Explore the vast range of titles available.

This paper investigates the application of three artificial intelligence methods, including multivariate adaptive regression splines (MARS), M5 model tree (M5Tree), and least squares support vector regression (LSSVR) for the prediction of the mechanical behavior of recycled aggregate concrete (RAC). A large and reliable experimental test database containing the results of 650 compressive strength, 421 elastic modulus, 152 flexural strength, and 346 splitting tensile strength tests of RACs with no pozzolanic admixtures assembled from the published literature was used to train, test, and validate the three data-driven-based models. The results of the model assessment show that the LSSVR model provides improved accuracy over the existing models in the prediction of the compressive strength of RACs. The results also indicate that, although all three models provide higher accuracy than the existing models in the prediction of the splitting tensile strength of RACs, only the performance of the LSSVR model exceeds those of the best-performing existing models for the flexural strength of RACs. The results of this study indicate that MARS, M5Tree, and LSSVR models can provide close predictions of the mechanical properties of RACs by accurately capturing the influences of the key parameters. This points to the possibility of the application of these three models in the pre-design and modeling of structures manufactured with RACs.

There has been much effort to provide eco-friendly and biodegradable materials for the next generation of composite products owing to global environmental concerns and increased awareness of renewable green resources. An increase in the use of natural materials in composites has led to a reduction in greenhouse gas emissions and carbon footprint of composites. In addition to the benefits obtained from green materials, there are some challenges in working with them, such as poor compatibility between the reinforcing natural fiber and matrix and the relatively high moisture absorption of natural fibers. Green composites can be a suitable alternative for petroleum-based materials. However, before this can be accomplished, there are a number of issues that need to be addressed, including poor interfacial adhesion between the matrix and natural fibers, moisture absorption, poor fire resistance, low impact strength, and low durability. Several researchers have studied the properties of natural fiber composites. These investigations have resulted in the development of several procedures for modifying natural fibers and resins. To address the increasing demand to use eco-friendly materials in different applications, an up-do-date review on natural fiber and resin types and sources, modification and processing techniques, physical and mechanical behaviors, applications, life-cycle assessment, and other properties of green composites is required to provide a better understanding of the behavior of green composites. This paper presents such a review based on 322 studies published since 1978.

Precisely forecasting how concrete reinforced with fiber-reinforced polymers (FRP) responds under compression is essential for fine-tuning structural designs, ensuring constructions fulfill safety criteria, avoiding overdesigning, and consequently minimizing material expenses and environmental impact. Therefore, this study explores the viability of gradient boosting regression tree (GBRT), random forest (RF), artificial neural network-multilayer perceptron (ANNMLP) and artificial neural network-radial basis function (ANNRBF) in predicting the compressive behavior of fiber-reinforced polymer (FRP)-confined concrete at ultimate. The accuracy of the proposed machine learning approaches was evaluated by comparing them with several empirical models concerning three different measures, including root mean square errors (RMSE), mean absolute errors (MAE), and determination coefficient (R 2 ). In this study, the evaluations were conducted using a substantial collection of axial compression test data involving 765 circular specimens of FRP-confined concrete assembled from published sources. The results indicate that the proposed GBRT algorithm considerably enhances the performance of machine learning models and empirical approaches for predicting strength ratio of confinement ( f′ cc /f′ co ) by an average improvement in RMSE as 17.3%, 0.65%, 66.81%, 46.12%, 46.31%, 46.87% and 69.94% compared to RF, ANNMLP, ANNRBF, and four applied empirical models, respectively. It is also found that the proposed ANNMLP algorithm exhibits notable superiority compared to other models in terms of reducing RMSE values as 9.67%, 11.29%, 75.11%, 68.83%, 73.64%, 69.49% and 83.74% compared to GBRT, RF, ANNRBF and four applied empirical models for predicting strain ratio of confinement (ε cc /ε co ), respectively. The superior performance of the GBRT and ANNMLP compared to other methods in predicting the strength and strain ratio confinements is important in evaluating structural integrity, guaranteeing secure functionality, and streamlining engineering plans for effective utilization of FRP confinement in building projects.

Cemented paste backfill (CPB) gains strength through the hydration of the binder constituent of the CPB, where mix temperature is a key influencing factor. Both rate of strength development and ultimate strength are influenced by the overarching temperature conditions in which the binder hydration occurs. This study investigates the influence of mixing water temperature on the thermal behaviour, hydration kinetics, and microstructural development of CPB using a combination of thermal finite element modelling, thermogravimetric analysis (TGA), scanning electron microscopy (SEM), and energy-dispersive X-ray spectroscopy (EDS). Five CPB mixtures were prepared, with water temperatures ranging from 5 °C to 50 °C, and tested under controlled conditions to isolate the effects of the initial thermal input. Results show that moderate mixing water temperatures (20–35 °C) optimize hydration and mechanical strength, while excessive temperatures (≥50 °C) increase the risk of thermal cracking due to generation of excessive heat. The thermal modelling results demonstrated that the highest temperatures were observed in the bottom section of the fill mass, in contact with the surrounding rock, where the combined effects of mix-generated heat and rock conduction were most pronounced. The 50 °C mix reached a peak internal temperature of 85.6 °C with a thermal gradient of 40.5 °C, while the 5 °C mix recorded a much lower peak of 55.7 °C and a gradient of 16.8 °C. These results highlight that higher mixing water temperatures accelerate early hydration reactions and significantly influence the internal thermal profile during the first 21 days of curing. Based on these findings, the design of paste plants can be improved by incorporating a heating/cooling system for the mixing water tank—firstly, to ensure the water temperature does not exceed 50 °C and secondly, to maintain water within an optimal temperature range, potentially reducing binder consumption.

Increasing the thermal insulation of building components to reduce the thermal energy loss of buildings has received significant attention. Owing to its porous structure, using expanded vermiculite as an alternative to natural river sand in the development of building materials would result in improvement of the thermal performance of buildings. This study investigates the properties of fly ash (FA)-based geopolymer mortars prepared with expanded vermiculite. The main aim of this study was to produce geopolymer mortar with lower thermal conductivity than conventional mortar for thermal insulation applications in buildings. A total of twelve batches of geopolymers were prepared for evaluating their different properties. The obtained results show that, at a given FA and expanded vermiculite content, the geopolymers prepared with a 10 molar NaOH solution exhibited a higher flowability, water absorption and porosity, as well as a lower dry unit weight, compressive strength, ultrasound pulse velocity and thermal conductivity compared with those prepared with a 15 molar NaOH solution. As is also shown, the geopolymers containing expanded vermiculite (15%) developed a lower flowability (~6%), dry unit weight (~6%), compressive strength (~7%), ultrasound pulse velocity (~6%) and thermal conductivity (~18%), as well as a higher apparent porosity (~6%) and water absorption (~9%) compared with those without expanded vermiculite at a given FA content and NaOH concentration. The findings of this study suggest that incorporating expanded vermiculite in FA-based geopolymer mortar can provide eco-friendly and lightweight building composites with improved sound and thermal insulation properties, contributing toward the reduction of the environmental effects of waste materials and conservation of natural sand.

The accurate prediction of reference points on the axial stress–axial strain relationship of fiber-reinforced polymer (FRP)-confined concrete is vital to pre-design structures made with this system. This study uses an artificial neural network (ANN) for predicting hoop rupture strain (εh,rup) and transition zone, namely transition strain (εc1) and stress (f’c1), on axial stress–strain curves of FRP-confined concrete. These are key parameters for estimating a transition zone of stress–strain curves. In this study, accompanied with these parameters, ultimate condition parameters, including compressive strength and ultimate axial strain, were predicted using a comprehensive database. Various combinations of input data and ANN parameters were used to increase the accuracy of the predictions. A sensitivity analysis and a model validation assessment were performed to evaluate the predictability of the developed models. At the end, a comparison between the proposed models in this study and existing ANN and design-oriented models was presented. It is shown that the accuracy of the developed ANN models in this study is higher or comparable to that of existing ANN models. Additionally, the developed models in this study to predict f’c1 and εc1 exhibit a higher accuracy compared to existing design-oriented models. These results indicate that the proposed ANN models capture the lateral confinement effect on ultimate and transition zones of FRP-confined concrete with a more robust performance compared to existing models.

Development of sustainable concrete as an alternative to conventional concrete helps in reducing carbon dioxide footprint associated with the use of cement and disposal of waste materials in landfill. One way to achieve that is the use of fly ash (FA) as an alternative to ordinary Portland cement (OPC) because FA is a pozzolanic material and has a high amount of alumina and silica content. Because of its excellent mechanical properties, several studies have been conducted to investigate the use of alkali-activated FA-based concrete as an alternative to conventional concrete. FA, as an industrial by-product, occupies land, thereby causing environmental pollution and health problems. FA-based concrete has numerous advantages, such as it has early strength gaining, it uses low natural resources, and it can be configurated into different structural elements. This study initially presents a review of the classifications, sources, chemical composition, curing regimes and clean production of FA. Then, physical, fresh, and mechanical properties of FA-based concretes are studied. This review helps in better understanding of the behavior of FA-based concrete as a sustainable and eco-friendly material used in construction and building industries.

A correct understanding of the fracture mechanism of Recycled Aggregate Concrete (RAC) plays an important role in the design of RAC structure and also in gaining a better understanding of the behavior of structures made from it. On the other hand, one of the most important parameters that affects cracking behavior and the fracture parameters of concrete is the water to cement ratio. The main objective of this study is to investigate the effect of different water to cement ratios on the fracture behavior of RAC. To achieve this objective, 125 notched concrete beams were subjected to three-point bending experiments, with W ranging 0.35 to 0.7. Specific fracture energy ( G F ) and characteristic length ( L ch ) from work-of-fracture method and initial fracture energy ( G f ), brittleness number, fracture toughness, effective length of fracture process zone ( C f ), and the critical crack-tip opening displacement from size effect method were evaluated. The results illustrate that G F and G f increase by 34 and 64% when W reduces from 0.7 to 0.35, respectively. Moreover, L ch and C f reduce from 378 to 208 mm and from 32.5 to 17.2 mm by decreasing W from 0.7 to 0.35, respectively. On average, G F /G f ratio for various W s attains 2.48 with the variation coefficient of 10.9%. Eventually, multivariate prediction models were developed for RACs with various W s. A comparison was made between prediction and experimental values of the present and previous research works.

The degradation of concrete structures is significantly influenced by carbonation, where atmospheric carbon dioxide (CO 2 ) penetrates the concrete matrix. Measuring how far carbonation penetrates into concrete plays a vital role in maintaining structural integrity and construction safety standards. Precisely forecasting the extent of carbonation penetration in recycled aggregate concrete (RAC) remains fundamental for understanding long-term performance and durability. This research is the first to introduce an innovative approach that leverages eight machine learning algorithms to estimate carbonation penetration depth. The selected techniques include NGBoost, GBRT, AdaBoost, CatBoost, XGBoost, LightGBM, HistGBRT, and MLR. Moreover, to evaluate model accuracy, four key performance indicators were employed. Additionally, SHapley Additive exPlanations (SHAP) was incorporated for enhanced model interpretability. Furthermore, the investigation examined six distinct input parameter configurations during training and testing to thoroughly assess model performance. Among the evaluated algorithms, XGBoost delivered the highest accuracy, with an RMSE of 1.389 mm, MAE of 1.005 mm, and R of 0.984. CatBoost followed closely, with RMSE of 1.772 mm, MAE of 1.344 mm, and R of 0.976. Then, the LightGBM ranked third in effectiveness, exhibiting an RMSE of 1.797 mm, MAE of 1.296 mm, and R of 0.975. These results demonstrate the reliability and interpretability of advanced machine learning models for carbonation depth estimation in RAC. The developed models offer practical tools for engineers seeking to evaluate how carbonation penetration affects structural integrity. These findings establish a strong foundation for understanding and predicting carbonation-related deterioration in concrete infrastructure.