Compressive Strength Of Concrete Research Articles

Mechanics guided data-driven model for seismic shear strength of exterior beam-column joints

This study presents an enhanced predictive model for the seismic shear strength of exterior beam-column joints (BCJs). Initially, the principles of strut-and-tie mechanism and variable selection procedures were first utilized to identify the most influential parameters. Subsequently, an evolutionary algorithm, specifically multigene genetic programming (MGGP), was utilized to search for the near-optimal predictive model. The dataset used to develop, train, and test the proposed model was compiled from previously published tests, focusing specifically on cyclically loaded exterior BCJs that encountered shear and flexure -shear failures. The prediction performance of the developed model was assessed through various statistical measures, and then compared with that of other existing models. Additionally, sensitivity analyses were also performed to identify the influence and importance of each design parameter. The results demonstrated that the methodology employed in this study yielded an elegant model that adheres to the underlying mechanics and provides higher prediction accuracy compared to existing models. Furthermore, the sensitivity analyses showed that BCJ shear strength positively correlates with concrete compressive strength, beam reinforcement, joint transverse reinforcement, column intermediate vertical reinforcement, and axial load ratio, while it negatively correlates with the joint aspect ratio. Among these design parameters, beam reinforcement has the greatest influence on the model response, followed by concrete compressive strength. Conversely, column intermediate vertical reinforcement and axial load ratio have the least impact on the model response. The notable prediction capabilities and robustness demonstrated by the developed model render it an efficient design tool with promising potentials for adoption by practicing engineers and for consideration in design guidelines.

Effects of coarse aggregate size on thickness and micro-properties of ITZ and the mechanical properties of concrete

This research delves into the impact of coarse aggregate particle size on the mechanical properties of concrete. Nano-indentation and scanning electron microscope (SEM) techniques were applied to characterize the micro-properties and thickness the Interfacial Transition Zone (ITZ). The effect of coarse aggregate size on concrete's compressive strength (σc) and elastic modulus (E) and the relationship between the micro properties of the ITZ and the macro properties of concrete were discussed. In addition, Griffith's microcrack theory was adopted to explain related mechanisms. The relationship between the microscopic properties of the ITZ and the macroscopic properties of concrete was discussed. The results show that, in concrete with a low water cement-ratio w/c (0.3), thickness of ITZ increased with the coarse aggregate size and concrete properties decreased. While, in concrete with a higher w/c (0.4), there exists an optimum coarse aggregate size for the lowest thickness of ITZ and highest strength. Taking the ITZ as the initial crack in concrete failure, concrete properties can be linked to ITZ thickness from Griffith's microcrack theory.

Multiscale model for concrete cured under geothermal environment: Theoretical analysis and experimental validation

Concrete poured as linings of geothermal tunnel would deviate normal curing condition. A multiscale model based on continuum micromechanics, accounting for temperature-dependent factors, is established from the cement paste level to the concrete level. This model predicts the physical properties and compressive strength of concrete and is validated against measured strength, which incorporates the impact of high-temperature curing on the hydration degree, density of C-S-H, and chemical shrinkage of cement. Evolutions of the average hydration degree and compressive strength of concrete were experimentally investigated to this end, and then simulated with multiscale approach. The specimens were subjected to curing temperature 20°C, 40°C, 60°C, and 80°C for first 7 days while maintaining constant relative humidity of 100 %, and then water curing at 20°C for the rest days till tests. The high-temperature curing accelerates the hydration process, but the variance in hydration degree between standard temperature (20°C) and high-temperature conditions diminishes with prolonged water curing. An enhancement in compressive strength is also observed in the early stages of high-temperature curing, succeeded by a decline compared with standard curing after the 50th curing day. Quantitative analysis reveals that volume fractions of hydrates and porosity subjected to high-temperature curing show a substantial increase in the first 7 curing days, and the denser layer of hydration products formed on cement slows down the hydration in later curing ages. The complex evolution of strength in concrete undergoing high-temperature curing is influenced by temporal consideration (the hydration degree) and spatial considerations (the density of C-S-H and the chemical shrinkage of cement). The surge in hydration significantly contributes to strength promotion in early stages. However, the pivotal factor leading to strength deterioration is the increase of porosity when the difference in the hydration degree is less than 0.065.

Investigating the Viability of Rubber Crumbs from Waste Tyres as Partial Replacement for Coarse Aggregates in Concrete

The number of waste tyres is on the increase, because of the growing use of transport vehicles. Almost one trillion waste tyres are generated in the world annually. Established methods of disposal, recycling and re-use of waste tyres have failed to keep pace with generation, proven to be ineffective, cost-intensive and in some cases environmentally unsustainable. This study aims to investigate the effects of utilizing crumbs from discarded rubber as a partial replacement for coarse aggregates in concrete. Rubber crumbs of 10 – 20mm nominal size were produced manually from waste tyres. The rubber crumbs were used to replace 10%, 20% and 30% of coarse aggregates in design concrete of 20N/mm2 target compressive strength. The effects of this material on the slump, water absorption and compressive strength of concrete were examined. The inclusion of rubber crumbs resulted in a decline in the slump of concrete up to 10% relative to the control specimen. Water absorption increased marginally at 10% replacement compared to the control specimen and recorded a maximum value of 0.77% with 30% replacement after 28 days of curing. The compressive strength of the concrete was negatively affected by the rubber crumbs. The maximum value of 13.9N/mm2 was attained at 10% replacement after 28 days of curing. Rubberized concrete with 10% replacement of coarse aggregates can be used for non-structural concrete members such as roof slabs, non–load–bearing partition walls, and roadside barriers. Chemical treatment of rubber crumbs to improve surface adhesion properties should be encouraged.

Rapid synthesis of solid polycarboxylate superplasticizers via photoinitiated radical polymerization

The synthesis and performance optimization of solid polycarboxylate superplasticizers (PCEs) present significant challenges. In our study, a rapid synthesis of a solid polycarboxylate superplasticizer (IPCE10) was achieved using photoinitiated free radical polymerization. IPCE10 exhibited good dispersibility and improved compressive strength in concrete. Dynamic light scattering tests and molecular dynamics simulations demonstrated that the adsorption conformation of IPCE10 on the calcium silicate hydrate surface was relatively dispersed, with a thicker adsorption layer. This indicates that IPCE10 has stronger steric hindrance, resulting in superior dispersibility. Additionally, density functional theory calculations of the reaction energy barriers for radical generation by photoinitiated and azo-initiated monomers revealed that the energy barrier in the photoinitiated system was significantly lower than that in the azo-initiated system, indicating that photoinitiated polymerization is more feasible. This study proposes a simple and rapid method for the preparation of solid polycarboxylate superplasticizers, providing valuable insights for the development of high-value-added construction materials.

Effects of Crude Oil on Workability and Compressive Strength of Concrete

The research aims to study the effect of adding crude oil on the workability and compressive strength of concrete, where it was noted that there are significant changes in the properties of concrete that were provided when varying percentages of crude oil were added. In this study, different percentages of crude oil were used, constituting (0%, 1%, 2%, 2.5%, 3%, 4%, 5%, 6%, 10%, 15%, 20%, 25%) of The weight of the fine aggregate used in the concrete mixtures, where the results of the laboratory examination of the amount of slump as a measure of the workability of the concrete showed that there was a collapse of the concrete after fixing it in the test cone when adding percentages of crude oil more than 6%, which indicates that the addition of crude oil causes a delay in the cement reactions And water, and this indicates that its presence hinders the bonding between the components of concrete, and thus leads to the separation of these components from each other. As for the results of the compressive strength test, the concrete cubes that were tested at the age of (7) days proved that the compressive strength decreases when adding percentages ranging from (1%) to (5%), then it starts to increase from (5%) to (10%) and then back. to decreasing again, which indicates an improvement in the compressive strength of concrete when adding a ratio of (10%) and a higher percentage of the compressive strength in the event that crude oil is not added to its components. The study also showed that there is an improvement in the compressive strength when adding percentages of crude oil ranging Between (6%) and (15%).

Eco-Friendly 3D-Printed Concrete Using Steel Slag Aggregate: Buildability, Printability and Mechanical Properties

Utilizing steel slag aggregate (SA) as a substitute for river sand in 3D concrete printing (3DCP) has emerged as a new technique as natural resources become increasingly scarce. This study investigates the feasibility of using steel slag (SS) as fine aggregate for 3DCP. Ninety mixtures with varying steel slag aggregate-to-cement ratios (SA/C), water-to-cement ratios (W/C), and silica fume (SF) contents were designed to study the workability and compressive strength of the 3D-printed concrete. Additionally, the actual components were printed to evaluate the printability of these mixtures. The experimental results indicate that it is feasible to fully employ SA in concrete for 3D printing. Mixtures with slump values ranging from 40 to 80 mm and slump flow values varying from 190 to 210 mm are recommended for 3D printing. The optimal mix is determined to have SA/C and W/C ratios of 1.0 and 0.51, respectively, and an SF content of 10% by cement weight. A statistical approach was utilized to construct the prediction models for slump and slump flow. Moreover, to predict the plastic failure of the 3D-printed concrete structure, the modified prediction model with an SA roughness coefficient of 4 was found to fit well with the experimental data. This research provides new insights into using eco-friendly materials for 3D concrete printing.

Effect of limestone powder on mechanical properties of concrete based on Griffith’s microcracking theory

In order to reveal the influence mechanism of limestone powder on the mechanical properties of concrete, the manufactured sand concrete with a water-cement ratio of 0.45 was taken as the research object. The effects of different limestone powder contents (0 %, 5 %, 10 %, 15 %, and 20 %) on the compressive strength of concrete were explored based on Griffith’s microcracking theory. The nano-indentation, ultra-depth-of-field microscopy, LF NMR, and other methods were used for testing. The test results show that with the increase of limestone powder content, the elastic modulus of the Interfacial Transition Zone (ITZ) and the paste increases first and then decreases, the thickness of the ITZ decreases first and then increases, and the total porosity of the paste decreases first and then increases. The microstructure of the ITZ and the paste is the densest, corresponding to the maximum compressive strength of the concrete as the limestone content is 10 %. It is found that the thickness of ITZ can be regarded as the initial crack of concrete. The compressive strength of concrete calculated by Griffith’s microcracking theory formula is the same as the measured value. The research results provide a theoretical reference for the influence mechanism of limestone powder on the mechanical properties of concrete.

The Application of Machine Learning Algorithms to Bond Strength between Steel Rebars and Concrete Using Bayesian Optimization.

The purpose of this study is to estimate the bond strength between steel rebars and concrete using machine learning (ML) algorithms with Bayesian optimization (BO). It is important to conduct beam tests to determine the bond strength since it is affected by stress fields. A machine learning approach for bond strength based on 401 beam tests with six impact factors is presented in this paper. The model is composed of three standard algorithms, including random forest (RF), support vector regression (SVR), and extreme gradient boosting (XGBoost), combined with the BO technique. Compared to empirical models, BO-XGB`oost was found to be the most accurate method, with values of R2, MAE, and RMSE of 0.87, 0.897 MPa, and 1.516 MPa for the test set. The development of a simplified model that contains three input variables (diameter of the rebar, yield strength of reinforcement, concrete compressive strength) has been proposed to make it more convenient to apply. According to this prediction, the Shapley additive explanation (SHAP) can help explain why the ML-based model predicts the particular outcome it does. By utilizing machine learning algorithms to predict complex interfacial mechanical behavior, it is possible to improve the accuracy of the model.

The Effects of Crystalline Admixtures on Concrete Permeability and Compressive Strength: A Review

The durability and strength of concrete in construction can be significantly compromised by permeability issues, which pose considerable challenges to its long-term effectiveness and reliability. By analyzing six selected articles from the Scopus database, this study meticulously synthesizes findings on the effectiveness of CAs in improving these essential properties of concrete. The research meticulously documents and analyzes key variables such as the CA dosage, water–cement ratio, evaluation duration, and treatment conditions, providing a thorough understanding of the factors that influence the performance of CAs in concrete. The results robustly indicate that CAs significantly reduce concrete permeability, thereby enhancing its resistance to water and other detrimental substances, and simultaneously boosts the compressive strength, leading to stronger and more durable concrete structures. However, the study also reveals that the impact of CAs can vary considerably depending on the specific conditions and methodologies employed in the individual studies. This underscores the importance of standardized testing procedures to ensure consistent and comparable results across different studies. This research provides valuable insights for optimizing the use of CAs in concrete formulations, ultimately aiming to improve the durability, performance, and sustainability of concrete in construction applications.

Effect of concrete strength on the seismic performance of circular reinforced concrete columns confined by basalt and carbon fiber-reinforced polymer

This paper investigated the effect of concrete strength on the seismic performance of circular reinforced concrete (RC) columns confined by basalt and carbon fiber-reinforced polymer (BFRP and CFRP). Eight confined columns and four control columns were tested under a low cyclic lateral load. The variables in the test included concrete compressive strength (i.e., 22.4 MPa, 31.4 MPa, 42.5 MPa and 57.8 MPa) and FRP type (i.e., basalt and carbon fiber). The test results demonstrated that all the columns exhibited flexural failure after confinement. The strength, ductility and energy dissipation capacity of the confined columns were effectively enhanced. With the same confining stress, the peak loads of the BFRP- and CFRP-confined columns were nearly the same. However, the BFRP-confined columns with low and moderate concrete strength showed larger ductility and energy dissipation capacity compared with the CFRP-confined counterparts, and these capacities of the CFRP-confined column with a concrete strength of 57.8 MPa were slightly better than those of the BFRP-confined equivalent. This showed that the FRP jackets with larger modulus had better confinement effect on the columns with higher concrete strength. Finally, formulas for calculating the load carrying and ductility capacities of different FRP-confined circular RC columns were proposed based on the experimental results.

The mechanical properties of concrete exposed to harsh and complex environments of plateaus at early ages

The independently designed walk-in concrete low-pressure forming chamber and complex environment simulation chamber were employed to more accurately investigate the evolution of mechanical properties of concrete under the complex environment of the plateau. The quantitative comparison of the differences in the impact of each environmental factor on performance under complex coupled environments was conducted using two methods: grey correlation analysis and relative strength method. Meanwhile, the hydration and pore structure of concrete under the complex environment of plateau were studied by TG analysis and MIP analysis. The results showed that the high-altitude complex environment has a significant deterioration effect on the mechanical properties of concrete, mainly due to the decrease in the degree of hydration and pore structure deterioration. The environmental humidity and temperature difference are the main factors affecting the mechanical properties, and the complex environment has a more significant effect on the flexural strength of concrete than the compressive strength of concrete.

A Comparative Study of Machine Learning and Conventional Techniques in Predicting Compressive Strength of Concrete with Eggshell and Glass Powder Additives

Recent research has focused on assessing the effectiveness of response surface methodology (RSM), a non-machine learning technique, and artificial neural networks (ANN), a machine learning approach, for predicting concrete performance. This research aims to predict and simulate the compressive strength of concrete that replaces cement and fine aggregate with waste materials such as eggshell powder (ESP) and waste glass powder (WGP) for sustainable construction materials. In order to ensure concrete’s durability and structural integrity, a compressive strength evaluation is essential. Precise predictions maximize efficiency and advance sustainability, particularly when dealing with waste materials like ESP and WGP. The response surface methodology (RSM) and artificial neural network (ANN) techniques are used to accomplish this for practical applications in the built environment. A dataset comprising previously published research was used to assess ANN and RSM’s predictive and generalization abilities. To model and improve the model, ANN used seven independent variables, while three variables, cement, waste glass powder, and eggshell powder, improved the RSM. Both the ANN and RSM techniques are effective instruments for predicting compressive strength, according to the statistical results, which include mean squared error (MSE), determination coefficient (R2), and adjusted coefficient (R2 adj). RSM was able to achieve the R2 by 0.8729 and 0.7532 for compressive strength, while the accuracy of the results for ANN was 0.907 and 0.956 for compressive strength. Moreover, the correlation between ANN and RSM models and experimental data is high. The artificial neural network model, however, exhibits superior accuracy.

Investigation and prediction of impact of aggregate size and shape on porosity and compressive strength of pervious concrete

ABSTRACT Pervious concrete is proven to environmentally benefit urban pavement construction. Optimising compaction energy evidently reduces uncertainty in the mass production of pervious concrete with uniform characteristics. The distribution of compaction energy in wet mix and rearrangement of binder-coated aggregate particles are affected by the size and shape of aggregates. This study analyses the impact of aggregate size and shape on porosity and compressive strength prediction from mix-design parameters. Aggregate-to-cement ratio (3, 4 and 5), compaction (0, 30 and 60 blows from standard Proctor rammer), aggregate sizes (5–12 mm, 12–18 mm and 18–25 mm) and aggregate shape (0, 200 and 1000 revolutions of milling in Los Angeles Abrasion Value) were used to cast a total number of 486 samples. Constituents were mixed in an electrically powered drum of capacity 96 L, for 20 min. Porosity was computed from constituent ratios (theoretical porosity) and apparent weight (measured porosity). The compressive strength of samples was recorded using a Universal Testing Machine. The measured porosity and theoretical porosity relationship was significantly affected by the shape of the aggregate and not by the size. Modified Ryshkewitch’s model predicted compressive strength from porosity, aggregate-to-cement ratio, compaction and aggregate size and shape with an accuracy of 0.92 (R2). Two of six arbitrary constants depended on aggregate shape and size.

Improving flexural response of rubberized RC beams with multi-dimensional sustainable approaches

This research presents a sustainable solution to waste tire disposal and raw material depletion by incorporating recycled rubber into concrete mixtures. To mitigate the reduction in mechanical properties, a novel slag pretreatment of rubber particles with controlled temperature is proposed. The study also investigates the effects of pouring concrete in layers with rubberized concrete (RuC) in tension side and normal concrete in compression side, as well as evaluating the use of GFRP compared to conventional steel, thereby introducing multiple innovative dimensions to enhance structural performance. The experimental study included a total of 27 specimens, consisting of normal concrete, untreated rubberized concrete, and treated rubberized concrete mixtures with 15 % rubber content. The study investigated both compression and tension mechanical properties of the concrete mixtures and assessed the flexural response of reinforced concrete (RC) beams. Parameters explored included rubber treatment, utilization of steel and GFRP as tensile reinforcement, and layered concrete pouring. Subsequently, a numerical study was conducted to address the impact of reinforcement ratio and layer depth on the behavior of slag-treated rubberized RC beams. The findings reveal a significant recovery of concrete compressive strength by 23 %, along with a 28 % enhancement in toughness and a 17 % increase in splitting tensile strength attributed to the application of slag treatment to rubberized concrete. The effect of rubber treatment was more pronounced in GFRP RC beams, as they showed similar load capacity as normal concrete. Furthermore, utilizing layered concrete beams with a 67 % depth of slag-treated RuC showed a comparable load capacity to normal RC beams, demonstrating only a 1 % reduction for steel-reinforced beams and a 2.4 % improvement for GFRP-reinforced beams. Notably, the numerical model emphasized this outcome and suggested that increasing the layer depth to 72 % of slag-treated depth displayed better performance.

An explainable machine learning approach to predict the compressive strength of graphene oxide-based concrete

Graphene oxide (GO) has shown promise in improving concrete strength. Despite its frequent use in cement composites, its effect on concrete properties is less explored. The influence of GO on concrete remains unclear due to various interactions among constituents such as GO type and percentage, Superplasticiser (SP) type and percentage, dispersion technique, and curing age. Therefore, making prediction of compressive strength using simple mathematical formation is challenging. This study represents the first-ever attempt at developing a comprehensively validated machine learning model to predict GO-concrete's compressive strength characteristics by considering all key variable parameters. A comprehensive laboratory experiment program was conducted to collect the data required for training the machine learning (ML) models. Once the ML models were trained, they were used to predict the relationship of each of those input variables towards the compressive strength properties. Four machine learning models—(a) multiple linear regression (MLR), (b) k-nearest neighbour (KNN), (c) random forest (RF) and (d) extreme gradient boost (XGB)—were utilised to model the relationship between input parameters and compressive strength. Also, explainable machine learning (XML) methods were employed to elucidate the impact of mixed constituents on the compressive strength of GO concrete. The results from test predictions showcase that the XGB has attained a coefficient of determination (R2) of 0.981, coefficient of correlation (R) of 0.99, mean square error (MSE) of 0.9, mean normalised bias (MNB) of 0.004, scatter index (SI) of 0.2 with mean absolute error (MAE) of 0.8 MPa for the predictions, outperforming the remaining models. XML highlighted the true impact of GO and the remaining variables, emphasising that the presence of GO significantly improves compressive strength. The optimum GO content and optimum superplasticiser content observed from the experimental work agreed with results obtained from the XML analysis, showing the consistency of the explanation with the experimental results. This implies the superiority of using XML methods in concrete mix design applications in industry.

Improving the Concrete Compressive and Flexural Strength with a Low Fraction Addition of Carboxylated Nitro-oxidized Cellulose Nanofibrils from Banana Rachis

Conventionally, concrete strength depends on the bonding interface, especially in hydrated products such as calcium silicate hydrate (CSH). As a result, concrete is sensitive under tensile load. With its unique properties, a low fraction of carboxylated nitro-oxidized cellulose nanofibrils (NOCNF) from the banana rachis is employed to improve the mechanical performance of the concrete nano structurally. Compressive and flexural strength using the NOCNF content at 0, 0.05, and 0.1 wt. % cured in 7 and 28 days were evaluated. Notably, the compressive strength increased by 16% and flexural strength by 13% at 0.1% NOCNF compared to plain concrete after the 28 curing days. A low NOCNF fraction achieved a good, albeit impossible, performance with the microscale fibers. The nanostructured effect was discussed twofold: an excellent interaction between the NOCNF and the hydrated products and the carboxylic groups on the NOCNF surface enhanced the cement hydration. These data are better than the literature based on the small-diameter cellulose nanofibrils without the carboxyl groups. As a sustainable nanocomponent, NOCNF could be a perfect candidate to improve concrete performance under mechanical load.

A comparative assessment of uncrushed-river concrete mix of Hari-River, and Kamar-Kalaq: the two widely used concrete mix in Herat, Afghanistan

Concrete, as a cornerstone of modern construction, heavily relies on the quality of its constituent materials, particularly aggregates. Among the critical factors contributing to high-quality concrete are proper gradation, absence of clay particles, and angular shape of aggregates. Adhering to these standards typically results in concrete with superior strength. However, aggregates sourced from riverbeds often possess a natural gradation, contain clay particles, and have rounded shapes. This study delves into a comparative analysis of aggregates sourced from two widely utilized riverbed regions, namely Hari-River and Kamar-Kalaq, situated within Herat province, Afghanistan. Given that over 90% of concrete in Herat province is sourced from these two riverbeds, the findings of this study carry immense significance. The research meticulously examines key parameters, including clay content, gradation, aggregate shape, and compressive strength, to determine the optimal choice for concrete production. Methodologically, samples were acquired following ASTM standards, and rigorous testing procedures were conducted, encompassing clay particle analysis, sieve analysis, and strength testing. The results reveal significant disparities between the two regions, with Hari-River demonstrating superior characteristics across various metrics. Particularly noteworthy is Hari-River’s lower clay content of 2.7% compared to Kamar-Kalaq’s 3.7%. The gradation of Hari-River for both coarse and fine aggregates is superior to that of Kamar-Kalaq when compared to size 67 aggregate range. Additionally, the average 28 days concrete compressive strength of Hari-River aggregates is 27.8 MPa, while that of Kamar-Kalaq is 23.4 MPa.

Predicting High-Strength Concrete's Compressive Strength: A Comparative Study of Artificial Neural Networks, Adaptive Neuro-Fuzzy Inference System, and Response Surface Methodology.

Machine learning and response surface methods for predicting the compressive strength of high-strength concrete have not been adequately compared. Therefore, this research aimed to predict the compressive strength of high-strength concrete (HSC) using different methods. To achieve this purpose, neuro-fuzzy inference systems (ANFISs), artificial neural networks (ANNs), and response surface methodology (RSM) were used as ensemble methods. Using an ANN and ANFIS, high-strength concrete (HSC) output was modeled and optimized as a function of five independent variables. The RSM was designed with three input variables: cement, and fine and coarse aggregate. To facilitate data entry into Design Expert, the RSM model was divided into six groups, with p-values of responses 1 to 6 of 0.027, 0.010, 0.003, 0.023, 0.002, and 0.026. The following metrics were used to evaluate model compressive strength projection: R, R2, and MSE for ANN and ANFIS modeling; R2, Adj. R2, and Pred. R2 for RSM modeling. Based on the data, it can be concluded that the ANN model (R = 0.999, R2 = 0.998, and MSE = 0.417), RSM model (R = 0.981 and R2 = 0.963), and ANFIS model (R = 0.962, R2 = 0.926, and MSE = 0.655) have a good chance of accurately predicting the compressive strength of high-strength concrete (HSC). Furthermore, there is a strong correlation between the ANN, RSM, and ANFIS models and the experimental data. Nevertheless, the artificial neural network model demonstrates exceptional accuracy. The sensitivity analysis of the ANN model shows that cement and fine aggregate have the most significant effect on predicting compressive strength (45.29% and 35.87%, respectively), while superplasticizer has the least effect (0.227%). RSME values for cement and fine aggregate in the ANFIS model were 0.313 and 0.453 during the test process and 0.733 and 0.563 during the training process. Thus, it was found that both ANN and RSM models presented better results with higher accuracy and can be used for predicting the compressive strength of construction materials.

Predicting the compressive strength of rubberized concrete containing silica fume using stacking ensemble learning model

As the construction industry advances toward sustainability, rubberized concrete emerges as a promising material due to its potential for recycling waste rubber. While silica fume (SF) is often used to address the reduced compressive strength resulting from rubber integration, the complex interactions between these materials present significant modeling challenges. This study employs a novel machine learning approach to effectively capture these interactions and accurately predict the compressive strength of SF-enhanced rubberized concrete. Utilizing a dataset comprising 237 experimental data points curated from 25 research studies, an advanced stacking ensemble model was developed. This model features a trainable meta-structure that integrates diverse, hyper-tuned base learners, including Decision Trees (DT), Artificial Neural Networks (ANN), eXtreme Gradient Boosting (XGBoost), Support Vector Machines (SVM), and K-Nearest Neighbors (KNN) regressors. Hyperparameter tuning, performed using 10-fold cross-validation, was applied to enhance overall model performance. The findings show that XGBoost outperformed other base models, achieving an overall Coefficient of Determination (R²) of 0.9194 and a Mean Squared Error (MSE) of 10.5625. The stacking approach, with KNN as the meta-learner, further refined individual model performances, resulting in an improved R² of 0.9397 and an MSE of 7.1671 on the testing data. Compared to traditional voting ensemble techniques, the stacking models offered a more nuanced enhancement of predictive outcomes, while the averaging ensembles were noted for their simplicity and competitive accuracy. Additionally, feature importance analysis using SHapley Additive exPlanations (SHAP) revealed that superplasticizer, rubber content, and SF were the most influential inputs in the developed model.