Compressive Strength Of Concrete Research Articles

Enhancing Compressive Strength in M45 Grade Concrete: A Comparative Evaluation of Micro-silica and Alccofine as Partial Cement Replacements

This study investigates the compressive strength and durability of M45 grade concrete using Micro-silica and Alccofine as partial replacements for cement. Experimental results indicate that Alccofine-based concrete achieves 28-day compressive strengths of up to 60.6 MPa at 10% replacement, outperforming Micro-silica-based mixes by 55.2 MPa. Alccofine also enhances workability, with slump values peaking at 144 mm and 135 mm for Micro-silica. The optimal replacement level for both materials is 10% by cement volume, where Alccofine’s dual pozzolanic-cementitious reactivity improves microstructure densification, reducing permeability and enhancing durability. These findings position Alccofine as a superior additive for high-strength concrete applications, offering significant mechanical and durability advantages.

Predicting the compressive strength of concrete incorporating waste powders exposed to elevated temperatures utilizing machine learning

The addition of powders from waste construction materials as partial cement substitute in concrete represents a significant step toward green concrete construction. High temperatures have a substantial influence on concrete strength, resulting in a reduction in mechanical properties. The prediction of the impacts of waste powders on concrete strength is an important topic in sustainable construction. Such models are needed to understand the complex interactions between waste materials’ powders and concrete strength. In this study, three machine learning approaches, extreme gradient boosting (XGBoost), random forest (RF), and M5P, were used for constructing the prediction model for the impact of elevated temperatures on the compressive strength of concrete modified by marble and granite construction waste powders as partial cement replacements in concrete. Dataset of 324 tested cubic specimens with four input variables, waste granite powder dose (GWP), waste marble powder (MWP), temperature (T), and duration (D) were chosen for developing the prediction models. The output was the concrete compressive strength (CS). MWP and GWP ranged between 0 and 9%, temperatures were ranged between 25 °C and 800 °C, and duration up to 2 h. Hyperparameters in the RF and XGB models were optimized using grid search. K-fold cross-validation and several statistical measures, including R2MAPE, RMSE, and MAE, were utilized to validate and check the accuracy of the proposed models. The developed models were evaluated against experimental data and previously established models. The XGB model demonstrated the highest R2 of 0.9989, alongside the lowest prediction errors: MAE of 0.1351 MPa, RMSE of 0.1842 MPa, and MAPE of 0.48%. The results showed that the XGB prediction model for the concrete compressive strength outperformed the other proposed models. The SHAP analysis, Individual Conditional Expectation (ICE), and Partial Dependence Plots (PDP) revealed that GWP and MWP positively influence the compressive strength, while the temperature exerts the most negative influence on predicting the compressive strength. Finally, a graphical user interface (GUI) for the compressive strength of concrete containing GWP and MWP subjected to elevated temperatures has been created, which may be of considerable assistance, guidance, and efficiency in research and construction industry contexts.

Transforming plastic waste into durable concrete: a pathway to sustainable infrastructure

Plastics are petroleum-based products with significant environmental challenges due to disposal and degradation issues. This study focuses on the use of shredded (SrPCA) and crushed plastic coarse aggregate (CPCA) as partial replacements for natural coarse aggregate (NCA) in concrete to enhance environmental sustainability. Preliminary tests showed that SrPCA (292.50 kg/m3) and CPCA (779.50 kg/m3) are lightweight aggregates with water absorption values (SrPCA: 0.08%, CPCA: 0.15%) lower than NCA (0.63%). The Densities of plastic concrete ranged between 2359 and 2470 kg/m3, classifying them as normal-weight concrete. Moreover, the compressive strengths result (33.8–45.2 N/mm2) exceeded the designed grade of 30 N/mm2, while the flexural strengths (4.44–5.97 N/mm2) aligned with recommended values of 10–15% concrete compressive strength. The concrete water absorption results (1.91–3.25%) also met quality standards (< 5%). Therefore, the study suggests that replacing 10% of NCA with plastic aggregate can produce durable and high-quality concrete, promoting environmental sustainability.

Time-dependent behavior of variable cross-section continuous box girder strengthened with external prestressing and web thickening

The time-dependent behavior of variable cross-section continuous box girder after strengthening is crucial for engineering post-evaluation. Firstly, the validity of the combined strengthening method utilizing external prestressing and web thickening was verified. The time-dependent behavior of the structure after combined strengthening was investigated by using ABAQUS software. The study examined the impacts of primary parameters on the time-dependent behavior, including the new concrete compressive strength, relative humidity, initial stress, thickness of web reinforcement and length of web reinforcement. Deflection versus time curves were got based on the confirmed finite element (FE) model. The longitudinal stress distributions were analyzed at the critical time points. The analysis revealed that because of the creep and shrinkage in reinforced regions, the deflection of the mid-span section was basically stable after one year of reinforcement, and the deflection was reduced by 6.5%. Simultaneously, the maximum compressive stress reserve at mid-span section decreased from −2.58 to −2.28 MPa, with a decrease of 11.63%. Finally, a simplified calculation method for predicting the long-term longitudinal strain of structure after strengthening was proposed, and the long-term performance could be better predicted. There was only a maximum error of −0.92% between the FE and calculation results.

Estimation of compressive strength of ultra-high performance lightweight concrete (UHPLC) using neural network.

High strength and lightweight are key trends in concrete development. Achieving a balance between these properties to produce high structural efficiency (strength-to-weight ratio) concrete is challenging due to the complex relationship between compressive strength and material components. In this study, two artificial neural network (ANN) models-the BP and Elman networks were used to predict the compressive strength of ultra-high-performance lightweight concrete (UHPLC), based on a robust database of 115 test datasets from previous studies. The investigated parameters included the cement grade (Grade 42.5 and Grade 52.5), cement content (352 kg/m3-938 kg/m3), silica fume content (0 kg/m3-350 kg/m3), fly ash content (0 kg/m3-220 kg/m3), microsphere content (0 kg/m3-624 kg/m3), lightweight sand types (pottery sand, expanded perlite sand, and expanded shale lightweight sand), lightweight sand content (0 kg/m3-769 kg/m3), sand type (quartz sand, river sand), sand content (0 kg/m3-1314 kg/m3), water (90 kg/m3-395 kg/m3), water reduce (0 kg/m3-42.8 kg/m3), steel fiber content (0 kg/m3-234 kg/m3). Correlation analysis and sensitive analysis indicated that lightweight sand content and sand content had the most significant effects on UHPLC compressive strength, followed by water content. Conversely, fly ash content and lightweight sand type had minimal impact. The developed ANN models for UHPLC compressive strength demonstrated high predictive accuracy for both training and testing datasets, which the RMSE of BP network and Elman network were 0.226 and 0.160, respectively, while R2 of both two developed models were more than 0.98. Additionally, UHPLC exhibited a higher compressive strength-to-density ratio than high-strength concrete, ultra-high-performance concrete, and even Q235 steel. Three strategies were proposed for creating ultra-high-performance lightweight composites: optimizing packing density and lowering the water-binder ratio, along with careful selection of lightweight aggregates.

Deformation Analysis of 50 m-Deep Cylindrical Retaining Shaft in Composite Strata

Cylindrical retaining structures are widely adopted in intercity railway tunnel engineering due to their exceptional load-bearing performance, no need for internal support, and efficient utilization of concrete compressive strength. Measured deformation data not only comprehensively reflect the influence of construction and hydrogeological conditions but also directly and clearly indicate the safety and stability status of structure. Therefore, based on two geometrically similar cylindrical shield tunnel shafts in Shenzhen, the surface deformation, structure deformation, and changes in groundwater outside the shafts during excavation were analyzed, and the deformation characteristics under the soil–rock composite stratum were summarized. Results indicate that the uneven distribution of surface surcharge and groundwater level are key factors causing differential deformations. The maximum horizontal deformation of the shafts wall is less than 0.05% of the current excavation depth (H), occurring primarily in two zones: from H − 20 m to H + 20 m and in the shallow 0–10 m range. Vertical deformations at the wall top are mostly within ±0.2% H. Localized groundwater leakage in joints may lead to groundwater redistribution and seepage-induced fine particle migration, exacerbating uneven deformations. Timely grouting when leakage occurs and selecting joints with superior waterproof sealing performance are essential measures to ensure effective sealing. Compared with general polygonal foundation pits, cylindrical retaining structures can achieve low environmental disturbances while possessing high structural stability.

Optimized machine learning models for predicting ultra-high-performance concrete compressive strength: a hyperopt-based approach

Optimized machine learning models for predicting ultra-high-performance concrete compressive strength: a hyperopt-based approach

Investigating the correlation between ultrasonic pulse velocity and compressive strength in polyurethane foam concrete

Using waste polyurethane foam as a partial replacement for natural coarse aggregates in concrete provides an eco-friendly solution by reducing waste and conserving natural resources. However, the strength behavior of polyurethane foam concrete differs from conventional concrete. To ensure effective design and quality control in the field, the viability of non-destructive testing methods for finding out the in situ mechanical properties of polyurethane foam concrete must be evaluated. This study establishes a correlation between compressive strength and ultrasonic pulse velocity (UPV) test to predict the compressive strength of polyurethane foam concrete using UPV test results. An experimental study was conducted on concrete specimens with varying percentages of polyurethane foam replacing natural coarse aggregate, ranging from 10 to 60% in 10% increments. The control concrete mix was 100% natural coarse aggregate without polyurethane foam. The properties of the specimens were evaluated after curing for 7, 14, and 28 days. It also examines polyurethane foam concrete workability, density, and microstructural properties. The findings show that the UPV and compressive strength of polyurethane foam concrete were lower than those of the control mix concrete for all replacement levels and curing ages. The empirical relationships between compressive strength and UPV were found to be exponential, with high correlation values ranging from 0.9012 to 0.9998. The predicted values and the experimentally measured results were compared in order to confirm the accuracy of the empirical equations for compressive strength prediction.

Predicting the Compressive Strength of Concrete Incorporating Olivine Aggregate at Varied Cement Dosages Using Artificial Intelligence

This study aimed to identify the most reliable prediction model for estimating the compressive strength of concrete by conducting a comparative analysis of Particle Swarm Optimization (PSO) and Artificial Neural Network (ANN) methodologies. The modeling process utilized 92 experimental data points for training purposes and allocated 28 data points for testing validation. PSO was employed to optimize coefficients within mathematical equations used for concrete compressive strength prediction, facilitating the development of appropriate models based on various error metrics. Specifically, PSO models optimized to minimize Weighted Root Mean Square Error (WRMSE), Root Mean Square Error (RMSE), and Mean Absolute Error (MAE) criteria were evaluated against the highest-performing model developed using ANN. Model A, optimized using a constant term and the WRMSE loss function within a PSO-ANN framework, achieved the highest performance, with a correlation coefficient exceeding 0.99 and low error values on the training dataset. The same model also demonstrated strong predictive accuracy and low error on the test dataset, indicating excellent generalization capability. In contrast, the standalone ANN model exhibited near-perfect accuracy on the training data (R2 = 0.9994) but suffered a significant drop in performance on the test data (correlation ≈ 0.60). This highlights the impact of overfitting and underscores the importance of regularization techniques for improving generalizability. Through comprehensive statistical and visual assessments using Taylor diagram analysis, PSO-based models demonstrated significantly superior accuracy compared to the ANN model. Furthermore, the constant-term WRMSE model exhibited optimal generalization performance and provided the most reliable predictions among all tested models. It has been observed that highly accurate predictions can be made even for values outside the range of the data used. The results obtained in this study indicate that reliable predictive models for concrete production can be developed using both the available data and information from the literature. In cases where data are lacking, it is also possible to establish these models by conducting a sufficient number of experiments.

ANN and RF Optimized by Hunter–Prey Algorithm for Predicting Post-Blast RC Column Morphology

The drilling and blasting method is commonly employed for the rapid demolition of outdated buildings by destroying key structural components and inducing progressive collapse. The residual bearing capacity of these components is governed by the deformation morphology of the longitudinal reinforcement, characterized by bending deflection and exposed height. This study develops and validates a finite element (FE) model of a reinforced concrete (RC) column subjected to demolition blasting. By varying concrete compressive strength, the yield strength of longitudinal reinforcement, the longitudinal reinforcement ratio, and the shear reinforcement ratio, 45 FE models are established to simulate the post-blast morphology of longitudinal reinforcement. Two databases are created: one containing 45 original simulation cases, and an augmented version with 225 cases generated through data augmentation. To predict bending deflection and the exposed height of longitudinal reinforcement, artificial neural network (ANN) and random forest (RF) models are optimized using the hunter–prey optimization (HPO) algorithm. Results show that the HPO-optimized RF model trained on the augmented database achieves the best performance, with MSE, MAE, and R2 values of 0.004, 0.041, and 0.931 on the training set, and 0.007, 0.057, and 0.865 on the testing set, respectively. Sensitivity analysis reveals that the yield strength of longitudinal reinforcement has the most significant impact, while the shear reinforcement ratio has the least influence on both output variables. The partial dependence plot (PDP) analysis indicates that the ratio of shear reinforcement has the most significant impact on the deformation of longitudinal reinforcement.

Predicting the permeability and compressive strength of pervious concrete using a stacking ensemble machine learning approach

Developing the relationship of pore characteristics and performance is vital for predicting the properties of pervious concrete. However, the current performance prediction models mainly relied on porosity, ignoring the influence of other pore structure parameters, resulting in insufficient prediction accuracy. The aim of this paper is to establish machine learning-based models for predicting permeability and compressive strength of pervious concrete. Firstly, six independent models, the multiple linear regression and the Stacking algorithm were applied to construct the ensemble model. Secondly, 90 groups of pervious concrete specimens with varying porosities and grades were prepared and tested to obtain the initial data set. Then, the initial data set was augmented, and the prediction models were trained. The results indicate that the six input parameters are effective in enabling the model to achieve a high prediction accuracy of 0.93, while also being straightforward to implement. The integrated model attained an R² of 0.925 for permeability coefficient prediction (MSE = 0.769, MAE = 0.623), and for compressive strength prediction, it reached an R² of 0.928 (MSE = 1.570, MAE = 0.910). This represents an improvement of 15.9–23.9% over the optimal single-model prediction accuracy. This enhancement can be attributed to the model’s ability to effectively address the limitations posed by the linear assumptions of traditional empirical formulations through base-learner feature reweighting and meta-learner dynamic fusion mechanisms. Consequently, the ensemble model demonstrates significantly superior performance compared to empirical formulations in predicting both permeability and compressive strength. Notably, the compressive strength of pervious concrete is more sensitive to variations in porosity than to those in permeability.

Taguchi-Based Optimization of Cellulose Nanocrystal and Fly Ash Dosage in Concrete for Enhanced Strength

Abstract The integration of industrial by-products and nanomaterials in concrete offers a sustainable approach while improving mechanical performance. This study investigated the combined effects of Cellulose Nanocrystals (CNC) and Fly Ash (FA) on the compressive strength of standard concrete using the Taguchi method. An L25 orthogonal array was designed with three parameters: FA (0–40 %), CNC (0–0.8 %), and Superplasticizer (0.6–1 %) across five levels. The results showed that the optimal composition for maximum 28-day compressive strength (53.97 MPa) was 20 % FA, 0.2 % CNC, and 0.6 % superplasticizer. Analysis of variance (ANOVA) indicated that CNC had the highest contribution (51.18 %) to strength improvement. The findings validated the Taguchi method as an effective optimization tool for sustainable concrete design.

Microbial Calcite Precipitation by Marine-Derived Rhodococcus Strain RK-15: Characterization and Application in Concrete

This study investigates the impact of ureolytic bacteria isolated from sea surface water on the compressive strength and water absorption characteristics of concrete. In this context, the strain RK-15 was selected in the preliminary screening with Stuart’s broth and used in further experiments. Phylogenetic analysis of the 16S rRNA gene sequence identified the isolate as Rhodococcus erythropolis. This strain demonstrated the highest urease activity on the 5th day at 30 °C and pH 8. The isolate accumulated spherical crystals in a solid Urea-CaCl2 medium. Energy-dispersive X-ray spectroscopy (EDS) analysis revealed the presence of calcium, carbon, and oxygen in the precipitated minerals. In concrete production, 0.5% of the cement weight (2 × 109 cells/ml) bacterial culture was used. Compressive strength and water absorption measurements were performed on the 3rd, 7th, and 28th days. Results showed that the addition of Rhodococcus strain RK-15 led to a 13.61% increase in compressive strength and a 23.33% reduction in water absorption by weight compared to the control group. These findings suggest that the addition of strain RK-15 offers a sustainable and environmentally friendly method to enhance the mechanical and physical properties of concrete.

Effect of Rubber Granulate Content on the Compressive Strength of Concrete for Industrial Vibration-Isolating Floors.

Ensuring vibration and impact isolation is crucial in industrial flooring design, especially where vibroacoustic comfort is a priority. Excessive vibrations can negatively affect sensitive equipment, structural durability, and personnel comfort. With the rise of automation and high-precision processes, effective vibration control in floor systems is increasingly important. Traditional solutions like elastomer pads, rubber mats, or floating floors often have high installation costs, complex construction, and long-term degradation. Therefore, there is growing interest in integrated, durable alternatives that can be incorporated directly into concrete structures. One such approach uses rubber granulates from recycled tires as a modifying additive in cementitious composites. This can improve damping, enhance impact energy absorption, and reduce the need for external insulating layers. However, adding rubber particles to concrete may affect its compressive strength, a key design parameter. This article presents experimental research on concrete and mortar mixtures modified with rubber granulates for vibration-isolating industrial floor systems. The proposed solution combines a conventional concrete subbase with a rubber-enhanced mortar layer, forming a composite system to mitigate vibration transmission. Laboratory tests and real-scale verification under industrial conditions showed that the slab with hybrid EPDM/SBR rubber granulate mortar achieved the highest vibration-damping efficiency, reducing vertical acceleration by 58.6% compared to the reference slab. The EPDM-only mortar also showed a significant reduction of 45.5%.

Optimized machine learning algorithms with SHAP analysis for predicting compressive strength in high-performance concrete

This research examines the application of eight different machine learning (ML) algorithms for predicting the compressive strength of high-performance concrete (HPC). Achieving precise predictions is crucial for enhancing structural reliability and optimizing resource usage in construction projects. The analysis utilized the “Concrete Compressive Strength” dataset, sourced from UC Irvine’s publicly available ML repository. The models evaluated include Gradient Boosting Regressor (GBR), Extreme Gradient Boosting Regression (XGBoost), Random Forest (RF), Support Vector Regression (SVR), Artificial Neural Network (ANN), Multilayer Perceptron (MLP), Lasso, and k-Nearest Neighbors (KNN). To enhance performance, critical data preprocessing steps were undertaken, which involved feature scaling, cleaning, and normalization. Hyperparameter tuning via Grid Search (GS) and K-fold cross-validation further optimized the models. Among those analyzed, XGBoost and GBR achieved the highest predictive accuracy, with R2 values of 93.49% and 92.09% respectively, coupled with lower mean squared error (MSE), mean absolute error (MAE), and root mean squared error (RMSE). SHapley Additive exPlanations (SHAP) analysis revealed cement content and curing age as the most significant factors affecting compressive strength. Validation against experimental data confirmed the reliability of XGBoost and GBR through consistent prediction patterns and close alignment with empirical measurements. The results establish ML as an effective approach for HPC strength prediction, offering advantages in computational efficiency and accuracy over conventional analytical methods.

Flexural Behavior of Pre-Tensioned Precast High-Performance Steel-Fiber-Reinforced Concrete Girder Without Conventional Reinforcement: Full-Scale Test and FE Modeling

In contrast to brittle normal-strength concrete (NSC), high-performance steel-fiber-reinforced concrete (HPSFRC) provides better tensile and shear resistance, enabling enhanced bridge girder design. To achieve a balance between cost efficiency and quality, reducing conventional reinforcement is a viable cost-saving strategy. This study focused on the flexural behavior of a type of pre-tensioned precast HPSFRC girder without longitudinal and shear reinforcement. This type of girder consists of HPSFRC and prestressed steel strands, balancing structural performance, fabrication convenience, and cost-effectiveness. A 30.0 m full-scale girder was randomly selected from the prefabrication factory and tested through a four-point bending test. The failure mode, load–deflection relationship, and strain distribution were investigated. The experimental results demonstrated that the girder exhibited ductile deflection-hardening behavior (47% progressive increase in load after the first crack), extensive cracking patterns, and large total deflection (1/86 of effective span length), meeting both the serviceability and ultimate limit state design requirements. To complement the experimental results, a nonlinear finite element model (FEM) was developed and validated against the test data. The flexural capacity predicted by the FEM had a marginal 0.8% difference from the test result, and the predicted load–deflection curve, crack distribution, and load–strain curve were in adequate agreement with the test outcomes, demonstrating reliability of the FEM in predicting the flexural behavior of the girder. Based on the FEM, parametric analysis was conducted to investigate the effects of key parameters, namely concrete tensile strength, concrete compressive strength, and prestress level, on the flexural responses of the girder. Eventually, design recommendations and future studies were suggested.

Use of BOIvy Optimization Algorithm-Based Machine Learning Models in Predicting the Compressive Strength of Bentonite Plastic Concrete.

The combination of bentonite and conventional plastic concrete is an effective method for projecting structures and adsorbing heavy metals. Determining the compressive strength (CS) is a crucial step in the design of bentonite plastic concrete (BPC). Traditional experimental analyses are resource-intensive, time-consuming, and prone to high uncertainties. To address these challenges, several machine learning (ML) models, including support vector regression (SVR), artificial neural network (ANN), and random forest (RF), are generated to forecast the CS of BPC materials. To improve the prediction accuracy, a meta-heuristic optimization, called the Ivy algorithm, is integrated with Bayesian optimization (BOIvy) to optimize the ML models. Several statistical indices, including the coefficient of determination (R2), root mean square error (RMSE), prediction accuracy (U1), prediction quality (U2), and variance accounted for (VAF), are adopted to evaluate the predictive performance of all models. Additionally, Shapley additive explanation (SHAP) and sensitivity analysis are conducted to enhance model interpretability. The results indicate that the best model is the BOIvy-ANN model, which achieves the optimal indices during the testing. Moreover, water, curing time, and cement are found to be more influential on the prediction of the CS of BPC than other features. This paper provides a strong example of applying artificial intelligence (AI) techniques to estimate the performance of BPC materials.

A State-of-the-Art Review on the Influence of Porosity on the Compressive Strength of Porous Concrete for Infrastructure Applications

The use of porous concrete in various infrastructure applications such as pavements, infiltration beds, and low-volume load areas is increasingly encouraged due to its environmental benefits. The performance of porous concrete is strongly influenced by its pore structure and overall porosity. Researchers have employed multiple methodologies to characterise pore size and distribution, and to assess their effects on permeability, hydraulic conductivity, and compressive strength. This review investigates several pore measurement techniques aimed at improving both the hydraulic and mechanical performance of porous concrete. Among these, image analysis emerges as the most accurate method for assessing porosity distribution, offering higher resolution and fewer limitations compared to traditional techniques. Despite these advancements, a debate remains regarding the relative importance of effective porosity versus total porosity. This work comprehensively evaluates and synthesises existing methods for pore structure analysis, thereby enhancing our understanding of how porosity influences concrete behaviour. The findings indicate that effective porosity alone is insufficient to predict hydraulic conductivity, whereas total porosity has a considerable effect on compressive strength. This insight can be used to optimise the balance between strength and permeability in porous concrete, supporting its broader implementation as a sustainable construction material.

Explainable machine learning model for predicting compressive strength of CO2-cured concrete

Explainable machine learning model for predicting compressive strength of CO2-cured concrete

Machine learning prediction and explainability analysis of high strength glass powder concrete using SHAP PDP and ICE

Achieving high-strength concrete (HSC) with sustainable supplementary cementitious materials (SCMs) remains a significant challenge in the construction industry. Although glass powder has shown promise as a partial cement substitute, its specific impact on HSC growth is still unclear. This study aims to evaluate the compressive strength (CS) of high strength glass-powder concrete (HSGPC) using machine learning (ML) models and enhance predictive accuracy through hybrid optimization techniques. A dataset comprising 598 points was compiled, considering cement, glass powder, aggregates, water, superplasticizer, and curing days as key input parameters. Three standalone ML models—K-Nearest Neighbors (KNN), Random Forest (RF), and Extreme Gradient Boosting (XGB)—were trained, with RF achieving R² = 0.963 and XGB achieving R² = 0.946 on the test set. To further enhance performance, XGB was optimized using Particle Swarm Optimization (PSO), Firefly Algorithm (FA), and Grey Wolf Optimizer (GWO). Among these, XGB-GWO demonstrated the highest accuracy, with R² improving to 0.991 and MSE decreasing significantly from 83.95 to 14.42, resulting in an 82.82% error reduction. SHAP, PDP, and ICE analyses identified superplasticizer dosage, curing days, and coarse aggregate as the most influential parameters affecting compressive strength (CS). PDP and ICE validated these findings, showing reduced strength gains beyond 600 kg/m³ of cement and a decline beyond 800 kg/m³ of coarse aggregate. This study highlights the potential of ML-driven optimization for sustainable concrete design, offering an efficient, data-driven approach to optimizing material proportions for high-strength, eco-friendly concrete.