This study, from the perspective of resource utilization and carbon sequestration, developed a novel lightweight carbonated solidified slurry material using reactive magnesium oxide (MgO), ground granulated blast furnace slag (GGBS), and carbide slag as stabilizers, with carbonation induced by a CO₂ foaming method. The physical and mechanical properties of the material were investigated. Based on the optimal mix proportion, the effects of MgO content, CO₂ foam dosage, and stabilizer dosage on wet density, flowability, moisture content, and unconfined compressive strength were analyzed. The results indicate that wet density increases with increasing MgO and stabilizer content but decreases with increasing CO₂ foam dosage. Flowability decreases with increasing MgO and stabilizer content but improves with a higher CO₂ foam dosage. Unconfined compressive strength increases with curing age and stabilizer content but decreases with increasing CO₂ foam dosage. Additionally, prolonged curing enhances both moisture content and unconfined compressive strength. These findings provide a theoretical basis for engineering applications.

In recent years, there have been several instances of building collapse incidents resulting from shear failure. The complicated stress state and extremely nonlinear behavior seen in RC structures under shear loading are responsible for this phenomenon. Scholars and engineers worldwide have yet to propose a suitable model to address the issue correctly. Most computational approaches currently in use rely on semi‐empirical and semi‐theoretical formulations. The primary modes of shear transmission in cracked reinforced concrete include shear stress inside the uncracked concrete region, aggregate interlock, dowel action, stirrup action, and tensile residual stress. The shear force calculation is contingent upon the choice of the shear transfer model. This study comprehensively overviews the current shear calculation techniques and their respective applications. The pros and cons of these techniques were thoroughly examined. The present study investigated the suitability of these shear calculation formulas for RC structures subjected to intricate natural conditions, mechanical stress, and high‐strength and high‐performance concrete structures.

There are many factors that affect the shear capacity of FRP (fiber-reinforced polymer)-strengthened reinforced concrete (RC) beams, and traditional capacity models based on empirical or semi-empirical formulas often suffer from insufficient accuracy. To enhance the predictive accuracy and generalization ability of the shear capacity of FRP-strengthened RC beams, this study proposes an interpretable machine learning model based on the Jaya-CNN-LSTM model. A comprehensive database consisting of 315 test data on shear capacity of FRP-strengthened RC beams, encompassing various FRP reinforcement modes, has been established. Key feature parameters for predicting the shear capacity of FRP-strengthened RC beams are selected through Pearson correlation coefficient analysis. Based on the Jaya algorithm, the hyperparameters of the ensemble CNN-LSTM prediction model are adaptively optimized. A comparative analysis is conducted between the proposed method, other machine learning models, and existing empirical formulas to evaluate the proposed model’s efficacy. The results demonstrate that the proposed model outperforms other machine learning models and empirical formulas in terms of prediction accuracy and stability. Furthermore, the machine learning-based predictions align more closely with experimental values than those derived from empirical formulas. Additionally, the SHAP method is utilized to quantify the critical parameters’ impact on predicting the shear capacity of FRP-strengthened RC beams. The results reveal that there is an explicit mapping relationship between key features such as shear-span ratio, concrete strength, and yield strength of stirrups and the shear capacity of FRP-strengthened RC beams, providing technical support for practical applications.

The high carbon emissions associated with cement-based materials in lightweight foamed soils have become a significant environmental concern. In addition to this applied problem, there is also a scientific challenge: current studies of carbon–magnesium reactions in lightweight carbonated soils (LCSS) lack multiparameter predictive models, which are essential for understanding the coupled effects of MgO dosage and CO₂ foam content on material performance. This study addresses this gap by systematically investigating the influence of MgO and CO₂ foam on the strength, resistivity, and carbonation behavior of LCSS. A multiparameter regression model was developed to predict these properties, and its statistical significance and predictive accuracy were verified. The results show that MgO dosage strongly promotes carbonation and strength development, while CO₂ foam content primarily regulates porosity and carbonation degree. The established model provides reliable predictions of LCSS performance and offers a scientific basis for optimizing carbon–magnesium reactions in sustainable soil stabilization.