Machine learning (ML) models in material science and construction engineering have significantly improved predictive accuracy and decision making. However, the practical implementation of these models often requires technical expertise, limiting their accessibility for engineers and practitioners. A user-friendly graphical user interface (GUI) can be an essential tool to bridge this gap. In this study, a sustainable approach to improve the compressive strength (C.S) of plastic-based mortar mixes (PMMs) by replacing cement with industrial waste materials was investigated using ML models such as support vector machine, AdaBoost regressor, and extreme gradient boosting. The significance of key mix parameters was further analyzed using SHapley Additive exPlanations (SHAPs) to interpret the influence of input variables on model predictions. To enhance the usability and real-world application of these ML models, a GUI was developed to provide an accessible platform for predicting the C.S of PMMs based on input material proportions. The ML models demonstrated strong correlations with experimental results, and the insights from SHAP analysis further support data-driven mix design strategies. The developed GUI serves as a practical and scalable decision support system, encouraging the adoption of ML-based approaches in sustainable construction engineering.
Abstract This study presents a novel data-driven approach to improving the compressive strength (C-S) of environmentally friendly rubberized mortar that incorporates ingredients that are in line with current sustainability objectives in construction: glass powder, marble powder, and silica fume. Our predictive models were built using state-of-the-art machine learning (ML) approaches, specifically gene expression programming (GEP) and multi-expression programming (MEP), employing a thorough experimental dataset. Thorough evaluations of the models were conducted using important statistical metrics, such as the R 2 coefficient, root mean square error, and mean absolute error. The use of individual conditional expectation plots and partial dependence plots allowed for both individual and average variable effect studies, which were conducted to improve interpretability. Despite the good performance of the GEP model ( R 2 = 0.91), the MEP model proved to be more effective in capturing complicated, nonlinear connections with its superior accuracy and generalization ( R 2 = 0.95). ML has the ability to greatly improve sustainable construction practices by reducing the need for experiments, speeding up the process of mix optimization, and encouraging the creation of cementitious composites that are less harmful to the environment. The findings contribute to the construction sector by integrating digital innovation with material sustainability.
This study introduces a novel methodology for enhancing the compressive strength of self-compacting concrete (SCC) via the use of the Explainable Boosting Machine (EBM), a sophisticated and interpretable machine learning algorithm. It presents a data-driven model that aims to accurately predict the strength of SCC by considering the intricate interactions among its various elements. Additionally, the model provides insights into the variables that influence SCC's compressive strength. By using EBM in conjunction with XGBoost and CatBoost algorithms, this study conducts a comparative examination of predictive abilities using datasets related to composition and rheology. The findings reveal that CatBoost has greater predictive performance using rheology dataset, as shown by an R2 value of 0.977. Conversely, XGBoost exhibits a higher predictive capability using the composition dataset, as indicated by an R2 value of 0.947. The EBM can provide comprehensive explanations at both global and local levels. It effectively identifies the key factors that have a significant influence on compressive strength. These factors include the coarse aggregate content, cement content, water content, viscosity, and V-funnel flow time. The study findings provide more evidence to support the notion that including rheological data into the model leads to a notable improvement in its accuracy. This outcome further confirms the existence of a direct correlation between rheological properties and compressive strength. The explanatory insights provided by EBM give practical instructions for customising SCC mixes to attain desired strengths. This facilitates quality control and enables personalised concrete design in the field of construction. This study highlights the potential of interpretable machine learning algorithms in improving the predictive modelling of SCC features. This advancement may lead to the development of more durable, efficient, and customised building materials.
The quest to enhance public health and the need for a reduction in the environmental solid wastes have prompted this study. Despite abundant studies on silica fume (SF or S) and waste glass powder (WGP or G), there is a need to understand the interaction of WGP with SF in the production of ordinary Portland cement (OPC or C)-based concrete using the water/binder ratio of 0.42. The investigated concrete comprised 90 wt.% of OPC and 10 wt.% of WGP+SF. The samples were denoted as C90GxS10−x such that x varied from 0–10 wt.% at the interval of 2.5. The findings revealed that an increase in the WGP/SF ratio enhanced the absorption of silica/glass blended concrete due to size incompatibility and proliferations of interfacial transition zones between the glass particle, silica fume and cement matrix. The density of fresh OPC concrete was higher than that of glass/silica blended concrete due to the difference in their relative densities. Incorporating WGP and SF in synergy enhanced silicate reorganization and led to a more amorphous binder and a reduction in hydroxyl-based compounds such as portlandite but caused microstructural heterogeneity in the morphology of the binder as obtained from XRD, FTIR and SEM/EDS results. The 28-day compressive strength of 46 MPa is achievable if the WGP and SF are kept within 2.5–5 wt.% and 5–7.5 wt.%, respectively. The study will foster the production of economic, environmental, and cost-efficient concrete.
Abstract The construction sector is quickly adopting 3D printing because of its many benefits, such as the capacity to build complex geometries, speed up timeframes, increase sustainability, and improve safety. Making changes to the mixture composition of 3D-printed fiber-reinforced concrete (3DP-FRC) involves a lot of trial and error due to the many interdependent variables. In order to estimate the compressive strength (CS) and flexural strength (FS) of 3DP-FRC, the present study used gene expression programming (GEP) and Multi expression programming (MEP) for machine learning (ML). We ran a sensitivity analysis to go further into how important the input parameters were. Among the models, MEP had better predictive performance for FS and CS than GEP did, with R 2 values of 0.958 and 0.978, respectively. In contrast, the GEP model found lower R 2 values of 0.945 for CS and 0.928 for FS. Sensitivity analysis exposed that for CS, water-binder ratio, silica fume, and water content were the most influential parameters, while load distribution, sand content, and fly ash had the highest impact for FS. The developed ML models provide a reliable means of estimating the strength characteristics of 3DP-FRC for sustainable building design based on various input parameter values, offering significant time and cost savings compared to traditional laboratory testing.
Abstract This research examines the efficiency of ultra-high-performance concrete (UHPC) when utilizing geranium plant (GP) ash, which is subjected to different curing temperatures ranging from 300 to 900°C for 3 h of burning time. The GP ash is used as a replacement for cement in varying amounts (10, 20, 30, 40, and 50 wt%). Crumb rubber powder is utilized as a substitute for fine aggregate. Polypropylene fibers have been used to improve concrete performance. The performance of UHPC is evaluated by assessing its mechanical qualities, such as flexural strength, splitting tensile strength, and compressive strength. The sorptivity test is also evaluated as a component of it. Scanning electron microscopy is used to analyze UHPC after exposure to temperatures as high as 900°C. The findings demonstrated a notable enhancement in the mechanical characteristics of all mixtures. The most favorable mixtures were achieved with proportions of 50, 40, 40, and 20% for mixtures including GP waste incinerated at temperatures ranging from 300 to 900°C. Furthermore, the optimal outcome is achieved when 40% substitution is performed at a temperature of 700°C, resulting in notable enhancements of 14% in compressive strength, 30% in flexural strength, and 17% splitting tensile strength, respectively. At a high temperature of 700°C, the decrease in strength increased to approximately 37–40% as a result of the initial removal of carbon dioxide from calcite at temperatures ranging from 600 to 900°C and reached 56% at 900°C. Great resistance to sorptivity, as well as a dense and compact microstructure with a high content of calcium and silicon, was obtained.
Abstract Glass powder, silica fume, and marble powder (MP) were investigated for their potential as sustainable additives to enhance mechanical properties, reduce environmental impact, and improve resource utilization in mortar formulations. This study utilized gene expression programming (GEP) and multi-expression programming (MEP) with experimental data to develop flexural strength models using these materials as eco-friendly mortar cement substitutes. The models were evaluated using R ² values, statistical tests, sensitivity analysis, partial dependence plots (PDPs), Taylor’s diagram generation, and test and predicted results. The statistical measures demonstrated that MEP was the more accurate model compared to GEP. The sensitivity study revealed that plastic and sand had the most significant influence on flexural strength prediction, emphasizing the importance of their proportions in the mixture. PDPs further showed that cement, silica fume, and MP positively impact flexural strength, while sand and plastic exhibit optimal levels for enhanced performance. The study also highlighted the particle interaction sensitivity of glass powder, underlining the importance of mix design optimization to achieve improved mechanical behavior. The findings support the use of equation-based modeling and sustainable industrial byproducts to optimize mortar formulations, contributing to greener construction practices and reduced dependence on conventional cement.
This study demonstrates the conversion of agricultural and industrial waste into construction materials by developing ultra-high-performance concrete using cold-bonded sesame ash and waste glass aggregates. The primary focus of this study was sustainability and waste valorization in self-curing concrete systems. This study focuses on many aspects of producing cementless concrete with superior short- and long-term properties, incorporating an innovative artificial aggregate premanufactured using sesame ash and waste glass. Prepacking technology of casting was used. A self-curing additive is used to reduce the energy required for curing. In cold-bonded aggregates (CBAs), the aggregate content ranged from 10 to 50% of the total sand volume. Polyethylene glycol was used as an internal curing agent to evaluate the mechanical properties of the concrete, including the compressive strength and tensile strength at different ages. The durability characteristics of the concrete were also analyzed in terms of its resistance to sulfates, chloride ion penetration, and performance at elevated temperatures of 300 and 600 °C. Microscopic analyses were conducted by scanning electron microscopy (SEM), thermogravimetric analysis (TGA), Fourier transform infrared spectroscopy (FTIR), and Differential Scanning Calorimetry (DSC). The results showed a significant improvement in the mechanical and durability performance, especially at 30%, which resulted in the highest compressive strength of 147.2 MPa at 90 days. This is an 11.93% increase compared with that of the reference mix. The tensile strength was also improved by 14.5% at the same replacement ratio. The mix containing 30% manufactured aggregate demonstrated the best thermal resistance, retaining the highest percentage of residual strength at both 300 °C and 600 °C, as well as superior sulfate impact resistance, with a strength reduction factor of 39.5%. When the replacement ratio was increased to 50%, the chloride penetration resistance improved significantly by 41% compared with that of the reference mix. FTIR, TGA, and DSC analyses also demonstrated enhanced silicate polymerization and increased carbonate formation, contributing to the improved chemical stability and density of the concrete matrix.
