Prediction Of Compressive Strength Research Articles

Development of chemistry-informed interpretable model for predicting compressive strength of recycled aggregate concrete containing supplementary cementitious materials

Accurate prediction of compressive strength of recycled aggregate concrete (RAC) has great value for promoting the sustainable development of concrete field. The study aims to propose a chemistry-informed interpretable model for predicting compressive strength of RAC containing supplementary cementitious materials. First, this study collected the compressive strength records of RAC. Then, the unsupervised learning algorithm isolation forest was utilized to perform data cleaning, and 1600 samples were obtained to build the dataset. And the topological network constraint was introduced to represent the reactivity of cementitious systems. The five machine learning (ML) algorithms were employed to predict compressive strength of RAC, and the prediction accuracy of above models were compared. In addition, SHapley Additive exPlanations (SHAP) method was integrated with the ML model to shed more light on the outcome of ML model. Results showed that the Categorical Boosting (CatBoost) outperformed other ML models on the test set, and the coefficient of determination (R2), root mean square error (RMSE), and mean absolute error (MAE) were 0.961, 2.650 MPa, and 1.636 MPa. The introduction of chemical information enhanced the predictive accuracy of model, and the R2 increased from 0.935 to 0.961, the RMSE and MAE decreased by 22.7% and 15.1%, respectively. The SHAP values of curing age, natural coarse aggregate replacement ratio and water-binder ratio were higher than those other input variables, indicating that the three features were essential for predictive results of model. And the curing age played a positive role in the strength development of RAC, and the increase of natural coarse aggregate replacement ratio and water-binder ratio caused the loss of compressive strength. The influence trends of features on the outputs were in accord with the engineering experience, which proved the reliability of predictions. The contribution and importance of features on the predictions provide a theoretical guidance to aid the concrete mixture design for engineers to obtain the desired performance.

Constitutive relationships and acoustic emission behavior of plant-fiber/magnesium oxychloride cement composites under uniaxial compressive load

Plant-fiber/magnesium oxychloride cement composites (PF-MOC) are bio-composite building materials that are produced by mixing magnesium oxychloride cement (MOC) with plant fibers. The application of PF-MOC in construction engineering can not only promote the reuse of bio-waste but also compensate for the shortage of wood. In this study, 33 prismatic specimens of PF-MOC were prepared using the extrusion molding method for the uniaxial compression test. The compression characteristics of PF-MOC under uniaxial compression load were studied by combining the test with acoustic emission (AE). The results illustrated that the apparent density of the PF-MOC ranged from 771 kg/m3 to 1806 kg/m3, and the compressive strength ranged from 4.7 MPa to 44 MPa. PF-MOC uniaxial compressive stress–strain relationship model was established. The compressive strength of PF-MOC with different types and content of plant fiber is closely related to the apparent density, and thus a compressive strength prediction model was developed. The PFC-MOC with bamboo scrap exhibited the highest AE energy near the peak load, indicating greater brittleness. Conversely, the PF-MOC with wheat straw demonstrated a well-distributed energy release throughout the compression process, suggesting lower brittleness in the straw specimens. The utilization of the b-value proved effective in characterizing the crack development and size transformation process of PF-MOC. Furthermore, SEM revealed that straw fibers exhibited the weakest bonding with the MOC matrix, while wood sawdust fibers and bamboo scrap showed superior interactions with the hydration products of MOC.

Prediction of the additional compressive strength due to PBO-FRCM-confinement of brick-masonry depending on the stiffening effect caused by different discontinuous wrappings: new design-oriented perspective

Fabric Reinforced Cementitious Mortar (FRCM) is an innovative composite system able to strength or rehabilitate masonry members with an efficacy, which is affected by the mechanical and geometrical properties of its constituents: matrix and fabric. Since one of the most appreciated benefits of FRCM is the breathability, the discontinuous application is commonly not considered in the retrofitting. On the other side, the thickness of the matrix may be considerable (ranging between 10 and 30 mm) implying an over-weight and over-stiffness which may influence the seismic response of the structure in a detrimental manner; especially when dealing with column confinement. Consequently, the experimental evidence and the proper design for the partially wrapping with FRCMs is currently lacking.For this reason, the present research reports on an experimental and analytical investigation about PBO (polybenzoxazoles) FRCM-confinement of clay-brick based masonry columns by varying the confinement scheme. The aim is to evaluate the effectiveness of the confinement in terms of axial bearing load capacity and ductility and, at the same time, focusing on the parameters related to the confining scheme showing how these affect the results. Two columns were tested unconfined as lower-bound reference; six columns (i.e. three couples) were partially confined respectively with 3, 4 and 5 wraps having the same width and lastly, a further couple was fully-jacketed as upper-bound reference. The findings evidenced that an appreciable gain in axial strength and deformability was ensured. On the other side, the axial stiffness increased proportionally to the number of confining wraps.Thus, a new analytical model was herein proposed considering the geometry of the confining scheme, as well as the stiffening effect related to it. In particular, a novel effectiveness coefficient (namely KE) is evaluated affecting the theoretical confining pressure based on the axial stiffness of the FRCM confined masonry. The comparison with the own and other available experimental data confirmed the reliability of the proposal which wants to offer a new perspective for the design of the FRCM partial confinement of masonry that needs further investigations to be confirmed by including a variety of masonry and FRCM typologies.

Soft computing techniques for predicting the properties of raw rice husk concrete bricks using regression-based machine learning approaches

In this study, the replacement of raw rice husk, fly ash, and hydrated lime for fine aggregate and cement was evaluated in making raw rice husk-concrete brick. This study optimizes compressive strength, water absorption, and dry density of concrete brick containing recycled aggregates via Response Surface Methodology. The optimized model's accuracy is validated through Artificial Neural Network and Multiple Linear Regression. The Artificial Neural Network model captured the 100 data's variability from RSM optimization as indicated by the high R threshold- (R > 0.9997), (R > 0.99993), (R > 0.99997). Multiple Linear Regression model captured the data's variability the decent R2 threshold confirming- (R2 > 0.9855), (R2 > 0.9768), (R2 > 0.9155). The raw rice husk-concrete brick 28-day compressive strength, water absorption, and density prediction were more accurate when using Response Surface Methodology and Artificial Neural Network compared to Multiple Linear Regression. Lower MAE and RMSE, coupled with higher R2 values, unequivocally indicate the model's superior performance. Additionally, employing sensitivity analysis, the influence of the six input parameters on outcomes was assessed. Machine learning aids efficient prediction of concrete's mechanical properties, conserving time, labor, and resources in civil engineering.

Compressive strength prediction and optimization design of sustainable concrete based on squirrel search algorithm-extreme gradient boosting technique

Compressive strength prediction and optimization design of sustainable concrete based on squirrel search algorithm-extreme gradient boosting technique

Prediction of concrete residual compressive strength under elevated temperatures: Response surface methodology (RSM) approach

Exposure of concrete to elevated temperatures causes irreversible damage to the concrete structure and poses a serious threat to its service life. Due to the importance of concrete fire performance, extensive research has been conducted to investigate its behavior under different conditions of elevated temperatures. The properties of concrete are significantly affected by various factors, including heating temperatures, heating durations, and cooling methods. Among these factors, the residual compressive strength of concrete is considered the most crucial characteristic after exposure to elevated temperatures. This paper aims to develop mathematical models for analyzing and predicting the relative residual compressive strength of concrete at high temperatures. Three independent factors were identified in this study: heating temperatures, heating duration, and cooling method. Two groups of datasets on the relative residual compressive strength of concrete under elevated temperatures were reviewed and collected from previous studies, serving as the benchmark dataset and validation dataset, respectively. Response Surface Methodology (RSM) was employed to analyze the datasets. The results of various statistical parameters, such as the coefficient of determination, sum of squares, F-value, and P-value, indicate the significance of the predicted model for estimating concrete's relative residual compressive strength under elevated temperatures. The RSM analysis reveals that heating temperatures have the most significant effect on the relative residual compressive strength of concrete. In summary, the RSM model shows a strong correlation with the validation datasets, with a coefficient of determination (R2) of 0.7869.

Machine learning-based apparent activation energy estimation for cementitious composites incorporating phase change materials

Phase change materials (PCMs) have emerged as a promising solution to reduce the operational energy consumption and carbon emissions of buildings in recent years. Concrete, as the most-consumed construction material, has been widely used as the host medium to incorporate PCMs. Despite integrating latent heat thermal energy storage (LHTES) capacity, microencapsulated PCMs (MPCMs) have proven to impact the hydration process and strength development of cement mortars and concretes due to several probable mechanisms proposed in the literature. Yet, the effect of MPCM addition on the maturity of cement-based composites needs further investigation. Therefore, this study employs a machine learning (ML) model to study the effect of diverse MPCMs having different thermophysical properties on the strength development of cement mortars and concretes cured under various temperatures. For this purpose, a dataset of mixture designs for MPCM-integrated concretes was compiled and a powerful ML model was developed. Results indicated that the ML model successfully captured the effect of MPCM incorporation on the strength development of mixtures cured at different temperatures. Furthermore, the predictor model was utilized to calculate the apparent activation energy of MPCM-integrated cement-based composites to enable the prediction of compressive strength using maturity curves. It was found that the addition of MPCMs reduced the apparent activation energy of the composites which is indicative of lower sensitivity of strength development to curing temperature. Accordingly, the addition of MPCMs at 10 and 15 wt% of cement reduced the apparent activation energy by approximately 25 and 32%, respectively. Additionally, the most influential parameters contributing to the strength gain of such composites were identified which can further assist the optimization of mixture design. The obtained results can be deployed to study the cracking behavior of hydrating MPCM-integrated concrete exposed to temperature variations in future research.

Characterization of thermal damage and compressive strength during drying at elevated temperatures using ultrasonic pulse velocity

This study attempts to visualize the thermal damage on a multiscale level and characterize the thermal damage and compressive strength of concrete using ultrasonic pulse velocity (UPV). First, based on the experimental results of mercury intrusion porosimetry (MIP), nitrogen adsorption, and scanning electron microscopy (SEM), the multiscale thermal damage of concrete subjected to elevated temperatures was visualized. Then, the UPV of the concrete during the entire drying process was detected. Consequently, the thermal damage can be characterized by the UPV. Finally, after considering the effect of both capillary pressure and thermal damage, a compressive strength prediction model, which could reflect the strength evolution during drying at elevated temperatures, was proposed. The model fits well with experimental results and provides an important basis for practical engineering.

Compressive strength prediction of ternary-blended concrete using deep neural network with tuned hyperparameters

Studies have been conducted to predict the compressive strength of ternary-blended concrete using regression models, such as support vector regression (SVR), random forest (RF), and artificial neural networks. In particular, deep neural networks (DNNs) are one of the most effective nonlinear regression models for predicting compressive strength based on the intricate relationships among constituent materials. However, because the DNN depends on training data, previous studies presented different varieties of ternary-blended concrete, suggesting that appropriate training is required. In addition, the analysis of optimal hyperparameter processes to ensure model performance has not been conducted extensively. This study established appropriate DNN models tuned with hyperparameters to effectively predict the compressive strength of ternary-blended concrete. The dataset used in this study was a set of 775 on-site mix proportions of ternary-blended concrete provided by a ready-mix concrete company in South Korea. Water, cement, fine aggregate, coarse aggregate, fly ash, blast furnace slag, curing temperature, and curing humidity were the inputs, and the compressive strength was set as the output. The basic statistical characteristics of the data used and the performance evaluation (mean square error [MSE] and mean absolute error [MAE]) of 15 models with hidden layers and units as variables were analyzed to determine the network architecture. Based on the model with the selected structure, hyperparameter tuning (batch size, dropout, and batch normalization) was applied to improve the performance of the DNN model. The advanced DNN model exhibited 18% lower MAE losses and 27% lower MSE losses than the conventional DNN model. In addition, based on the MAE losses and MSE losses, the advanced DNN model showed 4% and 12% lower errors than those of SVR, and 11% and 15% lower errors than those of RF, indicating that the DNN model with hyperparameter tuning performed better than the other models.

Tensile and Compression Strength Prediction and Validation in 3D-Printed Short-Fiber-Reinforced Polymers.

In the current study, a methodology is validated for predicting the internal spatially varying strength properties in a single 3D-printed bead composed of 13%, by weight, carbon-fiber-filled acrylonitrile butadiene styrene. The presented method allows for the characterization of the spatially varying microstructural behavior yielding a local anisotropic stiffness and strength that can be integrated in a finite element framework for a bulk estimate of the effective stiffness and strength. The modeling framework is presented with a focus on composite structures made from large area additive manufacturing (LAAM). LAAM is an extrusion-based process yielding components on the order of meters, with a typical raster size of 10 mm. The presented modeling methods are applicable to other short-fiber-reinforced polymer processing methods as well. The results provided indicate the modeling framework yields results for the effective strength and stiffness that align with experimental characterization to within ∼1% and ∼10% for the longitudinal compressive and tensile strength, respectively, and to within ∼3% and ∼50% for the longitudinal compressive and tensile stiffness, respectively.

Mixed artificial intelligence models for compressive strength prediction and analysis of fly ash concrete

The construction industry is facing challenges from the hazardous nature of Ordinary Portland Cement (OPC) production as one of the main contributors to global warming and CO2 emission. Given its increasing demand, the need to replace OPC with sustainable alternatives for green concrete production is essential. The promising results of using fly ash (FA) in concrete mixtures as a supplementary cementitious material (SCM) have attracted great attention. However, conventional laboratory procedures for the analysis of concrete properties like Compressive Strength (CS) are laborious and expensive. The objective of this paper is to predict the CS of fly ash concrete using five integrated models (BP-ANN, BP-GA, BP-PSO, RF, and XGBoost) in order to develop an accurate method for predicting the CS of fly ash concrete and to reduce the error of the prediction model, and to quantify the effect of parameter variations on the CS by using it for parameter impact analysis. In addition, performance statistics for the five algorithmic models mentioned above show that the BP-GA model has the best prediction performance for fly ash concrete CS, with prediction errors distributed within ±5%,The sensitivity investigation concludes that the water-to-binder ratio (w/b) has the greatest influence on the CS of fly ash concrete. Through parametric analysis, it was found that the early CS of fly ash concrete increased with increasing fly ash content when the fly ash replacement rate (FA%) was less than 30%, and decreased with increasing fly ash content when the FA% was greater than 30%.

Ensemble XGBoost schemes for improved compressive strength prediction of UHPC

XGBoost is a promising machine learning method capable of predicting essential concrete properties and enhancing advanced concrete design. However, its underlying version still requires further study and development. In this investigation, the effectiveness of advanced XGBoost versions, including Ada-XGBoost, Bagging-XGBoost, Stacking-XGBoost, and Voting-XGBoost, to predict the compressive strength (CS) of Ultra-high-performance concrete (UHPC) was accessed. A database covering 810 results from in the literature, including 15 inputs, such as 12 UHPC components, two curing conditions, and sample age, was utilized for training the models. The performance criteria for the five models, including RMSE, MAE, and R2, were evaluated using a combination of 10-Fold CV and Monte Carlo (MC) simulation. The results showed that the Stacking-XGBoost and XGBoost models outperformed other models in terms of prediction accuracy for the CS of UHPC. Based on SHAP values analysis, features such as age, fiber, slag, cement, sand, superplasticizer, water, relative humidity, and temperature were identified as the key parameters affecting UHPC’s CS. Furthermore, a quantitative analysis of their combined impact on UHPC's CS was also provided.

Optimal boosting method of HPC concrete compressive and tensile strength prediction

AbstractThe evaluation of fly ash (FA) and micro‐silica (MS) effects on the mechanical properties of concrete at various ages prompts the search for efficient factors in forecasting the compressive strength (CS) and tensile strength (TS), which are extendable for future investigation as well as practical use. The main aim of this article is to overcome the complexity caused by nonlinearity, which is rooted in the relationship between input variables and outputs. Also, the nonlinearity is getting worse through the existence of admixtures. The Adaptive Boosting (ADA) approach was utilized in the related study as a hybrid model to provide an optimal relation between the ingredients and the mechanical strengths for evaluating the parameters most useful in predicting the CS and TS of high‐performance concrete. Furthermore, model boosting is applied using the starling murmuration optimization (SMO), termite queen algorithm (TQO), and gannet optimization algorithm (GOA) algorithms to reach the highest convergence. As a result of assessing the related models, the ADA‐SMO obtained a coefficient correlation of 0.9981 and 0.9825 for the predictions of CS and TS, respectively. Considering the adaptive framework provided to have the best compatibility with the complex physics of the problem, the ADA‐SMO earned the highest level of accuracy in estimating CS and TS among other hybrid models and was introduced as a trustable model in the prediction of strength properties.

Prediction of Compressive Strength and Elastic Modulus for Recycled Aggregate Concrete Based on AutoGluon

While the civil construction industry brings great convenience to life, the large amount of waste concrete also poses a significant problem of construction waste disposal. As one of the effective ways to utilize waste concrete, recycled aggregate concrete (RAC) can improve the environment while reducing the consumption of construction materials. This study aims to use AutoGluon (AG), an automated machine learning platform, to predict both the compressive strength and elastic modulus of RAC. Then the performance of AG is compared with traditional empirical formulas and multiple linear regression models. The determination coefficient (R2) is chosen as one of the evaluation standards for predicting values. The results demonstrate that the WeightedEnsemble model of AG performed best in predicting both the compressive strength and elastic modulus, which provides a new method for the rapid and accurate prediction of the properties of RAC in engineering construction.

Prediction of the concrete compressive strength using improved random forest algorithm

Prediction of the concrete compressive strength using improved random forest algorithm

Efficient machine learning algorithm with enhanced cat swarm optimization for prediction of compressive strength of GGBS-based geopolymer concrete at elevated temperature

In order to assess building damage and develop fire safety applications, it is crucial to examine the mechanical behavior of concrete after exposure to high temperatures. Compressive strength is the most crucial mechanical characteristic of concrete which is vital for the quality assurance of engineering structures. But it is difficult to estimate the compressive strength with accuracy after geopolymer concrete (GPC) is exposed to extreme temperatures. The residual compressive strength of GGBS-based GPC is predicted in this study using a novel enhanced cat swarm-optimized extreme learning machine (ELM-ECSO) model. The ELM-ECSO compared executing statistical parameters such as the determination coefficient (R2), adjusted determination coefficient (Adj. R2), mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean squared error (RMSE) with simple ELM and ELM with cat swarm optimized to check its generalizability. To create a dataset for training and testing of the model, several experiments using various mix designs were carried out at high temperatures. The quasi-Monte Carlo method was implemented for the sensitivity analysis of the model. Assessment results showed that the ELM-ECSO model transcends the other two models owing to the highest prediction accuracy and showing the least error. Shapiro-Wilk statistical test was carried out to compare all the models. The sensitivity analysis indicated temperature exposure and curing age as the most impactful parameter while predicting the residual compressive strength of GPC. GPC with a Na2SiO3/NaOH ratio of 2.5 and alkaline solution/GGBS ratio of 0.40 shows better resilience against higher temperatures.

Triaxial Compression Strength Prediction of Fissured Rocks in Deep-Buried Coal Mines Based on an Improved Back Propagation Neural Network Model

In deep coal mine strata, characterized by high ground stress and extensive fracturing, predicting the strength of fractured rock masses is crucial for stability analysis of the surrounding rock in coal mine strata. In this study, rock samples were obtained from construction sites in deep coal mine strata and intact, as well as fissured, rock specimens were prepared and subjected to triaxial compression tests. A numerical model based on the discrete element method was then established and the micro-parameters were calibrated. A total of 288 triaxial compression tests on the rock specimens under different conditions of confining pressure, loading rate, fissure dip angle, and fissure length, were conducted to obtain the triaxial compressive strength of the fractured rock specimens under different conditions. To address the limitations of traditional back propagation (BP) neural networks in solving stochastic problems, a modified BP neural network model was developed using a random factor and an interlayer mean square error corrected network model evaluation function. The traditional and modified BP neural network models were then employed to predict the triaxial compressive strength of the fractured rock specimens. Through comparative analysis, it was found that the modified BP neural network prediction model exhibited smaller errors and significantly reduced overfitting, making it an effective tool for predicting the strength of fractured rocks in deep coal mine strata.

Compressive strength prediction of fly ash and blast furnace slag-based geopolymer concrete using convolutional neural network

Compressive strength prediction of fly ash and blast furnace slag-based geopolymer concrete using convolutional neural network

Prediction of compressive strength of cementitious grouts for semi-flexible pavement application using machine learning approach

This study involves the preparation of cement grout samples by varying proportions of superplasticizer (SP) and water-cement (w/c) ratio (0.25–0.45) which were tested for computing flow value and 1-day, 7-day, and 28-day compressive strength. With 75 data points a neural network model was developed to predict the 28-day compressive strength based on w/c ratio, superplasticizer percentage, flow value, and compressive strengths of 1-day and 7-day as input variables. Due to the better performance of Artificial Neural Networks (ANN) over other applied models, this study predicts a confident pattern of relationship between w/c ratio (indirect), superplasticizer (direct up to 3%), and the corresponding strength characteristics of the study samples. The prediction power of the developed model has been improved from R2 = 0.959 to R2 = 0.984 by optimizing the number of neurons, activation function, and optimizer. The best performance was observed in the case of Model45-R_A. The same model was used for assessing the effect of the percentage of superplasticizer and water cement ratio on 28 days compressive strength where the compressive strength of 73.941 MPa was recorded in the case of 3% superplasticizer and w/c of 0.25.

XGBoost Prediction Model Optimized with Bayesian for the Compressive Strength of Eco-Friendly Concrete Containing Ground Granulated Blast Furnace Slag and Recycled Coarse Aggregate

The construction industry has witnessed a substantial increase in the demand for eco-friendly and sustainable materials. Eco-friendly concrete containing Ground Granulated Blast Furnace Slag (GGBFS) and Recycled Coarse Aggregate (RCA) is such a material, which can contribute to a reduction in waste and promote environmental sustainability. Compressive strength is a crucial parameter in evaluating the performance of concrete. However, predicting the compressive strength of concrete containing GGBFS and RCA can be challenging. This study presents a novel XGBoost (eXtreme Gradient Boosting) prediction model for the compressive strength of eco-friendly concrete containing GGBFS and RCA, optimized using Bayesian optimization (BO). The model was trained on a comprehensive dataset consisting of several mix design parameters. The performance of the optimized XGBoost model was assessed using multiple evaluation metrics, including Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and coefficient of determination (R2). These metrics were calculated for both training and testing datasets to evaluate the model’s accuracy and generalization capabilities. The results demonstrated that the optimized XGBoost model outperformed other state-of-the-art machine learning models, such as Support Vector Regression (SVR), and K-nearest neighbors algorithm (KNN), in predicting the compressive strength of eco-friendly concrete containing GGBFS and RCA. An analysis using Partial Dependence Plots (PDP) was carried out to discern the influence of distinct input features on the compressive strength prediction. This PDP analysis highlighted the water-to-binder ratio, the age of the concrete, and the percentage of GGBFS used, as significant factors impacting the compressive strength of the eco-friendly concrete.