheology, and scanning electron microscopy (SEM) are applied. Experimental findings revealed that the addition of fly ash (FA) enhances CS with curing time as an outcome of pozzolanic action. CS for 20% FA reinforcement after curing for 28 days was 42.95 MPa, compared with 41.53 MPa for 50%. This indicates that a higher addition of FA lowers CS. The rheological findings revealed that FA enhanced the viscosity of the cement slurry. The SEM images demonstrated that the incorporation of CFFA with cement modified the contexture of hardened cement. Cement, water, oilwell cement (OWC), curing time, dispersant, and FA were assigned as input variables for GMDH-LM while CS from the experimental analysis was set as output. Machine learning (ML) findings indicated that GMDH-LM can effectively estimate the CS of OWC. GMDH-LM performed better than backpropagation neural network (BPNN), support vector machine (SVM), and normal GMDH models in predicting CS; it provided higher linearity during training as GMDH-LM gave R2 = 0.958, GMDH = 0.946, SVM = 0.925, BPNN = 0.897, and the least loss functions of mean square error (MSE) = 0.238, MSE = 1.685, MSE = 2.567, and MSE = 4.032, respectively. Similarly, good results were ascertained during testing GMDH-LM provided R2 = 0.928, GMDH = 0.907, SVM = 0.895, BPNN = 0.878, and the lowest loss functions of MSE = 0.304, MSE = 2.650, MSE = 3.494, and MSE = 5.678, respectively. Therefore, the comparative results of all experiments and predictions reveal that GMDH-LM can be deployed as an advanced approach for the estimation of cement hydration in oil and gas wells.

Utilization of response surface methodology in optimization of locally sourced aggregates

This research investigated the optimization of locally sourced aggregate, mixed with variable cement ratios to determine its optimum compressive strength. Samples of standard sizes of local fine and coarse aggregate were obtained at the popular excavation sites. The concrete materials were weighed, batched, mixed, cast and cured using four different mix proportions of 1:2:4, 1.2:2:4, 1.4:2:4 and 1.6:2:4 of cement, fine and coarse aggregate at constant water/cement ratio of 0.5. A total of 48 concrete cubes of 150mmx150mmx150mm were produced, cured for 7, 14, 21 and 28 days and tested. Mathematical model equation relating the compressive strength of the local stone with variability of cement was developed using Response Surface Methodology (RSM). The significance and suitability of the equation was confirmed using the analysis of variance (ANOVA). The ANOVA for the quadratic and Surface Cubic model shows that the adjusted R2 of 0.9808 and F-value of 227.76 in compressive strength of the concrete is confidently accounted for by the independent variable. This demonstrates that the equation's predictions of compressive strength for various concrete structures are accurate. Therefore, utilization of local aggregate is advised for the construction of most of the dominant low-rise residential buildings in Anambra and other neighbouring States.

Influence of waste refractory brick on the destructive and non-destructive properties of sustainable eco-friendly concrete

Concrete is one of the most popularly used structural materials in the construction. It is a composite mixture of cement, fine aggregate, coarse aggregate, water, and with or without admixture. For concrete production, large amounts of natural aggregates are being consumed and as a result, the environment is facing severe challenges. The imbalance in the ecosystem is creating immense complications in the environment due to the illegal mining of aggregate from natural resources. Under these circumstances, researchers are finding suitable alternatives to preserve natural resources and raise environmental awareness and consequently the concept of sustainability is introduced. Depending on the level of difficulties, the utilization of waste materials may be exercised for the preparation of sustainable concrete that are economically and environmentally acceptable. Refractory Bricks turn out to be such a waste after a few cyclic usages in various thermal industries and may be utilized in concrete. In this present experimental work, the utilization of waste refractory bricks are proposed for the partial/total replacement of natural fine aggregate at 10, 20, 30, 40, 50, 70, and 100% levels by crushing it into fine particles. In this study, experiments are mainly divided into two parts, one is non-destructive tests and others are destructive tests. In non-destructive section, the prediction of compressive strength by Rebound Hammer has been performed. Subsequently, destructive tests, like Compression test, Flexural test, and Split Tensile test have been performed to check the mechanical properties of the concrete specimens. From the compression and split tensile test 20% replacement level provided the optimum result. The specimen with 30% replacement presented the best Flexural Strength. All the test results of sustainable concrete specimens are being compared with conventional concrete to check the enrichment or retrenchment of properties of concrete specimens with the incorporation of waste refractory bricks.

Compressive behaviour and prediction model for short and slender FRP-confined GFRP bars

Glass fibre reinforced polymer (GFRP) composite bars can be used as internal reinforcement for concrete structures built in harsh environmental and service conditions. Their utilisation as longitudinal reinforcement for compression members is not widely recommended though due to the anisotropic nature of FRP, their complex failure modes, and limited research, especially for slender bars. A more recent innovation has resulted in the wrapping (confinement) of GFRP bars with FRP composites oriented in the hoop direction. These confined bars have demonstrated promising improvement in FRP bar compressive behaviour and ductility. In the current study, the experimental compressive behaviour of eighty short and slender FRP-confined GFRP bars is reported and a compressive strength model is proposed. The experimental parameters investigated are (i) wrapping layers (i.e. one, two, and three layers oriented ± 83.3° to the longitudinal axis of the bar), and (ii) slenderness ratios (i.e. 15, 30, 45, and 60). The resulting compressive load capacity and strength, stress–strain behaviour, and failure modes are then reported for each tested bar. Test results indicate that an increase in slenderness results in decreased strength. In addition, failure modes shifted from splitting to buckling of the longitudinal fibres. GFRP bars with at least two winding layers had a significantly higher compressive strength than the control GFRP bar (not including winding) and they also exhibited bi-linear stress–strain behaviour as well as ductile failure modes. A compressive strength prediction model is then developed, which is based on the modification of the Johnson-Euler buckling theory and correlates well with the experimental results. The research presented herein has the potential to contribute to the development of design guidelines for concrete compression members, such as columns, piers and piles, that are reinforced with FRP-confined GFRP bars.

Machine learning for prediction of the uniaxial compressive strength within carbonate rocks

Machine learning for prediction of the uniaxial compressive strength within carbonate rocks

Comparison of various machine learning algorithms used for compressive strength prediction of steel fiber-reinforced concrete

Adding hooked industrial steel fibers (ISF) to concrete boosts its tensile and flexural strength. However, the understanding of ISF’s influence on the compressive strength (CS) behavior of concrete is still questioned by the scientific society. The presented paper aims to use machine learning (ML) and deep learning (DL) algorithms to predict the CS of steel fiber reinforced concrete (SFRC) incorporating hooked ISF based on the data collected from the open literature. Accordingly, 176 sets of data are collected from different journals and conference papers. Based upon the initial sensitivity analysis, the most influential parameters like water-to-cement (W/C) ratio and content of fine aggregates (FA) tend to decrease the CS of SFRC. Meanwhile, the CS of SFRC could be enhanced by increasing the amount of superplasticizer (SP), fly ash, and cement (C). The least contributing factors include the maximum size of aggregates (Dmax) and the length-to-diameter ratio of hooked ISFs (L/DISF). Several statistical parameters are also used as metrics to evaluate the performance of implemented models, such as coefficient of determination (R2), mean absolute error (MAE), and mean of squared error (MSE). Among different ML algorithms, convolutional neural network (CNN) with R2 = 0.928, RMSE = 5.043, and MAE = 3.833 shows higher accuracy. On the other hand, K-nearest neighbor (KNN) algorithm with R2 = 0.881, RMSE = 6.477, and MAE = 4.648 results in the weakest performance.

Prediction of compressive strength fiber-reinforced geopolymer concrete (FRGC) using gene expression programming (GEP)

This paper examines the rapidly evolving fiber-reinforced geopolymer composites (FRGC), focusing on the material and geometrical properties of construction fibers and the mechanisms involved in fiber-binder interaction at different curing conditions to determine the compressive strength. To eliminate expensive and time-consuming experimental techniques, soft computing techniques, i.e., gene expression programming (GEP), were used to develop an empirical equation for the prediction of compressive strength (fc′) of FRGC. The database consists of 393 experimental datasets to determine the (fc′) with several curing days to train the GEP models. The mixtures contain the most influential parameters such as fly ash (FA), silica fume (SF), metakaolin (MK), ground granulated blast furnace slag (GGBS), aggregate (AG), sodium hydroxide (SH), sodium metasilicate (SM), alkaline activator (AAK), binder (B), superplasticizer (SP), water (W), curing age (CA), length (L), diameter (D), aspect ratio (AR), density (ρ), tensile strength (ft′), and fiber (F) to determine the fc′. The database is separated into two parts, 70% is used for training, and 30% is for testing. Several linking functions, chromosomes, head size, and genes have been undertaken to determine the optimal results. Expression trees (ETs) are developed and presented in the discussion section, and create the empirical equation from it. Determining the performance of the best model, MSE, RMSE, and R2 are calculated for the FRGC mixture to confirm the GEP models under various situations. Additionally, sensitivity analysis (SA) is also introduced to see the FRGC of each input parameter’s contribution to the prediction of fc′.

Machine learning prediction of 28-day compressive strength of CNT/cement composites with considering size effects

Machine learning prediction of 28-day compressive strength of CNT/cement composites with considering size effects

Genetic programming based compressive strength prediction model for green concrete

Machine Learning (ML) has transformed the workplace in all the engineering domains. Traditionally, the lab experiments are conducted to evaluate the compressive strength of concrete however, it’s have been proved to be time-consuming and labour-intensive. The high costs involved in the testing limits the number of trials and thus compromises with reliability of the construction. The study proposes state-of-art novel genetic programming (GP) based soft-computing prediction model for the estimation of the concrete compressive strength. The current focus on sustainable development goals have led to the innovations in high performance concrete from waste materials which can potentially reduce the adverse environmental impact of cement production, however, the non-linear correlation makes it difficult for the empirical relations and basic ML models to arrive at a reliable prediction model. For this purpose, a dataset of 144 trials of fly ash and silica fume concrete is taken from literature for training and testing the GP model. The GP model performs best with ten genes and a maximum tree depth of four. The population and tournament sizes have been set at 100 and 30, respectively. Crossover and mutation probabilities are 0.84 and 0.14, respectively. The GP model is authenticated using statistical parameters (R2 = 0.98 and RMSE = 0.03). The model proposes an easy-to-use equation for the prediction of compressive strength. The proposed model will save capital, labour and time along with allowing better planning since there is no need to wait for 28 long days. The models can be trained on the in-situ data and trained model can be put to use for variety of datasets in future research.

Compressive strength prediction of metakaolin based high-performance concrete with machine learning

Compressive strength prediction of metakaolin based high-performance concrete with machine learning

Stub Column Behavior of Concrete-Filled Cold-Formed Steel Semi-Oval Sections

This paper is an attempt to investigate the structural behavior of concrete-filled cold-formed steel stub columns with semi-oval cross sections via experimental and numerical studies. The test campaign included thirteen stub columns tests on four semi-oval sections infilled with both normal and high strength concrete. The details of test campaign and key observations are described and discussed. Validated against the test data obtained from this study, finite element model was developed to emulate the compressive behavior observed from tests and then used to derive more numerical data via parametric analyses. It is worth noting that the current codified design provisions for concrete-filled steel tubular columns do not explicitly include the semi-oval sections investigated herein. The acquired results from the test campaign and numerical analyses were employed to evaluate the applicability of the American Specifications (ANSI/AISC 360 and ACI318) as well as the European Code (EN1994-1-1). The evaluation results indicate that the aforementioned design rules are generally conservative for compressive strength predictions, among which the predictions by the European Code are the most accurate. Design method considering strength enhancement and confinement effect was proposed with improved accuracy. It is suggested to use the proposed design method for the compressive design of concrete-filled cold-formed steel semi-oval stub columns.

A comparative study of prediction of compressive strength of ultra‐high performance concrete using soft computing technique

AbstractConcrete which is the most commercialized construction material and thus it plays a key role in this era of development and hence its evolution is of utmost importance and therefore the evolution of the quality of concrete to that of its highly evolved type namely, ultra‐high performance concrete (UHPC) is undeniably the boon to this sector. Though, the correlations between the technical characteristics of UHPC and the composition of its mixture are complicated, nonlinear, and complex to characterize using standard statistical techniques. This paper is intended to use both deep neural network and ensemble machine learning algorithms namely gradient boosting, extreme gradient boosting, random forest regressor, extra tree regressor, and voting regressor trained with an 810 UHPC mixture collections with 15 input variables to predict its compressive strength. After adjusting a regression model, the prediction efficiency and generalization ability of the developed models are validated using a number of performance parameters. It was established that all employed models performed better at forecasting result, the extra tree regressor was the most accurate followed by extreme gradient boosting.

Toward improved prediction of recycled brick aggregate concrete compressive strength by designing ensemble machine learning models

The utilization of recycled brick aggregate concrete (RBC) is an area of active research, in which further investigation is needed to develop accurate models for predicting the behavior of RBC to ensure its safe and sustainable use in construction. This study presents an effective way to determine RBC's compressive strength (CS) based on an appropriate design of ensemble machine learning (ML) models, namely Gradient Boosting, Light Gradient boosting, AdaBoost, Extreme Gradient Boosting, Stacking, and Voting. A database covering 393 test results is compiled from the relevant literature for training and testing the models. In addition, 10-fold cross-validation and random splitting of data are used to ensure the reliability of predictions, as well as prevent overfitting. The findings reveal that the Stacking model has the greatest predictive ability, with a coefficient of determination of 0.95, root mean square error of 2.74 MPa, mean absolute error of 2.09 MPa, mean absolute percentage error of 0.10 on the testing dataset. In addition, Feature importance and Partial dependence plots analysis are utilized to investigate the impact of each RBC component on its CS. In RBC’s mixed-component design, the outcomes of this research, along with a developed Graphical User Interface (GUI) for the CS, might be of great use to material engineers.